End of training

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,174 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen1.5-0.5B-Chat
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 5fd20dd8-e5e9-4c7e-b857-0b756edd0afb
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: lora
+base_model: Qwen/Qwen1.5-0.5B-Chat
+bf16: auto
+chat_template: llama3
+cosine_min_lr_ratio: 0.1
+data_processes: 16
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 5c94dd176d8aa765_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/5c94dd176d8aa765_train_data.json
+  type:
+    field_instruction: instruction
+    field_output: output_1
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: auto
+do_eval: true
+early_stopping_patience: 1
+eval_batch_size: 1
+eval_sample_packing: false
+eval_steps: 25
+evaluation_strategy: steps
+flash_attention: false
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 32
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: sn5601/5fd20dd8-e5e9-4c7e-b857-0b756edd0afb
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0001
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 64
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lora_target_modules:
+- q_proj
+- v_proj
+lr_scheduler: cosine
+max_grad_norm: 1.0
+max_memory:
+  0: 70GiB
+  1: 70GiB
+  2: 70GiB
+  3: 70GiB
+max_steps: 100
+micro_batch_size: 1
+mlflow_experiment_name: /tmp/5c94dd176d8aa765_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+optimizer: adamw_torch
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 25
+save_strategy: steps
+sequence_len: 2048
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+torch_compile: false
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 50
+wandb_entity: sn56-miner
+wandb_mode: disabled
+wandb_name: 5fd20dd8-e5e9-4c7e-b857-0b756edd0afb
+wandb_project: god
+wandb_run: b141
+wandb_runid: 5fd20dd8-e5e9-4c7e-b857-0b756edd0afb
+warmup_ratio: 0.04
+weight_decay: 0.01
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 5fd20dd8-e5e9-4c7e-b857-0b756edd0afb
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2625
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 128
+- total_eval_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 4
+- training_steps: 100
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.2501        | 0.0261 | 1    | 1.6212          |
+| 1.2768        | 0.6520 | 25   | 1.3168          |
+| 1.1971        | 1.3040 | 50   | 1.2768          |
+| 1.5192        | 1.9560 | 75   | 1.2682          |
+| 1.253         | 2.6080 | 100  | 1.2625          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-0.5B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:783c4aec346216c0bfb6e9b480add856364525ccb5bbfa84cb4c4b0f3dd0b6dc
+size 60676170

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f8f4775ea2a17489d124c10a82d4b6b89d0f6a49aa048a337142cc30cc16e8
+size 60599872

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "Qwen/Qwen1.5-0.5B-Chat",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen1.5-0.5B-Chat
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **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]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+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
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[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 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-0.5B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f8f4775ea2a17489d124c10a82d4b6b89d0f6a49aa048a337142cc30cc16e8
+size 60599872

last-checkpoint/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db7f825f9d046cd65aaf44cc968f70c7b23cd4ffd0b11f10caf8174587cc789e
+size 121392706

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a843234d8a91b33fac7fb9f07e4d59b703173a124ad686a4e8a44169421bae
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fa0680f58afe49dd7111f8d1615d0c5f33eb88efa448da830c3eac06af969b6
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2157d2a8cbde8f7173e2ac9364e6fc1f18160eaa24f95696da4c0a05311e9e8f
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c790de0372f686a8f24a0df5306e891a3d0a87f41a7fc6bf38671e3ae214141d
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:051dee7dfbeecb34b46e8409ffafec324501f465585234624669bc8c9e863ae4
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,782 @@
+{
+  "best_metric": 1.2625093460083008,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 2.6079869600651997,
+  "eval_steps": 25,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.026079869600651995,
+      "grad_norm": 0.6620760560035706,
+      "learning_rate": 2.5e-05,
+      "loss": 1.2501,
+      "step": 1
+    },
+    {
+      "epoch": 0.026079869600651995,
+      "eval_loss": 1.6212151050567627,
+      "eval_runtime": 0.4971,
+      "eval_samples_per_second": 100.592,
+      "eval_steps_per_second": 26.154,
+      "step": 1
+    },
+    {
+      "epoch": 0.05215973920130399,
+      "grad_norm": 1.0186434984207153,
+      "learning_rate": 5e-05,
+      "loss": 1.4369,
+      "step": 2
+    },
+    {
+      "epoch": 0.07823960880195599,
+      "grad_norm": 0.7852559089660645,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.3094,
+      "step": 3
+    },
+    {
+      "epoch": 0.10431947840260798,
+      "grad_norm": 0.6789484024047852,
+      "learning_rate": 0.0001,
+      "loss": 1.3378,
+      "step": 4
+    },
+    {
+      "epoch": 0.13039934800325997,
+      "grad_norm": 0.5586358308792114,
+      "learning_rate": 9.997590643643647e-05,
+      "loss": 1.4974,
+      "step": 5
+    },
+    {
+      "epoch": 0.15647921760391198,
+      "grad_norm": 0.3749651610851288,
+      "learning_rate": 9.990365154573717e-05,
+      "loss": 1.3339,
+      "step": 6
+    },
+    {
+      "epoch": 0.18255908720456399,
+      "grad_norm": 0.42121371626853943,
+      "learning_rate": 9.978331270024886e-05,
+      "loss": 1.5307,
+      "step": 7
+    },
+    {
+      "epoch": 0.20863895680521596,
+      "grad_norm": 2.6662514209747314,
+      "learning_rate": 9.961501876182148e-05,
+      "loss": 1.7291,
+      "step": 8
+    },
+    {
+      "epoch": 0.23471882640586797,
+      "grad_norm": 0.906875491142273,
+      "learning_rate": 9.939894994381957e-05,
+      "loss": 1.7642,
+      "step": 9
+    },
+    {
+      "epoch": 0.26079869600651995,
+      "grad_norm": 0.32841840386390686,
+      "learning_rate": 9.913533761814537e-05,
+      "loss": 1.1277,
+      "step": 10
+    },
+    {
+      "epoch": 0.28687856560717195,
+      "grad_norm": 0.32854458689689636,
+      "learning_rate": 9.882446406748002e-05,
+      "loss": 1.2506,
+      "step": 11
+    },
+    {
+      "epoch": 0.31295843520782396,
+      "grad_norm": 0.2924271523952484,
+      "learning_rate": 9.846666218300807e-05,
+      "loss": 1.3405,
+      "step": 12
+    },
+    {
+      "epoch": 0.33903830480847597,
+      "grad_norm": 0.28709307312965393,
+      "learning_rate": 9.80623151079494e-05,
+      "loss": 1.276,
+      "step": 13
+    },
+    {
+      "epoch": 0.36511817440912797,
+      "grad_norm": 0.26937562227249146,
+      "learning_rate": 9.761185582727977e-05,
+      "loss": 1.3337,
+      "step": 14
+    },
+    {
+      "epoch": 0.39119804400978,
+      "grad_norm": 0.25019437074661255,
+      "learning_rate": 9.711576670407965e-05,
+      "loss": 1.3807,
+      "step": 15
+    },
+    {
+      "epoch": 0.4172779136104319,
+      "grad_norm": 0.27004799246788025,
+      "learning_rate": 9.657457896300791e-05,
+      "loss": 1.3273,
+      "step": 16
+    },
+    {
+      "epoch": 0.44335778321108393,
+      "grad_norm": 0.3201175034046173,
+      "learning_rate": 9.598887212145291e-05,
+      "loss": 1.5258,
+      "step": 17
+    },
+    {
+      "epoch": 0.46943765281173594,
+      "grad_norm": 0.4178328216075897,
+      "learning_rate": 9.535927336897098e-05,
+      "loss": 1.6499,
+      "step": 18
+    },
+    {
+      "epoch": 0.49551752241238795,
+      "grad_norm": 0.9188335537910461,
+      "learning_rate": 9.468645689567598e-05,
+      "loss": 1.846,
+      "step": 19
+    },
+    {
+      "epoch": 0.5215973920130399,
+      "grad_norm": 0.2169221043586731,
+      "learning_rate": 9.397114317029975e-05,
+      "loss": 1.1765,
+      "step": 20
+    },
+    {
+      "epoch": 0.5476772616136919,
+      "grad_norm": 0.2450340837240219,
+      "learning_rate": 9.321409816869605e-05,
+      "loss": 1.2586,
+      "step": 21
+    },
+    {
+      "epoch": 0.5737571312143439,
+      "grad_norm": 0.2194407731294632,
+      "learning_rate": 9.241613255361455e-05,
+      "loss": 1.2651,
+      "step": 22
+    },
+    {
+      "epoch": 0.5998370008149959,
+      "grad_norm": 0.216043621301651,
+      "learning_rate": 9.157810080662269e-05,
+      "loss": 1.2809,
+      "step": 23
+    },
+    {
+      "epoch": 0.6259168704156479,
+      "grad_norm": 0.2400970458984375,
+      "learning_rate": 9.070090031310558e-05,
+      "loss": 1.3573,
+      "step": 24
+    },
+    {
+      "epoch": 0.6519967400162999,
+      "grad_norm": 0.2485317438840866,
+      "learning_rate": 8.978547040132317e-05,
+      "loss": 1.2768,
+      "step": 25
+    },
+    {
+      "epoch": 0.6519967400162999,
+      "eval_loss": 1.3168331384658813,
+      "eval_runtime": 0.4947,
+      "eval_samples_per_second": 101.078,
+      "eval_steps_per_second": 26.28,
+      "step": 25
+    },
+    {
+      "epoch": 0.6780766096169519,
+      "grad_norm": 0.858853280544281,
+      "learning_rate": 8.883279133655399e-05,
+      "loss": 1.4349,
+      "step": 26
+    },
+    {
+      "epoch": 0.7041564792176039,
+      "grad_norm": 0.3207035958766937,
+      "learning_rate": 8.78438832714026e-05,
+      "loss": 1.5518,
+      "step": 27
+    },
+    {
+      "epoch": 0.7302363488182559,
+      "grad_norm": 0.47130295634269714,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 1.5278,
+      "step": 28
+    },
+    {
+      "epoch": 0.756316218418908,
+      "grad_norm": 0.18217793107032776,
+      "learning_rate": 8.57616535910292e-05,
+      "loss": 1.0693,
+      "step": 29
+    },
+    {
+      "epoch": 0.78239608801956,
+      "grad_norm": 0.21631065011024475,
+      "learning_rate": 8.467056167950311e-05,
+      "loss": 1.3558,
+      "step": 30
+    },
+    {
+      "epoch": 0.8084759576202118,
+      "grad_norm": 0.19864201545715332,
+      "learning_rate": 8.354769778736406e-05,
+      "loss": 1.3028,
+      "step": 31
+    },
+    {
+      "epoch": 0.8345558272208639,
+      "grad_norm": 0.19812346994876862,
+      "learning_rate": 8.239426430539243e-05,
+      "loss": 1.3066,
+      "step": 32
+    },
+    {
+      "epoch": 0.8606356968215159,
+      "grad_norm": 0.23884153366088867,
+      "learning_rate": 8.12114963590511e-05,
+      "loss": 1.3189,
+      "step": 33
+    },
+    {
+      "epoch": 0.8867155664221679,
+      "grad_norm": 0.2092161476612091,
+      "learning_rate": 8.000066048588211e-05,
+      "loss": 1.273,
+      "step": 34
+    },
+    {
+      "epoch": 0.9127954360228199,
+      "grad_norm": 0.26922526955604553,
+      "learning_rate": 7.876305327926657e-05,
+      "loss": 1.3761,
+      "step": 35
+    },
+    {
+      "epoch": 0.9388753056234719,
+      "grad_norm": 0.2948414087295532,
+      "learning_rate": 7.75e-05,
+      "loss": 1.3617,
+      "step": 36
+    },
+    {
+      "epoch": 0.9649551752241239,
+      "grad_norm": 0.44491636753082275,
+      "learning_rate": 7.62128531571699e-05,
+      "loss": 1.5529,
+      "step": 37
+    },
+    {
+      "epoch": 0.9910350448247759,
+      "grad_norm": 0.7980100512504578,
+      "learning_rate": 7.490299105985507e-05,
+      "loss": 1.6605,
+      "step": 38
+    },
+    {
+      "epoch": 1.017114914425428,
+      "grad_norm": 0.42900562286376953,
+      "learning_rate": 7.357181634119777e-05,
+      "loss": 1.9593,
+      "step": 39
+    },
+    {
+      "epoch": 1.0431947840260798,
+      "grad_norm": 0.17168301343917847,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 1.1427,
+      "step": 40
+    },
+    {
+      "epoch": 1.069274653626732,
+      "grad_norm": 0.18627986311912537,
+      "learning_rate": 7.085125215645552e-05,
+      "loss": 1.3079,
+      "step": 41
+    },
+    {
+      "epoch": 1.0953545232273838,
+      "grad_norm": 0.19410377740859985,
+      "learning_rate": 6.946477593864228e-05,
+      "loss": 1.2263,
+      "step": 42
+    },
+    {
+      "epoch": 1.121434392828036,
+      "grad_norm": 0.20103414356708527,
+      "learning_rate": 6.80628104764508e-05,
+      "loss": 1.29,
+      "step": 43
+    },
+    {
+      "epoch": 1.1475142624286878,
+      "grad_norm": 0.229043647646904,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 1.2465,
+      "step": 44
+    },
+    {
+      "epoch": 1.17359413202934,
+      "grad_norm": 1.0233486890792847,
+      "learning_rate": 6.52184318365468e-05,
+      "loss": 1.3942,
+      "step": 45
+    },
+    {
+      "epoch": 1.1996740016299918,
+      "grad_norm": 0.29909205436706543,
+      "learning_rate": 6.377906449072578e-05,
+      "loss": 1.4629,
+      "step": 46
+    },
+    {
+      "epoch": 1.225753871230644,
+      "grad_norm": 0.389396071434021,
+      "learning_rate": 6.23302963027565e-05,
+      "loss": 1.5736,
+      "step": 47
+    },
+    {
+      "epoch": 1.2518337408312958,
+      "grad_norm": 0.2234639823436737,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 0.7327,
+      "step": 48
+    },
+    {
+      "epoch": 1.277913610431948,
+      "grad_norm": 0.21025896072387695,
+      "learning_rate": 5.941077131483025e-05,
+      "loss": 1.5035,
+      "step": 49
+    },
+    {
+      "epoch": 1.3039934800325998,
+      "grad_norm": 0.17033106088638306,
+      "learning_rate": 5.794314081535644e-05,
+      "loss": 1.1971,
+      "step": 50
+    },
+    {
+      "epoch": 1.3039934800325998,
+      "eval_loss": 1.276837706565857,
+      "eval_runtime": 0.4933,
+      "eval_samples_per_second": 101.363,
+      "eval_steps_per_second": 26.355,
+      "step": 50
+    },
+    {
+      "epoch": 1.3300733496332517,
+      "grad_norm": 0.18216781318187714,
+      "learning_rate": 5.6472358726979935e-05,
+      "loss": 1.2561,
+      "step": 51
+    },
+    {
+      "epoch": 1.3561532192339039,
+      "grad_norm": 0.19190214574337006,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.2373,
+      "step": 52
+    },
+    {
+      "epoch": 1.3822330888345558,
+      "grad_norm": 0.20375579595565796,
+      "learning_rate": 5.352764127302008e-05,
+      "loss": 1.3094,
+      "step": 53
+    },
+    {
+      "epoch": 1.4083129584352079,
+      "grad_norm": 0.22090604901313782,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.2524,
+      "step": 54
+    },
+    {
+      "epoch": 1.4343928280358598,
+      "grad_norm": 0.2642119526863098,
+      "learning_rate": 5.058922868516978e-05,
+      "loss": 1.3616,
+      "step": 55
+    },
+    {
+      "epoch": 1.4604726976365119,
+      "grad_norm": 0.34405508637428284,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.5443,
+      "step": 56
+    },
+    {
+      "epoch": 1.4865525672371638,
+      "grad_norm": 0.5865151882171631,
+      "learning_rate": 4.7669703697243516e-05,
+      "loss": 1.7222,
+      "step": 57
+    },
+    {
+      "epoch": 1.5126324368378157,
+      "grad_norm": 0.3257847726345062,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.0614,
+      "step": 58
+    },
+    {
+      "epoch": 1.5387123064384678,
+      "grad_norm": 0.15625827014446259,
+      "learning_rate": 4.478156816345321e-05,
+      "loss": 1.1532,
+      "step": 59
+    },
+    {
+      "epoch": 1.56479217603912,
+      "grad_norm": 0.17408806085586548,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.185,
+      "step": 60
+    },
+    {
+      "epoch": 1.5908720456397718,
+      "grad_norm": 0.18832173943519592,
+      "learning_rate": 4.19371895235492e-05,
+      "loss": 1.1786,
+      "step": 61
+    },
+    {
+      "epoch": 1.6169519152404237,
+      "grad_norm": 0.19872711598873138,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.2668,
+      "step": 62
+    },
+    {
+      "epoch": 1.6430317848410758,
+      "grad_norm": 0.22072260081768036,
+      "learning_rate": 3.9148747843544495e-05,
+      "loss": 1.2622,
+      "step": 63
+    },
+    {
+      "epoch": 1.669111654441728,
+      "grad_norm": 0.25179487466812134,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.3652,
+      "step": 64
+    },
+    {
+      "epoch": 1.6951915240423798,
+      "grad_norm": 0.28402817249298096,
+      "learning_rate": 3.642818365880224e-05,
+      "loss": 1.4035,
+      "step": 65
+    },
+    {
+      "epoch": 1.7212713936430317,
+      "grad_norm": 0.4112336337566376,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.5314,
+      "step": 66
+    },
+    {
+      "epoch": 1.7473512632436838,
+      "grad_norm": 0.24410173296928406,
+      "learning_rate": 3.378714684283011e-05,
+      "loss": 0.8069,
+      "step": 67
+    },
+    {
+      "epoch": 1.7734311328443357,
+      "grad_norm": 0.20584547519683838,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.4517,
+      "step": 68
+    },
+    {
+      "epoch": 1.7995110024449876,
+      "grad_norm": 0.17557083070278168,
+      "learning_rate": 3.123694672073344e-05,
+      "loss": 1.216,
+      "step": 69
+    },
+    {
+      "epoch": 1.8255908720456397,
+      "grad_norm": 0.18803009390830994,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.2143,
+      "step": 70
+    },
+    {
+      "epoch": 1.8516707416462919,
+      "grad_norm": 0.19694343209266663,
+      "learning_rate": 2.8788503640948912e-05,
+      "loss": 1.2274,
+      "step": 71
+    },
+    {
+      "epoch": 1.8777506112469438,
+      "grad_norm": 0.20662301778793335,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.2995,
+      "step": 72
+    },
+    {
+      "epoch": 1.9038304808475957,
+      "grad_norm": 0.22804853320121765,
+      "learning_rate": 2.645230221263596e-05,
+      "loss": 1.2843,
+      "step": 73
+    },
+    {
+      "epoch": 1.9299103504482478,
+      "grad_norm": 0.2707391679286957,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.2768,
+      "step": 74
+    },
+    {
+      "epoch": 1.9559902200488999,
+      "grad_norm": 0.37075576186180115,
+      "learning_rate": 2.423834640897079e-05,
+      "loss": 1.5192,
+      "step": 75
+    },
+    {
+      "epoch": 1.9559902200488999,
+      "eval_loss": 1.2681915760040283,
+      "eval_runtime": 0.4943,
+      "eval_samples_per_second": 101.15,
+      "eval_steps_per_second": 26.299,
+      "step": 75
+    },
+    {
+      "epoch": 1.9820700896495518,
+      "grad_norm": 0.6423049569129944,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.6123,
+      "step": 76
+    },
+    {
+      "epoch": 2.0081499592502037,
+      "grad_norm": 0.43415480852127075,
+      "learning_rate": 2.215611672859741e-05,
+      "loss": 1.9664,
+      "step": 77
+    },
+    {
+      "epoch": 2.034229828850856,
+      "grad_norm": 0.150677889585495,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.0656,
+      "step": 78
+    },
+    {
+      "epoch": 2.060309698451508,
+      "grad_norm": 0.17479360103607178,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 1.1818,
+      "step": 79
+    },
+    {
+      "epoch": 2.0863895680521596,
+      "grad_norm": 0.18362055718898773,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.1829,
+      "step": 80
+    },
+    {
+      "epoch": 2.1124694376528117,
+      "grad_norm": 0.20285598933696747,
+      "learning_rate": 1.842189919337732e-05,
+      "loss": 1.2863,
+      "step": 81
+    },
+    {
+      "epoch": 2.138549307253464,
+      "grad_norm": 0.21474912762641907,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.3106,
+      "step": 82
+    },
+    {
+      "epoch": 2.164629176854116,
+      "grad_norm": 0.24042028188705444,
+      "learning_rate": 1.6785901831303956e-05,
+      "loss": 1.2384,
+      "step": 83
+    },
+    {
+      "epoch": 2.1907090464547676,
+      "grad_norm": 0.2615673243999481,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.328,
+      "step": 84
+    },
+    {
+      "epoch": 2.2167889160554197,
+      "grad_norm": 0.377523273229599,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 1.5058,
+      "step": 85
+    },
+    {
+      "epoch": 2.242868785656072,
+      "grad_norm": 0.32665538787841797,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.9337,
+      "step": 86
+    },
+    {
+      "epoch": 2.2689486552567235,
+      "grad_norm": 0.20789040625095367,
+      "learning_rate": 1.4011127878547087e-05,
+      "loss": 1.4827,
+      "step": 87
+    },
+    {
+      "epoch": 2.2950285248573756,
+      "grad_norm": 0.17642174661159515,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.2114,
+      "step": 88
+    },
+    {
+      "epoch": 2.3211083944580277,
+      "grad_norm": 0.17508623003959656,
+      "learning_rate": 1.2884233295920353e-05,
+      "loss": 1.2065,
+      "step": 89
+    },
+    {
+      "epoch": 2.34718826405868,
+      "grad_norm": 0.18353621661663055,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.2285,
+      "step": 90
+    },
+    {
+      "epoch": 2.3732681336593315,
+      "grad_norm": 0.20404478907585144,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 1.2864,
+      "step": 91
+    },
+    {
+      "epoch": 2.3993480032599837,
+      "grad_norm": 0.22320792078971863,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.2372,
+      "step": 92
+    },
+    {
+      "epoch": 2.4254278728606358,
+      "grad_norm": 0.25220105051994324,
+      "learning_rate": 1.1175535932519987e-05,
+      "loss": 1.3136,
+      "step": 93
+    },
+    {
+      "epoch": 2.451507742461288,
+      "grad_norm": 0.3090400695800781,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.364,
+      "step": 94
+    },
+    {
+      "epoch": 2.4775876120619396,
+      "grad_norm": 0.4767124056816101,
+      "learning_rate": 1.0601050056180447e-05,
+      "loss": 1.6821,
+      "step": 95
+    },
+    {
+      "epoch": 2.5036674816625917,
+      "grad_norm": 0.4842507839202881,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.1292,
+      "step": 96
+    },
+    {
+      "epoch": 2.529747351263244,
+      "grad_norm": 0.14696048200130463,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 1.1158,
+      "step": 97
+    },
+    {
+      "epoch": 2.555827220863896,
+      "grad_norm": 0.37997448444366455,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.2302,
+      "step": 98
+    },
+    {
+      "epoch": 2.5819070904645476,
+      "grad_norm": 0.1806773990392685,
+      "learning_rate": 1.0024093563563546e-05,
+      "loss": 1.1778,
+      "step": 99
+    },
+    {
+      "epoch": 2.6079869600651997,
+      "grad_norm": 0.20082679390907288,
+      "learning_rate": 1e-05,
+      "loss": 1.253,
+      "step": 100
+    },
+    {
+      "epoch": 2.6079869600651997,
+      "eval_loss": 1.2625093460083008,
+      "eval_runtime": 0.4948,
+      "eval_samples_per_second": 101.042,
+      "eval_steps_per_second": 26.271,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.08890810679296e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4368ec72db69a70c362a62758c03dc3f1826f1f19acde15c393a06a207e6e0
+size 6840

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4368ec72db69a70c362a62758c03dc3f1826f1f19acde15c393a06a207e6e0
+size 6840