End of training

README.md

@@ -0,0 +1,168 @@
+---
+library_name: peft
+license: mit
+base_model: fxmarty/really-tiny-falcon-testing
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 46b63180-22b5-4ce5-895a-a0a910eb81ff
+  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: fxmarty/really-tiny-falcon-testing
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 4214a6acaa4ea6d5_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/4214a6acaa4ea6d5_train_data.json
+  type:
+    field_input: tags
+    field_instruction: sentences
+    field_output: NER_TAGS
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+early_stopping_patience: null
+eval_max_new_tokens: 128
+eval_steps: null
+eval_table_size: null
+flash_attention: false
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: sn56m5/3c0765d8-301a-474f-b7ba-16b617cd5ec5
+hub_repo: null
+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_modules_to_save:
+- embed_tokens
+- lm_head
+lora_r: 32
+lora_target_linear: true
+lora_target_modules:
+- gate_proj
+- down_proj
+- up_proj
+- q_proj
+- v_proj
+- k_proj
+- o_proj
+lr_scheduler: cosine
+max_memory:
+  0: 70GB
+micro_batch_size: 4
+mlflow_experiment_name: /tmp/4214a6acaa4ea6d5_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 1
+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: 239
+sequence_len: 2048
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: sn56-miner
+wandb_mode: disabled
+wandb_name: sn56m5/3c0765d8
+wandb_project: god
+wandb_run: n8w9
+wandb_runid: sn56m5/3c0765d8
+warmup_steps: 100
+weight_decay: 0.1
+xformers_attention: true
+
+```
+
+</details><br>
+
+# 46b63180-22b5-4ce5-895a-a0a910eb81ff
+
+This model is a fine-tuned version of [fxmarty/really-tiny-falcon-testing](https://huggingface.co/fxmarty/really-tiny-falcon-testing) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.3569
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
+- 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: 100
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 41.3494       | 0.9944 | 134  | 10.3569         |
+
+
+### 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 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "fxmarty/really-tiny-falcon-testing",
+  "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": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "dense",
+    "v_proj",
+    "down_proj",
+    "query_key_value",
+    "k_proj",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "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 sha256:350868487946376f86feeab93cf5257c88531d67c47fb022af96aab936ee878a
+size 4291041

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9edd399ed501b70b7a758d9a9939c6fcdc8dcc78da3ba46cb73d2b86c725f7bb
+size 4286680

config.json

@@ -0,0 +1,40 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "fxmarty/really-tiny-falcon-testing",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-7b--configuration_falcon.FalconConfig",
+    "AutoModel": "tiiuae/falcon-7b--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": null,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": false,
+  "nm_kv_hears": 2,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_kv_heads": 71,
+  "parallel_attn": true,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 65024
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: fxmarty/really-tiny-falcon-testing
+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 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "fxmarty/really-tiny-falcon-testing",
+  "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": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "dense",
+    "v_proj",
+    "down_proj",
+    "query_key_value",
+    "k_proj",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
+  ],
+  "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 sha256:9edd399ed501b70b7a758d9a9939c6fcdc8dcc78da3ba46cb73d2b86c725f7bb
+size 4286680

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9272f988d48f4bbfea99f9d6aec8aec9b16042c906268a03a69c737b62127fe3
+size 8583659

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7683ae9331e002033937db08e12d045499ee9eb545764af3c383a49d7f2dfdbd
+size 14960

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a46bbb18c76e9672eac420453a1a7c1f3499dbaf374c3e686b88c1f20dffe01d
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140bd7d260b7341d7452c53cd36ed2e77da71da35b716684c9cf409afc75bf9f
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:627461a6da534121b40d84060cb71158db6c3295691b5d961d97aed650d714a7
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7632537d8ae9bf95eb35e56109ca14fb051643b03e4f55ad4c83d720697d269d
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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_config.json

@@ -0,0 +1,124 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "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": true,
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,971 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9944341372912802,
+  "eval_steps": 500,
+  "global_step": 134,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0074211502782931356,
+      "grad_norm": 12.875755310058594,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 43.8255,
+      "step": 1
+    },
+    {
+      "epoch": 0.014842300556586271,
+      "grad_norm": 13.694927215576172,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 43.7838,
+      "step": 2
+    },
+    {
+      "epoch": 0.022263450834879406,
+      "grad_norm": 13.845458984375,
+      "learning_rate": 3e-06,
+      "loss": 43.7845,
+      "step": 3
+    },
+    {
+      "epoch": 0.029684601113172542,
+      "grad_norm": 14.294939994812012,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 43.7597,
+      "step": 4
+    },
+    {
+      "epoch": 0.03710575139146568,
+      "grad_norm": 15.06674575805664,
+      "learning_rate": 5e-06,
+      "loss": 43.7169,
+      "step": 5
+    },
+    {
+      "epoch": 0.04452690166975881,
+      "grad_norm": 13.9005765914917,
+      "learning_rate": 6e-06,
+      "loss": 43.7717,
+      "step": 6
+    },
+    {
+      "epoch": 0.05194805194805195,
+      "grad_norm": 15.33477783203125,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 43.6955,
+      "step": 7
+    },
+    {
+      "epoch": 0.059369202226345084,
+      "grad_norm": 14.438776969909668,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 43.7294,
+      "step": 8
+    },
+    {
+      "epoch": 0.06679035250463822,
+      "grad_norm": 15.570612907409668,
+      "learning_rate": 9e-06,
+      "loss": 43.68,
+      "step": 9
+    },
+    {
+      "epoch": 0.07421150278293136,
+      "grad_norm": 15.746886253356934,
+      "learning_rate": 1e-05,
+      "loss": 43.6849,
+      "step": 10
+    },
+    {
+      "epoch": 0.08163265306122448,
+      "grad_norm": 16.453710556030273,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 43.6619,
+      "step": 11
+    },
+    {
+      "epoch": 0.08905380333951762,
+      "grad_norm": 15.958196640014648,
+      "learning_rate": 1.2e-05,
+      "loss": 43.714,
+      "step": 12
+    },
+    {
+      "epoch": 0.09647495361781076,
+      "grad_norm": 11.555306434631348,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 43.9281,
+      "step": 13
+    },
+    {
+      "epoch": 0.1038961038961039,
+      "grad_norm": 13.375900268554688,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 43.7942,
+      "step": 14
+    },
+    {
+      "epoch": 0.11131725417439703,
+      "grad_norm": 12.702278137207031,
+      "learning_rate": 1.5e-05,
+      "loss": 43.8003,
+      "step": 15
+    },
+    {
+      "epoch": 0.11873840445269017,
+      "grad_norm": 12.70096206665039,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 43.8271,
+      "step": 16
+    },
+    {
+      "epoch": 0.1261595547309833,
+      "grad_norm": 15.536250114440918,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 43.6431,
+      "step": 17
+    },
+    {
+      "epoch": 0.13358070500927643,
+      "grad_norm": 13.470147132873535,
+      "learning_rate": 1.8e-05,
+      "loss": 43.7472,
+      "step": 18
+    },
+    {
+      "epoch": 0.14100185528756956,
+      "grad_norm": 13.50928020477295,
+      "learning_rate": 1.9e-05,
+      "loss": 43.6878,
+      "step": 19
+    },
+    {
+      "epoch": 0.14842300556586271,
+      "grad_norm": 15.333284378051758,
+      "learning_rate": 2e-05,
+      "loss": 43.5126,
+      "step": 20
+    },
+    {
+      "epoch": 0.15584415584415584,
+      "grad_norm": 14.670302391052246,
+      "learning_rate": 2.1e-05,
+      "loss": 43.5365,
+      "step": 21
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 15.43974781036377,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 43.4889,
+      "step": 22
+    },
+    {
+      "epoch": 0.17068645640074212,
+      "grad_norm": 14.663032531738281,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 43.5321,
+      "step": 23
+    },
+    {
+      "epoch": 0.17810760667903525,
+      "grad_norm": 13.830320358276367,
+      "learning_rate": 2.4e-05,
+      "loss": 43.5709,
+      "step": 24
+    },
+    {
+      "epoch": 0.18552875695732837,
+      "grad_norm": 13.506930351257324,
+      "learning_rate": 2.5e-05,
+      "loss": 43.6988,
+      "step": 25
+    },
+    {
+      "epoch": 0.19294990723562153,
+      "grad_norm": 12.004054069519043,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 43.6786,
+      "step": 26
+    },
+    {
+      "epoch": 0.20037105751391465,
+      "grad_norm": 13.312070846557617,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 43.5779,
+      "step": 27
+    },
+    {
+      "epoch": 0.2077922077922078,
+      "grad_norm": 12.981239318847656,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 43.5942,
+      "step": 28
+    },
+    {
+      "epoch": 0.21521335807050093,
+      "grad_norm": 13.811375617980957,
+      "learning_rate": 2.9e-05,
+      "loss": 43.5102,
+      "step": 29
+    },
+    {
+      "epoch": 0.22263450834879406,
+      "grad_norm": 13.488224983215332,
+      "learning_rate": 3e-05,
+      "loss": 43.448,
+      "step": 30
+    },
+    {
+      "epoch": 0.2300556586270872,
+      "grad_norm": 14.316596031188965,
+      "learning_rate": 3.1e-05,
+      "loss": 43.3565,
+      "step": 31
+    },
+    {
+      "epoch": 0.23747680890538034,
+      "grad_norm": 11.307336807250977,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 43.585,
+      "step": 32
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 13.673873901367188,
+      "learning_rate": 3.3e-05,
+      "loss": 43.3772,
+      "step": 33
+    },
+    {
+      "epoch": 0.2523191094619666,
+      "grad_norm": 14.707979202270508,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 43.2863,
+      "step": 34
+    },
+    {
+      "epoch": 0.2597402597402597,
+      "grad_norm": 13.864319801330566,
+      "learning_rate": 3.5e-05,
+      "loss": 43.3462,
+      "step": 35
+    },
+    {
+      "epoch": 0.26716141001855287,
+      "grad_norm": 13.818319320678711,
+      "learning_rate": 3.6e-05,
+      "loss": 43.3571,
+      "step": 36
+    },
+    {
+      "epoch": 0.274582560296846,
+      "grad_norm": 13.928568840026855,
+      "learning_rate": 3.7e-05,
+      "loss": 43.3601,
+      "step": 37
+    },
+    {
+      "epoch": 0.2820037105751391,
+      "grad_norm": 11.747014045715332,
+      "learning_rate": 3.8e-05,
+      "loss": 43.5082,
+      "step": 38
+    },
+    {
+      "epoch": 0.2894248608534323,
+      "grad_norm": 13.3358793258667,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 43.2283,
+      "step": 39
+    },
+    {
+      "epoch": 0.29684601113172543,
+      "grad_norm": 12.018415451049805,
+      "learning_rate": 4e-05,
+      "loss": 43.3082,
+      "step": 40
+    },
+    {
+      "epoch": 0.3042671614100185,
+      "grad_norm": 13.584273338317871,
+      "learning_rate": 4.1e-05,
+      "loss": 43.1201,
+      "step": 41
+    },
+    {
+      "epoch": 0.3116883116883117,
+      "grad_norm": 12.351030349731445,
+      "learning_rate": 4.2e-05,
+      "loss": 43.2237,
+      "step": 42
+    },
+    {
+      "epoch": 0.31910946196660483,
+      "grad_norm": 11.146052360534668,
+      "learning_rate": 4.3e-05,
+      "loss": 43.3483,
+      "step": 43
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 12.65275764465332,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 43.1792,
+      "step": 44
+    },
+    {
+      "epoch": 0.3339517625231911,
+      "grad_norm": 12.845890998840332,
+      "learning_rate": 4.5e-05,
+      "loss": 43.1513,
+      "step": 45
+    },
+    {
+      "epoch": 0.34137291280148424,
+      "grad_norm": 13.390238761901855,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 43.0996,
+      "step": 46
+    },
+    {
+      "epoch": 0.34879406307977734,
+      "grad_norm": 11.83107852935791,
+      "learning_rate": 4.7e-05,
+      "loss": 43.2286,
+      "step": 47
+    },
+    {
+      "epoch": 0.3562152133580705,
+      "grad_norm": 13.277252197265625,
+      "learning_rate": 4.8e-05,
+      "loss": 43.1003,
+      "step": 48
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 12.586545944213867,
+      "learning_rate": 4.9e-05,
+      "loss": 43.1566,
+      "step": 49
+    },
+    {
+      "epoch": 0.37105751391465674,
+      "grad_norm": 11.365961074829102,
+      "learning_rate": 5e-05,
+      "loss": 43.3094,
+      "step": 50
+    },
+    {
+      "epoch": 0.3784786641929499,
+      "grad_norm": 11.266556739807129,
+      "learning_rate": 5.1000000000000006e-05,
+      "loss": 43.1328,
+      "step": 51
+    },
+    {
+      "epoch": 0.38589981447124305,
+      "grad_norm": 12.831755638122559,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 42.9348,
+      "step": 52
+    },
+    {
+      "epoch": 0.39332096474953615,
+      "grad_norm": 11.529878616333008,
+      "learning_rate": 5.300000000000001e-05,
+      "loss": 43.06,
+      "step": 53
+    },
+    {
+      "epoch": 0.4007421150278293,
+      "grad_norm": 10.949700355529785,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 43.1168,
+      "step": 54
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 11.29103946685791,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 43.0743,
+      "step": 55
+    },
+    {
+      "epoch": 0.4155844155844156,
+      "grad_norm": 13.43773365020752,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 42.8279,
+      "step": 56
+    },
+    {
+      "epoch": 0.4230055658627087,
+      "grad_norm": 11.960088729858398,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 42.9814,
+      "step": 57
+    },
+    {
+      "epoch": 0.43042671614100186,
+      "grad_norm": 12.002399444580078,
+      "learning_rate": 5.8e-05,
+      "loss": 42.9568,
+      "step": 58
+    },
+    {
+      "epoch": 0.437847866419295,
+      "grad_norm": 12.616547584533691,
+      "learning_rate": 5.9e-05,
+      "loss": 42.8704,
+      "step": 59
+    },
+    {
+      "epoch": 0.4452690166975881,
+      "grad_norm": 12.256824493408203,
+      "learning_rate": 6e-05,
+      "loss": 42.9143,
+      "step": 60
+    },
+    {
+      "epoch": 0.45269016697588127,
+      "grad_norm": 13.87753963470459,
+      "learning_rate": 6.1e-05,
+      "loss": 42.7471,
+      "step": 61
+    },
+    {
+      "epoch": 0.4601113172541744,
+      "grad_norm": 12.105416297912598,
+      "learning_rate": 6.2e-05,
+      "loss": 42.9175,
+      "step": 62
+    },
+    {
+      "epoch": 0.4675324675324675,
+      "grad_norm": 10.594766616821289,
+      "learning_rate": 6.3e-05,
+      "loss": 43.0602,
+      "step": 63
+    },
+    {
+      "epoch": 0.4749536178107607,
+      "grad_norm": 11.39623737335205,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 42.9701,
+      "step": 64
+    },
+    {
+      "epoch": 0.48237476808905383,
+      "grad_norm": 10.855255126953125,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 43.0287,
+      "step": 65
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 12.33413314819336,
+      "learning_rate": 6.6e-05,
+      "loss": 42.7315,
+      "step": 66
+    },
+    {
+      "epoch": 0.4972170686456401,
+      "grad_norm": 11.855805397033691,
+      "learning_rate": 6.7e-05,
+      "loss": 42.7659,
+      "step": 67
+    },
+    {
+      "epoch": 0.5046382189239332,
+      "grad_norm": 13.27923583984375,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 42.6242,
+      "step": 68
+    },
+    {
+      "epoch": 0.5120593692022264,
+      "grad_norm": 12.669722557067871,
+      "learning_rate": 6.9e-05,
+      "loss": 42.6433,
+      "step": 69
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "grad_norm": 12.479344367980957,
+      "learning_rate": 7e-05,
+      "loss": 42.6562,
+      "step": 70
+    },
+    {
+      "epoch": 0.5269016697588126,
+      "grad_norm": 13.821928977966309,
+      "learning_rate": 7.1e-05,
+      "loss": 42.5062,
+      "step": 71
+    },
+    {
+      "epoch": 0.5343228200371057,
+      "grad_norm": 13.465804100036621,
+      "learning_rate": 7.2e-05,
+      "loss": 42.5491,
+      "step": 72
+    },
+    {
+      "epoch": 0.5417439703153989,
+      "grad_norm": 13.117185592651367,
+      "learning_rate": 7.3e-05,
+      "loss": 42.5775,
+      "step": 73
+    },
+    {
+      "epoch": 0.549165120593692,
+      "grad_norm": 13.457059860229492,
+      "learning_rate": 7.4e-05,
+      "loss": 42.5438,
+      "step": 74
+    },
+    {
+      "epoch": 0.5565862708719852,
+      "grad_norm": 11.82220458984375,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 42.7438,
+      "step": 75
+    },
+    {
+      "epoch": 0.5640074211502782,
+      "grad_norm": 11.795948028564453,
+      "learning_rate": 7.6e-05,
+      "loss": 42.6739,
+      "step": 76
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 11.989442825317383,
+      "learning_rate": 7.7e-05,
+      "loss": 42.6388,
+      "step": 77
+    },
+    {
+      "epoch": 0.5788497217068646,
+      "grad_norm": 11.698662757873535,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 42.6519,
+      "step": 78
+    },
+    {
+      "epoch": 0.5862708719851577,
+      "grad_norm": 12.679130554199219,
+      "learning_rate": 7.900000000000001e-05,
+      "loss": 42.5315,
+      "step": 79
+    },
+    {
+      "epoch": 0.5936920222634509,
+      "grad_norm": 13.142966270446777,
+      "learning_rate": 8e-05,
+      "loss": 42.4409,
+      "step": 80
+    },
+    {
+      "epoch": 0.601113172541744,
+      "grad_norm": 12.649979591369629,
+      "learning_rate": 8.1e-05,
+      "loss": 42.4006,
+      "step": 81
+    },
+    {
+      "epoch": 0.608534322820037,
+      "grad_norm": 12.748927116394043,
+      "learning_rate": 8.2e-05,
+      "loss": 42.3853,
+      "step": 82
+    },
+    {
+      "epoch": 0.6159554730983302,
+      "grad_norm": 12.927495956420898,
+      "learning_rate": 8.3e-05,
+      "loss": 42.3356,
+      "step": 83
+    },
+    {
+      "epoch": 0.6233766233766234,
+      "grad_norm": 13.719474792480469,
+      "learning_rate": 8.4e-05,
+      "loss": 42.2403,
+      "step": 84
+    },
+    {
+      "epoch": 0.6307977736549165,
+      "grad_norm": 13.967941284179688,
+      "learning_rate": 8.5e-05,
+      "loss": 42.2092,
+      "step": 85
+    },
+    {
+      "epoch": 0.6382189239332097,
+      "grad_norm": 14.627005577087402,
+      "learning_rate": 8.6e-05,
+      "loss": 42.1375,
+      "step": 86
+    },
+    {
+      "epoch": 0.6456400742115028,
+      "grad_norm": 13.799325942993164,
+      "learning_rate": 8.7e-05,
+      "loss": 42.2202,
+      "step": 87
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 11.583959579467773,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 42.372,
+      "step": 88
+    },
+    {
+      "epoch": 0.660482374768089,
+      "grad_norm": 11.129148483276367,
+      "learning_rate": 8.900000000000001e-05,
+      "loss": 42.4314,
+      "step": 89
+    },
+    {
+      "epoch": 0.6679035250463822,
+      "grad_norm": 12.25344467163086,
+      "learning_rate": 9e-05,
+      "loss": 42.3057,
+      "step": 90
+    },
+    {
+      "epoch": 0.6753246753246753,
+      "grad_norm": 11.810912132263184,
+      "learning_rate": 9.1e-05,
+      "loss": 42.2905,
+      "step": 91
+    },
+    {
+      "epoch": 0.6827458256029685,
+      "grad_norm": 13.263050079345703,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 42.0628,
+      "step": 92
+    },
+    {
+      "epoch": 0.6901669758812616,
+      "grad_norm": 14.614550590515137,
+      "learning_rate": 9.300000000000001e-05,
+      "loss": 41.9321,
+      "step": 93
+    },
+    {
+      "epoch": 0.6975881261595547,
+      "grad_norm": 13.00090217590332,
+      "learning_rate": 9.4e-05,
+      "loss": 42.046,
+      "step": 94
+    },
+    {
+      "epoch": 0.7050092764378478,
+      "grad_norm": 13.673983573913574,
+      "learning_rate": 9.5e-05,
+      "loss": 41.99,
+      "step": 95
+    },
+    {
+      "epoch": 0.712430426716141,
+      "grad_norm": 13.868181228637695,
+      "learning_rate": 9.6e-05,
+      "loss": 41.9511,
+      "step": 96
+    },
+    {
+      "epoch": 0.7198515769944341,
+      "grad_norm": 13.319523811340332,
+      "learning_rate": 9.7e-05,
+      "loss": 41.9862,
+      "step": 97
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 13.251386642456055,
+      "learning_rate": 9.8e-05,
+      "loss": 41.9663,
+      "step": 98
+    },
+    {
+      "epoch": 0.7346938775510204,
+      "grad_norm": 13.171501159667969,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 41.969,
+      "step": 99
+    },
+    {
+      "epoch": 0.7421150278293135,
+      "grad_norm": 12.625286102294922,
+      "learning_rate": 0.0001,
+      "loss": 42.0612,
+      "step": 100
+    },
+    {
+      "epoch": 0.7495361781076066,
+      "grad_norm": 12.151773452758789,
+      "learning_rate": 9.978670881475172e-05,
+      "loss": 41.9509,
+      "step": 101
+    },
+    {
+      "epoch": 0.7569573283858998,
+      "grad_norm": 12.701147079467773,
+      "learning_rate": 9.91486549841951e-05,
+      "loss": 41.8777,
+      "step": 102
+    },
+    {
+      "epoch": 0.764378478664193,
+      "grad_norm": 12.010093688964844,
+      "learning_rate": 9.809128215864097e-05,
+      "loss": 41.8972,
+      "step": 103
+    },
+    {
+      "epoch": 0.7717996289424861,
+      "grad_norm": 13.549006462097168,
+      "learning_rate": 9.662361147021779e-05,
+      "loss": 41.7451,
+      "step": 104
+    },
+    {
+      "epoch": 0.7792207792207793,
+      "grad_norm": 13.478095054626465,
+      "learning_rate": 9.475816456775313e-05,
+      "loss": 41.7225,
+      "step": 105
+    },
+    {
+      "epoch": 0.7866419294990723,
+      "grad_norm": 12.72982120513916,
+      "learning_rate": 9.251085678648072e-05,
+      "loss": 41.7639,
+      "step": 106
+    },
+    {
+      "epoch": 0.7940630797773655,
+      "grad_norm": 12.287882804870605,
+      "learning_rate": 8.9900861364012e-05,
+      "loss": 41.7809,
+      "step": 107
+    },
+    {
+      "epoch": 0.8014842300556586,
+      "grad_norm": 13.526124000549316,
+      "learning_rate": 8.695044586103296e-05,
+      "loss": 41.6962,
+      "step": 108
+    },
+    {
+      "epoch": 0.8089053803339518,
+      "grad_norm": 14.581989288330078,
+      "learning_rate": 8.368478218232787e-05,
+      "loss": 41.5843,
+      "step": 109
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 13.089498519897461,
+      "learning_rate": 8.013173181896283e-05,
+      "loss": 41.6794,
+      "step": 110
+    },
+    {
+      "epoch": 0.8237476808905381,
+      "grad_norm": 15.09366226196289,
+      "learning_rate": 7.63216081438678e-05,
+      "loss": 41.5077,
+      "step": 111
+    },
+    {
+      "epoch": 0.8311688311688312,
+      "grad_norm": 13.623456954956055,
+      "learning_rate": 7.228691778882693e-05,
+      "loss": 41.523,
+      "step": 112
+    },
+    {
+      "epoch": 0.8385899814471243,
+      "grad_norm": 11.332221984863281,
+      "learning_rate": 6.806208330935766e-05,
+      "loss": 41.7106,
+      "step": 113
+    },
+    {
+      "epoch": 0.8460111317254174,
+      "grad_norm": 12.92172908782959,
+      "learning_rate": 6.368314950360415e-05,
+      "loss": 41.5414,
+      "step": 114
+    },
+    {
+      "epoch": 0.8534322820037106,
+      "grad_norm": 12.6735258102417,
+      "learning_rate": 5.918747589082853e-05,
+      "loss": 41.556,
+      "step": 115
+    },
+    {
+      "epoch": 0.8608534322820037,
+      "grad_norm": 13.531462669372559,
+      "learning_rate": 5.4613417973165106e-05,
+      "loss": 41.4722,
+      "step": 116
+    },
+    {
+      "epoch": 0.8682745825602969,
+      "grad_norm": 13.281898498535156,
+      "learning_rate": 5e-05,
+      "loss": 41.4847,
+      "step": 117
+    },
+    {
+      "epoch": 0.87569573283859,
+      "grad_norm": 14.396486282348633,
+      "learning_rate": 4.5386582026834906e-05,
+      "loss": 41.3873,
+      "step": 118
+    },
+    {
+      "epoch": 0.8831168831168831,
+      "grad_norm": 13.645459175109863,
+      "learning_rate": 4.0812524109171476e-05,
+      "loss": 41.4531,
+      "step": 119
+    },
+    {
+      "epoch": 0.8905380333951762,
+      "grad_norm": 14.890944480895996,
+      "learning_rate": 3.631685049639586e-05,
+      "loss": 41.3287,
+      "step": 120
+    },
+    {
+      "epoch": 0.8979591836734694,
+      "grad_norm": 13.579365730285645,
+      "learning_rate": 3.1937916690642356e-05,
+      "loss": 41.4408,
+      "step": 121
+    },
+    {
+      "epoch": 0.9053803339517625,
+      "grad_norm": 14.764871597290039,
+      "learning_rate": 2.771308221117309e-05,
+      "loss": 41.3545,
+      "step": 122
+    },
+    {
+      "epoch": 0.9128014842300557,
+      "grad_norm": 14.959582328796387,
+      "learning_rate": 2.3678391856132204e-05,
+      "loss": 41.3221,
+      "step": 123
+    },
+    {
+      "epoch": 0.9202226345083488,
+      "grad_norm": 15.105020523071289,
+      "learning_rate": 1.9868268181037185e-05,
+      "loss": 41.3208,
+      "step": 124
+    },
+    {
+      "epoch": 0.9276437847866419,
+      "grad_norm": 13.1837158203125,
+      "learning_rate": 1.631521781767214e-05,
+      "loss": 41.5126,
+      "step": 125
+    },
+    {
+      "epoch": 0.935064935064935,
+      "grad_norm": 11.447542190551758,
+      "learning_rate": 1.3049554138967051e-05,
+      "loss": 41.6001,
+      "step": 126
+    },
+    {
+      "epoch": 0.9424860853432282,
+      "grad_norm": 12.786081314086914,
+      "learning_rate": 1.0099138635988026e-05,
+      "loss": 41.5017,
+      "step": 127
+    },
+    {
+      "epoch": 0.9499072356215214,
+      "grad_norm": 12.717354774475098,
+      "learning_rate": 7.489143213519301e-06,
+      "loss": 41.5107,
+      "step": 128
+    },
+    {
+      "epoch": 0.9573283858998145,
+      "grad_norm": 12.408467292785645,
+      "learning_rate": 5.241835432246889e-06,
+      "loss": 41.5232,
+      "step": 129
+    },
+    {
+      "epoch": 0.9647495361781077,
+      "grad_norm": 12.033279418945312,
+      "learning_rate": 3.376388529782215e-06,
+      "loss": 41.5588,
+      "step": 130
+    },
+    {
+      "epoch": 0.9721706864564007,
+      "grad_norm": 13.827380180358887,
+      "learning_rate": 1.908717841359048e-06,
+      "loss": 41.3942,
+      "step": 131
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 13.951433181762695,
+      "learning_rate": 8.513450158049108e-07,
+      "loss": 41.3887,
+      "step": 132
+    },
+    {
+      "epoch": 0.987012987012987,
+      "grad_norm": 14.515254020690918,
+      "learning_rate": 2.1329118524827662e-07,
+      "loss": 41.3521,
+      "step": 133
+    },
+    {
+      "epoch": 0.9944341372912802,
+      "grad_norm": 14.542389869689941,
+      "learning_rate": 0.0,
+      "loss": 41.3494,
+      "step": 134
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 134,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 239,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 225116669607936.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5587cfd12cb5e803d97e9fad702405dc649e9d289d3ffd7d41cc5d5e1f0db8fe
+size 6776

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,124 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "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": true,
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5587cfd12cb5e803d97e9fad702405dc649e9d289d3ffd7d41cc5d5e1f0db8fe
+size 6776