diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..e8a17591b24538f7ef40db19f3b7b4cfded1101c 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-792/tokenizer.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ab88c7840eec526b1056409850ff16817316b4b5 --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +base_model: NousResearch/Hermes-3-Llama-3.1-8B +library_name: peft +license: other +tags: +- llama-factory +- lora +- generated_from_trainer +model-index: +- name: 4k_train_2024-10-16-13-29-59 + results: [] +--- + + + +# 4k_train_2024-10-16-13-29-59 + +This model is a fine-tuned version of [NousResearch/Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B) on the identity dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-05 +- train_batch_size: 2 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 2 +- gradient_accumulation_steps: 8 +- total_train_batch_size: 32 +- total_eval_batch_size: 16 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: cosine +- num_epochs: 6.0 + +### Training results + + + +### Framework versions + +- PEFT 0.12.0 +- Transformers 4.45.0 +- Pytorch 2.3.1+cu121 +- Datasets 2.21.0 +- Tokenizers 0.20.1 \ No newline at end of file diff --git a/adapter_config.json b/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4aa889ee5316659d91ab201b4f03e49477d31374 --- /dev/null +++ b/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "k_proj", + "v_proj", + "o_proj", + "down_proj", + "q_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapter_model.safetensors b/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e329f63cabe7bbabd90c66c3497bd5f522016f18 --- /dev/null +++ b/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b64d881e75b15b70ebdb13bdb6a15bc8897b67d9991a8bc5f766dffe7624b3a +size 83945296 diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000000000000000000000000000000000000..8ccc84add7ef6d69dfb324d1d2d516ff77282cd6 --- /dev/null +++ b/all_results.json @@ -0,0 +1,9 @@ +{ + "epoch": 5.971724787935909, + "num_input_tokens_seen": 8017392, + "total_flos": 3.6202835979167334e+17, + "train_loss": 2.4793783682163317, + "train_runtime": 5283.1732, + "train_samples_per_second": 4.82, + "train_steps_per_second": 0.15 +} \ No newline at end of file diff --git a/checkpoint-100/README.md b/checkpoint-100/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ba199ae8c078d293275e50b0a850beb3a458a43e --- /dev/null +++ b/checkpoint-100/README.md @@ -0,0 +1,202 @@ +--- +base_model: NousResearch/Hermes-3-Llama-3.1-8B +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/checkpoint-100/adapter_config.json b/checkpoint-100/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4aa889ee5316659d91ab201b4f03e49477d31374 --- /dev/null +++ b/checkpoint-100/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "k_proj", + "v_proj", + "o_proj", + "down_proj", + "q_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-100/adapter_model.safetensors b/checkpoint-100/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ff72df051d4e996d20848e97504ca37cfc726e9 --- /dev/null +++ b/checkpoint-100/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a7fddb0399cc21cebf141a256cd000dbc5a6ccb92f515082a6ef698427e7871 +size 83945296 diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..c1d2bf28e518ac304d920af30b570fa4a1801f32 --- /dev/null +++ b/checkpoint-100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf8752aff4e4c10a1a0af7b3c5f58eaf33cd8e7cbcfb00b723056481743da7fb +size 168149074 diff --git a/checkpoint-100/rng_state_0.pth b/checkpoint-100/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..b24ba5257472a7c82c4d4247a4c0210ee74f9e61 --- /dev/null +++ b/checkpoint-100/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d6a959372d5e0c2ea025dd26c9d0ad2046fce19352056cae8074dcbd0a6fd4 +size 14512 diff --git a/checkpoint-100/rng_state_1.pth b/checkpoint-100/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..9350a8206512bf8b857f4064425716468c2b7465 --- /dev/null +++ b/checkpoint-100/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f68a37892a1b445d21bb35cc10bf7a058a6f9ec8c363f5ed156ff4f49d90fb6 +size 14512 diff --git a/checkpoint-100/scheduler.pt b/checkpoint-100/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..a53ef2174c184393d666a31d31361036b4e0ed9a --- /dev/null +++ b/checkpoint-100/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:007585e9be6fcea10724fc5c4f995ce0d7c1a0cb64ea3e579daa75bb93d29802 +size 1064 diff --git a/checkpoint-100/special_tokens_map.json b/checkpoint-100/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1ad7f173822ffa805bd5f390acc9c3390d414e67 --- /dev/null +++ b/checkpoint-100/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-100/tokenizer.json b/checkpoint-100/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b --- /dev/null +++ b/checkpoint-100/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05 +size 17209403 diff --git a/checkpoint-100/tokenizer_config.json b/checkpoint-100/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a22a366f4a4df58d908d0fa483648703588ce0b1 --- /dev/null +++ b/checkpoint-100/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128039": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128040": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|im_end|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-100/trainer_state.json b/checkpoint-100/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..c7855f476a2b8cd938050db8c5586a20c71360b1 --- /dev/null +++ b/checkpoint-100/trainer_state.json @@ -0,0 +1,193 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.7540056550424128, + "eval_steps": 500, + "global_step": 100, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.03770028275212064, + "grad_norm": 3.988708734512329, + "learning_rate": 4.9995083170283816e-05, + "loss": 4.6192, + "num_input_tokens_seen": 50400, + "step": 5 + }, + { + "epoch": 0.07540056550424128, + "grad_norm": 2.142688512802124, + "learning_rate": 4.998033461515242e-05, + "loss": 3.9149, + "num_input_tokens_seen": 104016, + "step": 10 + }, + { + "epoch": 0.11310084825636192, + "grad_norm": 1.5928359031677246, + "learning_rate": 4.9955760135896534e-05, + "loss": 3.6912, + "num_input_tokens_seen": 155584, + "step": 15 + }, + { + "epoch": 0.15080113100848255, + "grad_norm": 1.5493167638778687, + "learning_rate": 4.992136939879856e-05, + "loss": 3.5556, + "num_input_tokens_seen": 202672, + "step": 20 + }, + { + "epoch": 0.1885014137606032, + "grad_norm": 1.7764347791671753, + "learning_rate": 4.9877175931330346e-05, + "loss": 3.4256, + "num_input_tokens_seen": 254800, + "step": 25 + }, + { + "epoch": 0.22620169651272384, + "grad_norm": 1.2482728958129883, + "learning_rate": 4.982319711683221e-05, + "loss": 3.3128, + "num_input_tokens_seen": 306352, + "step": 30 + }, + { + "epoch": 0.2639019792648445, + "grad_norm": 1.2829065322875977, + "learning_rate": 4.975945418767529e-05, + "loss": 3.2688, + "num_input_tokens_seen": 356352, + "step": 35 + }, + { + "epoch": 0.3016022620169651, + "grad_norm": 1.513293743133545, + "learning_rate": 4.968597221690986e-05, + "loss": 3.297, + "num_input_tokens_seen": 406672, + "step": 40 + }, + { + "epoch": 0.3393025447690858, + "grad_norm": 1.883090853691101, + "learning_rate": 4.96027801084029e-05, + "loss": 3.232, + "num_input_tokens_seen": 456160, + "step": 45 + }, + { + "epoch": 0.3770028275212064, + "grad_norm": 1.402272343635559, + "learning_rate": 4.950991058546893e-05, + "loss": 3.267, + "num_input_tokens_seen": 509680, + "step": 50 + }, + { + "epoch": 0.41470311027332707, + "grad_norm": 1.5488755702972412, + "learning_rate": 4.940740017799833e-05, + "loss": 3.2148, + "num_input_tokens_seen": 559968, + "step": 55 + }, + { + "epoch": 0.4524033930254477, + "grad_norm": 1.507287859916687, + "learning_rate": 4.929528920808854e-05, + "loss": 3.1403, + "num_input_tokens_seen": 610000, + "step": 60 + }, + { + "epoch": 0.49010367577756836, + "grad_norm": 1.9119170904159546, + "learning_rate": 4.917362177418342e-05, + "loss": 3.1515, + "num_input_tokens_seen": 661280, + "step": 65 + }, + { + "epoch": 0.527803958529689, + "grad_norm": 1.7253235578536987, + "learning_rate": 4.904244573372733e-05, + "loss": 3.1468, + "num_input_tokens_seen": 713264, + "step": 70 + }, + { + "epoch": 0.5655042412818096, + "grad_norm": 1.7201606035232544, + "learning_rate": 4.8901812684340564e-05, + "loss": 3.196, + "num_input_tokens_seen": 762576, + "step": 75 + }, + { + "epoch": 0.6032045240339302, + "grad_norm": 1.6135213375091553, + "learning_rate": 4.8751777943523634e-05, + "loss": 3.0593, + "num_input_tokens_seen": 813392, + "step": 80 + }, + { + "epoch": 0.6409048067860509, + "grad_norm": 1.7381868362426758, + "learning_rate": 4.8592400526898314e-05, + "loss": 3.0676, + "num_input_tokens_seen": 860608, + "step": 85 + }, + { + "epoch": 0.6786050895381716, + "grad_norm": 1.6142843961715698, + "learning_rate": 4.842374312499405e-05, + "loss": 3.1061, + "num_input_tokens_seen": 909104, + "step": 90 + }, + { + "epoch": 0.7163053722902922, + "grad_norm": 2.0389633178710938, + "learning_rate": 4.824587207858888e-05, + "loss": 2.9847, + "num_input_tokens_seen": 959600, + "step": 95 + }, + { + "epoch": 0.7540056550424128, + "grad_norm": 1.923561692237854, + "learning_rate": 4.805885735261454e-05, + "loss": 3.0289, + "num_input_tokens_seen": 1013648, + "step": 100 + } + ], + "logging_steps": 5, + "max_steps": 792, + "num_input_tokens_seen": 1013648, + "num_train_epochs": 6, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 4.577165786795213e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-100/training_args.bin b/checkpoint-100/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f8accff7ed19f472e4ab59934a52cd1b74989284 --- /dev/null +++ b/checkpoint-100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0abbac12d56c1934fca1078792064a59e7f00bea9a38a70efb9ce7fe81d8d0a2 +size 5432 diff --git a/checkpoint-200/README.md b/checkpoint-200/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ba199ae8c078d293275e50b0a850beb3a458a43e --- /dev/null +++ b/checkpoint-200/README.md @@ -0,0 +1,202 @@ +--- +base_model: NousResearch/Hermes-3-Llama-3.1-8B +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/checkpoint-200/adapter_config.json b/checkpoint-200/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4aa889ee5316659d91ab201b4f03e49477d31374 --- /dev/null +++ b/checkpoint-200/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "k_proj", + "v_proj", + "o_proj", + "down_proj", + "q_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-200/adapter_model.safetensors b/checkpoint-200/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..49a6f83695e214b1873cc6d90382384c7caf37ba --- /dev/null +++ b/checkpoint-200/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a83836d7a426a241a52659e473557cf0dc7f52f2a390ec9a9c493911f3aacb84 +size 83945296 diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..b58861fc9e0a532c76f74bb284d06e385d071e63 --- /dev/null +++ b/checkpoint-200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42d706d9aba1d1864830bc8cc0c37557c8ece3f71752bae0e0946e1ee00a2848 +size 168149074 diff --git a/checkpoint-200/rng_state_0.pth b/checkpoint-200/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..d46a9ba7690e83fef48d0cf5f4c34bd9df6cc737 --- /dev/null +++ b/checkpoint-200/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cb795a5cea0baa625c50007a6c9da09c6bbb5c16b560424070384a479e7d8a6 +size 14512 diff --git a/checkpoint-200/rng_state_1.pth b/checkpoint-200/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..23784d04394ff924f7fca03236f62241ce5f4b6e --- /dev/null +++ b/checkpoint-200/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f19604377bd828eb366c68946ad997a4ff4d69beaeea93ee58915135768ec63 +size 14512 diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..256a7585cec7c0986317830863d14bfa567b9de0 --- /dev/null +++ b/checkpoint-200/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa006138eee6fa0ff47a9911fb5414a64744afc4fa750d29d1a25fc9da929eba +size 1064 diff --git a/checkpoint-200/special_tokens_map.json b/checkpoint-200/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1ad7f173822ffa805bd5f390acc9c3390d414e67 --- /dev/null +++ b/checkpoint-200/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-200/tokenizer.json b/checkpoint-200/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b --- /dev/null +++ b/checkpoint-200/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05 +size 17209403 diff --git a/checkpoint-200/tokenizer_config.json b/checkpoint-200/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a22a366f4a4df58d908d0fa483648703588ce0b1 --- /dev/null +++ b/checkpoint-200/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128039": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128040": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|im_end|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..820c5b1dfacf01990099bc9abc54c209fc841b7f --- /dev/null +++ b/checkpoint-200/trainer_state.json @@ -0,0 +1,353 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.5080113100848256, + "eval_steps": 500, + "global_step": 200, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.03770028275212064, + "grad_norm": 3.988708734512329, + "learning_rate": 4.9995083170283816e-05, + "loss": 4.6192, + "num_input_tokens_seen": 50400, + "step": 5 + }, + { + "epoch": 0.07540056550424128, + "grad_norm": 2.142688512802124, + "learning_rate": 4.998033461515242e-05, + "loss": 3.9149, + "num_input_tokens_seen": 104016, + "step": 10 + }, + { + "epoch": 0.11310084825636192, + "grad_norm": 1.5928359031677246, + "learning_rate": 4.9955760135896534e-05, + "loss": 3.6912, + "num_input_tokens_seen": 155584, + "step": 15 + }, + { + "epoch": 0.15080113100848255, + "grad_norm": 1.5493167638778687, + "learning_rate": 4.992136939879856e-05, + "loss": 3.5556, + "num_input_tokens_seen": 202672, + "step": 20 + }, + { + "epoch": 0.1885014137606032, + "grad_norm": 1.7764347791671753, + "learning_rate": 4.9877175931330346e-05, + "loss": 3.4256, + "num_input_tokens_seen": 254800, + "step": 25 + }, + { + "epoch": 0.22620169651272384, + "grad_norm": 1.2482728958129883, + "learning_rate": 4.982319711683221e-05, + "loss": 3.3128, + "num_input_tokens_seen": 306352, + "step": 30 + }, + { + "epoch": 0.2639019792648445, + "grad_norm": 1.2829065322875977, + "learning_rate": 4.975945418767529e-05, + "loss": 3.2688, + "num_input_tokens_seen": 356352, + "step": 35 + }, + { + "epoch": 0.3016022620169651, + "grad_norm": 1.513293743133545, + "learning_rate": 4.968597221690986e-05, + "loss": 3.297, + "num_input_tokens_seen": 406672, + "step": 40 + }, + { + "epoch": 0.3393025447690858, + "grad_norm": 1.883090853691101, + "learning_rate": 4.96027801084029e-05, + "loss": 3.232, + "num_input_tokens_seen": 456160, + "step": 45 + }, + { + "epoch": 0.3770028275212064, + "grad_norm": 1.402272343635559, + "learning_rate": 4.950991058546893e-05, + "loss": 3.267, + "num_input_tokens_seen": 509680, + "step": 50 + }, + { + "epoch": 0.41470311027332707, + "grad_norm": 1.5488755702972412, + "learning_rate": 4.940740017799833e-05, + "loss": 3.2148, + "num_input_tokens_seen": 559968, + "step": 55 + }, + { + "epoch": 0.4524033930254477, + "grad_norm": 1.507287859916687, + "learning_rate": 4.929528920808854e-05, + "loss": 3.1403, + "num_input_tokens_seen": 610000, + "step": 60 + }, + { + "epoch": 0.49010367577756836, + "grad_norm": 1.9119170904159546, + "learning_rate": 4.917362177418342e-05, + "loss": 3.1515, + "num_input_tokens_seen": 661280, + "step": 65 + }, + { + "epoch": 0.527803958529689, + "grad_norm": 1.7253235578536987, + "learning_rate": 4.904244573372733e-05, + "loss": 3.1468, + "num_input_tokens_seen": 713264, + "step": 70 + }, + { + "epoch": 0.5655042412818096, + "grad_norm": 1.7201606035232544, + "learning_rate": 4.8901812684340564e-05, + "loss": 3.196, + "num_input_tokens_seen": 762576, + "step": 75 + }, + { + "epoch": 0.6032045240339302, + "grad_norm": 1.6135213375091553, + "learning_rate": 4.8751777943523634e-05, + "loss": 3.0593, + "num_input_tokens_seen": 813392, + "step": 80 + }, + { + "epoch": 0.6409048067860509, + "grad_norm": 1.7381868362426758, + "learning_rate": 4.8592400526898314e-05, + "loss": 3.0676, + "num_input_tokens_seen": 860608, + "step": 85 + }, + { + "epoch": 0.6786050895381716, + "grad_norm": 1.6142843961715698, + "learning_rate": 4.842374312499405e-05, + "loss": 3.1061, + "num_input_tokens_seen": 909104, + "step": 90 + }, + { + "epoch": 0.7163053722902922, + "grad_norm": 2.0389633178710938, + "learning_rate": 4.824587207858888e-05, + "loss": 2.9847, + "num_input_tokens_seen": 959600, + "step": 95 + }, + { + "epoch": 0.7540056550424128, + "grad_norm": 1.923561692237854, + "learning_rate": 4.805885735261454e-05, + "loss": 3.0289, + "num_input_tokens_seen": 1013648, + "step": 100 + }, + { + "epoch": 0.7917059377945335, + "grad_norm": 2.0325896739959717, + "learning_rate": 4.786277250863599e-05, + "loss": 2.9474, + "num_input_tokens_seen": 1065120, + "step": 105 + }, + { + "epoch": 0.8294062205466541, + "grad_norm": 1.6685590744018555, + "learning_rate": 4.765769467591625e-05, + "loss": 2.9713, + "num_input_tokens_seen": 1119424, + "step": 110 + }, + { + "epoch": 0.8671065032987747, + "grad_norm": 2.0325937271118164, + "learning_rate": 4.744370452107789e-05, + "loss": 3.0012, + "num_input_tokens_seen": 1169888, + "step": 115 + }, + { + "epoch": 0.9048067860508954, + "grad_norm": 1.7548010349273682, + "learning_rate": 4.722088621637309e-05, + "loss": 3.0399, + "num_input_tokens_seen": 1218944, + "step": 120 + }, + { + "epoch": 0.942507068803016, + "grad_norm": 1.6709191799163818, + "learning_rate": 4.698932740657479e-05, + "loss": 2.9156, + "num_input_tokens_seen": 1269920, + "step": 125 + }, + { + "epoch": 0.9802073515551367, + "grad_norm": 1.8369653224945068, + "learning_rate": 4.6749119174501975e-05, + "loss": 3.0288, + "num_input_tokens_seen": 1315536, + "step": 130 + }, + { + "epoch": 1.0179076343072573, + "grad_norm": 1.800703525543213, + "learning_rate": 4.6500356005192514e-05, + "loss": 2.8911, + "num_input_tokens_seen": 1360736, + "step": 135 + }, + { + "epoch": 1.055607917059378, + "grad_norm": 1.7134617567062378, + "learning_rate": 4.6243135748737864e-05, + "loss": 2.9148, + "num_input_tokens_seen": 1409808, + "step": 140 + }, + { + "epoch": 1.0933081998114986, + "grad_norm": 1.9385241270065308, + "learning_rate": 4.597755958179406e-05, + "loss": 2.868, + "num_input_tokens_seen": 1460864, + "step": 145 + }, + { + "epoch": 1.1310084825636193, + "grad_norm": 2.1658332347869873, + "learning_rate": 4.570373196778427e-05, + "loss": 2.7477, + "num_input_tokens_seen": 1512640, + "step": 150 + }, + { + "epoch": 1.1687087653157398, + "grad_norm": 2.239896774291992, + "learning_rate": 4.5421760615808474e-05, + "loss": 2.932, + "num_input_tokens_seen": 1556048, + "step": 155 + }, + { + "epoch": 1.2064090480678604, + "grad_norm": 2.0555717945098877, + "learning_rate": 4.513175643827647e-05, + "loss": 2.8219, + "num_input_tokens_seen": 1607232, + "step": 160 + }, + { + "epoch": 1.244109330819981, + "grad_norm": 2.0288779735565186, + "learning_rate": 4.4833833507280884e-05, + "loss": 2.8453, + "num_input_tokens_seen": 1653520, + "step": 165 + }, + { + "epoch": 1.2818096135721018, + "grad_norm": 1.9268651008605957, + "learning_rate": 4.4528109009727336e-05, + "loss": 2.7362, + "num_input_tokens_seen": 1703568, + "step": 170 + }, + { + "epoch": 1.3195098963242224, + "grad_norm": 2.413874387741089, + "learning_rate": 4.42147032012394e-05, + "loss": 2.9197, + "num_input_tokens_seen": 1752944, + "step": 175 + }, + { + "epoch": 1.3572101790763431, + "grad_norm": 2.2018630504608154, + "learning_rate": 4.389373935885646e-05, + "loss": 2.8897, + "num_input_tokens_seen": 1805600, + "step": 180 + }, + { + "epoch": 1.3949104618284638, + "grad_norm": 2.1807219982147217, + "learning_rate": 4.356534373254316e-05, + "loss": 2.7946, + "num_input_tokens_seen": 1860688, + "step": 185 + }, + { + "epoch": 1.4326107445805842, + "grad_norm": 2.2928526401519775, + "learning_rate": 4.322964549552943e-05, + "loss": 2.8149, + "num_input_tokens_seen": 1913056, + "step": 190 + }, + { + "epoch": 1.4703110273327051, + "grad_norm": 2.204533576965332, + "learning_rate": 4.288677669350066e-05, + "loss": 2.7811, + "num_input_tokens_seen": 1961744, + "step": 195 + }, + { + "epoch": 1.5080113100848256, + "grad_norm": 2.925762414932251, + "learning_rate": 4.2536872192658036e-05, + "loss": 2.8564, + "num_input_tokens_seen": 2011248, + "step": 200 + } + ], + "logging_steps": 5, + "max_steps": 792, + "num_input_tokens_seen": 2011248, + "num_train_epochs": 6, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 9.081866254548992e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-200/training_args.bin b/checkpoint-200/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f8accff7ed19f472e4ab59934a52cd1b74989284 --- /dev/null +++ b/checkpoint-200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0abbac12d56c1934fca1078792064a59e7f00bea9a38a70efb9ce7fe81d8d0a2 +size 5432 diff --git a/checkpoint-300/README.md b/checkpoint-300/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ba199ae8c078d293275e50b0a850beb3a458a43e --- /dev/null +++ b/checkpoint-300/README.md @@ -0,0 +1,202 @@ +--- +base_model: NousResearch/Hermes-3-Llama-3.1-8B +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/checkpoint-300/adapter_config.json b/checkpoint-300/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4aa889ee5316659d91ab201b4f03e49477d31374 --- /dev/null +++ b/checkpoint-300/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "k_proj", + "v_proj", + "o_proj", + "down_proj", + "q_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-300/adapter_model.safetensors b/checkpoint-300/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc5670d35766adb768b3f60e88ee0e69807af6da --- /dev/null +++ b/checkpoint-300/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff221a5c31d012ffd4e8a4ede9ff5a2c04b753be425031072449b9d269c53dce +size 83945296 diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..285989663992b39e307133925390a64c22a215e2 --- /dev/null +++ b/checkpoint-300/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba30541fe17ffbf04e9319876c0c426197fe4de4dfede11dc7f933f04a7872b +size 168149074 diff --git a/checkpoint-300/rng_state_0.pth b/checkpoint-300/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..9959dfa0d32cf7a8deece6c5a778423e8a10619a --- /dev/null +++ b/checkpoint-300/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34bcae41c589c7e4cab7b2ef263b878c90c2741404a6af11994dc31537b2319b +size 14512 diff --git a/checkpoint-300/rng_state_1.pth b/checkpoint-300/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..b8d192967011a6873fc38efe91068e31262ad585 --- /dev/null +++ b/checkpoint-300/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d05dc84075e8f7dd1191c36f3be9dda12073208e12f7d2cef433c38d6336774a +size 14512 diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..b81ae62f1b91366bf4f31885e9f5a6cfe9d897b7 --- /dev/null +++ b/checkpoint-300/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8ec54f6a0aea46713028de7bebd175e905179497901d87a9a354db5ce43f81a +size 1064 diff --git a/checkpoint-300/special_tokens_map.json b/checkpoint-300/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1ad7f173822ffa805bd5f390acc9c3390d414e67 --- /dev/null +++ b/checkpoint-300/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-300/tokenizer.json b/checkpoint-300/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b --- /dev/null +++ b/checkpoint-300/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05 +size 17209403 diff --git a/checkpoint-300/tokenizer_config.json b/checkpoint-300/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a22a366f4a4df58d908d0fa483648703588ce0b1 --- /dev/null +++ b/checkpoint-300/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128039": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128040": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|im_end|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..b3b3547bf5abff137bfdce5cc7d5e15990fd2620 --- /dev/null +++ b/checkpoint-300/trainer_state.json @@ -0,0 +1,513 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.2620169651272386, + "eval_steps": 500, + "global_step": 300, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.03770028275212064, + "grad_norm": 3.988708734512329, + "learning_rate": 4.9995083170283816e-05, + "loss": 4.6192, + "num_input_tokens_seen": 50400, + "step": 5 + }, + { + "epoch": 0.07540056550424128, + "grad_norm": 2.142688512802124, + "learning_rate": 4.998033461515242e-05, + "loss": 3.9149, + "num_input_tokens_seen": 104016, + "step": 10 + }, + { + "epoch": 0.11310084825636192, + "grad_norm": 1.5928359031677246, + "learning_rate": 4.9955760135896534e-05, + "loss": 3.6912, + "num_input_tokens_seen": 155584, + "step": 15 + }, + { + "epoch": 0.15080113100848255, + "grad_norm": 1.5493167638778687, + "learning_rate": 4.992136939879856e-05, + "loss": 3.5556, + "num_input_tokens_seen": 202672, + "step": 20 + }, + { + "epoch": 0.1885014137606032, + "grad_norm": 1.7764347791671753, + "learning_rate": 4.9877175931330346e-05, + "loss": 3.4256, + "num_input_tokens_seen": 254800, + "step": 25 + }, + { + "epoch": 0.22620169651272384, + "grad_norm": 1.2482728958129883, + "learning_rate": 4.982319711683221e-05, + "loss": 3.3128, + "num_input_tokens_seen": 306352, + "step": 30 + }, + { + "epoch": 0.2639019792648445, + "grad_norm": 1.2829065322875977, + "learning_rate": 4.975945418767529e-05, + "loss": 3.2688, + "num_input_tokens_seen": 356352, + "step": 35 + }, + { + "epoch": 0.3016022620169651, + "grad_norm": 1.513293743133545, + "learning_rate": 4.968597221690986e-05, + "loss": 3.297, + "num_input_tokens_seen": 406672, + "step": 40 + }, + { + "epoch": 0.3393025447690858, + "grad_norm": 1.883090853691101, + "learning_rate": 4.96027801084029e-05, + "loss": 3.232, + "num_input_tokens_seen": 456160, + "step": 45 + }, + { + "epoch": 0.3770028275212064, + "grad_norm": 1.402272343635559, + "learning_rate": 4.950991058546893e-05, + "loss": 3.267, + "num_input_tokens_seen": 509680, + "step": 50 + }, + { + "epoch": 0.41470311027332707, + "grad_norm": 1.5488755702972412, + "learning_rate": 4.940740017799833e-05, + "loss": 3.2148, + "num_input_tokens_seen": 559968, + "step": 55 + }, + { + "epoch": 0.4524033930254477, + "grad_norm": 1.507287859916687, + "learning_rate": 4.929528920808854e-05, + "loss": 3.1403, + "num_input_tokens_seen": 610000, + "step": 60 + }, + { + "epoch": 0.49010367577756836, + "grad_norm": 1.9119170904159546, + "learning_rate": 4.917362177418342e-05, + "loss": 3.1515, + "num_input_tokens_seen": 661280, + "step": 65 + }, + { + "epoch": 0.527803958529689, + "grad_norm": 1.7253235578536987, + "learning_rate": 4.904244573372733e-05, + "loss": 3.1468, + "num_input_tokens_seen": 713264, + "step": 70 + }, + { + "epoch": 0.5655042412818096, + "grad_norm": 1.7201606035232544, + "learning_rate": 4.8901812684340564e-05, + "loss": 3.196, + "num_input_tokens_seen": 762576, + "step": 75 + }, + { + "epoch": 0.6032045240339302, + "grad_norm": 1.6135213375091553, + "learning_rate": 4.8751777943523634e-05, + "loss": 3.0593, + "num_input_tokens_seen": 813392, + "step": 80 + }, + { + "epoch": 0.6409048067860509, + "grad_norm": 1.7381868362426758, + "learning_rate": 4.8592400526898314e-05, + "loss": 3.0676, + "num_input_tokens_seen": 860608, + "step": 85 + }, + { + "epoch": 0.6786050895381716, + "grad_norm": 1.6142843961715698, + "learning_rate": 4.842374312499405e-05, + "loss": 3.1061, + "num_input_tokens_seen": 909104, + "step": 90 + }, + { + "epoch": 0.7163053722902922, + "grad_norm": 2.0389633178710938, + "learning_rate": 4.824587207858888e-05, + "loss": 2.9847, + "num_input_tokens_seen": 959600, + "step": 95 + }, + { + "epoch": 0.7540056550424128, + "grad_norm": 1.923561692237854, + "learning_rate": 4.805885735261454e-05, + "loss": 3.0289, + "num_input_tokens_seen": 1013648, + "step": 100 + }, + { + "epoch": 0.7917059377945335, + "grad_norm": 2.0325896739959717, + "learning_rate": 4.786277250863599e-05, + "loss": 2.9474, + "num_input_tokens_seen": 1065120, + "step": 105 + }, + { + "epoch": 0.8294062205466541, + "grad_norm": 1.6685590744018555, + "learning_rate": 4.765769467591625e-05, + "loss": 2.9713, + "num_input_tokens_seen": 1119424, + "step": 110 + }, + { + "epoch": 0.8671065032987747, + "grad_norm": 2.0325937271118164, + "learning_rate": 4.744370452107789e-05, + "loss": 3.0012, + "num_input_tokens_seen": 1169888, + "step": 115 + }, + { + "epoch": 0.9048067860508954, + "grad_norm": 1.7548010349273682, + "learning_rate": 4.722088621637309e-05, + "loss": 3.0399, + "num_input_tokens_seen": 1218944, + "step": 120 + }, + { + "epoch": 0.942507068803016, + "grad_norm": 1.6709191799163818, + "learning_rate": 4.698932740657479e-05, + "loss": 2.9156, + "num_input_tokens_seen": 1269920, + "step": 125 + }, + { + "epoch": 0.9802073515551367, + "grad_norm": 1.8369653224945068, + "learning_rate": 4.6749119174501975e-05, + "loss": 3.0288, + "num_input_tokens_seen": 1315536, + "step": 130 + }, + { + "epoch": 1.0179076343072573, + "grad_norm": 1.800703525543213, + "learning_rate": 4.6500356005192514e-05, + "loss": 2.8911, + "num_input_tokens_seen": 1360736, + "step": 135 + }, + { + "epoch": 1.055607917059378, + "grad_norm": 1.7134617567062378, + "learning_rate": 4.6243135748737864e-05, + "loss": 2.9148, + "num_input_tokens_seen": 1409808, + "step": 140 + }, + { + "epoch": 1.0933081998114986, + "grad_norm": 1.9385241270065308, + "learning_rate": 4.597755958179406e-05, + "loss": 2.868, + "num_input_tokens_seen": 1460864, + "step": 145 + }, + { + "epoch": 1.1310084825636193, + "grad_norm": 2.1658332347869873, + "learning_rate": 4.570373196778427e-05, + "loss": 2.7477, + "num_input_tokens_seen": 1512640, + "step": 150 + }, + { + "epoch": 1.1687087653157398, + "grad_norm": 2.239896774291992, + "learning_rate": 4.5421760615808474e-05, + "loss": 2.932, + "num_input_tokens_seen": 1556048, + "step": 155 + }, + { + "epoch": 1.2064090480678604, + "grad_norm": 2.0555717945098877, + "learning_rate": 4.513175643827647e-05, + "loss": 2.8219, + "num_input_tokens_seen": 1607232, + "step": 160 + }, + { + "epoch": 1.244109330819981, + "grad_norm": 2.0288779735565186, + "learning_rate": 4.4833833507280884e-05, + "loss": 2.8453, + "num_input_tokens_seen": 1653520, + "step": 165 + }, + { + "epoch": 1.2818096135721018, + "grad_norm": 1.9268651008605957, + "learning_rate": 4.4528109009727336e-05, + "loss": 2.7362, + "num_input_tokens_seen": 1703568, + "step": 170 + }, + { + "epoch": 1.3195098963242224, + "grad_norm": 2.413874387741089, + "learning_rate": 4.42147032012394e-05, + "loss": 2.9197, + "num_input_tokens_seen": 1752944, + "step": 175 + }, + { + "epoch": 1.3572101790763431, + "grad_norm": 2.2018630504608154, + "learning_rate": 4.389373935885646e-05, + "loss": 2.8897, + "num_input_tokens_seen": 1805600, + "step": 180 + }, + { + "epoch": 1.3949104618284638, + "grad_norm": 2.1807219982147217, + "learning_rate": 4.356534373254316e-05, + "loss": 2.7946, + "num_input_tokens_seen": 1860688, + "step": 185 + }, + { + "epoch": 1.4326107445805842, + "grad_norm": 2.2928526401519775, + "learning_rate": 4.322964549552943e-05, + "loss": 2.8149, + "num_input_tokens_seen": 1913056, + "step": 190 + }, + { + "epoch": 1.4703110273327051, + "grad_norm": 2.204533576965332, + "learning_rate": 4.288677669350066e-05, + "loss": 2.7811, + "num_input_tokens_seen": 1961744, + "step": 195 + }, + { + "epoch": 1.5080113100848256, + "grad_norm": 2.925762414932251, + "learning_rate": 4.2536872192658036e-05, + "loss": 2.8564, + "num_input_tokens_seen": 2011248, + "step": 200 + }, + { + "epoch": 1.5457115928369463, + "grad_norm": 2.398651599884033, + "learning_rate": 4.218006962666934e-05, + "loss": 2.7966, + "num_input_tokens_seen": 2060640, + "step": 205 + }, + { + "epoch": 1.583411875589067, + "grad_norm": 2.452263355255127, + "learning_rate": 4.181650934253132e-05, + "loss": 2.7674, + "num_input_tokens_seen": 2113904, + "step": 210 + }, + { + "epoch": 1.6211121583411876, + "grad_norm": 2.5911788940429688, + "learning_rate": 4.144633434536467e-05, + "loss": 2.7607, + "num_input_tokens_seen": 2162608, + "step": 215 + }, + { + "epoch": 1.6588124410933083, + "grad_norm": 2.648517608642578, + "learning_rate": 4.1069690242163484e-05, + "loss": 2.8402, + "num_input_tokens_seen": 2211616, + "step": 220 + }, + { + "epoch": 1.6965127238454287, + "grad_norm": 2.6860735416412354, + "learning_rate": 4.06867251845213e-05, + "loss": 2.8019, + "num_input_tokens_seen": 2269440, + "step": 225 + }, + { + "epoch": 1.7342130065975496, + "grad_norm": 2.5891222953796387, + "learning_rate": 4.0297589810356165e-05, + "loss": 2.8311, + "num_input_tokens_seen": 2321936, + "step": 230 + }, + { + "epoch": 1.77191328934967, + "grad_norm": 2.695114850997925, + "learning_rate": 3.9902437184657784e-05, + "loss": 2.7626, + "num_input_tokens_seen": 2376720, + "step": 235 + }, + { + "epoch": 1.8096135721017907, + "grad_norm": 2.588127374649048, + "learning_rate": 3.9501422739279956e-05, + "loss": 2.8052, + "num_input_tokens_seen": 2429952, + "step": 240 + }, + { + "epoch": 1.8473138548539114, + "grad_norm": 2.1829710006713867, + "learning_rate": 3.909470421180201e-05, + "loss": 2.767, + "num_input_tokens_seen": 2481488, + "step": 245 + }, + { + "epoch": 1.885014137606032, + "grad_norm": 2.606924295425415, + "learning_rate": 3.8682441583483314e-05, + "loss": 2.7651, + "num_input_tokens_seen": 2530768, + "step": 250 + }, + { + "epoch": 1.9227144203581528, + "grad_norm": 2.3635494709014893, + "learning_rate": 3.8264797016335205e-05, + "loss": 2.8097, + "num_input_tokens_seen": 2583088, + "step": 255 + }, + { + "epoch": 1.9604147031102732, + "grad_norm": 2.560624361038208, + "learning_rate": 3.7841934789335164e-05, + "loss": 2.7269, + "num_input_tokens_seen": 2631456, + "step": 260 + }, + { + "epoch": 1.998114985862394, + "grad_norm": 2.7099437713623047, + "learning_rate": 3.741402123380828e-05, + "loss": 2.8586, + "num_input_tokens_seen": 2684848, + "step": 265 + }, + { + "epoch": 2.0358152686145146, + "grad_norm": 2.552143096923828, + "learning_rate": 3.6981224668001424e-05, + "loss": 2.6131, + "num_input_tokens_seen": 2733408, + "step": 270 + }, + { + "epoch": 2.0735155513666355, + "grad_norm": 2.9233176708221436, + "learning_rate": 3.654371533087586e-05, + "loss": 2.4891, + "num_input_tokens_seen": 2786832, + "step": 275 + }, + { + "epoch": 2.111215834118756, + "grad_norm": 2.7649636268615723, + "learning_rate": 3.610166531514436e-05, + "loss": 2.5783, + "num_input_tokens_seen": 2828464, + "step": 280 + }, + { + "epoch": 2.1489161168708764, + "grad_norm": 3.076122522354126, + "learning_rate": 3.565524849957921e-05, + "loss": 2.59, + "num_input_tokens_seen": 2878192, + "step": 285 + }, + { + "epoch": 2.1866163996229973, + "grad_norm": 3.242678642272949, + "learning_rate": 3.520464048061758e-05, + "loss": 2.5839, + "num_input_tokens_seen": 2928304, + "step": 290 + }, + { + "epoch": 2.2243166823751177, + "grad_norm": 3.139089584350586, + "learning_rate": 3.47500185032913e-05, + "loss": 2.567, + "num_input_tokens_seen": 2978144, + "step": 295 + }, + { + "epoch": 2.2620169651272386, + "grad_norm": 3.1967153549194336, + "learning_rate": 3.4291561391508185e-05, + "loss": 2.5694, + "num_input_tokens_seen": 3028240, + "step": 300 + } + ], + "logging_steps": 5, + "max_steps": 792, + "num_input_tokens_seen": 3028240, + "num_train_epochs": 6, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.367413199208448e+17, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f8accff7ed19f472e4ab59934a52cd1b74989284 --- /dev/null +++ b/checkpoint-300/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0abbac12d56c1934fca1078792064a59e7f00bea9a38a70efb9ce7fe81d8d0a2 +size 5432 diff --git a/checkpoint-400/README.md b/checkpoint-400/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ba199ae8c078d293275e50b0a850beb3a458a43e --- /dev/null +++ b/checkpoint-400/README.md @@ -0,0 +1,202 @@ +--- +base_model: NousResearch/Hermes-3-Llama-3.1-8B +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/checkpoint-400/adapter_config.json b/checkpoint-400/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4aa889ee5316659d91ab201b4f03e49477d31374 --- /dev/null +++ b/checkpoint-400/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "k_proj", + "v_proj", + "o_proj", + "down_proj", + "q_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-400/adapter_model.safetensors b/checkpoint-400/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c3ef839654963983c7a7a04bc844a0cda7d8a01d --- /dev/null +++ b/checkpoint-400/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e742cdb28a494e3db08f9700b0fc64f350555f1603bbfe726a08e0334caf989 +size 83945296 diff --git a/checkpoint-400/optimizer.pt b/checkpoint-400/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..121eba43f8a825988f968ea1128ecb6b1a9313a0 --- /dev/null +++ b/checkpoint-400/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b322aceeb1ca2d9a89f3fba69056d29168e9ddaa778feed389fcdefc685e2c9 +size 168149074 diff --git a/checkpoint-400/rng_state_0.pth b/checkpoint-400/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e39cd89edd6409a9e49b8db7f0d371695a2623d --- /dev/null +++ b/checkpoint-400/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9affc1541e7e94c18354d5173bc55400c5f07faf3d080c6d453d48e7a8d6ac3 +size 14512 diff --git a/checkpoint-400/rng_state_1.pth b/checkpoint-400/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..d1b839d26b0a64f427c73c634fb491ba9ddf3381 --- /dev/null +++ b/checkpoint-400/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4748c3ebf0e4c051c58b92e4a8c5b87cdb39d55cfdc2aec81a1baef0f02fc113 +size 14512 diff --git a/checkpoint-400/scheduler.pt b/checkpoint-400/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f81b56725280cc11fc5689d291a095dbb95bdb6 --- /dev/null +++ b/checkpoint-400/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f22ca2b24be2724497925de4a88dc3d652a6dcb3cb655731486697897d39d9be +size 1064 diff --git a/checkpoint-400/special_tokens_map.json b/checkpoint-400/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1ad7f173822ffa805bd5f390acc9c3390d414e67 --- /dev/null +++ b/checkpoint-400/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-400/tokenizer.json b/checkpoint-400/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b --- /dev/null +++ b/checkpoint-400/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05 +size 17209403 diff --git a/checkpoint-400/tokenizer_config.json b/checkpoint-400/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a22a366f4a4df58d908d0fa483648703588ce0b1 --- /dev/null +++ b/checkpoint-400/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128039": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128040": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|im_end|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-400/trainer_state.json b/checkpoint-400/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..4f2d6a89282bc6dbeba0e081418d8816c357876d --- /dev/null +++ b/checkpoint-400/trainer_state.json @@ -0,0 +1,673 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.016022620169651, + "eval_steps": 500, + "global_step": 400, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.03770028275212064, + "grad_norm": 3.988708734512329, + "learning_rate": 4.9995083170283816e-05, + "loss": 4.6192, + "num_input_tokens_seen": 50400, + "step": 5 + }, + { + "epoch": 0.07540056550424128, + "grad_norm": 2.142688512802124, + "learning_rate": 4.998033461515242e-05, + "loss": 3.9149, + "num_input_tokens_seen": 104016, + "step": 10 + }, + { + "epoch": 0.11310084825636192, + "grad_norm": 1.5928359031677246, + "learning_rate": 4.9955760135896534e-05, + "loss": 3.6912, + "num_input_tokens_seen": 155584, + "step": 15 + }, + { + "epoch": 0.15080113100848255, + "grad_norm": 1.5493167638778687, + "learning_rate": 4.992136939879856e-05, + "loss": 3.5556, + "num_input_tokens_seen": 202672, + "step": 20 + }, + { + "epoch": 0.1885014137606032, + "grad_norm": 1.7764347791671753, + "learning_rate": 4.9877175931330346e-05, + "loss": 3.4256, + "num_input_tokens_seen": 254800, + "step": 25 + }, + { + "epoch": 0.22620169651272384, + "grad_norm": 1.2482728958129883, + "learning_rate": 4.982319711683221e-05, + "loss": 3.3128, + "num_input_tokens_seen": 306352, + "step": 30 + }, + { + "epoch": 0.2639019792648445, + "grad_norm": 1.2829065322875977, + "learning_rate": 4.975945418767529e-05, + "loss": 3.2688, + "num_input_tokens_seen": 356352, + "step": 35 + }, + { + "epoch": 0.3016022620169651, + "grad_norm": 1.513293743133545, + "learning_rate": 4.968597221690986e-05, + "loss": 3.297, + "num_input_tokens_seen": 406672, + "step": 40 + }, + { + "epoch": 0.3393025447690858, + "grad_norm": 1.883090853691101, + "learning_rate": 4.96027801084029e-05, + "loss": 3.232, + "num_input_tokens_seen": 456160, + "step": 45 + }, + { + "epoch": 0.3770028275212064, + "grad_norm": 1.402272343635559, + "learning_rate": 4.950991058546893e-05, + "loss": 3.267, + "num_input_tokens_seen": 509680, + "step": 50 + }, + { + "epoch": 0.41470311027332707, + "grad_norm": 1.5488755702972412, + "learning_rate": 4.940740017799833e-05, + "loss": 3.2148, + "num_input_tokens_seen": 559968, + "step": 55 + }, + { + "epoch": 0.4524033930254477, + "grad_norm": 1.507287859916687, + "learning_rate": 4.929528920808854e-05, + "loss": 3.1403, + "num_input_tokens_seen": 610000, + "step": 60 + }, + { + "epoch": 0.49010367577756836, + "grad_norm": 1.9119170904159546, + "learning_rate": 4.917362177418342e-05, + "loss": 3.1515, + "num_input_tokens_seen": 661280, + "step": 65 + }, + { + "epoch": 0.527803958529689, + "grad_norm": 1.7253235578536987, + "learning_rate": 4.904244573372733e-05, + "loss": 3.1468, + "num_input_tokens_seen": 713264, + "step": 70 + }, + { + "epoch": 0.5655042412818096, + "grad_norm": 1.7201606035232544, + "learning_rate": 4.8901812684340564e-05, + "loss": 3.196, + "num_input_tokens_seen": 762576, + "step": 75 + }, + { + "epoch": 0.6032045240339302, + "grad_norm": 1.6135213375091553, + "learning_rate": 4.8751777943523634e-05, + "loss": 3.0593, + "num_input_tokens_seen": 813392, + "step": 80 + }, + { + "epoch": 0.6409048067860509, + "grad_norm": 1.7381868362426758, + "learning_rate": 4.8592400526898314e-05, + "loss": 3.0676, + "num_input_tokens_seen": 860608, + "step": 85 + }, + { + "epoch": 0.6786050895381716, + "grad_norm": 1.6142843961715698, + "learning_rate": 4.842374312499405e-05, + "loss": 3.1061, + "num_input_tokens_seen": 909104, + "step": 90 + }, + { + "epoch": 0.7163053722902922, + "grad_norm": 2.0389633178710938, + "learning_rate": 4.824587207858888e-05, + "loss": 2.9847, + "num_input_tokens_seen": 959600, + "step": 95 + }, + { + "epoch": 0.7540056550424128, + "grad_norm": 1.923561692237854, + "learning_rate": 4.805885735261454e-05, + "loss": 3.0289, + "num_input_tokens_seen": 1013648, + "step": 100 + }, + { + "epoch": 0.7917059377945335, + "grad_norm": 2.0325896739959717, + "learning_rate": 4.786277250863599e-05, + "loss": 2.9474, + "num_input_tokens_seen": 1065120, + "step": 105 + }, + { + "epoch": 0.8294062205466541, + "grad_norm": 1.6685590744018555, + "learning_rate": 4.765769467591625e-05, + "loss": 2.9713, + "num_input_tokens_seen": 1119424, + "step": 110 + }, + { + "epoch": 0.8671065032987747, + "grad_norm": 2.0325937271118164, + "learning_rate": 4.744370452107789e-05, + "loss": 3.0012, + "num_input_tokens_seen": 1169888, + "step": 115 + }, + { + "epoch": 0.9048067860508954, + "grad_norm": 1.7548010349273682, + "learning_rate": 4.722088621637309e-05, + "loss": 3.0399, + "num_input_tokens_seen": 1218944, + "step": 120 + }, + { + "epoch": 0.942507068803016, + "grad_norm": 1.6709191799163818, + "learning_rate": 4.698932740657479e-05, + "loss": 2.9156, + "num_input_tokens_seen": 1269920, + "step": 125 + }, + { + "epoch": 0.9802073515551367, + "grad_norm": 1.8369653224945068, + "learning_rate": 4.6749119174501975e-05, + "loss": 3.0288, + "num_input_tokens_seen": 1315536, + "step": 130 + }, + { + "epoch": 1.0179076343072573, + "grad_norm": 1.800703525543213, + "learning_rate": 4.6500356005192514e-05, + "loss": 2.8911, + "num_input_tokens_seen": 1360736, + "step": 135 + }, + { + "epoch": 1.055607917059378, + "grad_norm": 1.7134617567062378, + "learning_rate": 4.6243135748737864e-05, + "loss": 2.9148, + "num_input_tokens_seen": 1409808, + "step": 140 + }, + { + "epoch": 1.0933081998114986, + "grad_norm": 1.9385241270065308, + "learning_rate": 4.597755958179406e-05, + "loss": 2.868, + "num_input_tokens_seen": 1460864, + "step": 145 + }, + { + "epoch": 1.1310084825636193, + "grad_norm": 2.1658332347869873, + "learning_rate": 4.570373196778427e-05, + "loss": 2.7477, + "num_input_tokens_seen": 1512640, + "step": 150 + }, + { + "epoch": 1.1687087653157398, + "grad_norm": 2.239896774291992, + "learning_rate": 4.5421760615808474e-05, + "loss": 2.932, + "num_input_tokens_seen": 1556048, + "step": 155 + }, + { + "epoch": 1.2064090480678604, + "grad_norm": 2.0555717945098877, + "learning_rate": 4.513175643827647e-05, + "loss": 2.8219, + "num_input_tokens_seen": 1607232, + "step": 160 + }, + { + "epoch": 1.244109330819981, + "grad_norm": 2.0288779735565186, + "learning_rate": 4.4833833507280884e-05, + "loss": 2.8453, + "num_input_tokens_seen": 1653520, + "step": 165 + }, + { + "epoch": 1.2818096135721018, + "grad_norm": 1.9268651008605957, + "learning_rate": 4.4528109009727336e-05, + "loss": 2.7362, + "num_input_tokens_seen": 1703568, + "step": 170 + }, + { + "epoch": 1.3195098963242224, + "grad_norm": 2.413874387741089, + "learning_rate": 4.42147032012394e-05, + "loss": 2.9197, + "num_input_tokens_seen": 1752944, + "step": 175 + }, + { + "epoch": 1.3572101790763431, + "grad_norm": 2.2018630504608154, + "learning_rate": 4.389373935885646e-05, + "loss": 2.8897, + "num_input_tokens_seen": 1805600, + "step": 180 + }, + { + "epoch": 1.3949104618284638, + "grad_norm": 2.1807219982147217, + "learning_rate": 4.356534373254316e-05, + "loss": 2.7946, + "num_input_tokens_seen": 1860688, + "step": 185 + }, + { + "epoch": 1.4326107445805842, + "grad_norm": 2.2928526401519775, + "learning_rate": 4.322964549552943e-05, + "loss": 2.8149, + "num_input_tokens_seen": 1913056, + "step": 190 + }, + { + "epoch": 1.4703110273327051, + "grad_norm": 2.204533576965332, + "learning_rate": 4.288677669350066e-05, + "loss": 2.7811, + "num_input_tokens_seen": 1961744, + "step": 195 + }, + { + "epoch": 1.5080113100848256, + "grad_norm": 2.925762414932251, + "learning_rate": 4.2536872192658036e-05, + "loss": 2.8564, + "num_input_tokens_seen": 2011248, + "step": 200 + }, + { + "epoch": 1.5457115928369463, + "grad_norm": 2.398651599884033, + "learning_rate": 4.218006962666934e-05, + "loss": 2.7966, + "num_input_tokens_seen": 2060640, + "step": 205 + }, + { + "epoch": 1.583411875589067, + "grad_norm": 2.452263355255127, + "learning_rate": 4.181650934253132e-05, + "loss": 2.7674, + "num_input_tokens_seen": 2113904, + "step": 210 + }, + { + "epoch": 1.6211121583411876, + "grad_norm": 2.5911788940429688, + "learning_rate": 4.144633434536467e-05, + "loss": 2.7607, + "num_input_tokens_seen": 2162608, + "step": 215 + }, + { + "epoch": 1.6588124410933083, + "grad_norm": 2.648517608642578, + "learning_rate": 4.1069690242163484e-05, + "loss": 2.8402, + "num_input_tokens_seen": 2211616, + "step": 220 + }, + { + "epoch": 1.6965127238454287, + "grad_norm": 2.6860735416412354, + "learning_rate": 4.06867251845213e-05, + "loss": 2.8019, + "num_input_tokens_seen": 2269440, + "step": 225 + }, + { + "epoch": 1.7342130065975496, + "grad_norm": 2.5891222953796387, + "learning_rate": 4.0297589810356165e-05, + "loss": 2.8311, + "num_input_tokens_seen": 2321936, + "step": 230 + }, + { + "epoch": 1.77191328934967, + "grad_norm": 2.695114850997925, + "learning_rate": 3.9902437184657784e-05, + "loss": 2.7626, + "num_input_tokens_seen": 2376720, + "step": 235 + }, + { + "epoch": 1.8096135721017907, + "grad_norm": 2.588127374649048, + "learning_rate": 3.9501422739279956e-05, + "loss": 2.8052, + "num_input_tokens_seen": 2429952, + "step": 240 + }, + { + "epoch": 1.8473138548539114, + "grad_norm": 2.1829710006713867, + "learning_rate": 3.909470421180201e-05, + "loss": 2.767, + "num_input_tokens_seen": 2481488, + "step": 245 + }, + { + "epoch": 1.885014137606032, + "grad_norm": 2.606924295425415, + "learning_rate": 3.8682441583483314e-05, + "loss": 2.7651, + "num_input_tokens_seen": 2530768, + "step": 250 + }, + { + "epoch": 1.9227144203581528, + "grad_norm": 2.3635494709014893, + "learning_rate": 3.8264797016335205e-05, + "loss": 2.8097, + "num_input_tokens_seen": 2583088, + "step": 255 + }, + { + "epoch": 1.9604147031102732, + "grad_norm": 2.560624361038208, + "learning_rate": 3.7841934789335164e-05, + "loss": 2.7269, + "num_input_tokens_seen": 2631456, + "step": 260 + }, + { + "epoch": 1.998114985862394, + "grad_norm": 2.7099437713623047, + "learning_rate": 3.741402123380828e-05, + "loss": 2.8586, + "num_input_tokens_seen": 2684848, + "step": 265 + }, + { + "epoch": 2.0358152686145146, + "grad_norm": 2.552143096923828, + "learning_rate": 3.6981224668001424e-05, + "loss": 2.6131, + "num_input_tokens_seen": 2733408, + "step": 270 + }, + { + "epoch": 2.0735155513666355, + "grad_norm": 2.9233176708221436, + "learning_rate": 3.654371533087586e-05, + "loss": 2.4891, + "num_input_tokens_seen": 2786832, + "step": 275 + }, + { + "epoch": 2.111215834118756, + "grad_norm": 2.7649636268615723, + "learning_rate": 3.610166531514436e-05, + "loss": 2.5783, + "num_input_tokens_seen": 2828464, + "step": 280 + }, + { + "epoch": 2.1489161168708764, + "grad_norm": 3.076122522354126, + "learning_rate": 3.565524849957921e-05, + "loss": 2.59, + "num_input_tokens_seen": 2878192, + "step": 285 + }, + { + "epoch": 2.1866163996229973, + "grad_norm": 3.242678642272949, + "learning_rate": 3.520464048061758e-05, + "loss": 2.5839, + "num_input_tokens_seen": 2928304, + "step": 290 + }, + { + "epoch": 2.2243166823751177, + "grad_norm": 3.139089584350586, + "learning_rate": 3.47500185032913e-05, + "loss": 2.567, + "num_input_tokens_seen": 2978144, + "step": 295 + }, + { + "epoch": 2.2620169651272386, + "grad_norm": 3.1967153549194336, + "learning_rate": 3.4291561391508185e-05, + "loss": 2.5694, + "num_input_tokens_seen": 3028240, + "step": 300 + }, + { + "epoch": 2.299717247879359, + "grad_norm": 3.1987555027008057, + "learning_rate": 3.3829449477712324e-05, + "loss": 2.4965, + "num_input_tokens_seen": 3083328, + "step": 305 + }, + { + "epoch": 2.3374175306314795, + "grad_norm": 3.4724180698394775, + "learning_rate": 3.336386453195088e-05, + "loss": 2.599, + "num_input_tokens_seen": 3137072, + "step": 310 + }, + { + "epoch": 2.3751178133836004, + "grad_norm": 3.381075143814087, + "learning_rate": 3.2894989690375626e-05, + "loss": 2.524, + "num_input_tokens_seen": 3191136, + "step": 315 + }, + { + "epoch": 2.412818096135721, + "grad_norm": 3.650747537612915, + "learning_rate": 3.2423009383206876e-05, + "loss": 2.5338, + "num_input_tokens_seen": 3239952, + "step": 320 + }, + { + "epoch": 2.4505183788878417, + "grad_norm": 3.3886971473693848, + "learning_rate": 3.194810926218861e-05, + "loss": 2.5096, + "num_input_tokens_seen": 3291104, + "step": 325 + }, + { + "epoch": 2.488218661639962, + "grad_norm": 3.415850877761841, + "learning_rate": 3.147047612756302e-05, + "loss": 2.473, + "num_input_tokens_seen": 3340592, + "step": 330 + }, + { + "epoch": 2.525918944392083, + "grad_norm": 3.513828754425049, + "learning_rate": 3.099029785459328e-05, + "loss": 2.5778, + "num_input_tokens_seen": 3388224, + "step": 335 + }, + { + "epoch": 2.5636192271442035, + "grad_norm": 3.49721360206604, + "learning_rate": 3.0507763319663517e-05, + "loss": 2.5684, + "num_input_tokens_seen": 3440512, + "step": 340 + }, + { + "epoch": 2.6013195098963244, + "grad_norm": 3.5137672424316406, + "learning_rate": 3.002306232598497e-05, + "loss": 2.4923, + "num_input_tokens_seen": 3491744, + "step": 345 + }, + { + "epoch": 2.639019792648445, + "grad_norm": 3.7216403484344482, + "learning_rate": 2.9536385528937567e-05, + "loss": 2.4633, + "num_input_tokens_seen": 3542368, + "step": 350 + }, + { + "epoch": 2.6767200754005653, + "grad_norm": 3.48529052734375, + "learning_rate": 2.9047924361076345e-05, + "loss": 2.5703, + "num_input_tokens_seen": 3595360, + "step": 355 + }, + { + "epoch": 2.7144203581526862, + "grad_norm": 3.4676520824432373, + "learning_rate": 2.8557870956832132e-05, + "loss": 2.4087, + "num_input_tokens_seen": 3640912, + "step": 360 + }, + { + "epoch": 2.7521206409048067, + "grad_norm": 4.316717147827148, + "learning_rate": 2.8066418076936167e-05, + "loss": 2.5007, + "num_input_tokens_seen": 3690048, + "step": 365 + }, + { + "epoch": 2.7898209236569276, + "grad_norm": 4.2354736328125, + "learning_rate": 2.7573759032598366e-05, + "loss": 2.5312, + "num_input_tokens_seen": 3745104, + "step": 370 + }, + { + "epoch": 2.827521206409048, + "grad_norm": 3.457280397415161, + "learning_rate": 2.7080087609469062e-05, + "loss": 2.5333, + "num_input_tokens_seen": 3794160, + "step": 375 + }, + { + "epoch": 2.8652214891611685, + "grad_norm": 3.417656183242798, + "learning_rate": 2.6585597991414114e-05, + "loss": 2.4185, + "num_input_tokens_seen": 3846576, + "step": 380 + }, + { + "epoch": 2.9029217719132894, + "grad_norm": 3.7148749828338623, + "learning_rate": 2.6090484684133404e-05, + "loss": 2.4913, + "num_input_tokens_seen": 3891744, + "step": 385 + }, + { + "epoch": 2.9406220546654103, + "grad_norm": 3.562427520751953, + "learning_rate": 2.5594942438652688e-05, + "loss": 2.5319, + "num_input_tokens_seen": 3949568, + "step": 390 + }, + { + "epoch": 2.9783223374175307, + "grad_norm": 4.2560505867004395, + "learning_rate": 2.509916617471903e-05, + "loss": 2.6441, + "num_input_tokens_seen": 4002384, + "step": 395 + }, + { + "epoch": 3.016022620169651, + "grad_norm": 3.349701166152954, + "learning_rate": 2.46033509041298e-05, + "loss": 2.3576, + "num_input_tokens_seen": 4052688, + "step": 400 + } + ], + "logging_steps": 5, + "max_steps": 792, + "num_input_tokens_seen": 4052688, + "num_train_epochs": 6, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.830006553533481e+17, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-400/training_args.bin b/checkpoint-400/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f8accff7ed19f472e4ab59934a52cd1b74989284 --- /dev/null +++ b/checkpoint-400/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0abbac12d56c1934fca1078792064a59e7f00bea9a38a70efb9ce7fe81d8d0a2 +size 5432 diff --git a/checkpoint-500/README.md b/checkpoint-500/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ba199ae8c078d293275e50b0a850beb3a458a43e --- /dev/null +++ b/checkpoint-500/README.md @@ -0,0 +1,202 @@ +--- +base_model: NousResearch/Hermes-3-Llama-3.1-8B +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/checkpoint-500/adapter_config.json b/checkpoint-500/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4aa889ee5316659d91ab201b4f03e49477d31374 --- /dev/null +++ b/checkpoint-500/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "k_proj", + "v_proj", + "o_proj", + "down_proj", + "q_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-500/adapter_model.safetensors b/checkpoint-500/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fa0db92de33ac508cd224623c194e2c89943a3fc --- /dev/null +++ b/checkpoint-500/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:418021406f6f19ef641f40e9096b551e17e5800e3eb4ba9381e416f34dd765a8 +size 83945296 diff --git a/checkpoint-500/optimizer.pt b/checkpoint-500/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a95bfd0eec422931b5d8cbebee1a4f0f5362543 --- /dev/null +++ b/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89da9c269b055d18f2e7564d6307a02f0f16187624f2b52e9f44f326e170a41d +size 168149074 diff --git a/checkpoint-500/rng_state_0.pth b/checkpoint-500/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e39cd89edd6409a9e49b8db7f0d371695a2623d --- /dev/null +++ b/checkpoint-500/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9affc1541e7e94c18354d5173bc55400c5f07faf3d080c6d453d48e7a8d6ac3 +size 14512 diff --git a/checkpoint-500/rng_state_1.pth b/checkpoint-500/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..d1b839d26b0a64f427c73c634fb491ba9ddf3381 --- /dev/null +++ b/checkpoint-500/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4748c3ebf0e4c051c58b92e4a8c5b87cdb39d55cfdc2aec81a1baef0f02fc113 +size 14512 diff --git a/checkpoint-500/scheduler.pt b/checkpoint-500/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..2513a608779571bfcb21ffa99571a895303f452a --- /dev/null +++ b/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d076f944dc4da9aa8bf3d62dfd4d58d668f38c8a828d05146d0cbc3944cf8eb +size 1064 diff --git a/checkpoint-500/special_tokens_map.json b/checkpoint-500/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1ad7f173822ffa805bd5f390acc9c3390d414e67 --- /dev/null +++ b/checkpoint-500/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-500/tokenizer.json b/checkpoint-500/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b --- /dev/null +++ b/checkpoint-500/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05 +size 17209403 diff --git a/checkpoint-500/tokenizer_config.json b/checkpoint-500/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a22a366f4a4df58d908d0fa483648703588ce0b1 --- /dev/null +++ b/checkpoint-500/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128039": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128040": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|im_end|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-500/trainer_state.json b/checkpoint-500/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..48a0f703a3b5421c2da8282529d50f2e509f8547 --- /dev/null +++ b/checkpoint-500/trainer_state.json @@ -0,0 +1,833 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.770028275212064, + "eval_steps": 500, + "global_step": 500, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.03770028275212064, + "grad_norm": 3.988708734512329, + "learning_rate": 4.9995083170283816e-05, + "loss": 4.6192, + "num_input_tokens_seen": 50400, + "step": 5 + }, + { + "epoch": 0.07540056550424128, + "grad_norm": 2.142688512802124, + "learning_rate": 4.998033461515242e-05, + "loss": 3.9149, + "num_input_tokens_seen": 104016, + "step": 10 + }, + { + "epoch": 0.11310084825636192, + "grad_norm": 1.5928359031677246, + "learning_rate": 4.9955760135896534e-05, + "loss": 3.6912, + "num_input_tokens_seen": 155584, + "step": 15 + }, + { + "epoch": 0.15080113100848255, + "grad_norm": 1.5493167638778687, + "learning_rate": 4.992136939879856e-05, + "loss": 3.5556, + "num_input_tokens_seen": 202672, + "step": 20 + }, + { + "epoch": 0.1885014137606032, + "grad_norm": 1.7764347791671753, + "learning_rate": 4.9877175931330346e-05, + "loss": 3.4256, + "num_input_tokens_seen": 254800, + "step": 25 + }, + { + "epoch": 0.22620169651272384, + "grad_norm": 1.2482728958129883, + "learning_rate": 4.982319711683221e-05, + "loss": 3.3128, + "num_input_tokens_seen": 306352, + "step": 30 + }, + { + "epoch": 0.2639019792648445, + "grad_norm": 1.2829065322875977, + "learning_rate": 4.975945418767529e-05, + "loss": 3.2688, + "num_input_tokens_seen": 356352, + "step": 35 + }, + { + "epoch": 0.3016022620169651, + "grad_norm": 1.513293743133545, + "learning_rate": 4.968597221690986e-05, + "loss": 3.297, + "num_input_tokens_seen": 406672, + "step": 40 + }, + { + "epoch": 0.3393025447690858, + "grad_norm": 1.883090853691101, + "learning_rate": 4.96027801084029e-05, + "loss": 3.232, + "num_input_tokens_seen": 456160, + "step": 45 + }, + { + "epoch": 0.3770028275212064, + "grad_norm": 1.402272343635559, + "learning_rate": 4.950991058546893e-05, + "loss": 3.267, + "num_input_tokens_seen": 509680, + "step": 50 + }, + { + "epoch": 0.41470311027332707, + "grad_norm": 1.5488755702972412, + "learning_rate": 4.940740017799833e-05, + "loss": 3.2148, + "num_input_tokens_seen": 559968, + "step": 55 + }, + { + "epoch": 0.4524033930254477, + "grad_norm": 1.507287859916687, + "learning_rate": 4.929528920808854e-05, + "loss": 3.1403, + "num_input_tokens_seen": 610000, + "step": 60 + }, + { + "epoch": 0.49010367577756836, + "grad_norm": 1.9119170904159546, + "learning_rate": 4.917362177418342e-05, + "loss": 3.1515, + "num_input_tokens_seen": 661280, + "step": 65 + }, + { + "epoch": 0.527803958529689, + "grad_norm": 1.7253235578536987, + "learning_rate": 4.904244573372733e-05, + "loss": 3.1468, + "num_input_tokens_seen": 713264, + "step": 70 + }, + { + "epoch": 0.5655042412818096, + "grad_norm": 1.7201606035232544, + "learning_rate": 4.8901812684340564e-05, + "loss": 3.196, + "num_input_tokens_seen": 762576, + "step": 75 + }, + { + "epoch": 0.6032045240339302, + "grad_norm": 1.6135213375091553, + "learning_rate": 4.8751777943523634e-05, + "loss": 3.0593, + "num_input_tokens_seen": 813392, + "step": 80 + }, + { + "epoch": 0.6409048067860509, + "grad_norm": 1.7381868362426758, + "learning_rate": 4.8592400526898314e-05, + "loss": 3.0676, + "num_input_tokens_seen": 860608, + "step": 85 + }, + { + "epoch": 0.6786050895381716, + "grad_norm": 1.6142843961715698, + "learning_rate": 4.842374312499405e-05, + "loss": 3.1061, + "num_input_tokens_seen": 909104, + "step": 90 + }, + { + "epoch": 0.7163053722902922, + "grad_norm": 2.0389633178710938, + "learning_rate": 4.824587207858888e-05, + "loss": 2.9847, + "num_input_tokens_seen": 959600, + "step": 95 + }, + { + "epoch": 0.7540056550424128, + "grad_norm": 1.923561692237854, + "learning_rate": 4.805885735261454e-05, + "loss": 3.0289, + "num_input_tokens_seen": 1013648, + "step": 100 + }, + { + "epoch": 0.7917059377945335, + "grad_norm": 2.0325896739959717, + "learning_rate": 4.786277250863599e-05, + "loss": 2.9474, + "num_input_tokens_seen": 1065120, + "step": 105 + }, + { + "epoch": 0.8294062205466541, + "grad_norm": 1.6685590744018555, + "learning_rate": 4.765769467591625e-05, + "loss": 2.9713, + "num_input_tokens_seen": 1119424, + "step": 110 + }, + { + "epoch": 0.8671065032987747, + "grad_norm": 2.0325937271118164, + "learning_rate": 4.744370452107789e-05, + "loss": 3.0012, + "num_input_tokens_seen": 1169888, + "step": 115 + }, + { + "epoch": 0.9048067860508954, + "grad_norm": 1.7548010349273682, + "learning_rate": 4.722088621637309e-05, + "loss": 3.0399, + "num_input_tokens_seen": 1218944, + "step": 120 + }, + { + "epoch": 0.942507068803016, + "grad_norm": 1.6709191799163818, + "learning_rate": 4.698932740657479e-05, + "loss": 2.9156, + "num_input_tokens_seen": 1269920, + "step": 125 + }, + { + "epoch": 0.9802073515551367, + "grad_norm": 1.8369653224945068, + "learning_rate": 4.6749119174501975e-05, + "loss": 3.0288, + "num_input_tokens_seen": 1315536, + "step": 130 + }, + { + "epoch": 1.0179076343072573, + "grad_norm": 1.800703525543213, + "learning_rate": 4.6500356005192514e-05, + "loss": 2.8911, + "num_input_tokens_seen": 1360736, + "step": 135 + }, + { + "epoch": 1.055607917059378, + "grad_norm": 1.7134617567062378, + "learning_rate": 4.6243135748737864e-05, + "loss": 2.9148, + "num_input_tokens_seen": 1409808, + "step": 140 + }, + { + "epoch": 1.0933081998114986, + "grad_norm": 1.9385241270065308, + "learning_rate": 4.597755958179406e-05, + "loss": 2.868, + "num_input_tokens_seen": 1460864, + "step": 145 + }, + { + "epoch": 1.1310084825636193, + "grad_norm": 2.1658332347869873, + "learning_rate": 4.570373196778427e-05, + "loss": 2.7477, + "num_input_tokens_seen": 1512640, + "step": 150 + }, + { + "epoch": 1.1687087653157398, + "grad_norm": 2.239896774291992, + "learning_rate": 4.5421760615808474e-05, + "loss": 2.932, + "num_input_tokens_seen": 1556048, + "step": 155 + }, + { + "epoch": 1.2064090480678604, + "grad_norm": 2.0555717945098877, + "learning_rate": 4.513175643827647e-05, + "loss": 2.8219, + "num_input_tokens_seen": 1607232, + "step": 160 + }, + { + "epoch": 1.244109330819981, + "grad_norm": 2.0288779735565186, + "learning_rate": 4.4833833507280884e-05, + "loss": 2.8453, + "num_input_tokens_seen": 1653520, + "step": 165 + }, + { + "epoch": 1.2818096135721018, + "grad_norm": 1.9268651008605957, + "learning_rate": 4.4528109009727336e-05, + "loss": 2.7362, + "num_input_tokens_seen": 1703568, + "step": 170 + }, + { + "epoch": 1.3195098963242224, + "grad_norm": 2.413874387741089, + "learning_rate": 4.42147032012394e-05, + "loss": 2.9197, + "num_input_tokens_seen": 1752944, + "step": 175 + }, + { + "epoch": 1.3572101790763431, + "grad_norm": 2.2018630504608154, + "learning_rate": 4.389373935885646e-05, + "loss": 2.8897, + "num_input_tokens_seen": 1805600, + "step": 180 + }, + { + "epoch": 1.3949104618284638, + "grad_norm": 2.1807219982147217, + "learning_rate": 4.356534373254316e-05, + "loss": 2.7946, + "num_input_tokens_seen": 1860688, + "step": 185 + }, + { + "epoch": 1.4326107445805842, + "grad_norm": 2.2928526401519775, + "learning_rate": 4.322964549552943e-05, + "loss": 2.8149, + "num_input_tokens_seen": 1913056, + "step": 190 + }, + { + "epoch": 1.4703110273327051, + "grad_norm": 2.204533576965332, + "learning_rate": 4.288677669350066e-05, + "loss": 2.7811, + "num_input_tokens_seen": 1961744, + "step": 195 + }, + { + "epoch": 1.5080113100848256, + "grad_norm": 2.925762414932251, + "learning_rate": 4.2536872192658036e-05, + "loss": 2.8564, + "num_input_tokens_seen": 2011248, + "step": 200 + }, + { + "epoch": 1.5457115928369463, + "grad_norm": 2.398651599884033, + "learning_rate": 4.218006962666934e-05, + "loss": 2.7966, + "num_input_tokens_seen": 2060640, + "step": 205 + }, + { + "epoch": 1.583411875589067, + "grad_norm": 2.452263355255127, + "learning_rate": 4.181650934253132e-05, + "loss": 2.7674, + "num_input_tokens_seen": 2113904, + "step": 210 + }, + { + "epoch": 1.6211121583411876, + "grad_norm": 2.5911788940429688, + "learning_rate": 4.144633434536467e-05, + "loss": 2.7607, + "num_input_tokens_seen": 2162608, + "step": 215 + }, + { + "epoch": 1.6588124410933083, + "grad_norm": 2.648517608642578, + "learning_rate": 4.1069690242163484e-05, + "loss": 2.8402, + "num_input_tokens_seen": 2211616, + "step": 220 + }, + { + "epoch": 1.6965127238454287, + "grad_norm": 2.6860735416412354, + "learning_rate": 4.06867251845213e-05, + "loss": 2.8019, + "num_input_tokens_seen": 2269440, + "step": 225 + }, + { + "epoch": 1.7342130065975496, + "grad_norm": 2.5891222953796387, + "learning_rate": 4.0297589810356165e-05, + "loss": 2.8311, + "num_input_tokens_seen": 2321936, + "step": 230 + }, + { + "epoch": 1.77191328934967, + "grad_norm": 2.695114850997925, + "learning_rate": 3.9902437184657784e-05, + "loss": 2.7626, + "num_input_tokens_seen": 2376720, + "step": 235 + }, + { + "epoch": 1.8096135721017907, + "grad_norm": 2.588127374649048, + "learning_rate": 3.9501422739279956e-05, + "loss": 2.8052, + "num_input_tokens_seen": 2429952, + "step": 240 + }, + { + "epoch": 1.8473138548539114, + "grad_norm": 2.1829710006713867, + "learning_rate": 3.909470421180201e-05, + "loss": 2.767, + "num_input_tokens_seen": 2481488, + "step": 245 + }, + { + "epoch": 1.885014137606032, + "grad_norm": 2.606924295425415, + "learning_rate": 3.8682441583483314e-05, + "loss": 2.7651, + "num_input_tokens_seen": 2530768, + "step": 250 + }, + { + "epoch": 1.9227144203581528, + "grad_norm": 2.3635494709014893, + "learning_rate": 3.8264797016335205e-05, + "loss": 2.8097, + "num_input_tokens_seen": 2583088, + "step": 255 + }, + { + "epoch": 1.9604147031102732, + "grad_norm": 2.560624361038208, + "learning_rate": 3.7841934789335164e-05, + "loss": 2.7269, + "num_input_tokens_seen": 2631456, + "step": 260 + }, + { + "epoch": 1.998114985862394, + "grad_norm": 2.7099437713623047, + "learning_rate": 3.741402123380828e-05, + "loss": 2.8586, + "num_input_tokens_seen": 2684848, + "step": 265 + }, + { + "epoch": 2.0358152686145146, + "grad_norm": 2.552143096923828, + "learning_rate": 3.6981224668001424e-05, + "loss": 2.6131, + "num_input_tokens_seen": 2733408, + "step": 270 + }, + { + "epoch": 2.0735155513666355, + "grad_norm": 2.9233176708221436, + "learning_rate": 3.654371533087586e-05, + "loss": 2.4891, + "num_input_tokens_seen": 2786832, + "step": 275 + }, + { + "epoch": 2.111215834118756, + "grad_norm": 2.7649636268615723, + "learning_rate": 3.610166531514436e-05, + "loss": 2.5783, + "num_input_tokens_seen": 2828464, + "step": 280 + }, + { + "epoch": 2.1489161168708764, + "grad_norm": 3.076122522354126, + "learning_rate": 3.565524849957921e-05, + "loss": 2.59, + "num_input_tokens_seen": 2878192, + "step": 285 + }, + { + "epoch": 2.1866163996229973, + "grad_norm": 3.242678642272949, + "learning_rate": 3.520464048061758e-05, + "loss": 2.5839, + "num_input_tokens_seen": 2928304, + "step": 290 + }, + { + "epoch": 2.2243166823751177, + "grad_norm": 3.139089584350586, + "learning_rate": 3.47500185032913e-05, + "loss": 2.567, + "num_input_tokens_seen": 2978144, + "step": 295 + }, + { + "epoch": 2.2620169651272386, + "grad_norm": 3.1967153549194336, + "learning_rate": 3.4291561391508185e-05, + "loss": 2.5694, + "num_input_tokens_seen": 3028240, + "step": 300 + }, + { + "epoch": 2.299717247879359, + "grad_norm": 3.1987555027008057, + "learning_rate": 3.3829449477712324e-05, + "loss": 2.4965, + "num_input_tokens_seen": 3083328, + "step": 305 + }, + { + "epoch": 2.3374175306314795, + "grad_norm": 3.4724180698394775, + "learning_rate": 3.336386453195088e-05, + "loss": 2.599, + "num_input_tokens_seen": 3137072, + "step": 310 + }, + { + "epoch": 2.3751178133836004, + "grad_norm": 3.381075143814087, + "learning_rate": 3.2894989690375626e-05, + "loss": 2.524, + "num_input_tokens_seen": 3191136, + "step": 315 + }, + { + "epoch": 2.412818096135721, + "grad_norm": 3.650747537612915, + "learning_rate": 3.2423009383206876e-05, + "loss": 2.5338, + "num_input_tokens_seen": 3239952, + "step": 320 + }, + { + "epoch": 2.4505183788878417, + "grad_norm": 3.3886971473693848, + "learning_rate": 3.194810926218861e-05, + "loss": 2.5096, + "num_input_tokens_seen": 3291104, + "step": 325 + }, + { + "epoch": 2.488218661639962, + "grad_norm": 3.415850877761841, + "learning_rate": 3.147047612756302e-05, + "loss": 2.473, + "num_input_tokens_seen": 3340592, + "step": 330 + }, + { + "epoch": 2.525918944392083, + "grad_norm": 3.513828754425049, + "learning_rate": 3.099029785459328e-05, + "loss": 2.5778, + "num_input_tokens_seen": 3388224, + "step": 335 + }, + { + "epoch": 2.5636192271442035, + "grad_norm": 3.49721360206604, + "learning_rate": 3.0507763319663517e-05, + "loss": 2.5684, + "num_input_tokens_seen": 3440512, + "step": 340 + }, + { + "epoch": 2.6013195098963244, + "grad_norm": 3.5137672424316406, + "learning_rate": 3.002306232598497e-05, + "loss": 2.4923, + "num_input_tokens_seen": 3491744, + "step": 345 + }, + { + "epoch": 2.639019792648445, + "grad_norm": 3.7216403484344482, + "learning_rate": 2.9536385528937567e-05, + "loss": 2.4633, + "num_input_tokens_seen": 3542368, + "step": 350 + }, + { + "epoch": 2.6767200754005653, + "grad_norm": 3.48529052734375, + "learning_rate": 2.9047924361076345e-05, + "loss": 2.5703, + "num_input_tokens_seen": 3595360, + "step": 355 + }, + { + "epoch": 2.7144203581526862, + "grad_norm": 3.4676520824432373, + "learning_rate": 2.8557870956832132e-05, + "loss": 2.4087, + "num_input_tokens_seen": 3640912, + "step": 360 + }, + { + "epoch": 2.7521206409048067, + "grad_norm": 4.316717147827148, + "learning_rate": 2.8066418076936167e-05, + "loss": 2.5007, + "num_input_tokens_seen": 3690048, + "step": 365 + }, + { + "epoch": 2.7898209236569276, + "grad_norm": 4.2354736328125, + "learning_rate": 2.7573759032598366e-05, + "loss": 2.5312, + "num_input_tokens_seen": 3745104, + "step": 370 + }, + { + "epoch": 2.827521206409048, + "grad_norm": 3.457280397415161, + "learning_rate": 2.7080087609469062e-05, + "loss": 2.5333, + "num_input_tokens_seen": 3794160, + "step": 375 + }, + { + "epoch": 2.8652214891611685, + "grad_norm": 3.417656183242798, + "learning_rate": 2.6585597991414114e-05, + "loss": 2.4185, + "num_input_tokens_seen": 3846576, + "step": 380 + }, + { + "epoch": 2.9029217719132894, + "grad_norm": 3.7148749828338623, + "learning_rate": 2.6090484684133404e-05, + "loss": 2.4913, + "num_input_tokens_seen": 3891744, + "step": 385 + }, + { + "epoch": 2.9406220546654103, + "grad_norm": 3.562427520751953, + "learning_rate": 2.5594942438652688e-05, + "loss": 2.5319, + "num_input_tokens_seen": 3949568, + "step": 390 + }, + { + "epoch": 2.9783223374175307, + "grad_norm": 4.2560505867004395, + "learning_rate": 2.509916617471903e-05, + "loss": 2.6441, + "num_input_tokens_seen": 4002384, + "step": 395 + }, + { + "epoch": 3.016022620169651, + "grad_norm": 3.349701166152954, + "learning_rate": 2.46033509041298e-05, + "loss": 2.3576, + "num_input_tokens_seen": 4052688, + "step": 400 + }, + { + "epoch": 3.053722902921772, + "grad_norm": 3.660886287689209, + "learning_rate": 2.410769165402549e-05, + "loss": 2.3032, + "num_input_tokens_seen": 4107392, + "step": 405 + }, + { + "epoch": 3.0914231856738925, + "grad_norm": 4.248249530792236, + "learning_rate": 2.3612383390176503e-05, + "loss": 2.2542, + "num_input_tokens_seen": 4157984, + "step": 410 + }, + { + "epoch": 3.1291234684260134, + "grad_norm": 4.340310096740723, + "learning_rate": 2.3117620940294048e-05, + "loss": 2.2882, + "num_input_tokens_seen": 4213280, + "step": 415 + }, + { + "epoch": 3.166823751178134, + "grad_norm": 4.137709617614746, + "learning_rate": 2.2623598917395438e-05, + "loss": 2.2314, + "num_input_tokens_seen": 4265792, + "step": 420 + }, + { + "epoch": 3.2045240339302543, + "grad_norm": 4.506406307220459, + "learning_rate": 2.213051164325366e-05, + "loss": 2.2679, + "num_input_tokens_seen": 4310832, + "step": 425 + }, + { + "epoch": 3.242224316682375, + "grad_norm": 4.44052791595459, + "learning_rate": 2.1638553071961708e-05, + "loss": 2.2521, + "num_input_tokens_seen": 4353488, + "step": 430 + }, + { + "epoch": 3.2799245994344957, + "grad_norm": 4.674520015716553, + "learning_rate": 2.1147916713641367e-05, + "loss": 2.2071, + "num_input_tokens_seen": 4404384, + "step": 435 + }, + { + "epoch": 3.3176248821866166, + "grad_norm": 4.979199409484863, + "learning_rate": 2.0658795558326743e-05, + "loss": 2.2525, + "num_input_tokens_seen": 4453232, + "step": 440 + }, + { + "epoch": 3.355325164938737, + "grad_norm": 4.564790725708008, + "learning_rate": 2.017138200005236e-05, + "loss": 2.2431, + "num_input_tokens_seen": 4508640, + "step": 445 + }, + { + "epoch": 3.3930254476908575, + "grad_norm": 4.888641834259033, + "learning_rate": 1.9685867761175584e-05, + "loss": 2.3357, + "num_input_tokens_seen": 4559360, + "step": 450 + }, + { + "epoch": 3.4307257304429783, + "grad_norm": 4.425845623016357, + "learning_rate": 1.9202443816963425e-05, + "loss": 2.2875, + "num_input_tokens_seen": 4609584, + "step": 455 + }, + { + "epoch": 3.468426013195099, + "grad_norm": 5.38726282119751, + "learning_rate": 1.872130032047302e-05, + "loss": 2.2136, + "num_input_tokens_seen": 4665472, + "step": 460 + }, + { + "epoch": 3.5061262959472197, + "grad_norm": 4.473924160003662, + "learning_rate": 1.824262652775568e-05, + "loss": 2.294, + "num_input_tokens_seen": 4719360, + "step": 465 + }, + { + "epoch": 3.54382657869934, + "grad_norm": 5.171916484832764, + "learning_rate": 1.7766610723413684e-05, + "loss": 2.2146, + "num_input_tokens_seen": 4771504, + "step": 470 + }, + { + "epoch": 3.581526861451461, + "grad_norm": 5.492386817932129, + "learning_rate": 1.7293440146539196e-05, + "loss": 2.3166, + "num_input_tokens_seen": 4820432, + "step": 475 + }, + { + "epoch": 3.6192271442035815, + "grad_norm": 4.300539493560791, + "learning_rate": 1.682330091706446e-05, + "loss": 2.2775, + "num_input_tokens_seen": 4877984, + "step": 480 + }, + { + "epoch": 3.6569274269557024, + "grad_norm": 5.470084190368652, + "learning_rate": 1.6356377962552238e-05, + "loss": 2.2442, + "num_input_tokens_seen": 4927712, + "step": 485 + }, + { + "epoch": 3.694627709707823, + "grad_norm": 5.457830429077148, + "learning_rate": 1.589285494545514e-05, + "loss": 2.2499, + "num_input_tokens_seen": 4979520, + "step": 490 + }, + { + "epoch": 3.7323279924599433, + "grad_norm": 4.851473808288574, + "learning_rate": 1.5432914190872757e-05, + "loss": 2.214, + "num_input_tokens_seen": 5030720, + "step": 495 + }, + { + "epoch": 3.770028275212064, + "grad_norm": 4.645096302032471, + "learning_rate": 1.4976736614834664e-05, + "loss": 2.1646, + "num_input_tokens_seen": 5081376, + "step": 500 + } + ], + "logging_steps": 5, + "max_steps": 792, + "num_input_tokens_seen": 5081376, + "num_train_epochs": 6, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.2945145063001293e+17, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-500/training_args.bin b/checkpoint-500/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f8accff7ed19f472e4ab59934a52cd1b74989284 --- /dev/null +++ b/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0abbac12d56c1934fca1078792064a59e7f00bea9a38a70efb9ce7fe81d8d0a2 +size 5432 diff --git a/checkpoint-600/README.md b/checkpoint-600/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ba199ae8c078d293275e50b0a850beb3a458a43e --- /dev/null +++ b/checkpoint-600/README.md @@ -0,0 +1,202 @@ +--- +base_model: NousResearch/Hermes-3-Llama-3.1-8B +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/checkpoint-600/adapter_config.json b/checkpoint-600/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4aa889ee5316659d91ab201b4f03e49477d31374 --- /dev/null +++ b/checkpoint-600/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "k_proj", + "v_proj", + "o_proj", + "down_proj", + "q_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-600/adapter_model.safetensors b/checkpoint-600/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..75280c701c479c8889984bb301e5be6123630305 --- /dev/null +++ b/checkpoint-600/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7f5655772f9f2fc14b1de68745bbf3bf89804518edd03bc0fbfc88fec0410cd +size 83945296 diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..6f2e422a6c6d65f1764d0fb554b273b31143b255 --- /dev/null +++ b/checkpoint-600/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76da0acfc552b3ab38d1d63bd151b804b584c3a1d7d14fea39071034470e515d +size 168149074 diff --git a/checkpoint-600/rng_state_0.pth b/checkpoint-600/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..43606f86a072ecc959e43371efd6a451e74daac3 --- /dev/null +++ b/checkpoint-600/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7e52325e9d729519836af640f8f754a93ee06730fb2953b5309434b53b17562 +size 14512 diff --git a/checkpoint-600/rng_state_1.pth b/checkpoint-600/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..fbadae7125c23bf749649bf0b9cd0044d56679d3 --- /dev/null +++ b/checkpoint-600/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a93593cf0342eb47876986e1063102e1546354426a2324c46ddcf1cbecae803 +size 14512 diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..cf2f8c18e9d74869c988eab02430ad6319f17840 --- /dev/null +++ b/checkpoint-600/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:352d333818407c00acc00fba3e8fa8bd42f6825ddbcda95decb7921507cceb6c +size 1064 diff --git a/checkpoint-600/special_tokens_map.json b/checkpoint-600/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1ad7f173822ffa805bd5f390acc9c3390d414e67 --- /dev/null +++ b/checkpoint-600/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-600/tokenizer.json b/checkpoint-600/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b --- /dev/null +++ b/checkpoint-600/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05 +size 17209403 diff --git a/checkpoint-600/tokenizer_config.json b/checkpoint-600/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a22a366f4a4df58d908d0fa483648703588ce0b1 --- /dev/null +++ b/checkpoint-600/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128039": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128040": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|im_end|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..c2c0d125eef7c5451bc6a5a5aad0e701b4197ac7 --- /dev/null +++ b/checkpoint-600/trainer_state.json @@ -0,0 +1,993 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.524033930254477, + "eval_steps": 500, + "global_step": 600, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.03770028275212064, + "grad_norm": 3.988708734512329, + "learning_rate": 4.9995083170283816e-05, + "loss": 4.6192, + "num_input_tokens_seen": 50400, + "step": 5 + }, + { + "epoch": 0.07540056550424128, + "grad_norm": 2.142688512802124, + "learning_rate": 4.998033461515242e-05, + "loss": 3.9149, + "num_input_tokens_seen": 104016, + "step": 10 + }, + { + "epoch": 0.11310084825636192, + "grad_norm": 1.5928359031677246, + "learning_rate": 4.9955760135896534e-05, + "loss": 3.6912, + "num_input_tokens_seen": 155584, + "step": 15 + }, + { + "epoch": 0.15080113100848255, + "grad_norm": 1.5493167638778687, + "learning_rate": 4.992136939879856e-05, + "loss": 3.5556, + "num_input_tokens_seen": 202672, + "step": 20 + }, + { + "epoch": 0.1885014137606032, + "grad_norm": 1.7764347791671753, + "learning_rate": 4.9877175931330346e-05, + "loss": 3.4256, + "num_input_tokens_seen": 254800, + "step": 25 + }, + { + "epoch": 0.22620169651272384, + "grad_norm": 1.2482728958129883, + "learning_rate": 4.982319711683221e-05, + "loss": 3.3128, + "num_input_tokens_seen": 306352, + "step": 30 + }, + { + "epoch": 0.2639019792648445, + "grad_norm": 1.2829065322875977, + "learning_rate": 4.975945418767529e-05, + "loss": 3.2688, + "num_input_tokens_seen": 356352, + "step": 35 + }, + { + "epoch": 0.3016022620169651, + "grad_norm": 1.513293743133545, + "learning_rate": 4.968597221690986e-05, + "loss": 3.297, + "num_input_tokens_seen": 406672, + "step": 40 + }, + { + "epoch": 0.3393025447690858, + "grad_norm": 1.883090853691101, + "learning_rate": 4.96027801084029e-05, + "loss": 3.232, + "num_input_tokens_seen": 456160, + "step": 45 + }, + { + "epoch": 0.3770028275212064, + "grad_norm": 1.402272343635559, + "learning_rate": 4.950991058546893e-05, + "loss": 3.267, + "num_input_tokens_seen": 509680, + "step": 50 + }, + { + "epoch": 0.41470311027332707, + "grad_norm": 1.5488755702972412, + "learning_rate": 4.940740017799833e-05, + "loss": 3.2148, + "num_input_tokens_seen": 559968, + "step": 55 + }, + { + "epoch": 0.4524033930254477, + "grad_norm": 1.507287859916687, + "learning_rate": 4.929528920808854e-05, + "loss": 3.1403, + "num_input_tokens_seen": 610000, + "step": 60 + }, + { + "epoch": 0.49010367577756836, + "grad_norm": 1.9119170904159546, + "learning_rate": 4.917362177418342e-05, + "loss": 3.1515, + "num_input_tokens_seen": 661280, + "step": 65 + }, + { + "epoch": 0.527803958529689, + "grad_norm": 1.7253235578536987, + "learning_rate": 4.904244573372733e-05, + "loss": 3.1468, + "num_input_tokens_seen": 713264, + "step": 70 + }, + { + "epoch": 0.5655042412818096, + "grad_norm": 1.7201606035232544, + "learning_rate": 4.8901812684340564e-05, + "loss": 3.196, + "num_input_tokens_seen": 762576, + "step": 75 + }, + { + "epoch": 0.6032045240339302, + "grad_norm": 1.6135213375091553, + "learning_rate": 4.8751777943523634e-05, + "loss": 3.0593, + "num_input_tokens_seen": 813392, + "step": 80 + }, + { + "epoch": 0.6409048067860509, + "grad_norm": 1.7381868362426758, + "learning_rate": 4.8592400526898314e-05, + "loss": 3.0676, + "num_input_tokens_seen": 860608, + "step": 85 + }, + { + "epoch": 0.6786050895381716, + "grad_norm": 1.6142843961715698, + "learning_rate": 4.842374312499405e-05, + "loss": 3.1061, + "num_input_tokens_seen": 909104, + "step": 90 + }, + { + "epoch": 0.7163053722902922, + "grad_norm": 2.0389633178710938, + "learning_rate": 4.824587207858888e-05, + "loss": 2.9847, + "num_input_tokens_seen": 959600, + "step": 95 + }, + { + "epoch": 0.7540056550424128, + "grad_norm": 1.923561692237854, + "learning_rate": 4.805885735261454e-05, + "loss": 3.0289, + "num_input_tokens_seen": 1013648, + "step": 100 + }, + { + "epoch": 0.7917059377945335, + "grad_norm": 2.0325896739959717, + "learning_rate": 4.786277250863599e-05, + "loss": 2.9474, + "num_input_tokens_seen": 1065120, + "step": 105 + }, + { + "epoch": 0.8294062205466541, + "grad_norm": 1.6685590744018555, + "learning_rate": 4.765769467591625e-05, + "loss": 2.9713, + "num_input_tokens_seen": 1119424, + "step": 110 + }, + { + "epoch": 0.8671065032987747, + "grad_norm": 2.0325937271118164, + "learning_rate": 4.744370452107789e-05, + "loss": 3.0012, + "num_input_tokens_seen": 1169888, + "step": 115 + }, + { + "epoch": 0.9048067860508954, + "grad_norm": 1.7548010349273682, + "learning_rate": 4.722088621637309e-05, + "loss": 3.0399, + "num_input_tokens_seen": 1218944, + "step": 120 + }, + { + "epoch": 0.942507068803016, + "grad_norm": 1.6709191799163818, + "learning_rate": 4.698932740657479e-05, + "loss": 2.9156, + "num_input_tokens_seen": 1269920, + "step": 125 + }, + { + "epoch": 0.9802073515551367, + "grad_norm": 1.8369653224945068, + "learning_rate": 4.6749119174501975e-05, + "loss": 3.0288, + "num_input_tokens_seen": 1315536, + "step": 130 + }, + { + "epoch": 1.0179076343072573, + "grad_norm": 1.800703525543213, + "learning_rate": 4.6500356005192514e-05, + "loss": 2.8911, + "num_input_tokens_seen": 1360736, + "step": 135 + }, + { + "epoch": 1.055607917059378, + "grad_norm": 1.7134617567062378, + "learning_rate": 4.6243135748737864e-05, + "loss": 2.9148, + "num_input_tokens_seen": 1409808, + "step": 140 + }, + { + "epoch": 1.0933081998114986, + "grad_norm": 1.9385241270065308, + "learning_rate": 4.597755958179406e-05, + "loss": 2.868, + "num_input_tokens_seen": 1460864, + "step": 145 + }, + { + "epoch": 1.1310084825636193, + "grad_norm": 2.1658332347869873, + "learning_rate": 4.570373196778427e-05, + "loss": 2.7477, + "num_input_tokens_seen": 1512640, + "step": 150 + }, + { + "epoch": 1.1687087653157398, + "grad_norm": 2.239896774291992, + "learning_rate": 4.5421760615808474e-05, + "loss": 2.932, + "num_input_tokens_seen": 1556048, + "step": 155 + }, + { + "epoch": 1.2064090480678604, + "grad_norm": 2.0555717945098877, + "learning_rate": 4.513175643827647e-05, + "loss": 2.8219, + "num_input_tokens_seen": 1607232, + "step": 160 + }, + { + "epoch": 1.244109330819981, + "grad_norm": 2.0288779735565186, + "learning_rate": 4.4833833507280884e-05, + "loss": 2.8453, + "num_input_tokens_seen": 1653520, + "step": 165 + }, + { + "epoch": 1.2818096135721018, + "grad_norm": 1.9268651008605957, + "learning_rate": 4.4528109009727336e-05, + "loss": 2.7362, + "num_input_tokens_seen": 1703568, + "step": 170 + }, + { + "epoch": 1.3195098963242224, + "grad_norm": 2.413874387741089, + "learning_rate": 4.42147032012394e-05, + "loss": 2.9197, + "num_input_tokens_seen": 1752944, + "step": 175 + }, + { + "epoch": 1.3572101790763431, + "grad_norm": 2.2018630504608154, + "learning_rate": 4.389373935885646e-05, + "loss": 2.8897, + "num_input_tokens_seen": 1805600, + "step": 180 + }, + { + "epoch": 1.3949104618284638, + "grad_norm": 2.1807219982147217, + "learning_rate": 4.356534373254316e-05, + "loss": 2.7946, + "num_input_tokens_seen": 1860688, + "step": 185 + }, + { + "epoch": 1.4326107445805842, + "grad_norm": 2.2928526401519775, + "learning_rate": 4.322964549552943e-05, + "loss": 2.8149, + "num_input_tokens_seen": 1913056, + "step": 190 + }, + { + "epoch": 1.4703110273327051, + "grad_norm": 2.204533576965332, + "learning_rate": 4.288677669350066e-05, + "loss": 2.7811, + "num_input_tokens_seen": 1961744, + "step": 195 + }, + { + "epoch": 1.5080113100848256, + "grad_norm": 2.925762414932251, + "learning_rate": 4.2536872192658036e-05, + "loss": 2.8564, + "num_input_tokens_seen": 2011248, + "step": 200 + }, + { + "epoch": 1.5457115928369463, + "grad_norm": 2.398651599884033, + "learning_rate": 4.218006962666934e-05, + "loss": 2.7966, + "num_input_tokens_seen": 2060640, + "step": 205 + }, + { + "epoch": 1.583411875589067, + "grad_norm": 2.452263355255127, + "learning_rate": 4.181650934253132e-05, + "loss": 2.7674, + "num_input_tokens_seen": 2113904, + "step": 210 + }, + { + "epoch": 1.6211121583411876, + "grad_norm": 2.5911788940429688, + "learning_rate": 4.144633434536467e-05, + "loss": 2.7607, + "num_input_tokens_seen": 2162608, + "step": 215 + }, + { + "epoch": 1.6588124410933083, + "grad_norm": 2.648517608642578, + "learning_rate": 4.1069690242163484e-05, + "loss": 2.8402, + "num_input_tokens_seen": 2211616, + "step": 220 + }, + { + "epoch": 1.6965127238454287, + "grad_norm": 2.6860735416412354, + "learning_rate": 4.06867251845213e-05, + "loss": 2.8019, + "num_input_tokens_seen": 2269440, + "step": 225 + }, + { + "epoch": 1.7342130065975496, + "grad_norm": 2.5891222953796387, + "learning_rate": 4.0297589810356165e-05, + "loss": 2.8311, + "num_input_tokens_seen": 2321936, + "step": 230 + }, + { + "epoch": 1.77191328934967, + "grad_norm": 2.695114850997925, + "learning_rate": 3.9902437184657784e-05, + "loss": 2.7626, + "num_input_tokens_seen": 2376720, + "step": 235 + }, + { + "epoch": 1.8096135721017907, + "grad_norm": 2.588127374649048, + "learning_rate": 3.9501422739279956e-05, + "loss": 2.8052, + "num_input_tokens_seen": 2429952, + "step": 240 + }, + { + "epoch": 1.8473138548539114, + "grad_norm": 2.1829710006713867, + "learning_rate": 3.909470421180201e-05, + "loss": 2.767, + "num_input_tokens_seen": 2481488, + "step": 245 + }, + { + "epoch": 1.885014137606032, + "grad_norm": 2.606924295425415, + "learning_rate": 3.8682441583483314e-05, + "loss": 2.7651, + "num_input_tokens_seen": 2530768, + "step": 250 + }, + { + "epoch": 1.9227144203581528, + "grad_norm": 2.3635494709014893, + "learning_rate": 3.8264797016335205e-05, + "loss": 2.8097, + "num_input_tokens_seen": 2583088, + "step": 255 + }, + { + "epoch": 1.9604147031102732, + "grad_norm": 2.560624361038208, + "learning_rate": 3.7841934789335164e-05, + "loss": 2.7269, + "num_input_tokens_seen": 2631456, + "step": 260 + }, + { + "epoch": 1.998114985862394, + "grad_norm": 2.7099437713623047, + "learning_rate": 3.741402123380828e-05, + "loss": 2.8586, + "num_input_tokens_seen": 2684848, + "step": 265 + }, + { + "epoch": 2.0358152686145146, + "grad_norm": 2.552143096923828, + "learning_rate": 3.6981224668001424e-05, + "loss": 2.6131, + "num_input_tokens_seen": 2733408, + "step": 270 + }, + { + "epoch": 2.0735155513666355, + "grad_norm": 2.9233176708221436, + "learning_rate": 3.654371533087586e-05, + "loss": 2.4891, + "num_input_tokens_seen": 2786832, + "step": 275 + }, + { + "epoch": 2.111215834118756, + "grad_norm": 2.7649636268615723, + "learning_rate": 3.610166531514436e-05, + "loss": 2.5783, + "num_input_tokens_seen": 2828464, + "step": 280 + }, + { + "epoch": 2.1489161168708764, + "grad_norm": 3.076122522354126, + "learning_rate": 3.565524849957921e-05, + "loss": 2.59, + "num_input_tokens_seen": 2878192, + "step": 285 + }, + { + "epoch": 2.1866163996229973, + "grad_norm": 3.242678642272949, + "learning_rate": 3.520464048061758e-05, + "loss": 2.5839, + "num_input_tokens_seen": 2928304, + "step": 290 + }, + { + "epoch": 2.2243166823751177, + "grad_norm": 3.139089584350586, + "learning_rate": 3.47500185032913e-05, + "loss": 2.567, + "num_input_tokens_seen": 2978144, + "step": 295 + }, + { + "epoch": 2.2620169651272386, + "grad_norm": 3.1967153549194336, + "learning_rate": 3.4291561391508185e-05, + "loss": 2.5694, + "num_input_tokens_seen": 3028240, + "step": 300 + }, + { + "epoch": 2.299717247879359, + "grad_norm": 3.1987555027008057, + "learning_rate": 3.3829449477712324e-05, + "loss": 2.4965, + "num_input_tokens_seen": 3083328, + "step": 305 + }, + { + "epoch": 2.3374175306314795, + "grad_norm": 3.4724180698394775, + "learning_rate": 3.336386453195088e-05, + "loss": 2.599, + "num_input_tokens_seen": 3137072, + "step": 310 + }, + { + "epoch": 2.3751178133836004, + "grad_norm": 3.381075143814087, + "learning_rate": 3.2894989690375626e-05, + "loss": 2.524, + "num_input_tokens_seen": 3191136, + "step": 315 + }, + { + "epoch": 2.412818096135721, + "grad_norm": 3.650747537612915, + "learning_rate": 3.2423009383206876e-05, + "loss": 2.5338, + "num_input_tokens_seen": 3239952, + "step": 320 + }, + { + "epoch": 2.4505183788878417, + "grad_norm": 3.3886971473693848, + "learning_rate": 3.194810926218861e-05, + "loss": 2.5096, + "num_input_tokens_seen": 3291104, + "step": 325 + }, + { + "epoch": 2.488218661639962, + "grad_norm": 3.415850877761841, + "learning_rate": 3.147047612756302e-05, + "loss": 2.473, + "num_input_tokens_seen": 3340592, + "step": 330 + }, + { + "epoch": 2.525918944392083, + "grad_norm": 3.513828754425049, + "learning_rate": 3.099029785459328e-05, + "loss": 2.5778, + "num_input_tokens_seen": 3388224, + "step": 335 + }, + { + "epoch": 2.5636192271442035, + "grad_norm": 3.49721360206604, + "learning_rate": 3.0507763319663517e-05, + "loss": 2.5684, + "num_input_tokens_seen": 3440512, + "step": 340 + }, + { + "epoch": 2.6013195098963244, + "grad_norm": 3.5137672424316406, + "learning_rate": 3.002306232598497e-05, + "loss": 2.4923, + "num_input_tokens_seen": 3491744, + "step": 345 + }, + { + "epoch": 2.639019792648445, + "grad_norm": 3.7216403484344482, + "learning_rate": 2.9536385528937567e-05, + "loss": 2.4633, + "num_input_tokens_seen": 3542368, + "step": 350 + }, + { + "epoch": 2.6767200754005653, + "grad_norm": 3.48529052734375, + "learning_rate": 2.9047924361076345e-05, + "loss": 2.5703, + "num_input_tokens_seen": 3595360, + "step": 355 + }, + { + "epoch": 2.7144203581526862, + "grad_norm": 3.4676520824432373, + "learning_rate": 2.8557870956832132e-05, + "loss": 2.4087, + "num_input_tokens_seen": 3640912, + "step": 360 + }, + { + "epoch": 2.7521206409048067, + "grad_norm": 4.316717147827148, + "learning_rate": 2.8066418076936167e-05, + "loss": 2.5007, + "num_input_tokens_seen": 3690048, + "step": 365 + }, + { + "epoch": 2.7898209236569276, + "grad_norm": 4.2354736328125, + "learning_rate": 2.7573759032598366e-05, + "loss": 2.5312, + "num_input_tokens_seen": 3745104, + "step": 370 + }, + { + "epoch": 2.827521206409048, + "grad_norm": 3.457280397415161, + "learning_rate": 2.7080087609469062e-05, + "loss": 2.5333, + "num_input_tokens_seen": 3794160, + "step": 375 + }, + { + "epoch": 2.8652214891611685, + "grad_norm": 3.417656183242798, + "learning_rate": 2.6585597991414114e-05, + "loss": 2.4185, + "num_input_tokens_seen": 3846576, + "step": 380 + }, + { + "epoch": 2.9029217719132894, + "grad_norm": 3.7148749828338623, + "learning_rate": 2.6090484684133404e-05, + "loss": 2.4913, + "num_input_tokens_seen": 3891744, + "step": 385 + }, + { + "epoch": 2.9406220546654103, + "grad_norm": 3.562427520751953, + "learning_rate": 2.5594942438652688e-05, + "loss": 2.5319, + "num_input_tokens_seen": 3949568, + "step": 390 + }, + { + "epoch": 2.9783223374175307, + "grad_norm": 4.2560505867004395, + "learning_rate": 2.509916617471903e-05, + "loss": 2.6441, + "num_input_tokens_seen": 4002384, + "step": 395 + }, + { + "epoch": 3.016022620169651, + "grad_norm": 3.349701166152954, + "learning_rate": 2.46033509041298e-05, + "loss": 2.3576, + "num_input_tokens_seen": 4052688, + "step": 400 + }, + { + "epoch": 3.053722902921772, + "grad_norm": 3.660886287689209, + "learning_rate": 2.410769165402549e-05, + "loss": 2.3032, + "num_input_tokens_seen": 4107392, + "step": 405 + }, + { + "epoch": 3.0914231856738925, + "grad_norm": 4.248249530792236, + "learning_rate": 2.3612383390176503e-05, + "loss": 2.2542, + "num_input_tokens_seen": 4157984, + "step": 410 + }, + { + "epoch": 3.1291234684260134, + "grad_norm": 4.340310096740723, + "learning_rate": 2.3117620940294048e-05, + "loss": 2.2882, + "num_input_tokens_seen": 4213280, + "step": 415 + }, + { + "epoch": 3.166823751178134, + "grad_norm": 4.137709617614746, + "learning_rate": 2.2623598917395438e-05, + "loss": 2.2314, + "num_input_tokens_seen": 4265792, + "step": 420 + }, + { + "epoch": 3.2045240339302543, + "grad_norm": 4.506406307220459, + "learning_rate": 2.213051164325366e-05, + "loss": 2.2679, + "num_input_tokens_seen": 4310832, + "step": 425 + }, + { + "epoch": 3.242224316682375, + "grad_norm": 4.44052791595459, + "learning_rate": 2.1638553071961708e-05, + "loss": 2.2521, + "num_input_tokens_seen": 4353488, + "step": 430 + }, + { + "epoch": 3.2799245994344957, + "grad_norm": 4.674520015716553, + "learning_rate": 2.1147916713641367e-05, + "loss": 2.2071, + "num_input_tokens_seen": 4404384, + "step": 435 + }, + { + "epoch": 3.3176248821866166, + "grad_norm": 4.979199409484863, + "learning_rate": 2.0658795558326743e-05, + "loss": 2.2525, + "num_input_tokens_seen": 4453232, + "step": 440 + }, + { + "epoch": 3.355325164938737, + "grad_norm": 4.564790725708008, + "learning_rate": 2.017138200005236e-05, + "loss": 2.2431, + "num_input_tokens_seen": 4508640, + "step": 445 + }, + { + "epoch": 3.3930254476908575, + "grad_norm": 4.888641834259033, + "learning_rate": 1.9685867761175584e-05, + "loss": 2.3357, + "num_input_tokens_seen": 4559360, + "step": 450 + }, + { + "epoch": 3.4307257304429783, + "grad_norm": 4.425845623016357, + "learning_rate": 1.9202443816963425e-05, + "loss": 2.2875, + "num_input_tokens_seen": 4609584, + "step": 455 + }, + { + "epoch": 3.468426013195099, + "grad_norm": 5.38726282119751, + "learning_rate": 1.872130032047302e-05, + "loss": 2.2136, + "num_input_tokens_seen": 4665472, + "step": 460 + }, + { + "epoch": 3.5061262959472197, + "grad_norm": 4.473924160003662, + "learning_rate": 1.824262652775568e-05, + "loss": 2.294, + "num_input_tokens_seen": 4719360, + "step": 465 + }, + { + "epoch": 3.54382657869934, + "grad_norm": 5.171916484832764, + "learning_rate": 1.7766610723413684e-05, + "loss": 2.2146, + "num_input_tokens_seen": 4771504, + "step": 470 + }, + { + "epoch": 3.581526861451461, + "grad_norm": 5.492386817932129, + "learning_rate": 1.7293440146539196e-05, + "loss": 2.3166, + "num_input_tokens_seen": 4820432, + "step": 475 + }, + { + "epoch": 3.6192271442035815, + "grad_norm": 4.300539493560791, + "learning_rate": 1.682330091706446e-05, + "loss": 2.2775, + "num_input_tokens_seen": 4877984, + "step": 480 + }, + { + "epoch": 3.6569274269557024, + "grad_norm": 5.470084190368652, + "learning_rate": 1.6356377962552238e-05, + "loss": 2.2442, + "num_input_tokens_seen": 4927712, + "step": 485 + }, + { + "epoch": 3.694627709707823, + "grad_norm": 5.457830429077148, + "learning_rate": 1.589285494545514e-05, + "loss": 2.2499, + "num_input_tokens_seen": 4979520, + "step": 490 + }, + { + "epoch": 3.7323279924599433, + "grad_norm": 4.851473808288574, + "learning_rate": 1.5432914190872757e-05, + "loss": 2.214, + "num_input_tokens_seen": 5030720, + "step": 495 + }, + { + "epoch": 3.770028275212064, + "grad_norm": 4.645096302032471, + "learning_rate": 1.4976736614834664e-05, + "loss": 2.1646, + "num_input_tokens_seen": 5081376, + "step": 500 + }, + { + "epoch": 3.8077285579641846, + "grad_norm": 5.5402512550354, + "learning_rate": 1.4524501653137787e-05, + "loss": 2.3151, + "num_input_tokens_seen": 5127888, + "step": 505 + }, + { + "epoch": 3.8454288407163055, + "grad_norm": 4.753649711608887, + "learning_rate": 1.4076387190766017e-05, + "loss": 2.2602, + "num_input_tokens_seen": 5178720, + "step": 510 + }, + { + "epoch": 3.883129123468426, + "grad_norm": 5.488243579864502, + "learning_rate": 1.363256949191972e-05, + "loss": 2.1839, + "num_input_tokens_seen": 5227120, + "step": 515 + }, + { + "epoch": 3.9208294062205464, + "grad_norm": 5.427800178527832, + "learning_rate": 1.3193223130682936e-05, + "loss": 2.2833, + "num_input_tokens_seen": 5275760, + "step": 520 + }, + { + "epoch": 3.9585296889726673, + "grad_norm": 4.901040077209473, + "learning_rate": 1.2758520922355226e-05, + "loss": 2.1802, + "num_input_tokens_seen": 5319632, + "step": 525 + }, + { + "epoch": 3.9962299717247878, + "grad_norm": 4.977085590362549, + "learning_rate": 1.2328633855475429e-05, + "loss": 2.2383, + "num_input_tokens_seen": 5369936, + "step": 530 + }, + { + "epoch": 4.033930254476909, + "grad_norm": 4.724318027496338, + "learning_rate": 1.1903731024563966e-05, + "loss": 2.007, + "num_input_tokens_seen": 5421440, + "step": 535 + }, + { + "epoch": 4.071630537229029, + "grad_norm": 5.148896217346191, + "learning_rate": 1.148397956361007e-05, + "loss": 2.0286, + "num_input_tokens_seen": 5476736, + "step": 540 + }, + { + "epoch": 4.10933081998115, + "grad_norm": 5.690558433532715, + "learning_rate": 1.106954458033026e-05, + "loss": 2.0398, + "num_input_tokens_seen": 5531328, + "step": 545 + }, + { + "epoch": 4.147031102733271, + "grad_norm": 5.595386505126953, + "learning_rate": 1.0660589091223855e-05, + "loss": 2.1157, + "num_input_tokens_seen": 5579216, + "step": 550 + }, + { + "epoch": 4.184731385485391, + "grad_norm": 6.112159252166748, + "learning_rate": 1.025727395745095e-05, + "loss": 2.094, + "num_input_tokens_seen": 5626208, + "step": 555 + }, + { + "epoch": 4.222431668237512, + "grad_norm": 5.86374568939209, + "learning_rate": 9.859757821558337e-06, + "loss": 2.0531, + "num_input_tokens_seen": 5679360, + "step": 560 + }, + { + "epoch": 4.260131950989632, + "grad_norm": 5.2934699058532715, + "learning_rate": 9.468197045077976e-06, + "loss": 1.9652, + "num_input_tokens_seen": 5724608, + "step": 565 + }, + { + "epoch": 4.297832233741753, + "grad_norm": 6.302525043487549, + "learning_rate": 9.082745647022797e-06, + "loss": 2.0592, + "num_input_tokens_seen": 5779904, + "step": 570 + }, + { + "epoch": 4.335532516493874, + "grad_norm": 6.2651143074035645, + "learning_rate": 8.703555243303835e-06, + "loss": 2.0418, + "num_input_tokens_seen": 5826880, + "step": 575 + }, + { + "epoch": 4.3732327992459945, + "grad_norm": 6.225465774536133, + "learning_rate": 8.330774987092712e-06, + "loss": 1.991, + "num_input_tokens_seen": 5875440, + "step": 580 + }, + { + "epoch": 4.410933081998115, + "grad_norm": 5.812168121337891, + "learning_rate": 7.96455151015272e-06, + "loss": 2.0726, + "num_input_tokens_seen": 5924960, + "step": 585 + }, + { + "epoch": 4.448633364750235, + "grad_norm": 5.528653621673584, + "learning_rate": 7.605028865161809e-06, + "loss": 2.069, + "num_input_tokens_seen": 5976416, + "step": 590 + }, + { + "epoch": 4.486333647502356, + "grad_norm": 5.838290691375732, + "learning_rate": 7.25234846904993e-06, + "loss": 2.052, + "num_input_tokens_seen": 6027088, + "step": 595 + }, + { + "epoch": 4.524033930254477, + "grad_norm": 6.014201641082764, + "learning_rate": 6.906649047373246e-06, + "loss": 2.0651, + "num_input_tokens_seen": 6080528, + "step": 600 + } + ], + "logging_steps": 5, + "max_steps": 792, + "num_input_tokens_seen": 6080528, + "num_train_epochs": 6, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.745685354836132e+17, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f8accff7ed19f472e4ab59934a52cd1b74989284 --- /dev/null +++ b/checkpoint-600/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0abbac12d56c1934fca1078792064a59e7f00bea9a38a70efb9ce7fe81d8d0a2 +size 5432 diff --git a/checkpoint-700/README.md b/checkpoint-700/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ba199ae8c078d293275e50b0a850beb3a458a43e --- /dev/null +++ b/checkpoint-700/README.md @@ -0,0 +1,202 @@ +--- +base_model: NousResearch/Hermes-3-Llama-3.1-8B +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/checkpoint-700/adapter_config.json b/checkpoint-700/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4aa889ee5316659d91ab201b4f03e49477d31374 --- /dev/null +++ b/checkpoint-700/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "k_proj", + "v_proj", + "o_proj", + "down_proj", + "q_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-700/adapter_model.safetensors b/checkpoint-700/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..55724956c0d630fad6ac3053683030f384d17a00 --- /dev/null +++ b/checkpoint-700/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76e53f4a4d4bd878ac98bdcae0a4b2afd34966c3e4f47deb005d67f986dc3a62 +size 83945296 diff --git a/checkpoint-700/optimizer.pt b/checkpoint-700/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba25cf52aaa53a5a0d9c41a4157f26e86d835541 --- /dev/null +++ b/checkpoint-700/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbea2a32484fda676b50a67f2cbf42b7f9d36d62e87df434633cb146c9702392 +size 168149074 diff --git a/checkpoint-700/rng_state_0.pth b/checkpoint-700/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..07a546a3d8fa499648a42db76ea9733d09e5ca98 --- /dev/null +++ b/checkpoint-700/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7a17ffe4d1cfad70857491e1fd7e427c0413a789e2cb4398c4af3ca8efd92a5 +size 14512 diff --git a/checkpoint-700/rng_state_1.pth b/checkpoint-700/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..5552726456b4cc7d1cc941b486f870e723d6ab42 --- /dev/null +++ b/checkpoint-700/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8430d63cfb7960c36461376f5e1ef952c23b5128eae3a1f763753f4c308fd4aa +size 14512 diff --git a/checkpoint-700/scheduler.pt b/checkpoint-700/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..d06407581f27555700c0fbd2722a54c288fe6f84 --- /dev/null +++ b/checkpoint-700/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e73e049cc9ae3a3165d3a65ed3a46b19ca504dd75a711ee23051792926d4b31 +size 1064 diff --git a/checkpoint-700/special_tokens_map.json b/checkpoint-700/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1ad7f173822ffa805bd5f390acc9c3390d414e67 --- /dev/null +++ b/checkpoint-700/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-700/tokenizer.json b/checkpoint-700/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b --- /dev/null +++ b/checkpoint-700/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05 +size 17209403 diff --git a/checkpoint-700/tokenizer_config.json b/checkpoint-700/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a22a366f4a4df58d908d0fa483648703588ce0b1 --- /dev/null +++ b/checkpoint-700/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128039": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128040": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|im_end|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-700/trainer_state.json b/checkpoint-700/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..625c73a1fd73d59f345071a1eeedc9bb4d57ff2b --- /dev/null +++ b/checkpoint-700/trainer_state.json @@ -0,0 +1,1153 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 5.27803958529689, + "eval_steps": 500, + "global_step": 700, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.03770028275212064, + "grad_norm": 3.988708734512329, + "learning_rate": 4.9995083170283816e-05, + "loss": 4.6192, + "num_input_tokens_seen": 50400, + "step": 5 + }, + { + "epoch": 0.07540056550424128, + "grad_norm": 2.142688512802124, + "learning_rate": 4.998033461515242e-05, + "loss": 3.9149, + "num_input_tokens_seen": 104016, + "step": 10 + }, + { + "epoch": 0.11310084825636192, + "grad_norm": 1.5928359031677246, + "learning_rate": 4.9955760135896534e-05, + "loss": 3.6912, + "num_input_tokens_seen": 155584, + "step": 15 + }, + { + "epoch": 0.15080113100848255, + "grad_norm": 1.5493167638778687, + "learning_rate": 4.992136939879856e-05, + "loss": 3.5556, + "num_input_tokens_seen": 202672, + "step": 20 + }, + { + "epoch": 0.1885014137606032, + "grad_norm": 1.7764347791671753, + "learning_rate": 4.9877175931330346e-05, + "loss": 3.4256, + "num_input_tokens_seen": 254800, + "step": 25 + }, + { + "epoch": 0.22620169651272384, + "grad_norm": 1.2482728958129883, + "learning_rate": 4.982319711683221e-05, + "loss": 3.3128, + "num_input_tokens_seen": 306352, + "step": 30 + }, + { + "epoch": 0.2639019792648445, + "grad_norm": 1.2829065322875977, + "learning_rate": 4.975945418767529e-05, + "loss": 3.2688, + "num_input_tokens_seen": 356352, + "step": 35 + }, + { + "epoch": 0.3016022620169651, + "grad_norm": 1.513293743133545, + "learning_rate": 4.968597221690986e-05, + "loss": 3.297, + "num_input_tokens_seen": 406672, + "step": 40 + }, + { + "epoch": 0.3393025447690858, + "grad_norm": 1.883090853691101, + "learning_rate": 4.96027801084029e-05, + "loss": 3.232, + "num_input_tokens_seen": 456160, + "step": 45 + }, + { + "epoch": 0.3770028275212064, + "grad_norm": 1.402272343635559, + "learning_rate": 4.950991058546893e-05, + "loss": 3.267, + "num_input_tokens_seen": 509680, + "step": 50 + }, + { + "epoch": 0.41470311027332707, + "grad_norm": 1.5488755702972412, + "learning_rate": 4.940740017799833e-05, + "loss": 3.2148, + "num_input_tokens_seen": 559968, + "step": 55 + }, + { + "epoch": 0.4524033930254477, + "grad_norm": 1.507287859916687, + "learning_rate": 4.929528920808854e-05, + "loss": 3.1403, + "num_input_tokens_seen": 610000, + "step": 60 + }, + { + "epoch": 0.49010367577756836, + "grad_norm": 1.9119170904159546, + "learning_rate": 4.917362177418342e-05, + "loss": 3.1515, + "num_input_tokens_seen": 661280, + "step": 65 + }, + { + "epoch": 0.527803958529689, + "grad_norm": 1.7253235578536987, + "learning_rate": 4.904244573372733e-05, + "loss": 3.1468, + "num_input_tokens_seen": 713264, + "step": 70 + }, + { + "epoch": 0.5655042412818096, + "grad_norm": 1.7201606035232544, + "learning_rate": 4.8901812684340564e-05, + "loss": 3.196, + "num_input_tokens_seen": 762576, + "step": 75 + }, + { + "epoch": 0.6032045240339302, + "grad_norm": 1.6135213375091553, + "learning_rate": 4.8751777943523634e-05, + "loss": 3.0593, + "num_input_tokens_seen": 813392, + "step": 80 + }, + { + "epoch": 0.6409048067860509, + "grad_norm": 1.7381868362426758, + "learning_rate": 4.8592400526898314e-05, + "loss": 3.0676, + "num_input_tokens_seen": 860608, + "step": 85 + }, + { + "epoch": 0.6786050895381716, + "grad_norm": 1.6142843961715698, + "learning_rate": 4.842374312499405e-05, + "loss": 3.1061, + "num_input_tokens_seen": 909104, + "step": 90 + }, + { + "epoch": 0.7163053722902922, + "grad_norm": 2.0389633178710938, + "learning_rate": 4.824587207858888e-05, + "loss": 2.9847, + "num_input_tokens_seen": 959600, + "step": 95 + }, + { + "epoch": 0.7540056550424128, + "grad_norm": 1.923561692237854, + "learning_rate": 4.805885735261454e-05, + "loss": 3.0289, + "num_input_tokens_seen": 1013648, + "step": 100 + }, + { + "epoch": 0.7917059377945335, + "grad_norm": 2.0325896739959717, + "learning_rate": 4.786277250863599e-05, + "loss": 2.9474, + "num_input_tokens_seen": 1065120, + "step": 105 + }, + { + "epoch": 0.8294062205466541, + "grad_norm": 1.6685590744018555, + "learning_rate": 4.765769467591625e-05, + "loss": 2.9713, + "num_input_tokens_seen": 1119424, + "step": 110 + }, + { + "epoch": 0.8671065032987747, + "grad_norm": 2.0325937271118164, + "learning_rate": 4.744370452107789e-05, + "loss": 3.0012, + "num_input_tokens_seen": 1169888, + "step": 115 + }, + { + "epoch": 0.9048067860508954, + "grad_norm": 1.7548010349273682, + "learning_rate": 4.722088621637309e-05, + "loss": 3.0399, + "num_input_tokens_seen": 1218944, + "step": 120 + }, + { + "epoch": 0.942507068803016, + "grad_norm": 1.6709191799163818, + "learning_rate": 4.698932740657479e-05, + "loss": 2.9156, + "num_input_tokens_seen": 1269920, + "step": 125 + }, + { + "epoch": 0.9802073515551367, + "grad_norm": 1.8369653224945068, + "learning_rate": 4.6749119174501975e-05, + "loss": 3.0288, + "num_input_tokens_seen": 1315536, + "step": 130 + }, + { + "epoch": 1.0179076343072573, + "grad_norm": 1.800703525543213, + "learning_rate": 4.6500356005192514e-05, + "loss": 2.8911, + "num_input_tokens_seen": 1360736, + "step": 135 + }, + { + "epoch": 1.055607917059378, + "grad_norm": 1.7134617567062378, + "learning_rate": 4.6243135748737864e-05, + "loss": 2.9148, + "num_input_tokens_seen": 1409808, + "step": 140 + }, + { + "epoch": 1.0933081998114986, + "grad_norm": 1.9385241270065308, + "learning_rate": 4.597755958179406e-05, + "loss": 2.868, + "num_input_tokens_seen": 1460864, + "step": 145 + }, + { + "epoch": 1.1310084825636193, + "grad_norm": 2.1658332347869873, + "learning_rate": 4.570373196778427e-05, + "loss": 2.7477, + "num_input_tokens_seen": 1512640, + "step": 150 + }, + { + "epoch": 1.1687087653157398, + "grad_norm": 2.239896774291992, + "learning_rate": 4.5421760615808474e-05, + "loss": 2.932, + "num_input_tokens_seen": 1556048, + "step": 155 + }, + { + "epoch": 1.2064090480678604, + "grad_norm": 2.0555717945098877, + "learning_rate": 4.513175643827647e-05, + "loss": 2.8219, + "num_input_tokens_seen": 1607232, + "step": 160 + }, + { + "epoch": 1.244109330819981, + "grad_norm": 2.0288779735565186, + "learning_rate": 4.4833833507280884e-05, + "loss": 2.8453, + "num_input_tokens_seen": 1653520, + "step": 165 + }, + { + "epoch": 1.2818096135721018, + "grad_norm": 1.9268651008605957, + "learning_rate": 4.4528109009727336e-05, + "loss": 2.7362, + "num_input_tokens_seen": 1703568, + "step": 170 + }, + { + "epoch": 1.3195098963242224, + "grad_norm": 2.413874387741089, + "learning_rate": 4.42147032012394e-05, + "loss": 2.9197, + "num_input_tokens_seen": 1752944, + "step": 175 + }, + { + "epoch": 1.3572101790763431, + "grad_norm": 2.2018630504608154, + "learning_rate": 4.389373935885646e-05, + "loss": 2.8897, + "num_input_tokens_seen": 1805600, + "step": 180 + }, + { + "epoch": 1.3949104618284638, + "grad_norm": 2.1807219982147217, + "learning_rate": 4.356534373254316e-05, + "loss": 2.7946, + "num_input_tokens_seen": 1860688, + "step": 185 + }, + { + "epoch": 1.4326107445805842, + "grad_norm": 2.2928526401519775, + "learning_rate": 4.322964549552943e-05, + "loss": 2.8149, + "num_input_tokens_seen": 1913056, + "step": 190 + }, + { + "epoch": 1.4703110273327051, + "grad_norm": 2.204533576965332, + "learning_rate": 4.288677669350066e-05, + "loss": 2.7811, + "num_input_tokens_seen": 1961744, + "step": 195 + }, + { + "epoch": 1.5080113100848256, + "grad_norm": 2.925762414932251, + "learning_rate": 4.2536872192658036e-05, + "loss": 2.8564, + "num_input_tokens_seen": 2011248, + "step": 200 + }, + { + "epoch": 1.5457115928369463, + "grad_norm": 2.398651599884033, + "learning_rate": 4.218006962666934e-05, + "loss": 2.7966, + "num_input_tokens_seen": 2060640, + "step": 205 + }, + { + "epoch": 1.583411875589067, + "grad_norm": 2.452263355255127, + "learning_rate": 4.181650934253132e-05, + "loss": 2.7674, + "num_input_tokens_seen": 2113904, + "step": 210 + }, + { + "epoch": 1.6211121583411876, + "grad_norm": 2.5911788940429688, + "learning_rate": 4.144633434536467e-05, + "loss": 2.7607, + "num_input_tokens_seen": 2162608, + "step": 215 + }, + { + "epoch": 1.6588124410933083, + "grad_norm": 2.648517608642578, + "learning_rate": 4.1069690242163484e-05, + "loss": 2.8402, + "num_input_tokens_seen": 2211616, + "step": 220 + }, + { + "epoch": 1.6965127238454287, + "grad_norm": 2.6860735416412354, + "learning_rate": 4.06867251845213e-05, + "loss": 2.8019, + "num_input_tokens_seen": 2269440, + "step": 225 + }, + { + "epoch": 1.7342130065975496, + "grad_norm": 2.5891222953796387, + "learning_rate": 4.0297589810356165e-05, + "loss": 2.8311, + "num_input_tokens_seen": 2321936, + "step": 230 + }, + { + "epoch": 1.77191328934967, + "grad_norm": 2.695114850997925, + "learning_rate": 3.9902437184657784e-05, + "loss": 2.7626, + "num_input_tokens_seen": 2376720, + "step": 235 + }, + { + "epoch": 1.8096135721017907, + "grad_norm": 2.588127374649048, + "learning_rate": 3.9501422739279956e-05, + "loss": 2.8052, + "num_input_tokens_seen": 2429952, + "step": 240 + }, + { + "epoch": 1.8473138548539114, + "grad_norm": 2.1829710006713867, + "learning_rate": 3.909470421180201e-05, + "loss": 2.767, + "num_input_tokens_seen": 2481488, + "step": 245 + }, + { + "epoch": 1.885014137606032, + "grad_norm": 2.606924295425415, + "learning_rate": 3.8682441583483314e-05, + "loss": 2.7651, + "num_input_tokens_seen": 2530768, + "step": 250 + }, + { + "epoch": 1.9227144203581528, + "grad_norm": 2.3635494709014893, + "learning_rate": 3.8264797016335205e-05, + "loss": 2.8097, + "num_input_tokens_seen": 2583088, + "step": 255 + }, + { + "epoch": 1.9604147031102732, + "grad_norm": 2.560624361038208, + "learning_rate": 3.7841934789335164e-05, + "loss": 2.7269, + "num_input_tokens_seen": 2631456, + "step": 260 + }, + { + "epoch": 1.998114985862394, + "grad_norm": 2.7099437713623047, + "learning_rate": 3.741402123380828e-05, + "loss": 2.8586, + "num_input_tokens_seen": 2684848, + "step": 265 + }, + { + "epoch": 2.0358152686145146, + "grad_norm": 2.552143096923828, + "learning_rate": 3.6981224668001424e-05, + "loss": 2.6131, + "num_input_tokens_seen": 2733408, + "step": 270 + }, + { + "epoch": 2.0735155513666355, + "grad_norm": 2.9233176708221436, + "learning_rate": 3.654371533087586e-05, + "loss": 2.4891, + "num_input_tokens_seen": 2786832, + "step": 275 + }, + { + "epoch": 2.111215834118756, + "grad_norm": 2.7649636268615723, + "learning_rate": 3.610166531514436e-05, + "loss": 2.5783, + "num_input_tokens_seen": 2828464, + "step": 280 + }, + { + "epoch": 2.1489161168708764, + "grad_norm": 3.076122522354126, + "learning_rate": 3.565524849957921e-05, + "loss": 2.59, + "num_input_tokens_seen": 2878192, + "step": 285 + }, + { + "epoch": 2.1866163996229973, + "grad_norm": 3.242678642272949, + "learning_rate": 3.520464048061758e-05, + "loss": 2.5839, + "num_input_tokens_seen": 2928304, + "step": 290 + }, + { + "epoch": 2.2243166823751177, + "grad_norm": 3.139089584350586, + "learning_rate": 3.47500185032913e-05, + "loss": 2.567, + "num_input_tokens_seen": 2978144, + "step": 295 + }, + { + "epoch": 2.2620169651272386, + "grad_norm": 3.1967153549194336, + "learning_rate": 3.4291561391508185e-05, + "loss": 2.5694, + "num_input_tokens_seen": 3028240, + "step": 300 + }, + { + "epoch": 2.299717247879359, + "grad_norm": 3.1987555027008057, + "learning_rate": 3.3829449477712324e-05, + "loss": 2.4965, + "num_input_tokens_seen": 3083328, + "step": 305 + }, + { + "epoch": 2.3374175306314795, + "grad_norm": 3.4724180698394775, + "learning_rate": 3.336386453195088e-05, + "loss": 2.599, + "num_input_tokens_seen": 3137072, + "step": 310 + }, + { + "epoch": 2.3751178133836004, + "grad_norm": 3.381075143814087, + "learning_rate": 3.2894989690375626e-05, + "loss": 2.524, + "num_input_tokens_seen": 3191136, + "step": 315 + }, + { + "epoch": 2.412818096135721, + "grad_norm": 3.650747537612915, + "learning_rate": 3.2423009383206876e-05, + "loss": 2.5338, + "num_input_tokens_seen": 3239952, + "step": 320 + }, + { + "epoch": 2.4505183788878417, + "grad_norm": 3.3886971473693848, + "learning_rate": 3.194810926218861e-05, + "loss": 2.5096, + "num_input_tokens_seen": 3291104, + "step": 325 + }, + { + "epoch": 2.488218661639962, + "grad_norm": 3.415850877761841, + "learning_rate": 3.147047612756302e-05, + "loss": 2.473, + "num_input_tokens_seen": 3340592, + "step": 330 + }, + { + "epoch": 2.525918944392083, + "grad_norm": 3.513828754425049, + "learning_rate": 3.099029785459328e-05, + "loss": 2.5778, + "num_input_tokens_seen": 3388224, + "step": 335 + }, + { + "epoch": 2.5636192271442035, + "grad_norm": 3.49721360206604, + "learning_rate": 3.0507763319663517e-05, + "loss": 2.5684, + "num_input_tokens_seen": 3440512, + "step": 340 + }, + { + "epoch": 2.6013195098963244, + "grad_norm": 3.5137672424316406, + "learning_rate": 3.002306232598497e-05, + "loss": 2.4923, + "num_input_tokens_seen": 3491744, + "step": 345 + }, + { + "epoch": 2.639019792648445, + "grad_norm": 3.7216403484344482, + "learning_rate": 2.9536385528937567e-05, + "loss": 2.4633, + "num_input_tokens_seen": 3542368, + "step": 350 + }, + { + "epoch": 2.6767200754005653, + "grad_norm": 3.48529052734375, + "learning_rate": 2.9047924361076345e-05, + "loss": 2.5703, + "num_input_tokens_seen": 3595360, + "step": 355 + }, + { + "epoch": 2.7144203581526862, + "grad_norm": 3.4676520824432373, + "learning_rate": 2.8557870956832132e-05, + "loss": 2.4087, + "num_input_tokens_seen": 3640912, + "step": 360 + }, + { + "epoch": 2.7521206409048067, + "grad_norm": 4.316717147827148, + "learning_rate": 2.8066418076936167e-05, + "loss": 2.5007, + "num_input_tokens_seen": 3690048, + "step": 365 + }, + { + "epoch": 2.7898209236569276, + "grad_norm": 4.2354736328125, + "learning_rate": 2.7573759032598366e-05, + "loss": 2.5312, + "num_input_tokens_seen": 3745104, + "step": 370 + }, + { + "epoch": 2.827521206409048, + "grad_norm": 3.457280397415161, + "learning_rate": 2.7080087609469062e-05, + "loss": 2.5333, + "num_input_tokens_seen": 3794160, + "step": 375 + }, + { + "epoch": 2.8652214891611685, + "grad_norm": 3.417656183242798, + "learning_rate": 2.6585597991414114e-05, + "loss": 2.4185, + "num_input_tokens_seen": 3846576, + "step": 380 + }, + { + "epoch": 2.9029217719132894, + "grad_norm": 3.7148749828338623, + "learning_rate": 2.6090484684133404e-05, + "loss": 2.4913, + "num_input_tokens_seen": 3891744, + "step": 385 + }, + { + "epoch": 2.9406220546654103, + "grad_norm": 3.562427520751953, + "learning_rate": 2.5594942438652688e-05, + "loss": 2.5319, + "num_input_tokens_seen": 3949568, + "step": 390 + }, + { + "epoch": 2.9783223374175307, + "grad_norm": 4.2560505867004395, + "learning_rate": 2.509916617471903e-05, + "loss": 2.6441, + "num_input_tokens_seen": 4002384, + "step": 395 + }, + { + "epoch": 3.016022620169651, + "grad_norm": 3.349701166152954, + "learning_rate": 2.46033509041298e-05, + "loss": 2.3576, + "num_input_tokens_seen": 4052688, + "step": 400 + }, + { + "epoch": 3.053722902921772, + "grad_norm": 3.660886287689209, + "learning_rate": 2.410769165402549e-05, + "loss": 2.3032, + "num_input_tokens_seen": 4107392, + "step": 405 + }, + { + "epoch": 3.0914231856738925, + "grad_norm": 4.248249530792236, + "learning_rate": 2.3612383390176503e-05, + "loss": 2.2542, + "num_input_tokens_seen": 4157984, + "step": 410 + }, + { + "epoch": 3.1291234684260134, + "grad_norm": 4.340310096740723, + "learning_rate": 2.3117620940294048e-05, + "loss": 2.2882, + "num_input_tokens_seen": 4213280, + "step": 415 + }, + { + "epoch": 3.166823751178134, + "grad_norm": 4.137709617614746, + "learning_rate": 2.2623598917395438e-05, + "loss": 2.2314, + "num_input_tokens_seen": 4265792, + "step": 420 + }, + { + "epoch": 3.2045240339302543, + "grad_norm": 4.506406307220459, + "learning_rate": 2.213051164325366e-05, + "loss": 2.2679, + "num_input_tokens_seen": 4310832, + "step": 425 + }, + { + "epoch": 3.242224316682375, + "grad_norm": 4.44052791595459, + "learning_rate": 2.1638553071961708e-05, + "loss": 2.2521, + "num_input_tokens_seen": 4353488, + "step": 430 + }, + { + "epoch": 3.2799245994344957, + "grad_norm": 4.674520015716553, + "learning_rate": 2.1147916713641367e-05, + "loss": 2.2071, + "num_input_tokens_seen": 4404384, + "step": 435 + }, + { + "epoch": 3.3176248821866166, + "grad_norm": 4.979199409484863, + "learning_rate": 2.0658795558326743e-05, + "loss": 2.2525, + "num_input_tokens_seen": 4453232, + "step": 440 + }, + { + "epoch": 3.355325164938737, + "grad_norm": 4.564790725708008, + "learning_rate": 2.017138200005236e-05, + "loss": 2.2431, + "num_input_tokens_seen": 4508640, + "step": 445 + }, + { + "epoch": 3.3930254476908575, + "grad_norm": 4.888641834259033, + "learning_rate": 1.9685867761175584e-05, + "loss": 2.3357, + "num_input_tokens_seen": 4559360, + "step": 450 + }, + { + "epoch": 3.4307257304429783, + "grad_norm": 4.425845623016357, + "learning_rate": 1.9202443816963425e-05, + "loss": 2.2875, + "num_input_tokens_seen": 4609584, + "step": 455 + }, + { + "epoch": 3.468426013195099, + "grad_norm": 5.38726282119751, + "learning_rate": 1.872130032047302e-05, + "loss": 2.2136, + "num_input_tokens_seen": 4665472, + "step": 460 + }, + { + "epoch": 3.5061262959472197, + "grad_norm": 4.473924160003662, + "learning_rate": 1.824262652775568e-05, + "loss": 2.294, + "num_input_tokens_seen": 4719360, + "step": 465 + }, + { + "epoch": 3.54382657869934, + "grad_norm": 5.171916484832764, + "learning_rate": 1.7766610723413684e-05, + "loss": 2.2146, + "num_input_tokens_seen": 4771504, + "step": 470 + }, + { + "epoch": 3.581526861451461, + "grad_norm": 5.492386817932129, + "learning_rate": 1.7293440146539196e-05, + "loss": 2.3166, + "num_input_tokens_seen": 4820432, + "step": 475 + }, + { + "epoch": 3.6192271442035815, + "grad_norm": 4.300539493560791, + "learning_rate": 1.682330091706446e-05, + "loss": 2.2775, + "num_input_tokens_seen": 4877984, + "step": 480 + }, + { + "epoch": 3.6569274269557024, + "grad_norm": 5.470084190368652, + "learning_rate": 1.6356377962552238e-05, + "loss": 2.2442, + "num_input_tokens_seen": 4927712, + "step": 485 + }, + { + "epoch": 3.694627709707823, + "grad_norm": 5.457830429077148, + "learning_rate": 1.589285494545514e-05, + "loss": 2.2499, + "num_input_tokens_seen": 4979520, + "step": 490 + }, + { + "epoch": 3.7323279924599433, + "grad_norm": 4.851473808288574, + "learning_rate": 1.5432914190872757e-05, + "loss": 2.214, + "num_input_tokens_seen": 5030720, + "step": 495 + }, + { + "epoch": 3.770028275212064, + "grad_norm": 4.645096302032471, + "learning_rate": 1.4976736614834664e-05, + "loss": 2.1646, + "num_input_tokens_seen": 5081376, + "step": 500 + }, + { + "epoch": 3.8077285579641846, + "grad_norm": 5.5402512550354, + "learning_rate": 1.4524501653137787e-05, + "loss": 2.3151, + "num_input_tokens_seen": 5127888, + "step": 505 + }, + { + "epoch": 3.8454288407163055, + "grad_norm": 4.753649711608887, + "learning_rate": 1.4076387190766017e-05, + "loss": 2.2602, + "num_input_tokens_seen": 5178720, + "step": 510 + }, + { + "epoch": 3.883129123468426, + "grad_norm": 5.488243579864502, + "learning_rate": 1.363256949191972e-05, + "loss": 2.1839, + "num_input_tokens_seen": 5227120, + "step": 515 + }, + { + "epoch": 3.9208294062205464, + "grad_norm": 5.427800178527832, + "learning_rate": 1.3193223130682936e-05, + "loss": 2.2833, + "num_input_tokens_seen": 5275760, + "step": 520 + }, + { + "epoch": 3.9585296889726673, + "grad_norm": 4.901040077209473, + "learning_rate": 1.2758520922355226e-05, + "loss": 2.1802, + "num_input_tokens_seen": 5319632, + "step": 525 + }, + { + "epoch": 3.9962299717247878, + "grad_norm": 4.977085590362549, + "learning_rate": 1.2328633855475429e-05, + "loss": 2.2383, + "num_input_tokens_seen": 5369936, + "step": 530 + }, + { + "epoch": 4.033930254476909, + "grad_norm": 4.724318027496338, + "learning_rate": 1.1903731024563966e-05, + "loss": 2.007, + "num_input_tokens_seen": 5421440, + "step": 535 + }, + { + "epoch": 4.071630537229029, + "grad_norm": 5.148896217346191, + "learning_rate": 1.148397956361007e-05, + "loss": 2.0286, + "num_input_tokens_seen": 5476736, + "step": 540 + }, + { + "epoch": 4.10933081998115, + "grad_norm": 5.690558433532715, + "learning_rate": 1.106954458033026e-05, + "loss": 2.0398, + "num_input_tokens_seen": 5531328, + "step": 545 + }, + { + "epoch": 4.147031102733271, + "grad_norm": 5.595386505126953, + "learning_rate": 1.0660589091223855e-05, + "loss": 2.1157, + "num_input_tokens_seen": 5579216, + "step": 550 + }, + { + "epoch": 4.184731385485391, + "grad_norm": 6.112159252166748, + "learning_rate": 1.025727395745095e-05, + "loss": 2.094, + "num_input_tokens_seen": 5626208, + "step": 555 + }, + { + "epoch": 4.222431668237512, + "grad_norm": 5.86374568939209, + "learning_rate": 9.859757821558337e-06, + "loss": 2.0531, + "num_input_tokens_seen": 5679360, + "step": 560 + }, + { + "epoch": 4.260131950989632, + "grad_norm": 5.2934699058532715, + "learning_rate": 9.468197045077976e-06, + "loss": 1.9652, + "num_input_tokens_seen": 5724608, + "step": 565 + }, + { + "epoch": 4.297832233741753, + "grad_norm": 6.302525043487549, + "learning_rate": 9.082745647022797e-06, + "loss": 2.0592, + "num_input_tokens_seen": 5779904, + "step": 570 + }, + { + "epoch": 4.335532516493874, + "grad_norm": 6.2651143074035645, + "learning_rate": 8.703555243303835e-06, + "loss": 2.0418, + "num_input_tokens_seen": 5826880, + "step": 575 + }, + { + "epoch": 4.3732327992459945, + "grad_norm": 6.225465774536133, + "learning_rate": 8.330774987092712e-06, + "loss": 1.991, + "num_input_tokens_seen": 5875440, + "step": 580 + }, + { + "epoch": 4.410933081998115, + "grad_norm": 5.812168121337891, + "learning_rate": 7.96455151015272e-06, + "loss": 2.0726, + "num_input_tokens_seen": 5924960, + "step": 585 + }, + { + "epoch": 4.448633364750235, + "grad_norm": 5.528653621673584, + "learning_rate": 7.605028865161809e-06, + "loss": 2.069, + "num_input_tokens_seen": 5976416, + "step": 590 + }, + { + "epoch": 4.486333647502356, + "grad_norm": 5.838290691375732, + "learning_rate": 7.25234846904993e-06, + "loss": 2.052, + "num_input_tokens_seen": 6027088, + "step": 595 + }, + { + "epoch": 4.524033930254477, + "grad_norm": 6.014201641082764, + "learning_rate": 6.906649047373246e-06, + "loss": 2.0651, + "num_input_tokens_seen": 6080528, + "step": 600 + }, + { + "epoch": 4.561734213006598, + "grad_norm": 6.840231895446777, + "learning_rate": 6.568066579746901e-06, + "loss": 2.0546, + "num_input_tokens_seen": 6125904, + "step": 605 + }, + { + "epoch": 4.599434495758718, + "grad_norm": 6.350096702575684, + "learning_rate": 6.2367342463579475e-06, + "loss": 2.081, + "num_input_tokens_seen": 6173744, + "step": 610 + }, + { + "epoch": 4.6371347785108386, + "grad_norm": 6.259740352630615, + "learning_rate": 5.912782375579412e-06, + "loss": 2.0395, + "num_input_tokens_seen": 6222560, + "step": 615 + }, + { + "epoch": 4.674835061262959, + "grad_norm": 6.564173221588135, + "learning_rate": 5.596338392706077e-06, + "loss": 2.0659, + "num_input_tokens_seen": 6272544, + "step": 620 + }, + { + "epoch": 4.71253534401508, + "grad_norm": 5.375278949737549, + "learning_rate": 5.2875267698322325e-06, + "loss": 2.0247, + "num_input_tokens_seen": 6323024, + "step": 625 + }, + { + "epoch": 4.750235626767201, + "grad_norm": 5.922281265258789, + "learning_rate": 4.986468976890993e-06, + "loss": 2.0485, + "num_input_tokens_seen": 6374608, + "step": 630 + }, + { + "epoch": 4.787935909519321, + "grad_norm": 5.62613582611084, + "learning_rate": 4.693283433874565e-06, + "loss": 2.0561, + "num_input_tokens_seen": 6422208, + "step": 635 + }, + { + "epoch": 4.825636192271442, + "grad_norm": 6.259154796600342, + "learning_rate": 4.408085464254183e-06, + "loss": 2.1047, + "num_input_tokens_seen": 6468912, + "step": 640 + }, + { + "epoch": 4.863336475023563, + "grad_norm": 5.757895469665527, + "learning_rate": 4.130987249617993e-06, + "loss": 2.0481, + "num_input_tokens_seen": 6522848, + "step": 645 + }, + { + "epoch": 4.9010367577756835, + "grad_norm": 5.949391841888428, + "learning_rate": 3.8620977855448935e-06, + "loss": 2.0637, + "num_input_tokens_seen": 6578768, + "step": 650 + }, + { + "epoch": 4.938737040527804, + "grad_norm": 6.397491931915283, + "learning_rate": 3.601522838731461e-06, + "loss": 2.0429, + "num_input_tokens_seen": 6631936, + "step": 655 + }, + { + "epoch": 4.976437323279924, + "grad_norm": 6.2142157554626465, + "learning_rate": 3.3493649053890326e-06, + "loss": 2.1212, + "num_input_tokens_seen": 6682992, + "step": 660 + }, + { + "epoch": 5.014137606032045, + "grad_norm": 5.99893856048584, + "learning_rate": 3.1057231709272077e-06, + "loss": 2.0205, + "num_input_tokens_seen": 6735056, + "step": 665 + }, + { + "epoch": 5.051837888784166, + "grad_norm": 6.014187335968018, + "learning_rate": 2.8706934709395892e-06, + "loss": 1.9942, + "num_input_tokens_seen": 6784224, + "step": 670 + }, + { + "epoch": 5.089538171536287, + "grad_norm": 6.134748935699463, + "learning_rate": 2.6443682535072177e-06, + "loss": 1.868, + "num_input_tokens_seen": 6831040, + "step": 675 + }, + { + "epoch": 5.127238454288407, + "grad_norm": 5.91867733001709, + "learning_rate": 2.4268365428344736e-06, + "loss": 1.9132, + "num_input_tokens_seen": 6883552, + "step": 680 + }, + { + "epoch": 5.1649387370405275, + "grad_norm": 7.725922584533691, + "learning_rate": 2.21818390423168e-06, + "loss": 1.8698, + "num_input_tokens_seen": 6928272, + "step": 685 + }, + { + "epoch": 5.202639019792649, + "grad_norm": 5.97230863571167, + "learning_rate": 2.0184924104583613e-06, + "loss": 1.8974, + "num_input_tokens_seen": 6972496, + "step": 690 + }, + { + "epoch": 5.240339302544769, + "grad_norm": 6.879273414611816, + "learning_rate": 1.8278406094401623e-06, + "loss": 1.9096, + "num_input_tokens_seen": 7018496, + "step": 695 + }, + { + "epoch": 5.27803958529689, + "grad_norm": 6.802375793457031, + "learning_rate": 1.6463034933723337e-06, + "loss": 2.0098, + "num_input_tokens_seen": 7066400, + "step": 700 + } + ], + "logging_steps": 5, + "max_steps": 792, + "num_input_tokens_seen": 7066400, + "num_train_epochs": 6, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3.1908595767443456e+17, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-700/training_args.bin b/checkpoint-700/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f8accff7ed19f472e4ab59934a52cd1b74989284 --- /dev/null +++ b/checkpoint-700/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0abbac12d56c1934fca1078792064a59e7f00bea9a38a70efb9ce7fe81d8d0a2 +size 5432 diff --git a/checkpoint-792/README.md b/checkpoint-792/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ba199ae8c078d293275e50b0a850beb3a458a43e --- /dev/null +++ b/checkpoint-792/README.md @@ -0,0 +1,202 @@ +--- +base_model: NousResearch/Hermes-3-Llama-3.1-8B +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.12.0 \ No newline at end of file diff --git a/checkpoint-792/adapter_config.json b/checkpoint-792/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4aa889ee5316659d91ab201b4f03e49477d31374 --- /dev/null +++ b/checkpoint-792/adapter_config.json @@ -0,0 +1,34 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "bias": "none", + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_dropout": 0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 8, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "k_proj", + "v_proj", + "o_proj", + "down_proj", + "q_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-792/adapter_model.safetensors b/checkpoint-792/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e329f63cabe7bbabd90c66c3497bd5f522016f18 --- /dev/null +++ b/checkpoint-792/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b64d881e75b15b70ebdb13bdb6a15bc8897b67d9991a8bc5f766dffe7624b3a +size 83945296 diff --git a/checkpoint-792/optimizer.pt b/checkpoint-792/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b8c0a66a3be1427ec93a032a4d2e27fc8bda506 --- /dev/null +++ b/checkpoint-792/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74e026776c361b169d05fbd61d9f3e07a689bab85f891fde7e223180f198d3c4 +size 168149074 diff --git a/checkpoint-792/rng_state_0.pth b/checkpoint-792/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..07a546a3d8fa499648a42db76ea9733d09e5ca98 --- /dev/null +++ b/checkpoint-792/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7a17ffe4d1cfad70857491e1fd7e427c0413a789e2cb4398c4af3ca8efd92a5 +size 14512 diff --git a/checkpoint-792/rng_state_1.pth b/checkpoint-792/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..5552726456b4cc7d1cc941b486f870e723d6ab42 --- /dev/null +++ b/checkpoint-792/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8430d63cfb7960c36461376f5e1ef952c23b5128eae3a1f763753f4c308fd4aa +size 14512 diff --git a/checkpoint-792/scheduler.pt b/checkpoint-792/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..20399683afba80b004d44fb0c6ae5f70cf36ae7c --- /dev/null +++ b/checkpoint-792/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f73652ede104d225238e53c163ef7c39023640a346bd2fa7bdc03199391ac285 +size 1064 diff --git a/checkpoint-792/special_tokens_map.json b/checkpoint-792/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1ad7f173822ffa805bd5f390acc9c3390d414e67 --- /dev/null +++ b/checkpoint-792/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-792/tokenizer.json b/checkpoint-792/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b --- /dev/null +++ b/checkpoint-792/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05 +size 17209403 diff --git a/checkpoint-792/tokenizer_config.json b/checkpoint-792/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a22a366f4a4df58d908d0fa483648703588ce0b1 --- /dev/null +++ b/checkpoint-792/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128039": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128040": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|im_end|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-792/trainer_state.json b/checkpoint-792/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..dbced1559f97ad7779560be9cea874b2ecbed0c8 --- /dev/null +++ b/checkpoint-792/trainer_state.json @@ -0,0 +1,1297 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 5.971724787935909, + "eval_steps": 500, + "global_step": 792, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.03770028275212064, + "grad_norm": 3.988708734512329, + "learning_rate": 4.9995083170283816e-05, + "loss": 4.6192, + "num_input_tokens_seen": 50400, + "step": 5 + }, + { + "epoch": 0.07540056550424128, + "grad_norm": 2.142688512802124, + "learning_rate": 4.998033461515242e-05, + "loss": 3.9149, + "num_input_tokens_seen": 104016, + "step": 10 + }, + { + "epoch": 0.11310084825636192, + "grad_norm": 1.5928359031677246, + "learning_rate": 4.9955760135896534e-05, + "loss": 3.6912, + "num_input_tokens_seen": 155584, + "step": 15 + }, + { + "epoch": 0.15080113100848255, + "grad_norm": 1.5493167638778687, + "learning_rate": 4.992136939879856e-05, + "loss": 3.5556, + "num_input_tokens_seen": 202672, + "step": 20 + }, + { + "epoch": 0.1885014137606032, + "grad_norm": 1.7764347791671753, + "learning_rate": 4.9877175931330346e-05, + "loss": 3.4256, + "num_input_tokens_seen": 254800, + "step": 25 + }, + { + "epoch": 0.22620169651272384, + "grad_norm": 1.2482728958129883, + "learning_rate": 4.982319711683221e-05, + "loss": 3.3128, + "num_input_tokens_seen": 306352, + "step": 30 + }, + { + "epoch": 0.2639019792648445, + "grad_norm": 1.2829065322875977, + "learning_rate": 4.975945418767529e-05, + "loss": 3.2688, + "num_input_tokens_seen": 356352, + "step": 35 + }, + { + "epoch": 0.3016022620169651, + "grad_norm": 1.513293743133545, + "learning_rate": 4.968597221690986e-05, + "loss": 3.297, + "num_input_tokens_seen": 406672, + "step": 40 + }, + { + "epoch": 0.3393025447690858, + "grad_norm": 1.883090853691101, + "learning_rate": 4.96027801084029e-05, + "loss": 3.232, + "num_input_tokens_seen": 456160, + "step": 45 + }, + { + "epoch": 0.3770028275212064, + "grad_norm": 1.402272343635559, + "learning_rate": 4.950991058546893e-05, + "loss": 3.267, + "num_input_tokens_seen": 509680, + "step": 50 + }, + { + "epoch": 0.41470311027332707, + "grad_norm": 1.5488755702972412, + "learning_rate": 4.940740017799833e-05, + "loss": 3.2148, + "num_input_tokens_seen": 559968, + "step": 55 + }, + { + "epoch": 0.4524033930254477, + "grad_norm": 1.507287859916687, + "learning_rate": 4.929528920808854e-05, + "loss": 3.1403, + "num_input_tokens_seen": 610000, + "step": 60 + }, + { + "epoch": 0.49010367577756836, + "grad_norm": 1.9119170904159546, + "learning_rate": 4.917362177418342e-05, + "loss": 3.1515, + "num_input_tokens_seen": 661280, + "step": 65 + }, + { + "epoch": 0.527803958529689, + "grad_norm": 1.7253235578536987, + "learning_rate": 4.904244573372733e-05, + "loss": 3.1468, + "num_input_tokens_seen": 713264, + "step": 70 + }, + { + "epoch": 0.5655042412818096, + "grad_norm": 1.7201606035232544, + "learning_rate": 4.8901812684340564e-05, + "loss": 3.196, + "num_input_tokens_seen": 762576, + "step": 75 + }, + { + "epoch": 0.6032045240339302, + "grad_norm": 1.6135213375091553, + "learning_rate": 4.8751777943523634e-05, + "loss": 3.0593, + "num_input_tokens_seen": 813392, + "step": 80 + }, + { + "epoch": 0.6409048067860509, + "grad_norm": 1.7381868362426758, + "learning_rate": 4.8592400526898314e-05, + "loss": 3.0676, + "num_input_tokens_seen": 860608, + "step": 85 + }, + { + "epoch": 0.6786050895381716, + "grad_norm": 1.6142843961715698, + "learning_rate": 4.842374312499405e-05, + "loss": 3.1061, + "num_input_tokens_seen": 909104, + "step": 90 + }, + { + "epoch": 0.7163053722902922, + "grad_norm": 2.0389633178710938, + "learning_rate": 4.824587207858888e-05, + "loss": 2.9847, + "num_input_tokens_seen": 959600, + "step": 95 + }, + { + "epoch": 0.7540056550424128, + "grad_norm": 1.923561692237854, + "learning_rate": 4.805885735261454e-05, + "loss": 3.0289, + "num_input_tokens_seen": 1013648, + "step": 100 + }, + { + "epoch": 0.7917059377945335, + "grad_norm": 2.0325896739959717, + "learning_rate": 4.786277250863599e-05, + "loss": 2.9474, + "num_input_tokens_seen": 1065120, + "step": 105 + }, + { + "epoch": 0.8294062205466541, + "grad_norm": 1.6685590744018555, + "learning_rate": 4.765769467591625e-05, + "loss": 2.9713, + "num_input_tokens_seen": 1119424, + "step": 110 + }, + { + "epoch": 0.8671065032987747, + "grad_norm": 2.0325937271118164, + "learning_rate": 4.744370452107789e-05, + "loss": 3.0012, + "num_input_tokens_seen": 1169888, + "step": 115 + }, + { + "epoch": 0.9048067860508954, + "grad_norm": 1.7548010349273682, + "learning_rate": 4.722088621637309e-05, + "loss": 3.0399, + "num_input_tokens_seen": 1218944, + "step": 120 + }, + { + "epoch": 0.942507068803016, + "grad_norm": 1.6709191799163818, + "learning_rate": 4.698932740657479e-05, + "loss": 2.9156, + "num_input_tokens_seen": 1269920, + "step": 125 + }, + { + "epoch": 0.9802073515551367, + "grad_norm": 1.8369653224945068, + "learning_rate": 4.6749119174501975e-05, + "loss": 3.0288, + "num_input_tokens_seen": 1315536, + "step": 130 + }, + { + "epoch": 1.0179076343072573, + "grad_norm": 1.800703525543213, + "learning_rate": 4.6500356005192514e-05, + "loss": 2.8911, + "num_input_tokens_seen": 1360736, + "step": 135 + }, + { + "epoch": 1.055607917059378, + "grad_norm": 1.7134617567062378, + "learning_rate": 4.6243135748737864e-05, + "loss": 2.9148, + "num_input_tokens_seen": 1409808, + "step": 140 + }, + { + "epoch": 1.0933081998114986, + "grad_norm": 1.9385241270065308, + "learning_rate": 4.597755958179406e-05, + "loss": 2.868, + "num_input_tokens_seen": 1460864, + "step": 145 + }, + { + "epoch": 1.1310084825636193, + "grad_norm": 2.1658332347869873, + "learning_rate": 4.570373196778427e-05, + "loss": 2.7477, + "num_input_tokens_seen": 1512640, + "step": 150 + }, + { + "epoch": 1.1687087653157398, + "grad_norm": 2.239896774291992, + "learning_rate": 4.5421760615808474e-05, + "loss": 2.932, + "num_input_tokens_seen": 1556048, + "step": 155 + }, + { + "epoch": 1.2064090480678604, + "grad_norm": 2.0555717945098877, + "learning_rate": 4.513175643827647e-05, + "loss": 2.8219, + "num_input_tokens_seen": 1607232, + "step": 160 + }, + { + "epoch": 1.244109330819981, + "grad_norm": 2.0288779735565186, + "learning_rate": 4.4833833507280884e-05, + "loss": 2.8453, + "num_input_tokens_seen": 1653520, + "step": 165 + }, + { + "epoch": 1.2818096135721018, + "grad_norm": 1.9268651008605957, + "learning_rate": 4.4528109009727336e-05, + "loss": 2.7362, + "num_input_tokens_seen": 1703568, + "step": 170 + }, + { + "epoch": 1.3195098963242224, + "grad_norm": 2.413874387741089, + "learning_rate": 4.42147032012394e-05, + "loss": 2.9197, + "num_input_tokens_seen": 1752944, + "step": 175 + }, + { + "epoch": 1.3572101790763431, + "grad_norm": 2.2018630504608154, + "learning_rate": 4.389373935885646e-05, + "loss": 2.8897, + "num_input_tokens_seen": 1805600, + "step": 180 + }, + { + "epoch": 1.3949104618284638, + "grad_norm": 2.1807219982147217, + "learning_rate": 4.356534373254316e-05, + "loss": 2.7946, + "num_input_tokens_seen": 1860688, + "step": 185 + }, + { + "epoch": 1.4326107445805842, + "grad_norm": 2.2928526401519775, + "learning_rate": 4.322964549552943e-05, + "loss": 2.8149, + "num_input_tokens_seen": 1913056, + "step": 190 + }, + { + "epoch": 1.4703110273327051, + "grad_norm": 2.204533576965332, + "learning_rate": 4.288677669350066e-05, + "loss": 2.7811, + "num_input_tokens_seen": 1961744, + "step": 195 + }, + { + "epoch": 1.5080113100848256, + "grad_norm": 2.925762414932251, + "learning_rate": 4.2536872192658036e-05, + "loss": 2.8564, + "num_input_tokens_seen": 2011248, + "step": 200 + }, + { + "epoch": 1.5457115928369463, + "grad_norm": 2.398651599884033, + "learning_rate": 4.218006962666934e-05, + "loss": 2.7966, + "num_input_tokens_seen": 2060640, + "step": 205 + }, + { + "epoch": 1.583411875589067, + "grad_norm": 2.452263355255127, + "learning_rate": 4.181650934253132e-05, + "loss": 2.7674, + "num_input_tokens_seen": 2113904, + "step": 210 + }, + { + "epoch": 1.6211121583411876, + "grad_norm": 2.5911788940429688, + "learning_rate": 4.144633434536467e-05, + "loss": 2.7607, + "num_input_tokens_seen": 2162608, + "step": 215 + }, + { + "epoch": 1.6588124410933083, + "grad_norm": 2.648517608642578, + "learning_rate": 4.1069690242163484e-05, + "loss": 2.8402, + "num_input_tokens_seen": 2211616, + "step": 220 + }, + { + "epoch": 1.6965127238454287, + "grad_norm": 2.6860735416412354, + "learning_rate": 4.06867251845213e-05, + "loss": 2.8019, + "num_input_tokens_seen": 2269440, + "step": 225 + }, + { + "epoch": 1.7342130065975496, + "grad_norm": 2.5891222953796387, + "learning_rate": 4.0297589810356165e-05, + "loss": 2.8311, + "num_input_tokens_seen": 2321936, + "step": 230 + }, + { + "epoch": 1.77191328934967, + "grad_norm": 2.695114850997925, + "learning_rate": 3.9902437184657784e-05, + "loss": 2.7626, + "num_input_tokens_seen": 2376720, + "step": 235 + }, + { + "epoch": 1.8096135721017907, + "grad_norm": 2.588127374649048, + "learning_rate": 3.9501422739279956e-05, + "loss": 2.8052, + "num_input_tokens_seen": 2429952, + "step": 240 + }, + { + "epoch": 1.8473138548539114, + "grad_norm": 2.1829710006713867, + "learning_rate": 3.909470421180201e-05, + "loss": 2.767, + "num_input_tokens_seen": 2481488, + "step": 245 + }, + { + "epoch": 1.885014137606032, + "grad_norm": 2.606924295425415, + "learning_rate": 3.8682441583483314e-05, + "loss": 2.7651, + "num_input_tokens_seen": 2530768, + "step": 250 + }, + { + "epoch": 1.9227144203581528, + "grad_norm": 2.3635494709014893, + "learning_rate": 3.8264797016335205e-05, + "loss": 2.8097, + "num_input_tokens_seen": 2583088, + "step": 255 + }, + { + "epoch": 1.9604147031102732, + "grad_norm": 2.560624361038208, + "learning_rate": 3.7841934789335164e-05, + "loss": 2.7269, + "num_input_tokens_seen": 2631456, + "step": 260 + }, + { + "epoch": 1.998114985862394, + "grad_norm": 2.7099437713623047, + "learning_rate": 3.741402123380828e-05, + "loss": 2.8586, + "num_input_tokens_seen": 2684848, + "step": 265 + }, + { + "epoch": 2.0358152686145146, + "grad_norm": 2.552143096923828, + "learning_rate": 3.6981224668001424e-05, + "loss": 2.6131, + "num_input_tokens_seen": 2733408, + "step": 270 + }, + { + "epoch": 2.0735155513666355, + "grad_norm": 2.9233176708221436, + "learning_rate": 3.654371533087586e-05, + "loss": 2.4891, + "num_input_tokens_seen": 2786832, + "step": 275 + }, + { + "epoch": 2.111215834118756, + "grad_norm": 2.7649636268615723, + "learning_rate": 3.610166531514436e-05, + "loss": 2.5783, + "num_input_tokens_seen": 2828464, + "step": 280 + }, + { + "epoch": 2.1489161168708764, + "grad_norm": 3.076122522354126, + "learning_rate": 3.565524849957921e-05, + "loss": 2.59, + "num_input_tokens_seen": 2878192, + "step": 285 + }, + { + "epoch": 2.1866163996229973, + "grad_norm": 3.242678642272949, + "learning_rate": 3.520464048061758e-05, + "loss": 2.5839, + "num_input_tokens_seen": 2928304, + "step": 290 + }, + { + "epoch": 2.2243166823751177, + "grad_norm": 3.139089584350586, + "learning_rate": 3.47500185032913e-05, + "loss": 2.567, + "num_input_tokens_seen": 2978144, + "step": 295 + }, + { + "epoch": 2.2620169651272386, + "grad_norm": 3.1967153549194336, + "learning_rate": 3.4291561391508185e-05, + "loss": 2.5694, + "num_input_tokens_seen": 3028240, + "step": 300 + }, + { + "epoch": 2.299717247879359, + "grad_norm": 3.1987555027008057, + "learning_rate": 3.3829449477712324e-05, + "loss": 2.4965, + "num_input_tokens_seen": 3083328, + "step": 305 + }, + { + "epoch": 2.3374175306314795, + "grad_norm": 3.4724180698394775, + "learning_rate": 3.336386453195088e-05, + "loss": 2.599, + "num_input_tokens_seen": 3137072, + "step": 310 + }, + { + "epoch": 2.3751178133836004, + "grad_norm": 3.381075143814087, + "learning_rate": 3.2894989690375626e-05, + "loss": 2.524, + "num_input_tokens_seen": 3191136, + "step": 315 + }, + { + "epoch": 2.412818096135721, + "grad_norm": 3.650747537612915, + "learning_rate": 3.2423009383206876e-05, + "loss": 2.5338, + "num_input_tokens_seen": 3239952, + "step": 320 + }, + { + "epoch": 2.4505183788878417, + "grad_norm": 3.3886971473693848, + "learning_rate": 3.194810926218861e-05, + "loss": 2.5096, + "num_input_tokens_seen": 3291104, + "step": 325 + }, + { + "epoch": 2.488218661639962, + "grad_norm": 3.415850877761841, + "learning_rate": 3.147047612756302e-05, + "loss": 2.473, + "num_input_tokens_seen": 3340592, + "step": 330 + }, + { + "epoch": 2.525918944392083, + "grad_norm": 3.513828754425049, + "learning_rate": 3.099029785459328e-05, + "loss": 2.5778, + "num_input_tokens_seen": 3388224, + "step": 335 + }, + { + "epoch": 2.5636192271442035, + "grad_norm": 3.49721360206604, + "learning_rate": 3.0507763319663517e-05, + "loss": 2.5684, + "num_input_tokens_seen": 3440512, + "step": 340 + }, + { + "epoch": 2.6013195098963244, + "grad_norm": 3.5137672424316406, + "learning_rate": 3.002306232598497e-05, + "loss": 2.4923, + "num_input_tokens_seen": 3491744, + "step": 345 + }, + { + "epoch": 2.639019792648445, + "grad_norm": 3.7216403484344482, + "learning_rate": 2.9536385528937567e-05, + "loss": 2.4633, + "num_input_tokens_seen": 3542368, + "step": 350 + }, + { + "epoch": 2.6767200754005653, + "grad_norm": 3.48529052734375, + "learning_rate": 2.9047924361076345e-05, + "loss": 2.5703, + "num_input_tokens_seen": 3595360, + "step": 355 + }, + { + "epoch": 2.7144203581526862, + "grad_norm": 3.4676520824432373, + "learning_rate": 2.8557870956832132e-05, + "loss": 2.4087, + "num_input_tokens_seen": 3640912, + "step": 360 + }, + { + "epoch": 2.7521206409048067, + "grad_norm": 4.316717147827148, + "learning_rate": 2.8066418076936167e-05, + "loss": 2.5007, + "num_input_tokens_seen": 3690048, + "step": 365 + }, + { + "epoch": 2.7898209236569276, + "grad_norm": 4.2354736328125, + "learning_rate": 2.7573759032598366e-05, + "loss": 2.5312, + "num_input_tokens_seen": 3745104, + "step": 370 + }, + { + "epoch": 2.827521206409048, + "grad_norm": 3.457280397415161, + "learning_rate": 2.7080087609469062e-05, + "loss": 2.5333, + "num_input_tokens_seen": 3794160, + "step": 375 + }, + { + "epoch": 2.8652214891611685, + "grad_norm": 3.417656183242798, + "learning_rate": 2.6585597991414114e-05, + "loss": 2.4185, + "num_input_tokens_seen": 3846576, + "step": 380 + }, + { + "epoch": 2.9029217719132894, + "grad_norm": 3.7148749828338623, + "learning_rate": 2.6090484684133404e-05, + "loss": 2.4913, + "num_input_tokens_seen": 3891744, + "step": 385 + }, + { + "epoch": 2.9406220546654103, + "grad_norm": 3.562427520751953, + "learning_rate": 2.5594942438652688e-05, + "loss": 2.5319, + "num_input_tokens_seen": 3949568, + "step": 390 + }, + { + "epoch": 2.9783223374175307, + "grad_norm": 4.2560505867004395, + "learning_rate": 2.509916617471903e-05, + "loss": 2.6441, + "num_input_tokens_seen": 4002384, + "step": 395 + }, + { + "epoch": 3.016022620169651, + "grad_norm": 3.349701166152954, + "learning_rate": 2.46033509041298e-05, + "loss": 2.3576, + "num_input_tokens_seen": 4052688, + "step": 400 + }, + { + "epoch": 3.053722902921772, + "grad_norm": 3.660886287689209, + "learning_rate": 2.410769165402549e-05, + "loss": 2.3032, + "num_input_tokens_seen": 4107392, + "step": 405 + }, + { + "epoch": 3.0914231856738925, + "grad_norm": 4.248249530792236, + "learning_rate": 2.3612383390176503e-05, + "loss": 2.2542, + "num_input_tokens_seen": 4157984, + "step": 410 + }, + { + "epoch": 3.1291234684260134, + "grad_norm": 4.340310096740723, + "learning_rate": 2.3117620940294048e-05, + "loss": 2.2882, + "num_input_tokens_seen": 4213280, + "step": 415 + }, + { + "epoch": 3.166823751178134, + "grad_norm": 4.137709617614746, + "learning_rate": 2.2623598917395438e-05, + "loss": 2.2314, + "num_input_tokens_seen": 4265792, + "step": 420 + }, + { + "epoch": 3.2045240339302543, + "grad_norm": 4.506406307220459, + "learning_rate": 2.213051164325366e-05, + "loss": 2.2679, + "num_input_tokens_seen": 4310832, + "step": 425 + }, + { + "epoch": 3.242224316682375, + "grad_norm": 4.44052791595459, + "learning_rate": 2.1638553071961708e-05, + "loss": 2.2521, + "num_input_tokens_seen": 4353488, + "step": 430 + }, + { + "epoch": 3.2799245994344957, + "grad_norm": 4.674520015716553, + "learning_rate": 2.1147916713641367e-05, + "loss": 2.2071, + "num_input_tokens_seen": 4404384, + "step": 435 + }, + { + "epoch": 3.3176248821866166, + "grad_norm": 4.979199409484863, + "learning_rate": 2.0658795558326743e-05, + "loss": 2.2525, + "num_input_tokens_seen": 4453232, + "step": 440 + }, + { + "epoch": 3.355325164938737, + "grad_norm": 4.564790725708008, + "learning_rate": 2.017138200005236e-05, + "loss": 2.2431, + "num_input_tokens_seen": 4508640, + "step": 445 + }, + { + "epoch": 3.3930254476908575, + "grad_norm": 4.888641834259033, + "learning_rate": 1.9685867761175584e-05, + "loss": 2.3357, + "num_input_tokens_seen": 4559360, + "step": 450 + }, + { + "epoch": 3.4307257304429783, + "grad_norm": 4.425845623016357, + "learning_rate": 1.9202443816963425e-05, + "loss": 2.2875, + "num_input_tokens_seen": 4609584, + "step": 455 + }, + { + "epoch": 3.468426013195099, + "grad_norm": 5.38726282119751, + "learning_rate": 1.872130032047302e-05, + "loss": 2.2136, + "num_input_tokens_seen": 4665472, + "step": 460 + }, + { + "epoch": 3.5061262959472197, + "grad_norm": 4.473924160003662, + "learning_rate": 1.824262652775568e-05, + "loss": 2.294, + "num_input_tokens_seen": 4719360, + "step": 465 + }, + { + "epoch": 3.54382657869934, + "grad_norm": 5.171916484832764, + "learning_rate": 1.7766610723413684e-05, + "loss": 2.2146, + "num_input_tokens_seen": 4771504, + "step": 470 + }, + { + "epoch": 3.581526861451461, + "grad_norm": 5.492386817932129, + "learning_rate": 1.7293440146539196e-05, + "loss": 2.3166, + "num_input_tokens_seen": 4820432, + "step": 475 + }, + { + "epoch": 3.6192271442035815, + "grad_norm": 4.300539493560791, + "learning_rate": 1.682330091706446e-05, + "loss": 2.2775, + "num_input_tokens_seen": 4877984, + "step": 480 + }, + { + "epoch": 3.6569274269557024, + "grad_norm": 5.470084190368652, + "learning_rate": 1.6356377962552238e-05, + "loss": 2.2442, + "num_input_tokens_seen": 4927712, + "step": 485 + }, + { + "epoch": 3.694627709707823, + "grad_norm": 5.457830429077148, + "learning_rate": 1.589285494545514e-05, + "loss": 2.2499, + "num_input_tokens_seen": 4979520, + "step": 490 + }, + { + "epoch": 3.7323279924599433, + "grad_norm": 4.851473808288574, + "learning_rate": 1.5432914190872757e-05, + "loss": 2.214, + "num_input_tokens_seen": 5030720, + "step": 495 + }, + { + "epoch": 3.770028275212064, + "grad_norm": 4.645096302032471, + "learning_rate": 1.4976736614834664e-05, + "loss": 2.1646, + "num_input_tokens_seen": 5081376, + "step": 500 + }, + { + "epoch": 3.8077285579641846, + "grad_norm": 5.5402512550354, + "learning_rate": 1.4524501653137787e-05, + "loss": 2.3151, + "num_input_tokens_seen": 5127888, + "step": 505 + }, + { + "epoch": 3.8454288407163055, + "grad_norm": 4.753649711608887, + "learning_rate": 1.4076387190766017e-05, + "loss": 2.2602, + "num_input_tokens_seen": 5178720, + "step": 510 + }, + { + "epoch": 3.883129123468426, + "grad_norm": 5.488243579864502, + "learning_rate": 1.363256949191972e-05, + "loss": 2.1839, + "num_input_tokens_seen": 5227120, + "step": 515 + }, + { + "epoch": 3.9208294062205464, + "grad_norm": 5.427800178527832, + "learning_rate": 1.3193223130682936e-05, + "loss": 2.2833, + "num_input_tokens_seen": 5275760, + "step": 520 + }, + { + "epoch": 3.9585296889726673, + "grad_norm": 4.901040077209473, + "learning_rate": 1.2758520922355226e-05, + "loss": 2.1802, + "num_input_tokens_seen": 5319632, + "step": 525 + }, + { + "epoch": 3.9962299717247878, + "grad_norm": 4.977085590362549, + "learning_rate": 1.2328633855475429e-05, + "loss": 2.2383, + "num_input_tokens_seen": 5369936, + "step": 530 + }, + { + "epoch": 4.033930254476909, + "grad_norm": 4.724318027496338, + "learning_rate": 1.1903731024563966e-05, + "loss": 2.007, + "num_input_tokens_seen": 5421440, + "step": 535 + }, + { + "epoch": 4.071630537229029, + "grad_norm": 5.148896217346191, + "learning_rate": 1.148397956361007e-05, + "loss": 2.0286, + "num_input_tokens_seen": 5476736, + "step": 540 + }, + { + "epoch": 4.10933081998115, + "grad_norm": 5.690558433532715, + "learning_rate": 1.106954458033026e-05, + "loss": 2.0398, + "num_input_tokens_seen": 5531328, + "step": 545 + }, + { + "epoch": 4.147031102733271, + "grad_norm": 5.595386505126953, + "learning_rate": 1.0660589091223855e-05, + "loss": 2.1157, + "num_input_tokens_seen": 5579216, + "step": 550 + }, + { + "epoch": 4.184731385485391, + "grad_norm": 6.112159252166748, + "learning_rate": 1.025727395745095e-05, + "loss": 2.094, + "num_input_tokens_seen": 5626208, + "step": 555 + }, + { + "epoch": 4.222431668237512, + "grad_norm": 5.86374568939209, + "learning_rate": 9.859757821558337e-06, + "loss": 2.0531, + "num_input_tokens_seen": 5679360, + "step": 560 + }, + { + "epoch": 4.260131950989632, + "grad_norm": 5.2934699058532715, + "learning_rate": 9.468197045077976e-06, + "loss": 1.9652, + "num_input_tokens_seen": 5724608, + "step": 565 + }, + { + "epoch": 4.297832233741753, + "grad_norm": 6.302525043487549, + "learning_rate": 9.082745647022797e-06, + "loss": 2.0592, + "num_input_tokens_seen": 5779904, + "step": 570 + }, + { + "epoch": 4.335532516493874, + "grad_norm": 6.2651143074035645, + "learning_rate": 8.703555243303835e-06, + "loss": 2.0418, + "num_input_tokens_seen": 5826880, + "step": 575 + }, + { + "epoch": 4.3732327992459945, + "grad_norm": 6.225465774536133, + "learning_rate": 8.330774987092712e-06, + "loss": 1.991, + "num_input_tokens_seen": 5875440, + "step": 580 + }, + { + "epoch": 4.410933081998115, + "grad_norm": 5.812168121337891, + "learning_rate": 7.96455151015272e-06, + "loss": 2.0726, + "num_input_tokens_seen": 5924960, + "step": 585 + }, + { + "epoch": 4.448633364750235, + "grad_norm": 5.528653621673584, + "learning_rate": 7.605028865161809e-06, + "loss": 2.069, + "num_input_tokens_seen": 5976416, + "step": 590 + }, + { + "epoch": 4.486333647502356, + "grad_norm": 5.838290691375732, + "learning_rate": 7.25234846904993e-06, + "loss": 2.052, + "num_input_tokens_seen": 6027088, + "step": 595 + }, + { + "epoch": 4.524033930254477, + "grad_norm": 6.014201641082764, + "learning_rate": 6.906649047373246e-06, + "loss": 2.0651, + "num_input_tokens_seen": 6080528, + "step": 600 + }, + { + "epoch": 4.561734213006598, + "grad_norm": 6.840231895446777, + "learning_rate": 6.568066579746901e-06, + "loss": 2.0546, + "num_input_tokens_seen": 6125904, + "step": 605 + }, + { + "epoch": 4.599434495758718, + "grad_norm": 6.350096702575684, + "learning_rate": 6.2367342463579475e-06, + "loss": 2.081, + "num_input_tokens_seen": 6173744, + "step": 610 + }, + { + "epoch": 4.6371347785108386, + "grad_norm": 6.259740352630615, + "learning_rate": 5.912782375579412e-06, + "loss": 2.0395, + "num_input_tokens_seen": 6222560, + "step": 615 + }, + { + "epoch": 4.674835061262959, + "grad_norm": 6.564173221588135, + "learning_rate": 5.596338392706077e-06, + "loss": 2.0659, + "num_input_tokens_seen": 6272544, + "step": 620 + }, + { + "epoch": 4.71253534401508, + "grad_norm": 5.375278949737549, + "learning_rate": 5.2875267698322325e-06, + "loss": 2.0247, + "num_input_tokens_seen": 6323024, + "step": 625 + }, + { + "epoch": 4.750235626767201, + "grad_norm": 5.922281265258789, + "learning_rate": 4.986468976890993e-06, + "loss": 2.0485, + "num_input_tokens_seen": 6374608, + "step": 630 + }, + { + "epoch": 4.787935909519321, + "grad_norm": 5.62613582611084, + "learning_rate": 4.693283433874565e-06, + "loss": 2.0561, + "num_input_tokens_seen": 6422208, + "step": 635 + }, + { + "epoch": 4.825636192271442, + "grad_norm": 6.259154796600342, + "learning_rate": 4.408085464254183e-06, + "loss": 2.1047, + "num_input_tokens_seen": 6468912, + "step": 640 + }, + { + "epoch": 4.863336475023563, + "grad_norm": 5.757895469665527, + "learning_rate": 4.130987249617993e-06, + "loss": 2.0481, + "num_input_tokens_seen": 6522848, + "step": 645 + }, + { + "epoch": 4.9010367577756835, + "grad_norm": 5.949391841888428, + "learning_rate": 3.8620977855448935e-06, + "loss": 2.0637, + "num_input_tokens_seen": 6578768, + "step": 650 + }, + { + "epoch": 4.938737040527804, + "grad_norm": 6.397491931915283, + "learning_rate": 3.601522838731461e-06, + "loss": 2.0429, + "num_input_tokens_seen": 6631936, + "step": 655 + }, + { + "epoch": 4.976437323279924, + "grad_norm": 6.2142157554626465, + "learning_rate": 3.3493649053890326e-06, + "loss": 2.1212, + "num_input_tokens_seen": 6682992, + "step": 660 + }, + { + "epoch": 5.014137606032045, + "grad_norm": 5.99893856048584, + "learning_rate": 3.1057231709272077e-06, + "loss": 2.0205, + "num_input_tokens_seen": 6735056, + "step": 665 + }, + { + "epoch": 5.051837888784166, + "grad_norm": 6.014187335968018, + "learning_rate": 2.8706934709395892e-06, + "loss": 1.9942, + "num_input_tokens_seen": 6784224, + "step": 670 + }, + { + "epoch": 5.089538171536287, + "grad_norm": 6.134748935699463, + "learning_rate": 2.6443682535072177e-06, + "loss": 1.868, + "num_input_tokens_seen": 6831040, + "step": 675 + }, + { + "epoch": 5.127238454288407, + "grad_norm": 5.91867733001709, + "learning_rate": 2.4268365428344736e-06, + "loss": 1.9132, + "num_input_tokens_seen": 6883552, + "step": 680 + }, + { + "epoch": 5.1649387370405275, + "grad_norm": 7.725922584533691, + "learning_rate": 2.21818390423168e-06, + "loss": 1.8698, + "num_input_tokens_seen": 6928272, + "step": 685 + }, + { + "epoch": 5.202639019792649, + "grad_norm": 5.97230863571167, + "learning_rate": 2.0184924104583613e-06, + "loss": 1.8974, + "num_input_tokens_seen": 6972496, + "step": 690 + }, + { + "epoch": 5.240339302544769, + "grad_norm": 6.879273414611816, + "learning_rate": 1.8278406094401623e-06, + "loss": 1.9096, + "num_input_tokens_seen": 7018496, + "step": 695 + }, + { + "epoch": 5.27803958529689, + "grad_norm": 6.802375793457031, + "learning_rate": 1.6463034933723337e-06, + "loss": 2.0098, + "num_input_tokens_seen": 7066400, + "step": 700 + }, + { + "epoch": 5.31573986804901, + "grad_norm": 6.246311187744141, + "learning_rate": 1.4739524692218314e-06, + "loss": 1.9554, + "num_input_tokens_seen": 7113744, + "step": 705 + }, + { + "epoch": 5.353440150801131, + "grad_norm": 6.855324745178223, + "learning_rate": 1.3108553306396265e-06, + "loss": 2.0233, + "num_input_tokens_seen": 7166848, + "step": 710 + }, + { + "epoch": 5.391140433553252, + "grad_norm": 7.124240398406982, + "learning_rate": 1.1570762312943295e-06, + "loss": 1.9629, + "num_input_tokens_seen": 7220048, + "step": 715 + }, + { + "epoch": 5.4288407163053725, + "grad_norm": 6.546064853668213, + "learning_rate": 1.0126756596375686e-06, + "loss": 1.9036, + "num_input_tokens_seen": 7268064, + "step": 720 + }, + { + "epoch": 5.466540999057493, + "grad_norm": 6.543118953704834, + "learning_rate": 8.777104151110826e-07, + "loss": 1.988, + "num_input_tokens_seen": 7326512, + "step": 725 + }, + { + "epoch": 5.504241281809613, + "grad_norm": 6.955906391143799, + "learning_rate": 7.522335858048707e-07, + "loss": 1.9844, + "num_input_tokens_seen": 7382288, + "step": 730 + }, + { + "epoch": 5.541941564561734, + "grad_norm": 6.836036682128906, + "learning_rate": 6.362945275751736e-07, + "loss": 1.9743, + "num_input_tokens_seen": 7430544, + "step": 735 + }, + { + "epoch": 5.579641847313855, + "grad_norm": 6.253538608551025, + "learning_rate": 5.299388446305343e-07, + "loss": 2.007, + "num_input_tokens_seen": 7479488, + "step": 740 + }, + { + "epoch": 5.617342130065976, + "grad_norm": 5.982280731201172, + "learning_rate": 4.3320837159353813e-07, + "loss": 1.9413, + "num_input_tokens_seen": 7533536, + "step": 745 + }, + { + "epoch": 5.655042412818096, + "grad_norm": 5.737644195556641, + "learning_rate": 3.4614115704533767e-07, + "loss": 1.902, + "num_input_tokens_seen": 7589200, + "step": 750 + }, + { + "epoch": 5.6927426955702165, + "grad_norm": 6.928066730499268, + "learning_rate": 2.687714485593462e-07, + "loss": 2.0091, + "num_input_tokens_seen": 7638928, + "step": 755 + }, + { + "epoch": 5.730442978322337, + "grad_norm": 6.864605903625488, + "learning_rate": 2.011296792301165e-07, + "loss": 2.0389, + "num_input_tokens_seen": 7693680, + "step": 760 + }, + { + "epoch": 5.768143261074458, + "grad_norm": 6.230181694030762, + "learning_rate": 1.4324245570256633e-07, + "loss": 2.0012, + "num_input_tokens_seen": 7743904, + "step": 765 + }, + { + "epoch": 5.805843543826579, + "grad_norm": 6.436938285827637, + "learning_rate": 9.513254770636137e-08, + "loss": 2.0127, + "num_input_tokens_seen": 7790992, + "step": 770 + }, + { + "epoch": 5.843543826578699, + "grad_norm": 6.2262349128723145, + "learning_rate": 5.681887909952388e-08, + "loss": 2.0237, + "num_input_tokens_seen": 7843600, + "step": 775 + }, + { + "epoch": 5.88124410933082, + "grad_norm": 6.8672027587890625, + "learning_rate": 2.831652042480093e-08, + "loss": 1.9273, + "num_input_tokens_seen": 7893968, + "step": 780 + }, + { + "epoch": 5.918944392082941, + "grad_norm": 6.41185188293457, + "learning_rate": 9.636682981720158e-09, + "loss": 1.9827, + "num_input_tokens_seen": 7945856, + "step": 785 + }, + { + "epoch": 5.956644674835061, + "grad_norm": 6.624245643615723, + "learning_rate": 7.867144166728846e-10, + "loss": 1.9642, + "num_input_tokens_seen": 7998560, + "step": 790 + } + ], + "logging_steps": 5, + "max_steps": 792, + "num_input_tokens_seen": 8017392, + "num_train_epochs": 6, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 3.6202835979167334e+17, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-792/training_args.bin b/checkpoint-792/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f8accff7ed19f472e4ab59934a52cd1b74989284 --- /dev/null +++ b/checkpoint-792/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0abbac12d56c1934fca1078792064a59e7f00bea9a38a70efb9ce7fe81d8d0a2 +size 5432 diff --git a/llamaboard_config.yaml b/llamaboard_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..76ea7c116b14c914b8078ac56631284d82e9849c --- /dev/null +++ b/llamaboard_config.yaml @@ -0,0 +1,66 @@ +top.booster: auto +top.checkpoint_path: [] +top.finetuning_type: lora +top.model_name: LLaMA3.1-8B +top.quantization_bit: none +top.quantization_method: bitsandbytes +top.rope_scaling: none +top.template: llama3 +train.additional_target: '' +train.badam_mode: layer +train.badam_switch_interval: 50 +train.badam_switch_mode: ascending +train.badam_update_ratio: 0.05 +train.batch_size: 2 +train.compute_type: bf16 +train.create_new_adapter: false +train.cutoff_len: 1024 +train.dataset: +- identity +train.dataset_dir: data +train.ds_offload: false +train.ds_stage: none +train.freeze_extra_modules: '' +train.freeze_trainable_layers: 2 +train.freeze_trainable_modules: all +train.galore_rank: 16 +train.galore_scale: 0.25 +train.galore_target: all +train.galore_update_interval: 200 +train.gradient_accumulation_steps: 8 +train.learning_rate: 5e-5 +train.logging_steps: 5 +train.lora_alpha: 16 +train.lora_dropout: 0 +train.lora_rank: 8 +train.lora_target: '' +train.loraplus_lr_ratio: 0 +train.lr_scheduler_type: cosine +train.mask_history: false +train.max_grad_norm: '3.0' +train.max_samples: '100000' +train.neat_packing: false +train.neftune_alpha: 0 +train.num_train_epochs: '6.0' +train.optim: adamw_torch +train.packing: false +train.ppo_score_norm: false +train.ppo_whiten_rewards: false +train.pref_beta: 0.1 +train.pref_ftx: 0 +train.pref_loss: sigmoid +train.report_to: false +train.resize_vocab: false +train.reward_model: [] +train.save_steps: 100 +train.shift_attn: false +train.train_on_prompt: false +train.training_stage: Supervised Fine-Tuning +train.use_badam: false +train.use_dora: false +train.use_galore: false +train.use_llama_pro: false +train.use_pissa: false +train.use_rslora: false +train.val_size: 0 +train.warmup_steps: 0 diff --git a/running_log.txt b/running_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..c377c029fa01440b9cc809103e0561c5e2e583cb --- /dev/null +++ b/running_log.txt @@ -0,0 +1,612 @@ +[INFO|configuration_utils.py:672] 2024-10-16 13:31:32,921 >> loading configuration file config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/config.json + +[INFO|configuration_utils.py:739] 2024-10-16 13:31:32,923 >> Model config LlamaConfig { + "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128040, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.0", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|tokenization_utils_base.py:2214] 2024-10-16 13:31:33,179 >> loading file tokenizer.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/tokenizer.json + +[INFO|tokenization_utils_base.py:2214] 2024-10-16 13:31:33,180 >> loading file tokenizer.model from cache at None + +[INFO|tokenization_utils_base.py:2214] 2024-10-16 13:31:33,180 >> loading file added_tokens.json from cache at None + +[INFO|tokenization_utils_base.py:2214] 2024-10-16 13:31:33,180 >> loading file special_tokens_map.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/special_tokens_map.json + +[INFO|tokenization_utils_base.py:2214] 2024-10-16 13:31:33,180 >> loading file tokenizer_config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/tokenizer_config.json + +[INFO|tokenization_utils_base.py:2478] 2024-10-16 13:31:33,694 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. + +[INFO|configuration_utils.py:672] 2024-10-16 13:31:35,153 >> loading configuration file config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/config.json + +[INFO|configuration_utils.py:739] 2024-10-16 13:31:35,154 >> Model config LlamaConfig { + "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128040, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.0", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|tokenization_utils_base.py:2214] 2024-10-16 13:31:35,830 >> loading file tokenizer.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/tokenizer.json + +[INFO|tokenization_utils_base.py:2214] 2024-10-16 13:31:35,831 >> loading file tokenizer.model from cache at None + +[INFO|tokenization_utils_base.py:2214] 2024-10-16 13:31:35,831 >> loading file added_tokens.json from cache at None + +[INFO|tokenization_utils_base.py:2214] 2024-10-16 13:31:35,831 >> loading file special_tokens_map.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/special_tokens_map.json + +[INFO|tokenization_utils_base.py:2214] 2024-10-16 13:31:35,831 >> loading file tokenizer_config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/tokenizer_config.json + +[INFO|tokenization_utils_base.py:2478] 2024-10-16 13:31:36,165 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. + +[INFO|configuration_utils.py:672] 2024-10-16 13:31:40,950 >> loading configuration file config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/config.json + +[INFO|configuration_utils.py:739] 2024-10-16 13:31:40,952 >> Model config LlamaConfig { + "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128040, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.0", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|modeling_utils.py:3726] 2024-10-16 13:31:41,010 >> loading weights file model.safetensors from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/model.safetensors.index.json + +[INFO|modeling_utils.py:1622] 2024-10-16 13:31:41,012 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16. + +[INFO|configuration_utils.py:1099] 2024-10-16 13:31:41,013 >> Generate config GenerationConfig { + "bos_token_id": 128000, + "eos_token_id": 128040 +} + + +[INFO|modeling_utils.py:4568] 2024-10-16 13:39:26,337 >> All model checkpoint weights were used when initializing LlamaForCausalLM. + + +[INFO|modeling_utils.py:4576] 2024-10-16 13:39:26,337 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at NousResearch/Hermes-3-Llama-3.1-8B. +If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training. + +[INFO|configuration_utils.py:1054] 2024-10-16 13:39:26,714 >> loading configuration file generation_config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/generation_config.json + +[INFO|configuration_utils.py:1099] 2024-10-16 13:39:26,714 >> Generate config GenerationConfig { + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128040, + "temperature": 0.6, + "top_p": 0.9 +} + + +[INFO|trainer.py:667] 2024-10-16 13:39:27,203 >> Using auto half precision backend + +[INFO|trainer.py:2243] 2024-10-16 13:39:28,204 >> ***** Running training ***** + +[INFO|trainer.py:2244] 2024-10-16 13:39:28,204 >> Num examples = 4,244 + +[INFO|trainer.py:2245] 2024-10-16 13:39:28,204 >> Num Epochs = 6 + +[INFO|trainer.py:2246] 2024-10-16 13:39:28,204 >> Instantaneous batch size per device = 2 + +[INFO|trainer.py:2249] 2024-10-16 13:39:28,204 >> Total train batch size (w. parallel, distributed & accumulation) = 32 + +[INFO|trainer.py:2250] 2024-10-16 13:39:28,204 >> Gradient Accumulation steps = 8 + +[INFO|trainer.py:2251] 2024-10-16 13:39:28,204 >> Total optimization steps = 792 + +[INFO|trainer.py:2252] 2024-10-16 13:39:28,211 >> Number of trainable parameters = 20,971,520 + +[INFO|trainer.py:3705] 2024-10-16 13:50:33,869 >> Saving model checkpoint to saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-100 + +[INFO|configuration_utils.py:672] 2024-10-16 13:50:34,457 >> loading configuration file config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/config.json + +[INFO|configuration_utils.py:739] 2024-10-16 13:50:34,458 >> Model config LlamaConfig { + "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128040, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.0", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|tokenization_utils_base.py:2649] 2024-10-16 13:50:34,614 >> tokenizer config file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-100/tokenizer_config.json + +[INFO|tokenization_utils_base.py:2658] 2024-10-16 13:50:34,615 >> Special tokens file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-100/special_tokens_map.json + +[INFO|trainer.py:3705] 2024-10-16 14:01:29,859 >> Saving model checkpoint to saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-200 + +[INFO|configuration_utils.py:672] 2024-10-16 14:01:30,499 >> loading configuration file config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/config.json + +[INFO|configuration_utils.py:739] 2024-10-16 14:01:30,500 >> Model config LlamaConfig { + "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128040, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.0", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|tokenization_utils_base.py:2649] 2024-10-16 14:01:30,637 >> tokenizer config file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-200/tokenizer_config.json + +[INFO|tokenization_utils_base.py:2658] 2024-10-16 14:01:30,637 >> Special tokens file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-200/special_tokens_map.json + +[INFO|trainer.py:3705] 2024-10-16 14:12:39,845 >> Saving model checkpoint to saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-300 + +[INFO|configuration_utils.py:672] 2024-10-16 14:12:41,404 >> loading configuration file config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/config.json + +[INFO|configuration_utils.py:739] 2024-10-16 14:12:41,405 >> Model config LlamaConfig { + "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128040, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.0", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|tokenization_utils_base.py:2649] 2024-10-16 14:12:41,563 >> tokenizer config file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-300/tokenizer_config.json + +[INFO|tokenization_utils_base.py:2658] 2024-10-16 14:12:41,563 >> Special tokens file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-300/special_tokens_map.json + +[INFO|trainer.py:3705] 2024-10-16 14:23:58,146 >> Saving model checkpoint to saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-400 + +[INFO|configuration_utils.py:672] 2024-10-16 14:23:58,714 >> loading configuration file config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/config.json + +[INFO|configuration_utils.py:739] 2024-10-16 14:23:58,715 >> Model config LlamaConfig { + "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128040, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.0", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|tokenization_utils_base.py:2649] 2024-10-16 14:23:58,874 >> tokenizer config file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-400/tokenizer_config.json + +[INFO|tokenization_utils_base.py:2658] 2024-10-16 14:23:58,875 >> Special tokens file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-400/special_tokens_map.json + +[INFO|trainer.py:3705] 2024-10-16 14:35:15,746 >> Saving model checkpoint to saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-500 + +[INFO|configuration_utils.py:672] 2024-10-16 14:35:16,768 >> loading configuration file config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/config.json + +[INFO|configuration_utils.py:739] 2024-10-16 14:35:16,769 >> Model config LlamaConfig { + "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128040, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.0", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|tokenization_utils_base.py:2649] 2024-10-16 14:35:16,929 >> tokenizer config file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-500/tokenizer_config.json + +[INFO|tokenization_utils_base.py:2658] 2024-10-16 14:35:16,929 >> Special tokens file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-500/special_tokens_map.json + +[INFO|trainer.py:3705] 2024-10-16 14:46:13,837 >> Saving model checkpoint to saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-600 + +[INFO|configuration_utils.py:672] 2024-10-16 14:46:14,835 >> loading configuration file config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/config.json + +[INFO|configuration_utils.py:739] 2024-10-16 14:46:14,836 >> Model config LlamaConfig { + "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128040, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.0", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|tokenization_utils_base.py:2649] 2024-10-16 14:46:14,994 >> tokenizer config file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-600/tokenizer_config.json + +[INFO|tokenization_utils_base.py:2658] 2024-10-16 14:46:14,995 >> Special tokens file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-600/special_tokens_map.json + +[INFO|trainer.py:3705] 2024-10-16 14:57:08,664 >> Saving model checkpoint to saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-700 + +[INFO|configuration_utils.py:672] 2024-10-16 14:57:09,697 >> loading configuration file config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/config.json + +[INFO|configuration_utils.py:739] 2024-10-16 14:57:09,698 >> Model config LlamaConfig { + "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128040, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.0", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|tokenization_utils_base.py:2649] 2024-10-16 14:57:09,860 >> tokenizer config file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-700/tokenizer_config.json + +[INFO|tokenization_utils_base.py:2658] 2024-10-16 14:57:09,860 >> Special tokens file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-700/special_tokens_map.json + +[INFO|trainer.py:3705] 2024-10-16 15:07:30,273 >> Saving model checkpoint to saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-792 + +[INFO|configuration_utils.py:672] 2024-10-16 15:07:30,871 >> loading configuration file config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/config.json + +[INFO|configuration_utils.py:739] 2024-10-16 15:07:30,873 >> Model config LlamaConfig { + "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128040, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.0", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|tokenization_utils_base.py:2649] 2024-10-16 15:07:31,029 >> tokenizer config file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-792/tokenizer_config.json + +[INFO|tokenization_utils_base.py:2658] 2024-10-16 15:07:31,029 >> Special tokens file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/checkpoint-792/special_tokens_map.json + +[INFO|trainer.py:2505] 2024-10-16 15:07:31,384 >> + +Training completed. Do not forget to share your model on huggingface.co/models =) + + + +[INFO|trainer.py:3705] 2024-10-16 15:07:31,386 >> Saving model checkpoint to saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59 + +[INFO|configuration_utils.py:672] 2024-10-16 15:07:33,366 >> loading configuration file config.json from cache at /home/.cache/huggingface/hub/models--NousResearch--Hermes-3-Llama-3.1-8B/snapshots/896ea440e5a9e6070e3d8a2774daf2b481ab425b/config.json + +[INFO|configuration_utils.py:739] 2024-10-16 15:07:33,367 >> Model config LlamaConfig { + "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128040, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.0", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|tokenization_utils_base.py:2649] 2024-10-16 15:07:33,476 >> tokenizer config file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/tokenizer_config.json + +[INFO|tokenization_utils_base.py:2658] 2024-10-16 15:07:33,477 >> Special tokens file saved in saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59/special_tokens_map.json + +[INFO|modelcard.py:449] 2024-10-16 15:07:33,708 >> Dropping the following result as it does not have all the necessary fields: +{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} + diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1ad7f173822ffa805bd5f390acc9c3390d414e67 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..9b7e7b9c905172fa0715865e515d9ed64402eb6b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05 +size 17209403 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..a22a366f4a4df58d908d0fa483648703588ce0b1 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128015": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128016": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128017": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128018": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128019": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128020": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128021": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128022": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128023": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128024": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128025": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128026": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128027": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128028": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128029": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128030": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128031": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128032": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128033": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128034": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128035": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128036": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128037": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128038": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128039": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128040": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|im_end|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000000000000000000000000000000000000..8ccc84add7ef6d69dfb324d1d2d516ff77282cd6 --- /dev/null +++ b/train_results.json @@ -0,0 +1,9 @@ +{ + "epoch": 5.971724787935909, + "num_input_tokens_seen": 8017392, + "total_flos": 3.6202835979167334e+17, + "train_loss": 2.4793783682163317, + "train_runtime": 5283.1732, + "train_samples_per_second": 4.82, + "train_steps_per_second": 0.15 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..d482fa362f7193d3d700402b23ae4c50187c3231 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,159 @@ +{"current_steps": 5, "total_steps": 792, "loss": 4.6192, "learning_rate": 4.9995083170283816e-05, "epoch": 0.03770028275212064, "percentage": 0.63, "elapsed_time": "0:00:33", "remaining_time": "1:27:03", "throughput": 1518.75, "total_tokens": 50400} +{"current_steps": 10, "total_steps": 792, "loss": 3.9149, "learning_rate": 4.998033461515242e-05, "epoch": 0.07540056550424128, "percentage": 1.26, "elapsed_time": "0:01:08", "remaining_time": "1:28:40", "throughput": 1528.78, "total_tokens": 104016} +{"current_steps": 15, "total_steps": 792, "loss": 3.6912, "learning_rate": 4.9955760135896534e-05, "epoch": 0.11310084825636192, "percentage": 1.89, "elapsed_time": "0:01:41", "remaining_time": "1:27:55", "throughput": 1527.62, "total_tokens": 155584} +{"current_steps": 20, "total_steps": 792, "loss": 3.5556, "learning_rate": 4.992136939879856e-05, "epoch": 0.15080113100848255, "percentage": 2.53, "elapsed_time": "0:02:13", "remaining_time": "1:25:35", "throughput": 1523.21, "total_tokens": 202672} +{"current_steps": 25, "total_steps": 792, "loss": 3.4256, "learning_rate": 4.9877175931330346e-05, "epoch": 0.1885014137606032, "percentage": 3.16, "elapsed_time": "0:02:48", "remaining_time": "1:26:04", "throughput": 1513.8, "total_tokens": 254800} +{"current_steps": 30, "total_steps": 792, "loss": 3.3128, "learning_rate": 4.982319711683221e-05, "epoch": 0.22620169651272384, "percentage": 3.79, "elapsed_time": "0:03:23", "remaining_time": "1:25:58", "throughput": 1508.32, "total_tokens": 306352} +{"current_steps": 35, "total_steps": 792, "loss": 3.2688, "learning_rate": 4.975945418767529e-05, "epoch": 0.2639019792648445, "percentage": 4.42, "elapsed_time": "0:03:54", "remaining_time": "1:24:34", "throughput": 1518.88, "total_tokens": 356352} +{"current_steps": 40, "total_steps": 792, "loss": 3.297, "learning_rate": 4.968597221690986e-05, "epoch": 0.3016022620169651, "percentage": 5.05, "elapsed_time": "0:04:27", "remaining_time": "1:23:45", "throughput": 1521.48, "total_tokens": 406672} +{"current_steps": 45, "total_steps": 792, "loss": 3.232, "learning_rate": 4.96027801084029e-05, "epoch": 0.3393025447690858, "percentage": 5.68, "elapsed_time": "0:04:59", "remaining_time": "1:22:43", "throughput": 1525.5, "total_tokens": 456160} +{"current_steps": 50, "total_steps": 792, "loss": 3.267, "learning_rate": 4.950991058546893e-05, "epoch": 0.3770028275212064, "percentage": 6.31, "elapsed_time": "0:05:34", "remaining_time": "1:22:37", "throughput": 1525.56, "total_tokens": 509680} +{"current_steps": 55, "total_steps": 792, "loss": 3.2148, "learning_rate": 4.940740017799833e-05, "epoch": 0.41470311027332707, "percentage": 6.94, "elapsed_time": "0:06:07", "remaining_time": "1:22:00", "throughput": 1524.82, "total_tokens": 559968} +{"current_steps": 60, "total_steps": 792, "loss": 3.1403, "learning_rate": 4.929528920808854e-05, "epoch": 0.4524033930254477, "percentage": 7.58, "elapsed_time": "0:06:39", "remaining_time": "1:21:09", "throughput": 1528.24, "total_tokens": 610000} +{"current_steps": 65, "total_steps": 792, "loss": 3.1515, "learning_rate": 4.917362177418342e-05, "epoch": 0.49010367577756836, "percentage": 8.21, "elapsed_time": "0:07:13", "remaining_time": "1:20:43", "throughput": 1527.04, "total_tokens": 661280} +{"current_steps": 70, "total_steps": 792, "loss": 3.1468, "learning_rate": 4.904244573372733e-05, "epoch": 0.527803958529689, "percentage": 8.84, "elapsed_time": "0:07:47", "remaining_time": "1:20:20", "throughput": 1526.19, "total_tokens": 713264} +{"current_steps": 75, "total_steps": 792, "loss": 3.196, "learning_rate": 4.8901812684340564e-05, "epoch": 0.5655042412818096, "percentage": 9.47, "elapsed_time": "0:08:18", "remaining_time": "1:19:27", "throughput": 1528.99, "total_tokens": 762576} +{"current_steps": 80, "total_steps": 792, "loss": 3.0593, "learning_rate": 4.8751777943523634e-05, "epoch": 0.6032045240339302, "percentage": 10.1, "elapsed_time": "0:08:52", "remaining_time": "1:18:57", "throughput": 1528.02, "total_tokens": 813392} +{"current_steps": 85, "total_steps": 792, "loss": 3.0676, "learning_rate": 4.8592400526898314e-05, "epoch": 0.6409048067860509, "percentage": 10.73, "elapsed_time": "0:09:24", "remaining_time": "1:18:17", "throughput": 1523.96, "total_tokens": 860608} +{"current_steps": 90, "total_steps": 792, "loss": 3.1061, "learning_rate": 4.842374312499405e-05, "epoch": 0.6786050895381716, "percentage": 11.36, "elapsed_time": "0:09:56", "remaining_time": "1:17:29", "throughput": 1525.19, "total_tokens": 909104} +{"current_steps": 95, "total_steps": 792, "loss": 2.9847, "learning_rate": 4.824587207858888e-05, "epoch": 0.7163053722902922, "percentage": 11.99, "elapsed_time": "0:10:30", "remaining_time": "1:17:06", "throughput": 1521.9, "total_tokens": 959600} +{"current_steps": 100, "total_steps": 792, "loss": 3.0289, "learning_rate": 4.805885735261454e-05, "epoch": 0.7540056550424128, "percentage": 12.63, "elapsed_time": "0:11:05", "remaining_time": "1:16:45", "throughput": 1522.94, "total_tokens": 1013648} +{"current_steps": 105, "total_steps": 792, "loss": 2.9474, "learning_rate": 4.786277250863599e-05, "epoch": 0.7917059377945335, "percentage": 13.26, "elapsed_time": "0:11:40", "remaining_time": "1:16:22", "throughput": 1520.69, "total_tokens": 1065120} +{"current_steps": 110, "total_steps": 792, "loss": 2.9713, "learning_rate": 4.765769467591625e-05, "epoch": 0.8294062205466541, "percentage": 13.89, "elapsed_time": "0:12:14", "remaining_time": "1:15:55", "throughput": 1523.69, "total_tokens": 1119424} +{"current_steps": 115, "total_steps": 792, "loss": 3.0012, "learning_rate": 4.744370452107789e-05, "epoch": 0.8671065032987747, "percentage": 14.52, "elapsed_time": "0:12:47", "remaining_time": "1:15:18", "throughput": 1524.28, "total_tokens": 1169888} +{"current_steps": 120, "total_steps": 792, "loss": 3.0399, "learning_rate": 4.722088621637309e-05, "epoch": 0.9048067860508954, "percentage": 15.15, "elapsed_time": "0:13:18", "remaining_time": "1:14:30", "throughput": 1526.84, "total_tokens": 1218944} +{"current_steps": 125, "total_steps": 792, "loss": 2.9156, "learning_rate": 4.698932740657479e-05, "epoch": 0.942507068803016, "percentage": 15.78, "elapsed_time": "0:13:53", "remaining_time": "1:14:07", "throughput": 1523.71, "total_tokens": 1269920} +{"current_steps": 130, "total_steps": 792, "loss": 3.0288, "learning_rate": 4.6749119174501975e-05, "epoch": 0.9802073515551367, "percentage": 16.41, "elapsed_time": "0:14:23", "remaining_time": "1:13:15", "throughput": 1524.09, "total_tokens": 1315536} +{"current_steps": 135, "total_steps": 792, "loss": 2.8911, "learning_rate": 4.6500356005192514e-05, "epoch": 1.0179076343072573, "percentage": 17.05, "elapsed_time": "0:14:54", "remaining_time": "1:12:31", "throughput": 1521.83, "total_tokens": 1360736} +{"current_steps": 140, "total_steps": 792, "loss": 2.9148, "learning_rate": 4.6243135748737864e-05, "epoch": 1.055607917059378, "percentage": 17.68, "elapsed_time": "0:15:24", "remaining_time": "1:11:47", "throughput": 1524.16, "total_tokens": 1409808} +{"current_steps": 145, "total_steps": 792, "loss": 2.868, "learning_rate": 4.597755958179406e-05, "epoch": 1.0933081998114986, "percentage": 18.31, "elapsed_time": "0:15:57", "remaining_time": "1:11:12", "throughput": 1525.54, "total_tokens": 1460864} +{"current_steps": 150, "total_steps": 792, "loss": 2.7477, "learning_rate": 4.570373196778427e-05, "epoch": 1.1310084825636193, "percentage": 18.94, "elapsed_time": "0:16:32", "remaining_time": "1:10:48", "throughput": 1523.68, "total_tokens": 1512640} +{"current_steps": 155, "total_steps": 792, "loss": 2.932, "learning_rate": 4.5421760615808474e-05, "epoch": 1.1687087653157398, "percentage": 19.57, "elapsed_time": "0:17:02", "remaining_time": "1:10:00", "throughput": 1522.5, "total_tokens": 1556048} +{"current_steps": 160, "total_steps": 792, "loss": 2.8219, "learning_rate": 4.513175643827647e-05, "epoch": 1.2064090480678604, "percentage": 20.2, "elapsed_time": "0:17:35", "remaining_time": "1:09:29", "throughput": 1522.58, "total_tokens": 1607232} +{"current_steps": 165, "total_steps": 792, "loss": 2.8453, "learning_rate": 4.4833833507280884e-05, "epoch": 1.244109330819981, "percentage": 20.83, "elapsed_time": "0:18:05", "remaining_time": "1:08:44", "throughput": 1523.48, "total_tokens": 1653520} +{"current_steps": 170, "total_steps": 792, "loss": 2.7362, "learning_rate": 4.4528109009727336e-05, "epoch": 1.2818096135721018, "percentage": 21.46, "elapsed_time": "0:18:37", "remaining_time": "1:08:10", "throughput": 1523.88, "total_tokens": 1703568} +{"current_steps": 175, "total_steps": 792, "loss": 2.9197, "learning_rate": 4.42147032012394e-05, "epoch": 1.3195098963242224, "percentage": 22.1, "elapsed_time": "0:19:09", "remaining_time": "1:07:32", "throughput": 1525.1, "total_tokens": 1752944} +{"current_steps": 180, "total_steps": 792, "loss": 2.8897, "learning_rate": 4.389373935885646e-05, "epoch": 1.3572101790763431, "percentage": 22.73, "elapsed_time": "0:19:44", "remaining_time": "1:07:07", "throughput": 1524.15, "total_tokens": 1805600} +{"current_steps": 185, "total_steps": 792, "loss": 2.7946, "learning_rate": 4.356534373254316e-05, "epoch": 1.3949104618284638, "percentage": 23.36, "elapsed_time": "0:20:22", "remaining_time": "1:06:51", "throughput": 1522.01, "total_tokens": 1860688} +{"current_steps": 190, "total_steps": 792, "loss": 2.8149, "learning_rate": 4.322964549552943e-05, "epoch": 1.4326107445805842, "percentage": 23.99, "elapsed_time": "0:20:56", "remaining_time": "1:06:20", "throughput": 1522.68, "total_tokens": 1913056} +{"current_steps": 195, "total_steps": 792, "loss": 2.7811, "learning_rate": 4.288677669350066e-05, "epoch": 1.4703110273327051, "percentage": 24.62, "elapsed_time": "0:21:29", "remaining_time": "1:05:46", "throughput": 1521.72, "total_tokens": 1961744} +{"current_steps": 200, "total_steps": 792, "loss": 2.8564, "learning_rate": 4.2536872192658036e-05, "epoch": 1.5080113100848256, "percentage": 25.25, "elapsed_time": "0:22:01", "remaining_time": "1:05:11", "throughput": 1521.86, "total_tokens": 2011248} +{"current_steps": 205, "total_steps": 792, "loss": 2.7966, "learning_rate": 4.218006962666934e-05, "epoch": 1.5457115928369463, "percentage": 25.88, "elapsed_time": "0:22:35", "remaining_time": "1:04:42", "throughput": 1519.75, "total_tokens": 2060640} +{"current_steps": 210, "total_steps": 792, "loss": 2.7674, "learning_rate": 4.181650934253132e-05, "epoch": 1.583411875589067, "percentage": 26.52, "elapsed_time": "0:23:09", "remaining_time": "1:04:10", "throughput": 1521.48, "total_tokens": 2113904} +{"current_steps": 215, "total_steps": 792, "loss": 2.7607, "learning_rate": 4.144633434536467e-05, "epoch": 1.6211121583411876, "percentage": 27.15, "elapsed_time": "0:23:41", "remaining_time": "1:03:35", "throughput": 1521.17, "total_tokens": 2162608} +{"current_steps": 220, "total_steps": 792, "loss": 2.8402, "learning_rate": 4.1069690242163484e-05, "epoch": 1.6588124410933083, "percentage": 27.78, "elapsed_time": "0:24:13", "remaining_time": "1:03:00", "throughput": 1521.12, "total_tokens": 2211616} +{"current_steps": 225, "total_steps": 792, "loss": 2.8019, "learning_rate": 4.06867251845213e-05, "epoch": 1.6965127238454287, "percentage": 28.41, "elapsed_time": "0:24:53", "remaining_time": "1:02:43", "throughput": 1519.42, "total_tokens": 2269440} +{"current_steps": 230, "total_steps": 792, "loss": 2.8311, "learning_rate": 4.0297589810356165e-05, "epoch": 1.7342130065975496, "percentage": 29.04, "elapsed_time": "0:25:29", "remaining_time": "1:02:16", "throughput": 1518.26, "total_tokens": 2321936} +{"current_steps": 235, "total_steps": 792, "loss": 2.7626, "learning_rate": 3.9902437184657784e-05, "epoch": 1.77191328934967, "percentage": 29.67, "elapsed_time": "0:26:05", "remaining_time": "1:01:51", "throughput": 1517.85, "total_tokens": 2376720} +{"current_steps": 240, "total_steps": 792, "loss": 2.8052, "learning_rate": 3.9501422739279956e-05, "epoch": 1.8096135721017907, "percentage": 30.3, "elapsed_time": "0:26:41", "remaining_time": "1:01:22", "throughput": 1517.76, "total_tokens": 2429952} +{"current_steps": 245, "total_steps": 792, "loss": 2.767, "learning_rate": 3.909470421180201e-05, "epoch": 1.8473138548539114, "percentage": 30.93, "elapsed_time": "0:27:14", "remaining_time": "1:00:49", "throughput": 1518.09, "total_tokens": 2481488} +{"current_steps": 250, "total_steps": 792, "loss": 2.7651, "learning_rate": 3.8682441583483314e-05, "epoch": 1.885014137606032, "percentage": 31.57, "elapsed_time": "0:27:45", "remaining_time": "1:00:10", "throughput": 1519.58, "total_tokens": 2530768} +{"current_steps": 255, "total_steps": 792, "loss": 2.8097, "learning_rate": 3.8264797016335205e-05, "epoch": 1.9227144203581528, "percentage": 32.2, "elapsed_time": "0:28:18", "remaining_time": "0:59:36", "throughput": 1520.77, "total_tokens": 2583088} +{"current_steps": 260, "total_steps": 792, "loss": 2.7269, "learning_rate": 3.7841934789335164e-05, "epoch": 1.9604147031102732, "percentage": 32.83, "elapsed_time": "0:28:51", "remaining_time": "0:59:02", "throughput": 1520.08, "total_tokens": 2631456} +{"current_steps": 265, "total_steps": 792, "loss": 2.8586, "learning_rate": 3.741402123380828e-05, "epoch": 1.998114985862394, "percentage": 33.46, "elapsed_time": "0:29:25", "remaining_time": "0:58:31", "throughput": 1520.65, "total_tokens": 2684848} +{"current_steps": 270, "total_steps": 792, "loss": 2.6131, "learning_rate": 3.6981224668001424e-05, "epoch": 2.0358152686145146, "percentage": 34.09, "elapsed_time": "0:29:58", "remaining_time": "0:57:56", "throughput": 1519.94, "total_tokens": 2733408} +{"current_steps": 275, "total_steps": 792, "loss": 2.4891, "learning_rate": 3.654371533087586e-05, "epoch": 2.0735155513666355, "percentage": 34.72, "elapsed_time": "0:30:34", "remaining_time": "0:57:29", "throughput": 1518.93, "total_tokens": 2786832} +{"current_steps": 280, "total_steps": 792, "loss": 2.5783, "learning_rate": 3.610166531514436e-05, "epoch": 2.111215834118756, "percentage": 35.35, "elapsed_time": "0:31:02", "remaining_time": "0:56:44", "throughput": 1519.0, "total_tokens": 2828464} +{"current_steps": 285, "total_steps": 792, "loss": 2.59, "learning_rate": 3.565524849957921e-05, "epoch": 2.1489161168708764, "percentage": 35.98, "elapsed_time": "0:31:35", "remaining_time": "0:56:12", "throughput": 1518.36, "total_tokens": 2878192} +{"current_steps": 290, "total_steps": 792, "loss": 2.5839, "learning_rate": 3.520464048061758e-05, "epoch": 2.1866163996229973, "percentage": 36.62, "elapsed_time": "0:32:06", "remaining_time": "0:55:35", "throughput": 1519.8, "total_tokens": 2928304} +{"current_steps": 295, "total_steps": 792, "loss": 2.567, "learning_rate": 3.47500185032913e-05, "epoch": 2.2243166823751177, "percentage": 37.25, "elapsed_time": "0:32:37", "remaining_time": "0:54:57", "throughput": 1521.62, "total_tokens": 2978144} +{"current_steps": 300, "total_steps": 792, "loss": 2.5694, "learning_rate": 3.4291561391508185e-05, "epoch": 2.2620169651272386, "percentage": 37.88, "elapsed_time": "0:33:11", "remaining_time": "0:54:26", "throughput": 1520.54, "total_tokens": 3028240} +{"current_steps": 305, "total_steps": 792, "loss": 2.4965, "learning_rate": 3.3829449477712324e-05, "epoch": 2.299717247879359, "percentage": 38.51, "elapsed_time": "0:33:50", "remaining_time": "0:54:02", "throughput": 1518.52, "total_tokens": 3083328} +{"current_steps": 310, "total_steps": 792, "loss": 2.599, "learning_rate": 3.336386453195088e-05, "epoch": 2.3374175306314795, "percentage": 39.14, "elapsed_time": "0:34:25", "remaining_time": "0:53:32", "throughput": 1518.53, "total_tokens": 3137072} +{"current_steps": 315, "total_steps": 792, "loss": 2.524, "learning_rate": 3.2894989690375626e-05, "epoch": 2.3751178133836004, "percentage": 39.77, "elapsed_time": "0:35:00", "remaining_time": "0:53:00", "throughput": 1519.54, "total_tokens": 3191136} +{"current_steps": 320, "total_steps": 792, "loss": 2.5338, "learning_rate": 3.2423009383206876e-05, "epoch": 2.412818096135721, "percentage": 40.4, "elapsed_time": "0:35:31", "remaining_time": "0:52:23", "throughput": 1520.03, "total_tokens": 3239952} +{"current_steps": 325, "total_steps": 792, "loss": 2.5096, "learning_rate": 3.194810926218861e-05, "epoch": 2.4505183788878417, "percentage": 41.04, "elapsed_time": "0:36:05", "remaining_time": "0:51:51", "throughput": 1519.97, "total_tokens": 3291104} +{"current_steps": 330, "total_steps": 792, "loss": 2.473, "learning_rate": 3.147047612756302e-05, "epoch": 2.488218661639962, "percentage": 41.67, "elapsed_time": "0:36:38", "remaining_time": "0:51:18", "throughput": 1519.35, "total_tokens": 3340592} +{"current_steps": 335, "total_steps": 792, "loss": 2.5778, "learning_rate": 3.099029785459328e-05, "epoch": 2.525918944392083, "percentage": 42.3, "elapsed_time": "0:37:10", "remaining_time": "0:50:43", "throughput": 1518.86, "total_tokens": 3388224} +{"current_steps": 340, "total_steps": 792, "loss": 2.5684, "learning_rate": 3.0507763319663517e-05, "epoch": 2.5636192271442035, "percentage": 42.93, "elapsed_time": "0:37:44", "remaining_time": "0:50:10", "throughput": 1519.11, "total_tokens": 3440512} +{"current_steps": 345, "total_steps": 792, "loss": 2.4923, "learning_rate": 3.002306232598497e-05, "epoch": 2.6013195098963244, "percentage": 43.56, "elapsed_time": "0:38:18", "remaining_time": "0:49:38", "throughput": 1519.13, "total_tokens": 3491744} +{"current_steps": 350, "total_steps": 792, "loss": 2.4633, "learning_rate": 2.9536385528937567e-05, "epoch": 2.639019792648445, "percentage": 44.19, "elapsed_time": "0:38:52", "remaining_time": "0:49:06", "throughput": 1518.45, "total_tokens": 3542368} +{"current_steps": 355, "total_steps": 792, "loss": 2.5703, "learning_rate": 2.9047924361076345e-05, "epoch": 2.6767200754005653, "percentage": 44.82, "elapsed_time": "0:39:28", "remaining_time": "0:48:35", "throughput": 1518.15, "total_tokens": 3595360} +{"current_steps": 360, "total_steps": 792, "loss": 2.4087, "learning_rate": 2.8557870956832132e-05, "epoch": 2.7144203581526862, "percentage": 45.45, "elapsed_time": "0:39:57", "remaining_time": "0:47:57", "throughput": 1518.58, "total_tokens": 3640912} +{"current_steps": 365, "total_steps": 792, "loss": 2.5007, "learning_rate": 2.8066418076936167e-05, "epoch": 2.7521206409048067, "percentage": 46.09, "elapsed_time": "0:40:31", "remaining_time": "0:47:24", "throughput": 1517.51, "total_tokens": 3690048} +{"current_steps": 370, "total_steps": 792, "loss": 2.5312, "learning_rate": 2.7573759032598366e-05, "epoch": 2.7898209236569276, "percentage": 46.72, "elapsed_time": "0:41:07", "remaining_time": "0:46:54", "throughput": 1517.71, "total_tokens": 3745104} +{"current_steps": 375, "total_steps": 792, "loss": 2.5333, "learning_rate": 2.7080087609469062e-05, "epoch": 2.827521206409048, "percentage": 47.35, "elapsed_time": "0:41:40", "remaining_time": "0:46:20", "throughput": 1517.41, "total_tokens": 3794160} +{"current_steps": 380, "total_steps": 792, "loss": 2.4185, "learning_rate": 2.6585597991414114e-05, "epoch": 2.8652214891611685, "percentage": 47.98, "elapsed_time": "0:42:14", "remaining_time": "0:45:48", "throughput": 1517.61, "total_tokens": 3846576} +{"current_steps": 385, "total_steps": 792, "loss": 2.4913, "learning_rate": 2.6090484684133404e-05, "epoch": 2.9029217719132894, "percentage": 48.61, "elapsed_time": "0:42:43", "remaining_time": "0:45:09", "throughput": 1518.25, "total_tokens": 3891744} +{"current_steps": 390, "total_steps": 792, "loss": 2.5319, "learning_rate": 2.5594942438652688e-05, "epoch": 2.9406220546654103, "percentage": 49.24, "elapsed_time": "0:43:20", "remaining_time": "0:44:40", "throughput": 1519.01, "total_tokens": 3949568} +{"current_steps": 395, "total_steps": 792, "loss": 2.6441, "learning_rate": 2.509916617471903e-05, "epoch": 2.9783223374175307, "percentage": 49.87, "elapsed_time": "0:43:56", "remaining_time": "0:44:09", "throughput": 1518.07, "total_tokens": 4002384} +{"current_steps": 400, "total_steps": 792, "loss": 2.3576, "learning_rate": 2.46033509041298e-05, "epoch": 3.016022620169651, "percentage": 50.51, "elapsed_time": "0:44:29", "remaining_time": "0:43:36", "throughput": 1517.94, "total_tokens": 4052688} +{"current_steps": 405, "total_steps": 792, "loss": 2.3032, "learning_rate": 2.410769165402549e-05, "epoch": 3.053722902921772, "percentage": 51.14, "elapsed_time": "0:45:06", "remaining_time": "0:43:06", "throughput": 1517.37, "total_tokens": 4107392} +{"current_steps": 410, "total_steps": 792, "loss": 2.2542, "learning_rate": 2.3612383390176503e-05, "epoch": 3.0914231856738925, "percentage": 51.77, "elapsed_time": "0:45:39", "remaining_time": "0:42:32", "throughput": 1517.78, "total_tokens": 4157984} +{"current_steps": 415, "total_steps": 792, "loss": 2.2882, "learning_rate": 2.3117620940294048e-05, "epoch": 3.1291234684260134, "percentage": 52.4, "elapsed_time": "0:46:16", "remaining_time": "0:42:02", "throughput": 1517.57, "total_tokens": 4213280} +{"current_steps": 420, "total_steps": 792, "loss": 2.2314, "learning_rate": 2.2623598917395438e-05, "epoch": 3.166823751178134, "percentage": 53.03, "elapsed_time": "0:46:50", "remaining_time": "0:41:29", "throughput": 1517.89, "total_tokens": 4265792} +{"current_steps": 425, "total_steps": 792, "loss": 2.2679, "learning_rate": 2.213051164325366e-05, "epoch": 3.2045240339302543, "percentage": 53.66, "elapsed_time": "0:47:19", "remaining_time": "0:40:52", "throughput": 1518.1, "total_tokens": 4310832} +{"current_steps": 430, "total_steps": 792, "loss": 2.2521, "learning_rate": 2.1638553071961708e-05, "epoch": 3.242224316682375, "percentage": 54.29, "elapsed_time": "0:47:48", "remaining_time": "0:40:14", "throughput": 1517.79, "total_tokens": 4353488} +{"current_steps": 435, "total_steps": 792, "loss": 2.2071, "learning_rate": 2.1147916713641367e-05, "epoch": 3.2799245994344957, "percentage": 54.92, "elapsed_time": "0:48:21", "remaining_time": "0:39:41", "throughput": 1517.71, "total_tokens": 4404384} +{"current_steps": 440, "total_steps": 792, "loss": 2.2525, "learning_rate": 2.0658795558326743e-05, "epoch": 3.3176248821866166, "percentage": 55.56, "elapsed_time": "0:48:53", "remaining_time": "0:39:07", "throughput": 1517.82, "total_tokens": 4453232} +{"current_steps": 445, "total_steps": 792, "loss": 2.2431, "learning_rate": 2.017138200005236e-05, "epoch": 3.355325164938737, "percentage": 56.19, "elapsed_time": "0:49:29", "remaining_time": "0:38:35", "throughput": 1518.13, "total_tokens": 4508640} +{"current_steps": 450, "total_steps": 792, "loss": 2.3357, "learning_rate": 1.9685867761175584e-05, "epoch": 3.3930254476908575, "percentage": 56.82, "elapsed_time": "0:50:03", "remaining_time": "0:38:02", "throughput": 1518.04, "total_tokens": 4559360} +{"current_steps": 455, "total_steps": 792, "loss": 2.2875, "learning_rate": 1.9202443816963425e-05, "epoch": 3.4307257304429783, "percentage": 57.45, "elapsed_time": "0:50:37", "remaining_time": "0:37:29", "throughput": 1517.67, "total_tokens": 4609584} +{"current_steps": 460, "total_steps": 792, "loss": 2.2136, "learning_rate": 1.872130032047302e-05, "epoch": 3.468426013195099, "percentage": 58.08, "elapsed_time": "0:51:13", "remaining_time": "0:36:58", "throughput": 1518.07, "total_tokens": 4665472} +{"current_steps": 465, "total_steps": 792, "loss": 2.294, "learning_rate": 1.824262652775568e-05, "epoch": 3.5061262959472197, "percentage": 58.71, "elapsed_time": "0:51:46", "remaining_time": "0:36:24", "throughput": 1518.95, "total_tokens": 4719360} +{"current_steps": 470, "total_steps": 792, "loss": 2.2146, "learning_rate": 1.7766610723413684e-05, "epoch": 3.54382657869934, "percentage": 59.34, "elapsed_time": "0:52:23", "remaining_time": "0:35:53", "throughput": 1518.13, "total_tokens": 4771504} +{"current_steps": 475, "total_steps": 792, "loss": 2.3166, "learning_rate": 1.7293440146539196e-05, "epoch": 3.581526861451461, "percentage": 59.97, "elapsed_time": "0:52:55", "remaining_time": "0:35:18", "throughput": 1518.21, "total_tokens": 4820432} +{"current_steps": 480, "total_steps": 792, "loss": 2.2775, "learning_rate": 1.682330091706446e-05, "epoch": 3.6192271442035815, "percentage": 60.61, "elapsed_time": "0:53:33", "remaining_time": "0:34:48", "throughput": 1517.93, "total_tokens": 4877984} +{"current_steps": 485, "total_steps": 792, "loss": 2.2442, "learning_rate": 1.6356377962552238e-05, "epoch": 3.6569274269557024, "percentage": 61.24, "elapsed_time": "0:54:06", "remaining_time": "0:34:15", "throughput": 1517.77, "total_tokens": 4927712} +{"current_steps": 490, "total_steps": 792, "loss": 2.2499, "learning_rate": 1.589285494545514e-05, "epoch": 3.694627709707823, "percentage": 61.87, "elapsed_time": "0:54:41", "remaining_time": "0:33:42", "throughput": 1517.37, "total_tokens": 4979520} +{"current_steps": 495, "total_steps": 792, "loss": 2.214, "learning_rate": 1.5432914190872757e-05, "epoch": 3.7323279924599433, "percentage": 62.5, "elapsed_time": "0:55:14", "remaining_time": "0:33:08", "throughput": 1517.77, "total_tokens": 5030720} +{"current_steps": 500, "total_steps": 792, "loss": 2.1646, "learning_rate": 1.4976736614834664e-05, "epoch": 3.770028275212064, "percentage": 63.13, "elapsed_time": "0:55:47", "remaining_time": "0:32:34", "throughput": 1517.98, "total_tokens": 5081376} +{"current_steps": 505, "total_steps": 792, "loss": 2.3151, "learning_rate": 1.4524501653137787e-05, "epoch": 3.8077285579641846, "percentage": 63.76, "elapsed_time": "0:56:19", "remaining_time": "0:32:00", "throughput": 1517.49, "total_tokens": 5127888} +{"current_steps": 510, "total_steps": 792, "loss": 2.2602, "learning_rate": 1.4076387190766017e-05, "epoch": 3.8454288407163055, "percentage": 64.39, "elapsed_time": "0:56:52", "remaining_time": "0:31:26", "throughput": 1517.54, "total_tokens": 5178720} +{"current_steps": 515, "total_steps": 792, "loss": 2.1839, "learning_rate": 1.363256949191972e-05, "epoch": 3.883129123468426, "percentage": 65.03, "elapsed_time": "0:57:25", "remaining_time": "0:30:53", "throughput": 1516.96, "total_tokens": 5227120} +{"current_steps": 520, "total_steps": 792, "loss": 2.2833, "learning_rate": 1.3193223130682936e-05, "epoch": 3.9208294062205464, "percentage": 65.66, "elapsed_time": "0:57:57", "remaining_time": "0:30:19", "throughput": 1516.97, "total_tokens": 5275760} +{"current_steps": 525, "total_steps": 792, "loss": 2.1802, "learning_rate": 1.2758520922355226e-05, "epoch": 3.9585296889726673, "percentage": 66.29, "elapsed_time": "0:58:26", "remaining_time": "0:29:43", "throughput": 1517.09, "total_tokens": 5319632} +{"current_steps": 530, "total_steps": 792, "loss": 2.2383, "learning_rate": 1.2328633855475429e-05, "epoch": 3.9962299717247878, "percentage": 66.92, "elapsed_time": "0:59:00", "remaining_time": "0:29:10", "throughput": 1516.88, "total_tokens": 5369936} +{"current_steps": 535, "total_steps": 792, "loss": 2.007, "learning_rate": 1.1903731024563966e-05, "epoch": 4.033930254476909, "percentage": 67.55, "elapsed_time": "0:59:32", "remaining_time": "0:28:36", "throughput": 1517.52, "total_tokens": 5421440} +{"current_steps": 540, "total_steps": 792, "loss": 2.0286, "learning_rate": 1.148397956361007e-05, "epoch": 4.071630537229029, "percentage": 68.18, "elapsed_time": "1:00:08", "remaining_time": "0:28:04", "throughput": 1517.66, "total_tokens": 5476736} +{"current_steps": 545, "total_steps": 792, "loss": 2.0398, "learning_rate": 1.106954458033026e-05, "epoch": 4.10933081998115, "percentage": 68.81, "elapsed_time": "1:00:45", "remaining_time": "0:27:32", "throughput": 1517.35, "total_tokens": 5531328} +{"current_steps": 550, "total_steps": 792, "loss": 2.1157, "learning_rate": 1.0660589091223855e-05, "epoch": 4.147031102733271, "percentage": 69.44, "elapsed_time": "1:01:16", "remaining_time": "0:26:57", "throughput": 1517.68, "total_tokens": 5579216} +{"current_steps": 555, "total_steps": 792, "loss": 2.094, "learning_rate": 1.025727395745095e-05, "epoch": 4.184731385485391, "percentage": 70.08, "elapsed_time": "1:01:46", "remaining_time": "0:26:22", "throughput": 1517.83, "total_tokens": 5626208} +{"current_steps": 560, "total_steps": 792, "loss": 2.0531, "learning_rate": 9.859757821558337e-06, "epoch": 4.222431668237512, "percentage": 70.71, "elapsed_time": "1:02:21", "remaining_time": "0:25:50", "throughput": 1517.83, "total_tokens": 5679360} +{"current_steps": 565, "total_steps": 792, "loss": 1.9652, "learning_rate": 9.468197045077976e-06, "epoch": 4.260131950989632, "percentage": 71.34, "elapsed_time": "1:02:51", "remaining_time": "0:25:15", "throughput": 1517.87, "total_tokens": 5724608} +{"current_steps": 570, "total_steps": 792, "loss": 2.0592, "learning_rate": 9.082745647022797e-06, "epoch": 4.297832233741753, "percentage": 71.97, "elapsed_time": "1:03:28", "remaining_time": "0:24:43", "throughput": 1517.79, "total_tokens": 5779904} +{"current_steps": 575, "total_steps": 792, "loss": 2.0418, "learning_rate": 8.703555243303835e-06, "epoch": 4.335532516493874, "percentage": 72.6, "elapsed_time": "1:03:59", "remaining_time": "0:24:08", "throughput": 1517.79, "total_tokens": 5826880} +{"current_steps": 580, "total_steps": 792, "loss": 1.991, "learning_rate": 8.330774987092712e-06, "epoch": 4.3732327992459945, "percentage": 73.23, "elapsed_time": "1:04:30", "remaining_time": "0:23:34", "throughput": 1517.97, "total_tokens": 5875440} +{"current_steps": 585, "total_steps": 792, "loss": 2.0726, "learning_rate": 7.96455151015272e-06, "epoch": 4.410933081998115, "percentage": 73.86, "elapsed_time": "1:05:03", "remaining_time": "0:23:01", "throughput": 1517.74, "total_tokens": 5924960} +{"current_steps": 590, "total_steps": 792, "loss": 2.069, "learning_rate": 7.605028865161809e-06, "epoch": 4.448633364750235, "percentage": 74.49, "elapsed_time": "1:05:38", "remaining_time": "0:22:28", "throughput": 1517.53, "total_tokens": 5976416} +{"current_steps": 595, "total_steps": 792, "loss": 2.052, "learning_rate": 7.25234846904993e-06, "epoch": 4.486333647502356, "percentage": 75.13, "elapsed_time": "1:06:11", "remaining_time": "0:21:54", "throughput": 1517.75, "total_tokens": 6027088} +{"current_steps": 600, "total_steps": 792, "loss": 2.0651, "learning_rate": 6.906649047373246e-06, "epoch": 4.524033930254477, "percentage": 75.76, "elapsed_time": "1:06:45", "remaining_time": "0:21:21", "throughput": 1518.02, "total_tokens": 6080528} +{"current_steps": 605, "total_steps": 792, "loss": 2.0546, "learning_rate": 6.568066579746901e-06, "epoch": 4.561734213006598, "percentage": 76.39, "elapsed_time": "1:07:16", "remaining_time": "0:20:47", "throughput": 1517.81, "total_tokens": 6125904} +{"current_steps": 610, "total_steps": 792, "loss": 2.081, "learning_rate": 6.2367342463579475e-06, "epoch": 4.599434495758718, "percentage": 77.02, "elapsed_time": "1:07:49", "remaining_time": "0:20:14", "throughput": 1517.22, "total_tokens": 6173744} +{"current_steps": 615, "total_steps": 792, "loss": 2.0395, "learning_rate": 5.912782375579412e-06, "epoch": 4.6371347785108386, "percentage": 77.65, "elapsed_time": "1:08:22", "remaining_time": "0:19:40", "throughput": 1516.71, "total_tokens": 6222560} +{"current_steps": 620, "total_steps": 792, "loss": 2.0659, "learning_rate": 5.596338392706077e-06, "epoch": 4.674835061262959, "percentage": 78.28, "elapsed_time": "1:08:54", "remaining_time": "0:19:07", "throughput": 1517.06, "total_tokens": 6272544} +{"current_steps": 625, "total_steps": 792, "loss": 2.0247, "learning_rate": 5.2875267698322325e-06, "epoch": 4.71253534401508, "percentage": 78.91, "elapsed_time": "1:09:27", "remaining_time": "0:18:33", "throughput": 1517.29, "total_tokens": 6323024} +{"current_steps": 630, "total_steps": 792, "loss": 2.0485, "learning_rate": 4.986468976890993e-06, "epoch": 4.750235626767201, "percentage": 79.55, "elapsed_time": "1:10:00", "remaining_time": "0:18:00", "throughput": 1517.64, "total_tokens": 6374608} +{"current_steps": 635, "total_steps": 792, "loss": 2.0561, "learning_rate": 4.693283433874565e-06, "epoch": 4.787935909519321, "percentage": 80.18, "elapsed_time": "1:10:30", "remaining_time": "0:17:26", "throughput": 1517.9, "total_tokens": 6422208} +{"current_steps": 640, "total_steps": 792, "loss": 2.1047, "learning_rate": 4.408085464254183e-06, "epoch": 4.825636192271442, "percentage": 80.81, "elapsed_time": "1:11:01", "remaining_time": "0:16:52", "throughput": 1517.88, "total_tokens": 6468912} +{"current_steps": 645, "total_steps": 792, "loss": 2.0481, "learning_rate": 4.130987249617993e-06, "epoch": 4.863336475023563, "percentage": 81.44, "elapsed_time": "1:11:36", "remaining_time": "0:16:19", "throughput": 1518.15, "total_tokens": 6522848} +{"current_steps": 650, "total_steps": 792, "loss": 2.0637, "learning_rate": 3.8620977855448935e-06, "epoch": 4.9010367577756835, "percentage": 82.07, "elapsed_time": "1:12:12", "remaining_time": "0:15:46", "throughput": 1518.35, "total_tokens": 6578768} +{"current_steps": 655, "total_steps": 792, "loss": 2.0429, "learning_rate": 3.601522838731461e-06, "epoch": 4.938737040527804, "percentage": 82.7, "elapsed_time": "1:12:47", "remaining_time": "0:15:13", "throughput": 1518.35, "total_tokens": 6631936} +{"current_steps": 660, "total_steps": 792, "loss": 2.1212, "learning_rate": 3.3493649053890326e-06, "epoch": 4.976437323279924, "percentage": 83.33, "elapsed_time": "1:13:22", "remaining_time": "0:14:40", "throughput": 1517.95, "total_tokens": 6682992} +{"current_steps": 665, "total_steps": 792, "loss": 2.0205, "learning_rate": 3.1057231709272077e-06, "epoch": 5.014137606032045, "percentage": 83.96, "elapsed_time": "1:13:59", "remaining_time": "0:14:07", "throughput": 1517.21, "total_tokens": 6735056} +{"current_steps": 670, "total_steps": 792, "loss": 1.9942, "learning_rate": 2.8706934709395892e-06, "epoch": 5.051837888784166, "percentage": 84.6, "elapsed_time": "1:14:31", "remaining_time": "0:13:34", "throughput": 1517.06, "total_tokens": 6784224} +{"current_steps": 675, "total_steps": 792, "loss": 1.868, "learning_rate": 2.6443682535072177e-06, "epoch": 5.089538171536287, "percentage": 85.23, "elapsed_time": "1:15:02", "remaining_time": "0:13:00", "throughput": 1517.24, "total_tokens": 6831040} +{"current_steps": 680, "total_steps": 792, "loss": 1.9132, "learning_rate": 2.4268365428344736e-06, "epoch": 5.127238454288407, "percentage": 85.86, "elapsed_time": "1:15:37", "remaining_time": "0:12:27", "throughput": 1516.96, "total_tokens": 6883552} +{"current_steps": 685, "total_steps": 792, "loss": 1.8698, "learning_rate": 2.21818390423168e-06, "epoch": 5.1649387370405275, "percentage": 86.49, "elapsed_time": "1:16:08", "remaining_time": "0:11:53", "throughput": 1516.56, "total_tokens": 6928272} +{"current_steps": 690, "total_steps": 792, "loss": 1.8974, "learning_rate": 2.0184924104583613e-06, "epoch": 5.202639019792649, "percentage": 87.12, "elapsed_time": "1:16:38", "remaining_time": "0:11:19", "throughput": 1516.26, "total_tokens": 6972496} +{"current_steps": 695, "total_steps": 792, "loss": 1.9096, "learning_rate": 1.8278406094401623e-06, "epoch": 5.240339302544769, "percentage": 87.75, "elapsed_time": "1:17:08", "remaining_time": "0:10:46", "throughput": 1516.21, "total_tokens": 7018496} +{"current_steps": 700, "total_steps": 792, "loss": 2.0098, "learning_rate": 1.6463034933723337e-06, "epoch": 5.27803958529689, "percentage": 88.38, "elapsed_time": "1:17:40", "remaining_time": "0:10:12", "throughput": 1516.27, "total_tokens": 7066400} +{"current_steps": 705, "total_steps": 792, "loss": 1.9554, "learning_rate": 1.4739524692218314e-06, "epoch": 5.31573986804901, "percentage": 89.02, "elapsed_time": "1:18:13", "remaining_time": "0:09:39", "throughput": 1515.51, "total_tokens": 7113744} +{"current_steps": 710, "total_steps": 792, "loss": 2.0233, "learning_rate": 1.3108553306396265e-06, "epoch": 5.353440150801131, "percentage": 89.65, "elapsed_time": "1:18:48", "remaining_time": "0:09:06", "throughput": 1515.74, "total_tokens": 7166848} +{"current_steps": 715, "total_steps": 792, "loss": 1.9629, "learning_rate": 1.1570762312943295e-06, "epoch": 5.391140433553252, "percentage": 90.28, "elapsed_time": "1:19:23", "remaining_time": "0:08:32", "throughput": 1515.8, "total_tokens": 7220048} +{"current_steps": 720, "total_steps": 792, "loss": 1.9036, "learning_rate": 1.0126756596375686e-06, "epoch": 5.4288407163053725, "percentage": 90.91, "elapsed_time": "1:19:55", "remaining_time": "0:07:59", "throughput": 1515.7, "total_tokens": 7268064} +{"current_steps": 725, "total_steps": 792, "loss": 1.988, "learning_rate": 8.777104151110826e-07, "epoch": 5.466540999057493, "percentage": 91.54, "elapsed_time": "1:20:33", "remaining_time": "0:07:26", "throughput": 1515.83, "total_tokens": 7326512} +{"current_steps": 730, "total_steps": 792, "loss": 1.9844, "learning_rate": 7.522335858048707e-07, "epoch": 5.504241281809613, "percentage": 92.17, "elapsed_time": "1:21:10", "remaining_time": "0:06:53", "throughput": 1515.78, "total_tokens": 7382288} +{"current_steps": 735, "total_steps": 792, "loss": 1.9743, "learning_rate": 6.362945275751736e-07, "epoch": 5.541941564561734, "percentage": 92.8, "elapsed_time": "1:21:40", "remaining_time": "0:06:20", "throughput": 1516.23, "total_tokens": 7430544} +{"current_steps": 740, "total_steps": 792, "loss": 2.007, "learning_rate": 5.299388446305343e-07, "epoch": 5.579641847313855, "percentage": 93.43, "elapsed_time": "1:22:12", "remaining_time": "0:05:46", "throughput": 1516.44, "total_tokens": 7479488} +{"current_steps": 745, "total_steps": 792, "loss": 1.9413, "learning_rate": 4.3320837159353813e-07, "epoch": 5.617342130065976, "percentage": 94.07, "elapsed_time": "1:22:48", "remaining_time": "0:05:13", "throughput": 1516.32, "total_tokens": 7533536} +{"current_steps": 750, "total_steps": 792, "loss": 1.902, "learning_rate": 3.4614115704533767e-07, "epoch": 5.655042412818096, "percentage": 94.7, "elapsed_time": "1:23:24", "remaining_time": "0:04:40", "throughput": 1516.39, "total_tokens": 7589200} +{"current_steps": 755, "total_steps": 792, "loss": 2.0091, "learning_rate": 2.687714485593462e-07, "epoch": 5.6927426955702165, "percentage": 95.33, "elapsed_time": "1:23:56", "remaining_time": "0:04:06", "throughput": 1516.65, "total_tokens": 7638928} +{"current_steps": 760, "total_steps": 792, "loss": 2.0389, "learning_rate": 2.011296792301165e-07, "epoch": 5.730442978322337, "percentage": 95.96, "elapsed_time": "1:24:33", "remaining_time": "0:03:33", "throughput": 1516.57, "total_tokens": 7693680} +{"current_steps": 765, "total_steps": 792, "loss": 2.0012, "learning_rate": 1.4324245570256633e-07, "epoch": 5.768143261074458, "percentage": 96.59, "elapsed_time": "1:25:05", "remaining_time": "0:03:00", "throughput": 1516.87, "total_tokens": 7743904} +{"current_steps": 770, "total_steps": 792, "loss": 2.0127, "learning_rate": 9.513254770636137e-08, "epoch": 5.805843543826579, "percentage": 97.22, "elapsed_time": "1:25:36", "remaining_time": "0:02:26", "throughput": 1516.8, "total_tokens": 7790992} +{"current_steps": 775, "total_steps": 792, "loss": 2.0237, "learning_rate": 5.681887909952388e-08, "epoch": 5.843543826578699, "percentage": 97.85, "elapsed_time": "1:26:11", "remaining_time": "0:01:53", "throughput": 1516.79, "total_tokens": 7843600} +{"current_steps": 780, "total_steps": 792, "loss": 1.9273, "learning_rate": 2.831652042480093e-08, "epoch": 5.88124410933082, "percentage": 98.48, "elapsed_time": "1:26:43", "remaining_time": "0:01:20", "throughput": 1517.02, "total_tokens": 7893968} +{"current_steps": 785, "total_steps": 792, "loss": 1.9827, "learning_rate": 9.636682981720158e-09, "epoch": 5.918944392082941, "percentage": 99.12, "elapsed_time": "1:27:16", "remaining_time": "0:00:46", "throughput": 1517.49, "total_tokens": 7945856} +{"current_steps": 790, "total_steps": 792, "loss": 1.9642, "learning_rate": 7.867144166728846e-10, "epoch": 5.956644674835061, "percentage": 99.75, "elapsed_time": "1:27:50", "remaining_time": "0:00:13", "throughput": 1517.51, "total_tokens": 7998560} +{"current_steps": 792, "total_steps": 792, "epoch": 5.971724787935909, "percentage": 100.0, "elapsed_time": "1:28:03", "remaining_time": "0:00:00", "throughput": 1517.55, "total_tokens": 8017392} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..025e1b9b3027a78c3d6fc28e232b2b49684b83a7 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,1307 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 5.971724787935909, + "eval_steps": 500, + "global_step": 792, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.03770028275212064, + "grad_norm": 3.988708734512329, + "learning_rate": 4.9995083170283816e-05, + "loss": 4.6192, + "num_input_tokens_seen": 50400, + "step": 5 + }, + { + "epoch": 0.07540056550424128, + "grad_norm": 2.142688512802124, + "learning_rate": 4.998033461515242e-05, + "loss": 3.9149, + "num_input_tokens_seen": 104016, + "step": 10 + }, + { + "epoch": 0.11310084825636192, + "grad_norm": 1.5928359031677246, + "learning_rate": 4.9955760135896534e-05, + "loss": 3.6912, + "num_input_tokens_seen": 155584, + "step": 15 + }, + { + "epoch": 0.15080113100848255, + "grad_norm": 1.5493167638778687, + "learning_rate": 4.992136939879856e-05, + "loss": 3.5556, + "num_input_tokens_seen": 202672, + "step": 20 + }, + { + "epoch": 0.1885014137606032, + "grad_norm": 1.7764347791671753, + "learning_rate": 4.9877175931330346e-05, + "loss": 3.4256, + "num_input_tokens_seen": 254800, + "step": 25 + }, + { + "epoch": 0.22620169651272384, + "grad_norm": 1.2482728958129883, + "learning_rate": 4.982319711683221e-05, + "loss": 3.3128, + "num_input_tokens_seen": 306352, + "step": 30 + }, + { + "epoch": 0.2639019792648445, + "grad_norm": 1.2829065322875977, + "learning_rate": 4.975945418767529e-05, + "loss": 3.2688, + "num_input_tokens_seen": 356352, + "step": 35 + }, + { + "epoch": 0.3016022620169651, + "grad_norm": 1.513293743133545, + "learning_rate": 4.968597221690986e-05, + "loss": 3.297, + "num_input_tokens_seen": 406672, + "step": 40 + }, + { + "epoch": 0.3393025447690858, + "grad_norm": 1.883090853691101, + "learning_rate": 4.96027801084029e-05, + "loss": 3.232, + "num_input_tokens_seen": 456160, + "step": 45 + }, + { + "epoch": 0.3770028275212064, + "grad_norm": 1.402272343635559, + "learning_rate": 4.950991058546893e-05, + "loss": 3.267, + "num_input_tokens_seen": 509680, + "step": 50 + }, + { + "epoch": 0.41470311027332707, + "grad_norm": 1.5488755702972412, + "learning_rate": 4.940740017799833e-05, + "loss": 3.2148, + "num_input_tokens_seen": 559968, + "step": 55 + }, + { + "epoch": 0.4524033930254477, + "grad_norm": 1.507287859916687, + "learning_rate": 4.929528920808854e-05, + "loss": 3.1403, + "num_input_tokens_seen": 610000, + "step": 60 + }, + { + "epoch": 0.49010367577756836, + "grad_norm": 1.9119170904159546, + "learning_rate": 4.917362177418342e-05, + "loss": 3.1515, + "num_input_tokens_seen": 661280, + "step": 65 + }, + { + "epoch": 0.527803958529689, + "grad_norm": 1.7253235578536987, + "learning_rate": 4.904244573372733e-05, + "loss": 3.1468, + "num_input_tokens_seen": 713264, + "step": 70 + }, + { + "epoch": 0.5655042412818096, + "grad_norm": 1.7201606035232544, + "learning_rate": 4.8901812684340564e-05, + "loss": 3.196, + "num_input_tokens_seen": 762576, + "step": 75 + }, + { + "epoch": 0.6032045240339302, + "grad_norm": 1.6135213375091553, + "learning_rate": 4.8751777943523634e-05, + "loss": 3.0593, + "num_input_tokens_seen": 813392, + "step": 80 + }, + { + "epoch": 0.6409048067860509, + "grad_norm": 1.7381868362426758, + "learning_rate": 4.8592400526898314e-05, + "loss": 3.0676, + "num_input_tokens_seen": 860608, + "step": 85 + }, + { + "epoch": 0.6786050895381716, + "grad_norm": 1.6142843961715698, + "learning_rate": 4.842374312499405e-05, + "loss": 3.1061, + "num_input_tokens_seen": 909104, + "step": 90 + }, + { + "epoch": 0.7163053722902922, + "grad_norm": 2.0389633178710938, + "learning_rate": 4.824587207858888e-05, + "loss": 2.9847, + "num_input_tokens_seen": 959600, + "step": 95 + }, + { + "epoch": 0.7540056550424128, + "grad_norm": 1.923561692237854, + "learning_rate": 4.805885735261454e-05, + "loss": 3.0289, + "num_input_tokens_seen": 1013648, + "step": 100 + }, + { + "epoch": 0.7917059377945335, + "grad_norm": 2.0325896739959717, + "learning_rate": 4.786277250863599e-05, + "loss": 2.9474, + "num_input_tokens_seen": 1065120, + "step": 105 + }, + { + "epoch": 0.8294062205466541, + "grad_norm": 1.6685590744018555, + "learning_rate": 4.765769467591625e-05, + "loss": 2.9713, + "num_input_tokens_seen": 1119424, + "step": 110 + }, + { + "epoch": 0.8671065032987747, + "grad_norm": 2.0325937271118164, + "learning_rate": 4.744370452107789e-05, + "loss": 3.0012, + "num_input_tokens_seen": 1169888, + "step": 115 + }, + { + "epoch": 0.9048067860508954, + "grad_norm": 1.7548010349273682, + "learning_rate": 4.722088621637309e-05, + "loss": 3.0399, + "num_input_tokens_seen": 1218944, + "step": 120 + }, + { + "epoch": 0.942507068803016, + "grad_norm": 1.6709191799163818, + "learning_rate": 4.698932740657479e-05, + "loss": 2.9156, + "num_input_tokens_seen": 1269920, + "step": 125 + }, + { + "epoch": 0.9802073515551367, + "grad_norm": 1.8369653224945068, + "learning_rate": 4.6749119174501975e-05, + "loss": 3.0288, + "num_input_tokens_seen": 1315536, + "step": 130 + }, + { + "epoch": 1.0179076343072573, + "grad_norm": 1.800703525543213, + "learning_rate": 4.6500356005192514e-05, + "loss": 2.8911, + "num_input_tokens_seen": 1360736, + "step": 135 + }, + { + "epoch": 1.055607917059378, + "grad_norm": 1.7134617567062378, + "learning_rate": 4.6243135748737864e-05, + "loss": 2.9148, + "num_input_tokens_seen": 1409808, + "step": 140 + }, + { + "epoch": 1.0933081998114986, + "grad_norm": 1.9385241270065308, + "learning_rate": 4.597755958179406e-05, + "loss": 2.868, + "num_input_tokens_seen": 1460864, + "step": 145 + }, + { + "epoch": 1.1310084825636193, + "grad_norm": 2.1658332347869873, + "learning_rate": 4.570373196778427e-05, + "loss": 2.7477, + "num_input_tokens_seen": 1512640, + "step": 150 + }, + { + "epoch": 1.1687087653157398, + "grad_norm": 2.239896774291992, + "learning_rate": 4.5421760615808474e-05, + "loss": 2.932, + "num_input_tokens_seen": 1556048, + "step": 155 + }, + { + "epoch": 1.2064090480678604, + "grad_norm": 2.0555717945098877, + "learning_rate": 4.513175643827647e-05, + "loss": 2.8219, + "num_input_tokens_seen": 1607232, + "step": 160 + }, + { + "epoch": 1.244109330819981, + "grad_norm": 2.0288779735565186, + "learning_rate": 4.4833833507280884e-05, + "loss": 2.8453, + "num_input_tokens_seen": 1653520, + "step": 165 + }, + { + "epoch": 1.2818096135721018, + "grad_norm": 1.9268651008605957, + "learning_rate": 4.4528109009727336e-05, + "loss": 2.7362, + "num_input_tokens_seen": 1703568, + "step": 170 + }, + { + "epoch": 1.3195098963242224, + "grad_norm": 2.413874387741089, + "learning_rate": 4.42147032012394e-05, + "loss": 2.9197, + "num_input_tokens_seen": 1752944, + "step": 175 + }, + { + "epoch": 1.3572101790763431, + "grad_norm": 2.2018630504608154, + "learning_rate": 4.389373935885646e-05, + "loss": 2.8897, + "num_input_tokens_seen": 1805600, + "step": 180 + }, + { + "epoch": 1.3949104618284638, + "grad_norm": 2.1807219982147217, + "learning_rate": 4.356534373254316e-05, + "loss": 2.7946, + "num_input_tokens_seen": 1860688, + "step": 185 + }, + { + "epoch": 1.4326107445805842, + "grad_norm": 2.2928526401519775, + "learning_rate": 4.322964549552943e-05, + "loss": 2.8149, + "num_input_tokens_seen": 1913056, + "step": 190 + }, + { + "epoch": 1.4703110273327051, + "grad_norm": 2.204533576965332, + "learning_rate": 4.288677669350066e-05, + "loss": 2.7811, + "num_input_tokens_seen": 1961744, + "step": 195 + }, + { + "epoch": 1.5080113100848256, + "grad_norm": 2.925762414932251, + "learning_rate": 4.2536872192658036e-05, + "loss": 2.8564, + "num_input_tokens_seen": 2011248, + "step": 200 + }, + { + "epoch": 1.5457115928369463, + "grad_norm": 2.398651599884033, + "learning_rate": 4.218006962666934e-05, + "loss": 2.7966, + "num_input_tokens_seen": 2060640, + "step": 205 + }, + { + "epoch": 1.583411875589067, + "grad_norm": 2.452263355255127, + "learning_rate": 4.181650934253132e-05, + "loss": 2.7674, + "num_input_tokens_seen": 2113904, + "step": 210 + }, + { + "epoch": 1.6211121583411876, + "grad_norm": 2.5911788940429688, + "learning_rate": 4.144633434536467e-05, + "loss": 2.7607, + "num_input_tokens_seen": 2162608, + "step": 215 + }, + { + "epoch": 1.6588124410933083, + "grad_norm": 2.648517608642578, + "learning_rate": 4.1069690242163484e-05, + "loss": 2.8402, + "num_input_tokens_seen": 2211616, + "step": 220 + }, + { + "epoch": 1.6965127238454287, + "grad_norm": 2.6860735416412354, + "learning_rate": 4.06867251845213e-05, + "loss": 2.8019, + "num_input_tokens_seen": 2269440, + "step": 225 + }, + { + "epoch": 1.7342130065975496, + "grad_norm": 2.5891222953796387, + "learning_rate": 4.0297589810356165e-05, + "loss": 2.8311, + "num_input_tokens_seen": 2321936, + "step": 230 + }, + { + "epoch": 1.77191328934967, + "grad_norm": 2.695114850997925, + "learning_rate": 3.9902437184657784e-05, + "loss": 2.7626, + "num_input_tokens_seen": 2376720, + "step": 235 + }, + { + "epoch": 1.8096135721017907, + "grad_norm": 2.588127374649048, + "learning_rate": 3.9501422739279956e-05, + "loss": 2.8052, + "num_input_tokens_seen": 2429952, + "step": 240 + }, + { + "epoch": 1.8473138548539114, + "grad_norm": 2.1829710006713867, + "learning_rate": 3.909470421180201e-05, + "loss": 2.767, + "num_input_tokens_seen": 2481488, + "step": 245 + }, + { + "epoch": 1.885014137606032, + "grad_norm": 2.606924295425415, + "learning_rate": 3.8682441583483314e-05, + "loss": 2.7651, + "num_input_tokens_seen": 2530768, + "step": 250 + }, + { + "epoch": 1.9227144203581528, + "grad_norm": 2.3635494709014893, + "learning_rate": 3.8264797016335205e-05, + "loss": 2.8097, + "num_input_tokens_seen": 2583088, + "step": 255 + }, + { + "epoch": 1.9604147031102732, + "grad_norm": 2.560624361038208, + "learning_rate": 3.7841934789335164e-05, + "loss": 2.7269, + "num_input_tokens_seen": 2631456, + "step": 260 + }, + { + "epoch": 1.998114985862394, + "grad_norm": 2.7099437713623047, + "learning_rate": 3.741402123380828e-05, + "loss": 2.8586, + "num_input_tokens_seen": 2684848, + "step": 265 + }, + { + "epoch": 2.0358152686145146, + "grad_norm": 2.552143096923828, + "learning_rate": 3.6981224668001424e-05, + "loss": 2.6131, + "num_input_tokens_seen": 2733408, + "step": 270 + }, + { + "epoch": 2.0735155513666355, + "grad_norm": 2.9233176708221436, + "learning_rate": 3.654371533087586e-05, + "loss": 2.4891, + "num_input_tokens_seen": 2786832, + "step": 275 + }, + { + "epoch": 2.111215834118756, + "grad_norm": 2.7649636268615723, + "learning_rate": 3.610166531514436e-05, + "loss": 2.5783, + "num_input_tokens_seen": 2828464, + "step": 280 + }, + { + "epoch": 2.1489161168708764, + "grad_norm": 3.076122522354126, + "learning_rate": 3.565524849957921e-05, + "loss": 2.59, + "num_input_tokens_seen": 2878192, + "step": 285 + }, + { + "epoch": 2.1866163996229973, + "grad_norm": 3.242678642272949, + "learning_rate": 3.520464048061758e-05, + "loss": 2.5839, + "num_input_tokens_seen": 2928304, + "step": 290 + }, + { + "epoch": 2.2243166823751177, + "grad_norm": 3.139089584350586, + "learning_rate": 3.47500185032913e-05, + "loss": 2.567, + "num_input_tokens_seen": 2978144, + "step": 295 + }, + { + "epoch": 2.2620169651272386, + "grad_norm": 3.1967153549194336, + "learning_rate": 3.4291561391508185e-05, + "loss": 2.5694, + "num_input_tokens_seen": 3028240, + "step": 300 + }, + { + "epoch": 2.299717247879359, + "grad_norm": 3.1987555027008057, + "learning_rate": 3.3829449477712324e-05, + "loss": 2.4965, + "num_input_tokens_seen": 3083328, + "step": 305 + }, + { + "epoch": 2.3374175306314795, + "grad_norm": 3.4724180698394775, + "learning_rate": 3.336386453195088e-05, + "loss": 2.599, + "num_input_tokens_seen": 3137072, + "step": 310 + }, + { + "epoch": 2.3751178133836004, + "grad_norm": 3.381075143814087, + "learning_rate": 3.2894989690375626e-05, + "loss": 2.524, + "num_input_tokens_seen": 3191136, + "step": 315 + }, + { + "epoch": 2.412818096135721, + "grad_norm": 3.650747537612915, + "learning_rate": 3.2423009383206876e-05, + "loss": 2.5338, + "num_input_tokens_seen": 3239952, + "step": 320 + }, + { + "epoch": 2.4505183788878417, + "grad_norm": 3.3886971473693848, + "learning_rate": 3.194810926218861e-05, + "loss": 2.5096, + "num_input_tokens_seen": 3291104, + "step": 325 + }, + { + "epoch": 2.488218661639962, + "grad_norm": 3.415850877761841, + "learning_rate": 3.147047612756302e-05, + "loss": 2.473, + "num_input_tokens_seen": 3340592, + "step": 330 + }, + { + "epoch": 2.525918944392083, + "grad_norm": 3.513828754425049, + "learning_rate": 3.099029785459328e-05, + "loss": 2.5778, + "num_input_tokens_seen": 3388224, + "step": 335 + }, + { + "epoch": 2.5636192271442035, + "grad_norm": 3.49721360206604, + "learning_rate": 3.0507763319663517e-05, + "loss": 2.5684, + "num_input_tokens_seen": 3440512, + "step": 340 + }, + { + "epoch": 2.6013195098963244, + "grad_norm": 3.5137672424316406, + "learning_rate": 3.002306232598497e-05, + "loss": 2.4923, + "num_input_tokens_seen": 3491744, + "step": 345 + }, + { + "epoch": 2.639019792648445, + "grad_norm": 3.7216403484344482, + "learning_rate": 2.9536385528937567e-05, + "loss": 2.4633, + "num_input_tokens_seen": 3542368, + "step": 350 + }, + { + "epoch": 2.6767200754005653, + "grad_norm": 3.48529052734375, + "learning_rate": 2.9047924361076345e-05, + "loss": 2.5703, + "num_input_tokens_seen": 3595360, + "step": 355 + }, + { + "epoch": 2.7144203581526862, + "grad_norm": 3.4676520824432373, + "learning_rate": 2.8557870956832132e-05, + "loss": 2.4087, + "num_input_tokens_seen": 3640912, + "step": 360 + }, + { + "epoch": 2.7521206409048067, + "grad_norm": 4.316717147827148, + "learning_rate": 2.8066418076936167e-05, + "loss": 2.5007, + "num_input_tokens_seen": 3690048, + "step": 365 + }, + { + "epoch": 2.7898209236569276, + "grad_norm": 4.2354736328125, + "learning_rate": 2.7573759032598366e-05, + "loss": 2.5312, + "num_input_tokens_seen": 3745104, + "step": 370 + }, + { + "epoch": 2.827521206409048, + "grad_norm": 3.457280397415161, + "learning_rate": 2.7080087609469062e-05, + "loss": 2.5333, + "num_input_tokens_seen": 3794160, + "step": 375 + }, + { + "epoch": 2.8652214891611685, + "grad_norm": 3.417656183242798, + "learning_rate": 2.6585597991414114e-05, + "loss": 2.4185, + "num_input_tokens_seen": 3846576, + "step": 380 + }, + { + "epoch": 2.9029217719132894, + "grad_norm": 3.7148749828338623, + "learning_rate": 2.6090484684133404e-05, + "loss": 2.4913, + "num_input_tokens_seen": 3891744, + "step": 385 + }, + { + "epoch": 2.9406220546654103, + "grad_norm": 3.562427520751953, + "learning_rate": 2.5594942438652688e-05, + "loss": 2.5319, + "num_input_tokens_seen": 3949568, + "step": 390 + }, + { + "epoch": 2.9783223374175307, + "grad_norm": 4.2560505867004395, + "learning_rate": 2.509916617471903e-05, + "loss": 2.6441, + "num_input_tokens_seen": 4002384, + "step": 395 + }, + { + "epoch": 3.016022620169651, + "grad_norm": 3.349701166152954, + "learning_rate": 2.46033509041298e-05, + "loss": 2.3576, + "num_input_tokens_seen": 4052688, + "step": 400 + }, + { + "epoch": 3.053722902921772, + "grad_norm": 3.660886287689209, + "learning_rate": 2.410769165402549e-05, + "loss": 2.3032, + "num_input_tokens_seen": 4107392, + "step": 405 + }, + { + "epoch": 3.0914231856738925, + "grad_norm": 4.248249530792236, + "learning_rate": 2.3612383390176503e-05, + "loss": 2.2542, + "num_input_tokens_seen": 4157984, + "step": 410 + }, + { + "epoch": 3.1291234684260134, + "grad_norm": 4.340310096740723, + "learning_rate": 2.3117620940294048e-05, + "loss": 2.2882, + "num_input_tokens_seen": 4213280, + "step": 415 + }, + { + "epoch": 3.166823751178134, + "grad_norm": 4.137709617614746, + "learning_rate": 2.2623598917395438e-05, + "loss": 2.2314, + "num_input_tokens_seen": 4265792, + "step": 420 + }, + { + "epoch": 3.2045240339302543, + "grad_norm": 4.506406307220459, + "learning_rate": 2.213051164325366e-05, + "loss": 2.2679, + "num_input_tokens_seen": 4310832, + "step": 425 + }, + { + "epoch": 3.242224316682375, + "grad_norm": 4.44052791595459, + "learning_rate": 2.1638553071961708e-05, + "loss": 2.2521, + "num_input_tokens_seen": 4353488, + "step": 430 + }, + { + "epoch": 3.2799245994344957, + "grad_norm": 4.674520015716553, + "learning_rate": 2.1147916713641367e-05, + "loss": 2.2071, + "num_input_tokens_seen": 4404384, + "step": 435 + }, + { + "epoch": 3.3176248821866166, + "grad_norm": 4.979199409484863, + "learning_rate": 2.0658795558326743e-05, + "loss": 2.2525, + "num_input_tokens_seen": 4453232, + "step": 440 + }, + { + "epoch": 3.355325164938737, + "grad_norm": 4.564790725708008, + "learning_rate": 2.017138200005236e-05, + "loss": 2.2431, + "num_input_tokens_seen": 4508640, + "step": 445 + }, + { + "epoch": 3.3930254476908575, + "grad_norm": 4.888641834259033, + "learning_rate": 1.9685867761175584e-05, + "loss": 2.3357, + "num_input_tokens_seen": 4559360, + "step": 450 + }, + { + "epoch": 3.4307257304429783, + "grad_norm": 4.425845623016357, + "learning_rate": 1.9202443816963425e-05, + "loss": 2.2875, + "num_input_tokens_seen": 4609584, + "step": 455 + }, + { + "epoch": 3.468426013195099, + "grad_norm": 5.38726282119751, + "learning_rate": 1.872130032047302e-05, + "loss": 2.2136, + "num_input_tokens_seen": 4665472, + "step": 460 + }, + { + "epoch": 3.5061262959472197, + "grad_norm": 4.473924160003662, + "learning_rate": 1.824262652775568e-05, + "loss": 2.294, + "num_input_tokens_seen": 4719360, + "step": 465 + }, + { + "epoch": 3.54382657869934, + "grad_norm": 5.171916484832764, + "learning_rate": 1.7766610723413684e-05, + "loss": 2.2146, + "num_input_tokens_seen": 4771504, + "step": 470 + }, + { + "epoch": 3.581526861451461, + "grad_norm": 5.492386817932129, + "learning_rate": 1.7293440146539196e-05, + "loss": 2.3166, + "num_input_tokens_seen": 4820432, + "step": 475 + }, + { + "epoch": 3.6192271442035815, + "grad_norm": 4.300539493560791, + "learning_rate": 1.682330091706446e-05, + "loss": 2.2775, + "num_input_tokens_seen": 4877984, + "step": 480 + }, + { + "epoch": 3.6569274269557024, + "grad_norm": 5.470084190368652, + "learning_rate": 1.6356377962552238e-05, + "loss": 2.2442, + "num_input_tokens_seen": 4927712, + "step": 485 + }, + { + "epoch": 3.694627709707823, + "grad_norm": 5.457830429077148, + "learning_rate": 1.589285494545514e-05, + "loss": 2.2499, + "num_input_tokens_seen": 4979520, + "step": 490 + }, + { + "epoch": 3.7323279924599433, + "grad_norm": 4.851473808288574, + "learning_rate": 1.5432914190872757e-05, + "loss": 2.214, + "num_input_tokens_seen": 5030720, + "step": 495 + }, + { + "epoch": 3.770028275212064, + "grad_norm": 4.645096302032471, + "learning_rate": 1.4976736614834664e-05, + "loss": 2.1646, + "num_input_tokens_seen": 5081376, + "step": 500 + }, + { + "epoch": 3.8077285579641846, + "grad_norm": 5.5402512550354, + "learning_rate": 1.4524501653137787e-05, + "loss": 2.3151, + "num_input_tokens_seen": 5127888, + "step": 505 + }, + { + "epoch": 3.8454288407163055, + "grad_norm": 4.753649711608887, + "learning_rate": 1.4076387190766017e-05, + "loss": 2.2602, + "num_input_tokens_seen": 5178720, + "step": 510 + }, + { + "epoch": 3.883129123468426, + "grad_norm": 5.488243579864502, + "learning_rate": 1.363256949191972e-05, + "loss": 2.1839, + "num_input_tokens_seen": 5227120, + "step": 515 + }, + { + "epoch": 3.9208294062205464, + "grad_norm": 5.427800178527832, + "learning_rate": 1.3193223130682936e-05, + "loss": 2.2833, + "num_input_tokens_seen": 5275760, + "step": 520 + }, + { + "epoch": 3.9585296889726673, + "grad_norm": 4.901040077209473, + "learning_rate": 1.2758520922355226e-05, + "loss": 2.1802, + "num_input_tokens_seen": 5319632, + "step": 525 + }, + { + "epoch": 3.9962299717247878, + "grad_norm": 4.977085590362549, + "learning_rate": 1.2328633855475429e-05, + "loss": 2.2383, + "num_input_tokens_seen": 5369936, + "step": 530 + }, + { + "epoch": 4.033930254476909, + "grad_norm": 4.724318027496338, + "learning_rate": 1.1903731024563966e-05, + "loss": 2.007, + "num_input_tokens_seen": 5421440, + "step": 535 + }, + { + "epoch": 4.071630537229029, + "grad_norm": 5.148896217346191, + "learning_rate": 1.148397956361007e-05, + "loss": 2.0286, + "num_input_tokens_seen": 5476736, + "step": 540 + }, + { + "epoch": 4.10933081998115, + "grad_norm": 5.690558433532715, + "learning_rate": 1.106954458033026e-05, + "loss": 2.0398, + "num_input_tokens_seen": 5531328, + "step": 545 + }, + { + "epoch": 4.147031102733271, + "grad_norm": 5.595386505126953, + "learning_rate": 1.0660589091223855e-05, + "loss": 2.1157, + "num_input_tokens_seen": 5579216, + "step": 550 + }, + { + "epoch": 4.184731385485391, + "grad_norm": 6.112159252166748, + "learning_rate": 1.025727395745095e-05, + "loss": 2.094, + "num_input_tokens_seen": 5626208, + "step": 555 + }, + { + "epoch": 4.222431668237512, + "grad_norm": 5.86374568939209, + "learning_rate": 9.859757821558337e-06, + "loss": 2.0531, + "num_input_tokens_seen": 5679360, + "step": 560 + }, + { + "epoch": 4.260131950989632, + "grad_norm": 5.2934699058532715, + "learning_rate": 9.468197045077976e-06, + "loss": 1.9652, + "num_input_tokens_seen": 5724608, + "step": 565 + }, + { + "epoch": 4.297832233741753, + "grad_norm": 6.302525043487549, + "learning_rate": 9.082745647022797e-06, + "loss": 2.0592, + "num_input_tokens_seen": 5779904, + "step": 570 + }, + { + "epoch": 4.335532516493874, + "grad_norm": 6.2651143074035645, + "learning_rate": 8.703555243303835e-06, + "loss": 2.0418, + "num_input_tokens_seen": 5826880, + "step": 575 + }, + { + "epoch": 4.3732327992459945, + "grad_norm": 6.225465774536133, + "learning_rate": 8.330774987092712e-06, + "loss": 1.991, + "num_input_tokens_seen": 5875440, + "step": 580 + }, + { + "epoch": 4.410933081998115, + "grad_norm": 5.812168121337891, + "learning_rate": 7.96455151015272e-06, + "loss": 2.0726, + "num_input_tokens_seen": 5924960, + "step": 585 + }, + { + "epoch": 4.448633364750235, + "grad_norm": 5.528653621673584, + "learning_rate": 7.605028865161809e-06, + "loss": 2.069, + "num_input_tokens_seen": 5976416, + "step": 590 + }, + { + "epoch": 4.486333647502356, + "grad_norm": 5.838290691375732, + "learning_rate": 7.25234846904993e-06, + "loss": 2.052, + "num_input_tokens_seen": 6027088, + "step": 595 + }, + { + "epoch": 4.524033930254477, + "grad_norm": 6.014201641082764, + "learning_rate": 6.906649047373246e-06, + "loss": 2.0651, + "num_input_tokens_seen": 6080528, + "step": 600 + }, + { + "epoch": 4.561734213006598, + "grad_norm": 6.840231895446777, + "learning_rate": 6.568066579746901e-06, + "loss": 2.0546, + "num_input_tokens_seen": 6125904, + "step": 605 + }, + { + "epoch": 4.599434495758718, + "grad_norm": 6.350096702575684, + "learning_rate": 6.2367342463579475e-06, + "loss": 2.081, + "num_input_tokens_seen": 6173744, + "step": 610 + }, + { + "epoch": 4.6371347785108386, + "grad_norm": 6.259740352630615, + "learning_rate": 5.912782375579412e-06, + "loss": 2.0395, + "num_input_tokens_seen": 6222560, + "step": 615 + }, + { + "epoch": 4.674835061262959, + "grad_norm": 6.564173221588135, + "learning_rate": 5.596338392706077e-06, + "loss": 2.0659, + "num_input_tokens_seen": 6272544, + "step": 620 + }, + { + "epoch": 4.71253534401508, + "grad_norm": 5.375278949737549, + "learning_rate": 5.2875267698322325e-06, + "loss": 2.0247, + "num_input_tokens_seen": 6323024, + "step": 625 + }, + { + "epoch": 4.750235626767201, + "grad_norm": 5.922281265258789, + "learning_rate": 4.986468976890993e-06, + "loss": 2.0485, + "num_input_tokens_seen": 6374608, + "step": 630 + }, + { + "epoch": 4.787935909519321, + "grad_norm": 5.62613582611084, + "learning_rate": 4.693283433874565e-06, + "loss": 2.0561, + "num_input_tokens_seen": 6422208, + "step": 635 + }, + { + "epoch": 4.825636192271442, + "grad_norm": 6.259154796600342, + "learning_rate": 4.408085464254183e-06, + "loss": 2.1047, + "num_input_tokens_seen": 6468912, + "step": 640 + }, + { + "epoch": 4.863336475023563, + "grad_norm": 5.757895469665527, + "learning_rate": 4.130987249617993e-06, + "loss": 2.0481, + "num_input_tokens_seen": 6522848, + "step": 645 + }, + { + "epoch": 4.9010367577756835, + "grad_norm": 5.949391841888428, + "learning_rate": 3.8620977855448935e-06, + "loss": 2.0637, + "num_input_tokens_seen": 6578768, + "step": 650 + }, + { + "epoch": 4.938737040527804, + "grad_norm": 6.397491931915283, + "learning_rate": 3.601522838731461e-06, + "loss": 2.0429, + "num_input_tokens_seen": 6631936, + "step": 655 + }, + { + "epoch": 4.976437323279924, + "grad_norm": 6.2142157554626465, + "learning_rate": 3.3493649053890326e-06, + "loss": 2.1212, + "num_input_tokens_seen": 6682992, + "step": 660 + }, + { + "epoch": 5.014137606032045, + "grad_norm": 5.99893856048584, + "learning_rate": 3.1057231709272077e-06, + "loss": 2.0205, + "num_input_tokens_seen": 6735056, + "step": 665 + }, + { + "epoch": 5.051837888784166, + "grad_norm": 6.014187335968018, + "learning_rate": 2.8706934709395892e-06, + "loss": 1.9942, + "num_input_tokens_seen": 6784224, + "step": 670 + }, + { + "epoch": 5.089538171536287, + "grad_norm": 6.134748935699463, + "learning_rate": 2.6443682535072177e-06, + "loss": 1.868, + "num_input_tokens_seen": 6831040, + "step": 675 + }, + { + "epoch": 5.127238454288407, + "grad_norm": 5.91867733001709, + "learning_rate": 2.4268365428344736e-06, + "loss": 1.9132, + "num_input_tokens_seen": 6883552, + "step": 680 + }, + { + "epoch": 5.1649387370405275, + "grad_norm": 7.725922584533691, + "learning_rate": 2.21818390423168e-06, + "loss": 1.8698, + "num_input_tokens_seen": 6928272, + "step": 685 + }, + { + "epoch": 5.202639019792649, + "grad_norm": 5.97230863571167, + "learning_rate": 2.0184924104583613e-06, + "loss": 1.8974, + "num_input_tokens_seen": 6972496, + "step": 690 + }, + { + "epoch": 5.240339302544769, + "grad_norm": 6.879273414611816, + "learning_rate": 1.8278406094401623e-06, + "loss": 1.9096, + "num_input_tokens_seen": 7018496, + "step": 695 + }, + { + "epoch": 5.27803958529689, + "grad_norm": 6.802375793457031, + "learning_rate": 1.6463034933723337e-06, + "loss": 2.0098, + "num_input_tokens_seen": 7066400, + "step": 700 + }, + { + "epoch": 5.31573986804901, + "grad_norm": 6.246311187744141, + "learning_rate": 1.4739524692218314e-06, + "loss": 1.9554, + "num_input_tokens_seen": 7113744, + "step": 705 + }, + { + "epoch": 5.353440150801131, + "grad_norm": 6.855324745178223, + "learning_rate": 1.3108553306396265e-06, + "loss": 2.0233, + "num_input_tokens_seen": 7166848, + "step": 710 + }, + { + "epoch": 5.391140433553252, + "grad_norm": 7.124240398406982, + "learning_rate": 1.1570762312943295e-06, + "loss": 1.9629, + "num_input_tokens_seen": 7220048, + "step": 715 + }, + { + "epoch": 5.4288407163053725, + "grad_norm": 6.546064853668213, + "learning_rate": 1.0126756596375686e-06, + "loss": 1.9036, + "num_input_tokens_seen": 7268064, + "step": 720 + }, + { + "epoch": 5.466540999057493, + "grad_norm": 6.543118953704834, + "learning_rate": 8.777104151110826e-07, + "loss": 1.988, + "num_input_tokens_seen": 7326512, + "step": 725 + }, + { + "epoch": 5.504241281809613, + "grad_norm": 6.955906391143799, + "learning_rate": 7.522335858048707e-07, + "loss": 1.9844, + "num_input_tokens_seen": 7382288, + "step": 730 + }, + { + "epoch": 5.541941564561734, + "grad_norm": 6.836036682128906, + "learning_rate": 6.362945275751736e-07, + "loss": 1.9743, + "num_input_tokens_seen": 7430544, + "step": 735 + }, + { + "epoch": 5.579641847313855, + "grad_norm": 6.253538608551025, + "learning_rate": 5.299388446305343e-07, + "loss": 2.007, + "num_input_tokens_seen": 7479488, + "step": 740 + }, + { + "epoch": 5.617342130065976, + "grad_norm": 5.982280731201172, + "learning_rate": 4.3320837159353813e-07, + "loss": 1.9413, + "num_input_tokens_seen": 7533536, + "step": 745 + }, + { + "epoch": 5.655042412818096, + "grad_norm": 5.737644195556641, + "learning_rate": 3.4614115704533767e-07, + "loss": 1.902, + "num_input_tokens_seen": 7589200, + "step": 750 + }, + { + "epoch": 5.6927426955702165, + "grad_norm": 6.928066730499268, + "learning_rate": 2.687714485593462e-07, + "loss": 2.0091, + "num_input_tokens_seen": 7638928, + "step": 755 + }, + { + "epoch": 5.730442978322337, + "grad_norm": 6.864605903625488, + "learning_rate": 2.011296792301165e-07, + "loss": 2.0389, + "num_input_tokens_seen": 7693680, + "step": 760 + }, + { + "epoch": 5.768143261074458, + "grad_norm": 6.230181694030762, + "learning_rate": 1.4324245570256633e-07, + "loss": 2.0012, + "num_input_tokens_seen": 7743904, + "step": 765 + }, + { + "epoch": 5.805843543826579, + "grad_norm": 6.436938285827637, + "learning_rate": 9.513254770636137e-08, + "loss": 2.0127, + "num_input_tokens_seen": 7790992, + "step": 770 + }, + { + "epoch": 5.843543826578699, + "grad_norm": 6.2262349128723145, + "learning_rate": 5.681887909952388e-08, + "loss": 2.0237, + "num_input_tokens_seen": 7843600, + "step": 775 + }, + { + "epoch": 5.88124410933082, + "grad_norm": 6.8672027587890625, + "learning_rate": 2.831652042480093e-08, + "loss": 1.9273, + "num_input_tokens_seen": 7893968, + "step": 780 + }, + { + "epoch": 5.918944392082941, + "grad_norm": 6.41185188293457, + "learning_rate": 9.636682981720158e-09, + "loss": 1.9827, + "num_input_tokens_seen": 7945856, + "step": 785 + }, + { + "epoch": 5.956644674835061, + "grad_norm": 6.624245643615723, + "learning_rate": 7.867144166728846e-10, + "loss": 1.9642, + "num_input_tokens_seen": 7998560, + "step": 790 + }, + { + "epoch": 5.971724787935909, + "num_input_tokens_seen": 8017392, + "step": 792, + "total_flos": 3.6202835979167334e+17, + "train_loss": 2.4793783682163317, + "train_runtime": 5283.1732, + "train_samples_per_second": 4.82, + "train_steps_per_second": 0.15 + } + ], + "logging_steps": 5, + "max_steps": 792, + "num_input_tokens_seen": 8017392, + "num_train_epochs": 6, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 3.6202835979167334e+17, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..f8accff7ed19f472e4ab59934a52cd1b74989284 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0abbac12d56c1934fca1078792064a59e7f00bea9a38a70efb9ce7fe81d8d0a2 +size 5432 diff --git a/training_args.yaml b/training_args.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b0e82af06b5eac68832fbb728c9000db2ef91477 --- /dev/null +++ b/training_args.yaml @@ -0,0 +1,32 @@ +bf16: true +cutoff_len: 1024 +dataset: identity +dataset_dir: data +ddp_timeout: 180000000 +do_train: true +finetuning_type: lora +flash_attn: auto +gradient_accumulation_steps: 8 +include_num_input_tokens_seen: true +learning_rate: 5.0e-05 +logging_steps: 5 +lora_alpha: 16 +lora_dropout: 0 +lora_rank: 8 +lora_target: all +lr_scheduler_type: cosine +max_grad_norm: 3.0 +max_samples: 100000 +model_name_or_path: NousResearch/Hermes-3-Llama-3.1-8B +num_train_epochs: 6.0 +optim: adamw_torch +output_dir: saves/LLaMA3.1-8B/lora/4k_train_2024-10-16-13-29-59 +packing: false +per_device_train_batch_size: 2 +plot_loss: true +preprocessing_num_workers: 16 +report_to: none +save_steps: 100 +stage: sft +template: llama3 +warmup_steps: 0 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000000000000000000000000000000000000..7adc1fac11be9a9872fd816b1f4eda2fe7566310 Binary files /dev/null and b/training_loss.png differ