Upload folder using huggingface_hub

README.md

@@ -0,0 +1,167 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: tiiuae/falcon-7b
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 96ae7c9d-e269-44ae-ac8f-8e892f5e553e
+  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: tiiuae/falcon-7b
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 230b0e535b611494_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/230b0e535b611494_train_data.json
+  type:
+    field_input: background
+    field_instruction: abstract
+    field_output: full_description
+    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: sn5601/96ae7c9d-e269-44ae-ac8f-8e892f5e553e
+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/230b0e535b611494_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
+special_tokens:
+  pad_token: <|endoftext|>
+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: 96ae7c9d-e269-44ae-ac8f-8e892f5e553e
+wandb_project: god
+wandb_run: z7u7
+wandb_runid: 96ae7c9d-e269-44ae-ac8f-8e892f5e553e
+warmup_steps: 200
+weight_decay: 0.1
+xformers_attention: true
+
+```
+
+</details><br>
+
+# 96ae7c9d-e269-44ae-ac8f-8e892f5e553e
+
+This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0451
+
+## 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
+- gradient_accumulation_steps: 4
+- total_train_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: 200
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 5.0888        | 0.9991 | 555  | 1.0451          |
+
+
+### 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": "tiiuae/falcon-7b",
+  "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": [
+    "dense_4h_to_h",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "dense_h_to_4h",
+    "dense",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "query_key_value",
+    "k_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:f13b41d82afd85c6e28f2ba34f01310f93b37416a50e339d26918a60a824c80e
+size 852128398

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79fb06849c08c453ccb6f79df8173014311915d931dc6fc6b2e66f3e2cdc8975
+size 852070064

config.json

@@ -0,0 +1,36 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "tiiuae/falcon-7b",
+  "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": 4544,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 71,
+  "num_hidden_layers": 32,
+  "num_kv_heads": 71,
+  "parallel_attn": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 65024
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: tiiuae/falcon-7b
+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": "tiiuae/falcon-7b",
+  "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": [
+    "dense_4h_to_h",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "dense_h_to_4h",
+    "dense",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "query_key_value",
+    "k_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 sha256:79fb06849c08c453ccb6f79df8173014311915d931dc6fc6b2e66f3e2cdc8975
+size 852070064

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fba6a204b403b8bd399fa971dcc79afb3d8609fcda4db2d9c57b94397e376ee2
+size 1704283770

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7e1b92f1136974d6226ccf7e352544631adbaec6bd532d7fc3ed4f3404ee2b
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fa5404a9d5a7f82472a09215ed58ac37185a39533d448975bd7ab0b239729ef
+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": false,
+  "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 +1,3918 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9990999099909991,
+  "eval_steps": 500,
+  "global_step": 555,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0018001800180018,
+      "grad_norm": 28.85651397705078,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 14.6669,
+      "step": 1
+    },
+    {
+      "epoch": 0.0036003600360036,
+      "grad_norm": 20.232847213745117,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 12.6879,
+      "step": 2
+    },
+    {
+      "epoch": 0.0054005400540054005,
+      "grad_norm": 20.170488357543945,
+      "learning_rate": 1.5e-06,
+      "loss": 9.9005,
+      "step": 3
+    },
+    {
+      "epoch": 0.0072007200720072,
+      "grad_norm": 18.635835647583008,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 9.5553,
+      "step": 4
+    },
+    {
+      "epoch": 0.009000900090009001,
+      "grad_norm": 17.15140724182129,
+      "learning_rate": 2.5e-06,
+      "loss": 8.7361,
+      "step": 5
+    },
+    {
+      "epoch": 0.010801080108010801,
+      "grad_norm": 14.188899993896484,
+      "learning_rate": 3e-06,
+      "loss": 8.5991,
+      "step": 6
+    },
+    {
+      "epoch": 0.012601260126012601,
+      "grad_norm": 16.08758544921875,
+      "learning_rate": 3.5000000000000004e-06,
+      "loss": 8.1545,
+      "step": 7
+    },
+    {
+      "epoch": 0.0144014401440144,
+      "grad_norm": 15.893816947937012,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 7.9389,
+      "step": 8
+    },
+    {
+      "epoch": 0.016201620162016202,
+      "grad_norm": 13.540562629699707,
+      "learning_rate": 4.5e-06,
+      "loss": 7.9457,
+      "step": 9
+    },
+    {
+      "epoch": 0.018001800180018002,
+      "grad_norm": 12.593961715698242,
+      "learning_rate": 5e-06,
+      "loss": 7.9617,
+      "step": 10
+    },
+    {
+      "epoch": 0.019801980198019802,
+      "grad_norm": 14.274964332580566,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 7.7485,
+      "step": 11
+    },
+    {
+      "epoch": 0.021602160216021602,
+      "grad_norm": 13.785284996032715,
+      "learning_rate": 6e-06,
+      "loss": 8.1615,
+      "step": 12
+    },
+    {
+      "epoch": 0.023402340234023402,
+      "grad_norm": 12.692747116088867,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 7.9709,
+      "step": 13
+    },
+    {
+      "epoch": 0.025202520252025202,
+      "grad_norm": 11.758572578430176,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 7.5982,
+      "step": 14
+    },
+    {
+      "epoch": 0.027002700270027002,
+      "grad_norm": 11.451689720153809,
+      "learning_rate": 7.5e-06,
+      "loss": 7.8241,
+      "step": 15
+    },
+    {
+      "epoch": 0.0288028802880288,
+      "grad_norm": 13.09874153137207,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 7.679,
+      "step": 16
+    },
+    {
+      "epoch": 0.0306030603060306,
+      "grad_norm": 11.725943565368652,
+      "learning_rate": 8.500000000000002e-06,
+      "loss": 7.8199,
+      "step": 17
+    },
+    {
+      "epoch": 0.032403240324032405,
+      "grad_norm": 12.393065452575684,
+      "learning_rate": 9e-06,
+      "loss": 7.8977,
+      "step": 18
+    },
+    {
+      "epoch": 0.034203420342034205,
+      "grad_norm": 11.96495246887207,
+      "learning_rate": 9.5e-06,
+      "loss": 7.4002,
+      "step": 19
+    },
+    {
+      "epoch": 0.036003600360036005,
+      "grad_norm": 10.148777961730957,
+      "learning_rate": 1e-05,
+      "loss": 7.6521,
+      "step": 20
+    },
+    {
+      "epoch": 0.037803780378037805,
+      "grad_norm": 9.769454956054688,
+      "learning_rate": 1.05e-05,
+      "loss": 7.5508,
+      "step": 21
+    },
+    {
+      "epoch": 0.039603960396039604,
+      "grad_norm": 8.934900283813477,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 7.263,
+      "step": 22
+    },
+    {
+      "epoch": 0.041404140414041404,
+      "grad_norm": 8.807928085327148,
+      "learning_rate": 1.1500000000000002e-05,
+      "loss": 7.4388,
+      "step": 23
+    },
+    {
+      "epoch": 0.043204320432043204,
+      "grad_norm": 10.690240859985352,
+      "learning_rate": 1.2e-05,
+      "loss": 6.5005,
+      "step": 24
+    },
+    {
+      "epoch": 0.045004500450045004,
+      "grad_norm": 8.784053802490234,
+      "learning_rate": 1.25e-05,
+      "loss": 6.7989,
+      "step": 25
+    },
+    {
+      "epoch": 0.046804680468046804,
+      "grad_norm": 8.401625633239746,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 6.8476,
+      "step": 26
+    },
+    {
+      "epoch": 0.048604860486048604,
+      "grad_norm": 7.974181175231934,
+      "learning_rate": 1.3500000000000001e-05,
+      "loss": 6.8067,
+      "step": 27
+    },
+    {
+      "epoch": 0.050405040504050404,
+      "grad_norm": 6.8001909255981445,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 6.8886,
+      "step": 28
+    },
+    {
+      "epoch": 0.052205220522052204,
+      "grad_norm": 7.849862098693848,
+      "learning_rate": 1.45e-05,
+      "loss": 6.7455,
+      "step": 29
+    },
+    {
+      "epoch": 0.054005400540054004,
+      "grad_norm": 7.1335625648498535,
+      "learning_rate": 1.5e-05,
+      "loss": 6.1861,
+      "step": 30
+    },
+    {
+      "epoch": 0.0558055805580558,
+      "grad_norm": 6.963135719299316,
+      "learning_rate": 1.55e-05,
+      "loss": 6.2953,
+      "step": 31
+    },
+    {
+      "epoch": 0.0576057605760576,
+      "grad_norm": 6.415379524230957,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 6.4054,
+      "step": 32
+    },
+    {
+      "epoch": 0.0594059405940594,
+      "grad_norm": 6.006982326507568,
+      "learning_rate": 1.65e-05,
+      "loss": 6.6365,
+      "step": 33
+    },
+    {
+      "epoch": 0.0612061206120612,
+      "grad_norm": 5.94774866104126,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 6.3694,
+      "step": 34
+    },
+    {
+      "epoch": 0.063006300630063,
+      "grad_norm": 5.748636722564697,
+      "learning_rate": 1.75e-05,
+      "loss": 6.0299,
+      "step": 35
+    },
+    {
+      "epoch": 0.06480648064806481,
+      "grad_norm": 5.941126346588135,
+      "learning_rate": 1.8e-05,
+      "loss": 6.1121,
+      "step": 36
+    },
+    {
+      "epoch": 0.0666066606660666,
+      "grad_norm": 5.799063682556152,
+      "learning_rate": 1.85e-05,
+      "loss": 6.1198,
+      "step": 37
+    },
+    {
+      "epoch": 0.06840684068406841,
+      "grad_norm": 6.232558250427246,
+      "learning_rate": 1.9e-05,
+      "loss": 5.8275,
+      "step": 38
+    },
+    {
+      "epoch": 0.0702070207020702,
+      "grad_norm": 5.436257362365723,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 6.6235,
+      "step": 39
+    },
+    {
+      "epoch": 0.07200720072007201,
+      "grad_norm": 5.369800090789795,
+      "learning_rate": 2e-05,
+      "loss": 6.3276,
+      "step": 40
+    },
+    {
+      "epoch": 0.0738073807380738,
+      "grad_norm": 5.262800693511963,
+      "learning_rate": 2.05e-05,
+      "loss": 5.5985,
+      "step": 41
+    },
+    {
+      "epoch": 0.07560756075607561,
+      "grad_norm": 5.9995903968811035,
+      "learning_rate": 2.1e-05,
+      "loss": 7.043,
+      "step": 42
+    },
+    {
+      "epoch": 0.0774077407740774,
+      "grad_norm": 5.5932183265686035,
+      "learning_rate": 2.15e-05,
+      "loss": 5.9072,
+      "step": 43
+    },
+    {
+      "epoch": 0.07920792079207921,
+      "grad_norm": 5.312334060668945,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 7.0407,
+      "step": 44
+    },
+    {
+      "epoch": 0.081008100810081,
+      "grad_norm": 5.7829155921936035,
+      "learning_rate": 2.25e-05,
+      "loss": 6.006,
+      "step": 45
+    },
+    {
+      "epoch": 0.08280828082808281,
+      "grad_norm": 5.04926872253418,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 6.7709,
+      "step": 46
+    },
+    {
+      "epoch": 0.0846084608460846,
+      "grad_norm": 5.008914470672607,
+      "learning_rate": 2.35e-05,
+      "loss": 7.0494,
+      "step": 47
+    },
+    {
+      "epoch": 0.08640864086408641,
+      "grad_norm": 4.904027938842773,
+      "learning_rate": 2.4e-05,
+      "loss": 6.2418,
+      "step": 48
+    },
+    {
+      "epoch": 0.08820882088208822,
+      "grad_norm": 5.208195686340332,
+      "learning_rate": 2.45e-05,
+      "loss": 6.1476,
+      "step": 49
+    },
+    {
+      "epoch": 0.09000900090009001,
+      "grad_norm": 5.478446006774902,
+      "learning_rate": 2.5e-05,
+      "loss": 6.1826,
+      "step": 50
+    },
+    {
+      "epoch": 0.09180918091809182,
+      "grad_norm": 18.321847915649414,
+      "learning_rate": 2.5500000000000003e-05,
+      "loss": 11.8766,
+      "step": 51
+    },
+    {
+      "epoch": 0.09360936093609361,
+      "grad_norm": 22.275039672851562,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 9.0741,
+      "step": 52
+    },
+    {
+      "epoch": 0.09540954095409541,
+      "grad_norm": 18.914152145385742,
+      "learning_rate": 2.6500000000000004e-05,
+      "loss": 6.9466,
+      "step": 53
+    },
+    {
+      "epoch": 0.09720972097209721,
+      "grad_norm": 10.226181030273438,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 5.7314,
+      "step": 54
+    },
+    {
+      "epoch": 0.09900990099009901,
+      "grad_norm": 7.28556489944458,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 4.9557,
+      "step": 55
+    },
+    {
+      "epoch": 0.10081008100810081,
+      "grad_norm": 6.028027057647705,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 5.4561,
+      "step": 56
+    },
+    {
+      "epoch": 0.10261026102610261,
+      "grad_norm": 6.356996536254883,
+      "learning_rate": 2.8499999999999998e-05,
+      "loss": 5.1208,
+      "step": 57
+    },
+    {
+      "epoch": 0.10441044104410441,
+      "grad_norm": 5.628063201904297,
+      "learning_rate": 2.9e-05,
+      "loss": 5.31,
+      "step": 58
+    },
+    {
+      "epoch": 0.10621062106210621,
+      "grad_norm": 5.183619022369385,
+      "learning_rate": 2.95e-05,
+      "loss": 4.8533,
+      "step": 59
+    },
+    {
+      "epoch": 0.10801080108010801,
+      "grad_norm": 5.032276630401611,
+      "learning_rate": 3e-05,
+      "loss": 4.5937,
+      "step": 60
+    },
+    {
+      "epoch": 0.10981098109810981,
+      "grad_norm": 4.725021839141846,
+      "learning_rate": 3.05e-05,
+      "loss": 4.8969,
+      "step": 61
+    },
+    {
+      "epoch": 0.1116111611161116,
+      "grad_norm": 4.868443965911865,
+      "learning_rate": 3.1e-05,
+      "loss": 5.03,
+      "step": 62
+    },
+    {
+      "epoch": 0.11341134113411341,
+      "grad_norm": 4.929288864135742,
+      "learning_rate": 3.15e-05,
+      "loss": 4.9148,
+      "step": 63
+    },
+    {
+      "epoch": 0.1152115211521152,
+      "grad_norm": 5.14013671875,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 5.2505,
+      "step": 64
+    },
+    {
+      "epoch": 0.11701170117011701,
+      "grad_norm": 5.411927223205566,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 4.91,
+      "step": 65
+    },
+    {
+      "epoch": 0.1188118811881188,
+      "grad_norm": 4.524367809295654,
+      "learning_rate": 3.3e-05,
+      "loss": 5.1703,
+      "step": 66
+    },
+    {
+      "epoch": 0.12061206120612061,
+      "grad_norm": 4.979662895202637,
+      "learning_rate": 3.35e-05,
+      "loss": 5.1811,
+      "step": 67
+    },
+    {
+      "epoch": 0.1224122412241224,
+      "grad_norm": 4.6250457763671875,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 4.8259,
+      "step": 68
+    },
+    {
+      "epoch": 0.12421242124212421,
+      "grad_norm": 4.706791400909424,
+      "learning_rate": 3.45e-05,
+      "loss": 4.4952,
+      "step": 69
+    },
+    {
+      "epoch": 0.126012601260126,
+      "grad_norm": 4.518699645996094,
+      "learning_rate": 3.5e-05,
+      "loss": 4.7958,
+      "step": 70
+    },
+    {
+      "epoch": 0.1278127812781278,
+      "grad_norm": 3.9459586143493652,
+      "learning_rate": 3.55e-05,
+      "loss": 5.0545,
+      "step": 71
+    },
+    {
+      "epoch": 0.12961296129612962,
+      "grad_norm": 3.954882860183716,
+      "learning_rate": 3.6e-05,
+      "loss": 4.9021,
+      "step": 72
+    },
+    {
+      "epoch": 0.13141314131413143,
+      "grad_norm": 4.027074813842773,
+      "learning_rate": 3.65e-05,
+      "loss": 4.6918,
+      "step": 73
+    },
+    {
+      "epoch": 0.1332133213321332,
+      "grad_norm": 4.441482067108154,
+      "learning_rate": 3.7e-05,
+      "loss": 4.9625,
+      "step": 74
+    },
+    {
+      "epoch": 0.135013501350135,
+      "grad_norm": 4.631096839904785,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 4.7489,
+      "step": 75
+    },
+    {
+      "epoch": 0.13681368136813682,
+      "grad_norm": 4.464879989624023,
+      "learning_rate": 3.8e-05,
+      "loss": 4.4667,
+      "step": 76
+    },
+    {
+      "epoch": 0.13861386138613863,
+      "grad_norm": 4.17475700378418,
+      "learning_rate": 3.85e-05,
+      "loss": 5.517,
+      "step": 77
+    },
+    {
+      "epoch": 0.1404140414041404,
+      "grad_norm": 4.135541915893555,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 5.1446,
+      "step": 78
+    },
+    {
+      "epoch": 0.1422142214221422,
+      "grad_norm": 4.521326541900635,
+      "learning_rate": 3.9500000000000005e-05,
+      "loss": 5.0185,
+      "step": 79
+    },
+    {
+      "epoch": 0.14401440144014402,
+      "grad_norm": 4.14456844329834,
+      "learning_rate": 4e-05,
+      "loss": 4.5989,
+      "step": 80
+    },
+    {
+      "epoch": 0.14581458145814583,
+      "grad_norm": 4.918880462646484,
+      "learning_rate": 4.05e-05,
+      "loss": 5.1453,
+      "step": 81
+    },
+    {
+      "epoch": 0.1476147614761476,
+      "grad_norm": 3.9074041843414307,
+      "learning_rate": 4.1e-05,
+      "loss": 4.5343,
+      "step": 82
+    },
+    {
+      "epoch": 0.1494149414941494,
+      "grad_norm": 4.088869094848633,
+      "learning_rate": 4.15e-05,
+      "loss": 5.2312,
+      "step": 83
+    },
+    {
+      "epoch": 0.15121512151215122,
+      "grad_norm": 4.230950355529785,
+      "learning_rate": 4.2e-05,
+      "loss": 5.2262,
+      "step": 84
+    },
+    {
+      "epoch": 0.15301530153015303,
+      "grad_norm": 3.9280920028686523,
+      "learning_rate": 4.25e-05,
+      "loss": 5.0867,
+      "step": 85
+    },
+    {
+      "epoch": 0.1548154815481548,
+      "grad_norm": 4.369322776794434,
+      "learning_rate": 4.3e-05,
+      "loss": 5.6706,
+      "step": 86
+    },
+    {
+      "epoch": 0.1566156615661566,
+      "grad_norm": 4.20168924331665,
+      "learning_rate": 4.35e-05,
+      "loss": 5.2653,
+      "step": 87
+    },
+    {
+      "epoch": 0.15841584158415842,
+      "grad_norm": 4.246135711669922,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 5.3541,
+      "step": 88
+    },
+    {
+      "epoch": 0.16021602160216022,
+      "grad_norm": 4.878535270690918,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 5.2614,
+      "step": 89
+    },
+    {
+      "epoch": 0.162016201620162,
+      "grad_norm": 4.4837799072265625,
+      "learning_rate": 4.5e-05,
+      "loss": 5.7189,
+      "step": 90
+    },
+    {
+      "epoch": 0.1638163816381638,
+      "grad_norm": 4.485711574554443,
+      "learning_rate": 4.55e-05,
+      "loss": 6.1362,
+      "step": 91
+    },
+    {
+      "epoch": 0.16561656165616562,
+      "grad_norm": 4.198153495788574,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 5.5297,
+      "step": 92
+    },
+    {
+      "epoch": 0.16741674167416742,
+      "grad_norm": 5.264278411865234,
+      "learning_rate": 4.6500000000000005e-05,
+      "loss": 5.475,
+      "step": 93
+    },
+    {
+      "epoch": 0.1692169216921692,
+      "grad_norm": 4.983798503875732,
+      "learning_rate": 4.7e-05,
+      "loss": 5.8982,
+      "step": 94
+    },
+    {
+      "epoch": 0.171017101710171,
+      "grad_norm": 4.64500617980957,
+      "learning_rate": 4.75e-05,
+      "loss": 5.4172,
+      "step": 95
+    },
+    {
+      "epoch": 0.17281728172817282,
+      "grad_norm": 4.246720314025879,
+      "learning_rate": 4.8e-05,
+      "loss": 6.1043,
+      "step": 96
+    },
+    {
+      "epoch": 0.17461746174617462,
+      "grad_norm": 4.144988536834717,
+      "learning_rate": 4.85e-05,
+      "loss": 6.1926,
+      "step": 97
+    },
+    {
+      "epoch": 0.17641764176417643,
+      "grad_norm": 4.693668842315674,
+      "learning_rate": 4.9e-05,
+      "loss": 6.3127,
+      "step": 98
+    },
+    {
+      "epoch": 0.1782178217821782,
+      "grad_norm": 4.599040985107422,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 5.5763,
+      "step": 99
+    },
+    {
+      "epoch": 0.18001800180018002,
+      "grad_norm": 4.811699390411377,
+      "learning_rate": 5e-05,
+      "loss": 6.2599,
+      "step": 100
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 23.242341995239258,
+      "learning_rate": 5.05e-05,
+      "loss": 10.2299,
+      "step": 101
+    },
+    {
+      "epoch": 0.18361836183618363,
+      "grad_norm": 24.24691390991211,
+      "learning_rate": 5.1000000000000006e-05,
+      "loss": 6.5731,
+      "step": 102
+    },
+    {
+      "epoch": 0.1854185418541854,
+      "grad_norm": 13.8417387008667,
+      "learning_rate": 5.1500000000000005e-05,
+      "loss": 4.5894,
+      "step": 103
+    },
+    {
+      "epoch": 0.18721872187218722,
+      "grad_norm": 7.606777667999268,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 4.422,
+      "step": 104
+    },
+    {
+      "epoch": 0.18901890189018902,
+      "grad_norm": 7.0894598960876465,
+      "learning_rate": 5.25e-05,
+      "loss": 4.4822,
+      "step": 105
+    },
+    {
+      "epoch": 0.19081908190819083,
+      "grad_norm": 4.703729152679443,
+      "learning_rate": 5.300000000000001e-05,
+      "loss": 4.0663,
+      "step": 106
+    },
+    {
+      "epoch": 0.1926192619261926,
+      "grad_norm": 3.9182114601135254,
+      "learning_rate": 5.3500000000000006e-05,
+      "loss": 3.7222,
+      "step": 107
+    },
+    {
+      "epoch": 0.19441944194419442,
+      "grad_norm": 4.467214584350586,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 4.4871,
+      "step": 108
+    },
+    {
+      "epoch": 0.19621962196219622,
+      "grad_norm": 4.333056926727295,
+      "learning_rate": 5.45e-05,
+      "loss": 4.1119,
+      "step": 109
+    },
+    {
+      "epoch": 0.19801980198019803,
+      "grad_norm": 4.1896467208862305,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.8633,
+      "step": 110
+    },
+    {
+      "epoch": 0.1998199819981998,
+      "grad_norm": 4.409817218780518,
+      "learning_rate": 5.550000000000001e-05,
+      "loss": 4.1133,
+      "step": 111
+    },
+    {
+      "epoch": 0.20162016201620162,
+      "grad_norm": 4.587196350097656,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 4.085,
+      "step": 112
+    },
+    {
+      "epoch": 0.20342034203420342,
+      "grad_norm": 4.2752556800842285,
+      "learning_rate": 5.65e-05,
+      "loss": 4.3178,
+      "step": 113
+    },
+    {
+      "epoch": 0.20522052205220523,
+      "grad_norm": 4.687012672424316,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 4.4426,
+      "step": 114
+    },
+    {
+      "epoch": 0.207020702070207,
+      "grad_norm": 4.1435017585754395,
+      "learning_rate": 5.7499999999999995e-05,
+      "loss": 4.268,
+      "step": 115
+    },
+    {
+      "epoch": 0.20882088208820881,
+      "grad_norm": 4.161345481872559,
+      "learning_rate": 5.8e-05,
+      "loss": 4.4851,
+      "step": 116
+    },
+    {
+      "epoch": 0.21062106210621062,
+      "grad_norm": 3.927691698074341,
+      "learning_rate": 5.85e-05,
+      "loss": 4.0147,
+      "step": 117
+    },
+    {
+      "epoch": 0.21242124212421243,
+      "grad_norm": 4.2265944480896,
+      "learning_rate": 5.9e-05,
+      "loss": 4.3646,
+      "step": 118
+    },
+    {
+      "epoch": 0.21422142214221424,
+      "grad_norm": 4.2369704246521,
+      "learning_rate": 5.95e-05,
+      "loss": 4.3241,
+      "step": 119
+    },
+    {
+      "epoch": 0.21602160216021601,
+      "grad_norm": 4.384726047515869,
+      "learning_rate": 6e-05,
+      "loss": 4.4394,
+      "step": 120
+    },
+    {
+      "epoch": 0.21782178217821782,
+      "grad_norm": 4.316718578338623,
+      "learning_rate": 6.05e-05,
+      "loss": 4.0843,
+      "step": 121
+    },
+    {
+      "epoch": 0.21962196219621963,
+      "grad_norm": 3.7887487411499023,
+      "learning_rate": 6.1e-05,
+      "loss": 4.1607,
+      "step": 122
+    },
+    {
+      "epoch": 0.22142214221422143,
+      "grad_norm": 4.181461334228516,
+      "learning_rate": 6.15e-05,
+      "loss": 4.2074,
+      "step": 123
+    },
+    {
+      "epoch": 0.2232223222322232,
+      "grad_norm": 3.9978582859039307,
+      "learning_rate": 6.2e-05,
+      "loss": 4.4763,
+      "step": 124
+    },
+    {
+      "epoch": 0.22502250225022502,
+      "grad_norm": 4.156275749206543,
+      "learning_rate": 6.25e-05,
+      "loss": 4.2295,
+      "step": 125
+    },
+    {
+      "epoch": 0.22682268226822683,
+      "grad_norm": 3.867684841156006,
+      "learning_rate": 6.3e-05,
+      "loss": 4.4481,
+      "step": 126
+    },
+    {
+      "epoch": 0.22862286228622863,
+      "grad_norm": 4.037459373474121,
+      "learning_rate": 6.35e-05,
+      "loss": 4.157,
+      "step": 127
+    },
+    {
+      "epoch": 0.2304230423042304,
+      "grad_norm": 4.304506778717041,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 4.5553,
+      "step": 128
+    },
+    {
+      "epoch": 0.23222322232223222,
+      "grad_norm": 4.406405925750732,
+      "learning_rate": 6.450000000000001e-05,
+      "loss": 4.7441,
+      "step": 129
+    },
+    {
+      "epoch": 0.23402340234023403,
+      "grad_norm": 4.19051456451416,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 4.7459,
+      "step": 130
+    },
+    {
+      "epoch": 0.23582358235823583,
+      "grad_norm": 4.138574600219727,
+      "learning_rate": 6.55e-05,
+      "loss": 4.6568,
+      "step": 131
+    },
+    {
+      "epoch": 0.2376237623762376,
+      "grad_norm": 4.434947967529297,
+      "learning_rate": 6.6e-05,
+      "loss": 4.8297,
+      "step": 132
+    },
+    {
+      "epoch": 0.23942394239423942,
+      "grad_norm": 3.5757968425750732,
+      "learning_rate": 6.65e-05,
+      "loss": 4.2438,
+      "step": 133
+    },
+    {
+      "epoch": 0.24122412241224123,
+      "grad_norm": 4.133842945098877,
+      "learning_rate": 6.7e-05,
+      "loss": 4.5298,
+      "step": 134
+    },
+    {
+      "epoch": 0.24302430243024303,
+      "grad_norm": 4.089065074920654,
+      "learning_rate": 6.750000000000001e-05,
+      "loss": 5.4232,
+      "step": 135
+    },
+    {
+      "epoch": 0.2448244824482448,
+      "grad_norm": 4.211568832397461,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 5.3946,
+      "step": 136
+    },
+    {
+      "epoch": 0.24662466246624662,
+      "grad_norm": 4.204323768615723,
+      "learning_rate": 6.850000000000001e-05,
+      "loss": 4.9143,
+      "step": 137
+    },
+    {
+      "epoch": 0.24842484248424843,
+      "grad_norm": 4.3052873611450195,
+      "learning_rate": 6.9e-05,
+      "loss": 5.5809,
+      "step": 138
+    },
+    {
+      "epoch": 0.2502250225022502,
+      "grad_norm": 3.8890812397003174,
+      "learning_rate": 6.95e-05,
+      "loss": 5.0493,
+      "step": 139
+    },
+    {
+      "epoch": 0.252025202520252,
+      "grad_norm": 4.273584842681885,
+      "learning_rate": 7e-05,
+      "loss": 5.45,
+      "step": 140
+    },
+    {
+      "epoch": 0.2538253825382538,
+      "grad_norm": 4.8961358070373535,
+      "learning_rate": 7.05e-05,
+      "loss": 5.5538,
+      "step": 141
+    },
+    {
+      "epoch": 0.2556255625562556,
+      "grad_norm": 4.320993423461914,
+      "learning_rate": 7.1e-05,
+      "loss": 5.3233,
+      "step": 142
+    },
+    {
+      "epoch": 0.25742574257425743,
+      "grad_norm": 3.967057704925537,
+      "learning_rate": 7.15e-05,
+      "loss": 5.1942,
+      "step": 143
+    },
+    {
+      "epoch": 0.25922592259225924,
+      "grad_norm": 4.173534870147705,
+      "learning_rate": 7.2e-05,
+      "loss": 5.1138,
+      "step": 144
+    },
+    {
+      "epoch": 0.26102610261026105,
+      "grad_norm": 4.54023551940918,
+      "learning_rate": 7.25e-05,
+      "loss": 5.6945,
+      "step": 145
+    },
+    {
+      "epoch": 0.26282628262826285,
+      "grad_norm": 4.46029806137085,
+      "learning_rate": 7.3e-05,
+      "loss": 5.5752,
+      "step": 146
+    },
+    {
+      "epoch": 0.2646264626462646,
+      "grad_norm": 4.0620574951171875,
+      "learning_rate": 7.35e-05,
+      "loss": 5.2059,
+      "step": 147
+    },
+    {
+      "epoch": 0.2664266426642664,
+      "grad_norm": 4.501194477081299,
+      "learning_rate": 7.4e-05,
+      "loss": 5.6742,
+      "step": 148
+    },
+    {
+      "epoch": 0.2682268226822682,
+      "grad_norm": 4.779675483703613,
+      "learning_rate": 7.450000000000001e-05,
+      "loss": 6.3616,
+      "step": 149
+    },
+    {
+      "epoch": 0.27002700270027,
+      "grad_norm": 5.094762802124023,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 5.8473,
+      "step": 150
+    },
+    {
+      "epoch": 0.27182718271827183,
+      "grad_norm": 30.64379119873047,
+      "learning_rate": 7.55e-05,
+      "loss": 6.9989,
+      "step": 151
+    },
+    {
+      "epoch": 0.27362736273627364,
+      "grad_norm": 11.478928565979004,
+      "learning_rate": 7.6e-05,
+      "loss": 3.2922,
+      "step": 152
+    },
+    {
+      "epoch": 0.27542754275427545,
+      "grad_norm": 5.4645466804504395,
+      "learning_rate": 7.65e-05,
+      "loss": 3.4407,
+      "step": 153
+    },
+    {
+      "epoch": 0.27722772277227725,
+      "grad_norm": 5.904770374298096,
+      "learning_rate": 7.7e-05,
+      "loss": 3.5843,
+      "step": 154
+    },
+    {
+      "epoch": 0.279027902790279,
+      "grad_norm": 4.119198322296143,
+      "learning_rate": 7.75e-05,
+      "loss": 3.1653,
+      "step": 155
+    },
+    {
+      "epoch": 0.2808280828082808,
+      "grad_norm": 4.040031909942627,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 3.4589,
+      "step": 156
+    },
+    {
+      "epoch": 0.2826282628262826,
+      "grad_norm": 4.188577175140381,
+      "learning_rate": 7.850000000000001e-05,
+      "loss": 3.7084,
+      "step": 157
+    },
+    {
+      "epoch": 0.2844284428442844,
+      "grad_norm": 4.088983058929443,
+      "learning_rate": 7.900000000000001e-05,
+      "loss": 3.8008,
+      "step": 158
+    },
+    {
+      "epoch": 0.28622862286228623,
+      "grad_norm": 3.6383821964263916,
+      "learning_rate": 7.950000000000001e-05,
+      "loss": 3.9436,
+      "step": 159
+    },
+    {
+      "epoch": 0.28802880288028804,
+      "grad_norm": 4.231886863708496,
+      "learning_rate": 8e-05,
+      "loss": 4.5073,
+      "step": 160
+    },
+    {
+      "epoch": 0.28982898289828984,
+      "grad_norm": 4.518820762634277,
+      "learning_rate": 8.05e-05,
+      "loss": 3.5422,
+      "step": 161
+    },
+    {
+      "epoch": 0.29162916291629165,
+      "grad_norm": 4.026054382324219,
+      "learning_rate": 8.1e-05,
+      "loss": 3.7513,
+      "step": 162
+    },
+    {
+      "epoch": 0.2934293429342934,
+      "grad_norm": 3.7655909061431885,
+      "learning_rate": 8.15e-05,
+      "loss": 4.2454,
+      "step": 163
+    },
+    {
+      "epoch": 0.2952295229522952,
+      "grad_norm": 3.6118693351745605,
+      "learning_rate": 8.2e-05,
+      "loss": 3.7299,
+      "step": 164
+    },
+    {
+      "epoch": 0.297029702970297,
+      "grad_norm": 4.284143447875977,
+      "learning_rate": 8.25e-05,
+      "loss": 4.07,
+      "step": 165
+    },
+    {
+      "epoch": 0.2988298829882988,
+      "grad_norm": 4.056666374206543,
+      "learning_rate": 8.3e-05,
+      "loss": 4.1954,
+      "step": 166
+    },
+    {
+      "epoch": 0.30063006300630063,
+      "grad_norm": 4.1431565284729,
+      "learning_rate": 8.35e-05,
+      "loss": 4.252,
+      "step": 167
+    },
+    {
+      "epoch": 0.30243024302430244,
+      "grad_norm": 4.241552829742432,
+      "learning_rate": 8.4e-05,
+      "loss": 4.1166,
+      "step": 168
+    },
+    {
+      "epoch": 0.30423042304230424,
+      "grad_norm": 4.314858913421631,
+      "learning_rate": 8.450000000000001e-05,
+      "loss": 4.0205,
+      "step": 169
+    },
+    {
+      "epoch": 0.30603060306030605,
+      "grad_norm": 4.8378400802612305,
+      "learning_rate": 8.5e-05,
+      "loss": 4.4915,
+      "step": 170
+    },
+    {
+      "epoch": 0.30783078307830786,
+      "grad_norm": 3.758328437805176,
+      "learning_rate": 8.55e-05,
+      "loss": 4.2785,
+      "step": 171
+    },
+    {
+      "epoch": 0.3096309630963096,
+      "grad_norm": 4.4342360496521,
+      "learning_rate": 8.6e-05,
+      "loss": 4.2285,
+      "step": 172
+    },
+    {
+      "epoch": 0.3114311431143114,
+      "grad_norm": 4.5404052734375,
+      "learning_rate": 8.65e-05,
+      "loss": 4.3089,
+      "step": 173
+    },
+    {
+      "epoch": 0.3132313231323132,
+      "grad_norm": 3.7609307765960693,
+      "learning_rate": 8.7e-05,
+      "loss": 4.3388,
+      "step": 174
+    },
+    {
+      "epoch": 0.31503150315031503,
+      "grad_norm": 4.27951717376709,
+      "learning_rate": 8.75e-05,
+      "loss": 4.3054,
+      "step": 175
+    },
+    {
+      "epoch": 0.31683168316831684,
+      "grad_norm": 4.713607311248779,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 4.5114,
+      "step": 176
+    },
+    {
+      "epoch": 0.31863186318631864,
+      "grad_norm": 3.725269079208374,
+      "learning_rate": 8.850000000000001e-05,
+      "loss": 4.4626,
+      "step": 177
+    },
+    {
+      "epoch": 0.32043204320432045,
+      "grad_norm": 4.011518478393555,
+      "learning_rate": 8.900000000000001e-05,
+      "loss": 4.4429,
+      "step": 178
+    },
+    {
+      "epoch": 0.32223222322232226,
+      "grad_norm": 4.707291603088379,
+      "learning_rate": 8.950000000000001e-05,
+      "loss": 4.3184,
+      "step": 179
+    },
+    {
+      "epoch": 0.324032403240324,
+      "grad_norm": 4.8839192390441895,
+      "learning_rate": 9e-05,
+      "loss": 4.9505,
+      "step": 180
+    },
+    {
+      "epoch": 0.3258325832583258,
+      "grad_norm": 4.054986953735352,
+      "learning_rate": 9.05e-05,
+      "loss": 4.754,
+      "step": 181
+    },
+    {
+      "epoch": 0.3276327632763276,
+      "grad_norm": 3.74249529838562,
+      "learning_rate": 9.1e-05,
+      "loss": 4.5569,
+      "step": 182
+    },
+    {
+      "epoch": 0.32943294329432943,
+      "grad_norm": 4.3617939949035645,
+      "learning_rate": 9.15e-05,
+      "loss": 4.1692,
+      "step": 183
+    },
+    {
+      "epoch": 0.33123312331233123,
+      "grad_norm": 4.2513346672058105,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 4.6149,
+      "step": 184
+    },
+    {
+      "epoch": 0.33303330333033304,
+      "grad_norm": 4.553803443908691,
+      "learning_rate": 9.250000000000001e-05,
+      "loss": 4.5845,
+      "step": 185
+    },
+    {
+      "epoch": 0.33483348334833485,
+      "grad_norm": 3.855337619781494,
+      "learning_rate": 9.300000000000001e-05,
+      "loss": 4.5672,
+      "step": 186
+    },
+    {
+      "epoch": 0.33663366336633666,
+      "grad_norm": 4.010441303253174,
+      "learning_rate": 9.350000000000001e-05,
+      "loss": 5.1355,
+      "step": 187
+    },
+    {
+      "epoch": 0.3384338433843384,
+      "grad_norm": 4.344321250915527,
+      "learning_rate": 9.4e-05,
+      "loss": 5.2234,
+      "step": 188
+    },
+    {
+      "epoch": 0.3402340234023402,
+      "grad_norm": 3.883000373840332,
+      "learning_rate": 9.449999999999999e-05,
+      "loss": 4.6074,
+      "step": 189
+    },
+    {
+      "epoch": 0.342034203420342,
+      "grad_norm": 4.245122909545898,
+      "learning_rate": 9.5e-05,
+      "loss": 4.7656,
+      "step": 190
+    },
+    {
+      "epoch": 0.3438343834383438,
+      "grad_norm": 4.1966023445129395,
+      "learning_rate": 9.55e-05,
+      "loss": 5.1034,
+      "step": 191
+    },
+    {
+      "epoch": 0.34563456345634563,
+      "grad_norm": 4.888998031616211,
+      "learning_rate": 9.6e-05,
+      "loss": 4.543,
+      "step": 192
+    },
+    {
+      "epoch": 0.34743474347434744,
+      "grad_norm": 4.0577311515808105,
+      "learning_rate": 9.65e-05,
+      "loss": 5.0657,
+      "step": 193
+    },
+    {
+      "epoch": 0.34923492349234925,
+      "grad_norm": 4.154134750366211,
+      "learning_rate": 9.7e-05,
+      "loss": 5.1474,
+      "step": 194
+    },
+    {
+      "epoch": 0.35103510351035105,
+      "grad_norm": 4.5482282638549805,
+      "learning_rate": 9.75e-05,
+      "loss": 5.611,
+      "step": 195
+    },
+    {
+      "epoch": 0.35283528352835286,
+      "grad_norm": 4.7754292488098145,
+      "learning_rate": 9.8e-05,
+      "loss": 5.8798,
+      "step": 196
+    },
+    {
+      "epoch": 0.3546354635463546,
+      "grad_norm": 4.595111846923828,
+      "learning_rate": 9.850000000000001e-05,
+      "loss": 5.5665,
+      "step": 197
+    },
+    {
+      "epoch": 0.3564356435643564,
+      "grad_norm": 4.434641361236572,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 5.017,
+      "step": 198
+    },
+    {
+      "epoch": 0.3582358235823582,
+      "grad_norm": 4.628114223480225,
+      "learning_rate": 9.95e-05,
+      "loss": 5.4085,
+      "step": 199
+    },
+    {
+      "epoch": 0.36003600360036003,
+      "grad_norm": 4.574793815612793,
+      "learning_rate": 0.0001,
+      "loss": 4.868,
+      "step": 200
+    },
+    {
+      "epoch": 0.36183618361836184,
+      "grad_norm": 48.827030181884766,
+      "learning_rate": 9.999804214640151e-05,
+      "loss": 5.6442,
+      "step": 201
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 7.539086818695068,
+      "learning_rate": 9.999216873893363e-05,
+      "loss": 2.9833,
+      "step": 202
+    },
+    {
+      "epoch": 0.36543654365436545,
+      "grad_norm": 4.620749473571777,
+      "learning_rate": 9.998238023756727e-05,
+      "loss": 2.9572,
+      "step": 203
+    },
+    {
+      "epoch": 0.36723672367236726,
+      "grad_norm": 3.8858468532562256,
+      "learning_rate": 9.996867740888052e-05,
+      "loss": 3.4909,
+      "step": 204
+    },
+    {
+      "epoch": 0.369036903690369,
+      "grad_norm": 4.157265663146973,
+      "learning_rate": 9.995106132599869e-05,
+      "loss": 3.794,
+      "step": 205
+    },
+    {
+      "epoch": 0.3708370837083708,
+      "grad_norm": 3.5816516876220703,
+      "learning_rate": 9.99295333685102e-05,
+      "loss": 3.6478,
+      "step": 206
+    },
+    {
+      "epoch": 0.3726372637263726,
+      "grad_norm": 4.691586494445801,
+      "learning_rate": 9.990409522235866e-05,
+      "loss": 3.6508,
+      "step": 207
+    },
+    {
+      "epoch": 0.37443744374437443,
+      "grad_norm": 4.206489562988281,
+      "learning_rate": 9.987474887971067e-05,
+      "loss": 4.0346,
+      "step": 208
+    },
+    {
+      "epoch": 0.37623762376237624,
+      "grad_norm": 4.957794189453125,
+      "learning_rate": 9.984149663879993e-05,
+      "loss": 3.9599,
+      "step": 209
+    },
+    {
+      "epoch": 0.37803780378037805,
+      "grad_norm": 3.705470561981201,
+      "learning_rate": 9.980434110374724e-05,
+      "loss": 3.7593,
+      "step": 210
+    },
+    {
+      "epoch": 0.37983798379837985,
+      "grad_norm": 3.760009288787842,
+      "learning_rate": 9.976328518435653e-05,
+      "loss": 3.6834,
+      "step": 211
+    },
+    {
+      "epoch": 0.38163816381638166,
+      "grad_norm": 4.849155902862549,
+      "learning_rate": 9.971833209588696e-05,
+      "loss": 3.7644,
+      "step": 212
+    },
+    {
+      "epoch": 0.38343834383438347,
+      "grad_norm": 4.008197784423828,
+      "learning_rate": 9.966948535880118e-05,
+      "loss": 3.9239,
+      "step": 213
+    },
+    {
+      "epoch": 0.3852385238523852,
+      "grad_norm": 4.340366840362549,
+      "learning_rate": 9.961674879848957e-05,
+      "loss": 3.8541,
+      "step": 214
+    },
+    {
+      "epoch": 0.387038703870387,
+      "grad_norm": 4.3433332443237305,
+      "learning_rate": 9.956012654497074e-05,
+      "loss": 3.6372,
+      "step": 215
+    },
+    {
+      "epoch": 0.38883888388838883,
+      "grad_norm": 3.838965654373169,
+      "learning_rate": 9.949962303256796e-05,
+      "loss": 4.1607,
+      "step": 216
+    },
+    {
+      "epoch": 0.39063906390639064,
+      "grad_norm": 3.958833932876587,
+      "learning_rate": 9.943524299956207e-05,
+      "loss": 4.0357,
+      "step": 217
+    },
+    {
+      "epoch": 0.39243924392439244,
+      "grad_norm": 4.2294840812683105,
+      "learning_rate": 9.936699148782019e-05,
+      "loss": 4.1384,
+      "step": 218
+    },
+    {
+      "epoch": 0.39423942394239425,
+      "grad_norm": 4.255922317504883,
+      "learning_rate": 9.929487384240103e-05,
+      "loss": 4.3947,
+      "step": 219
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 4.967748641967773,
+      "learning_rate": 9.921889571113628e-05,
+      "loss": 4.2571,
+      "step": 220
+    },
+    {
+      "epoch": 0.39783978397839787,
+      "grad_norm": 5.7947845458984375,
+      "learning_rate": 9.913906304418825e-05,
+      "loss": 4.3985,
+      "step": 221
+    },
+    {
+      "epoch": 0.3996399639963996,
+      "grad_norm": 4.166469097137451,
+      "learning_rate": 9.90553820935839e-05,
+      "loss": 4.3324,
+      "step": 222
+    },
+    {
+      "epoch": 0.4014401440144014,
+      "grad_norm": 3.7093265056610107,
+      "learning_rate": 9.896785941272523e-05,
+      "loss": 4.4313,
+      "step": 223
+    },
+    {
+      "epoch": 0.40324032403240323,
+      "grad_norm": 4.43189001083374,
+      "learning_rate": 9.887650185587612e-05,
+      "loss": 4.723,
+      "step": 224
+    },
+    {
+      "epoch": 0.40504050405040504,
+      "grad_norm": 4.146303653717041,
+      "learning_rate": 9.878131657762535e-05,
+      "loss": 4.555,
+      "step": 225
+    },
+    {
+      "epoch": 0.40684068406840684,
+      "grad_norm": 4.075449466705322,
+      "learning_rate": 9.868231103232655e-05,
+      "loss": 4.4108,
+      "step": 226
+    },
+    {
+      "epoch": 0.40864086408640865,
+      "grad_norm": 4.104311943054199,
+      "learning_rate": 9.857949297351422e-05,
+      "loss": 4.867,
+      "step": 227
+    },
+    {
+      "epoch": 0.41044104410441046,
+      "grad_norm": 3.903787612915039,
+      "learning_rate": 9.847287045329666e-05,
+      "loss": 4.3154,
+      "step": 228
+    },
+    {
+      "epoch": 0.41224122412241226,
+      "grad_norm": 4.177591800689697,
+      "learning_rate": 9.83624518217252e-05,
+      "loss": 4.3139,
+      "step": 229
+    },
+    {
+      "epoch": 0.414041404140414,
+      "grad_norm": 3.577852725982666,
+      "learning_rate": 9.824824572614051e-05,
+      "loss": 4.6006,
+      "step": 230
+    },
+    {
+      "epoch": 0.4158415841584158,
+      "grad_norm": 4.238375186920166,
+      "learning_rate": 9.813026111049515e-05,
+      "loss": 4.1235,
+      "step": 231
+    },
+    {
+      "epoch": 0.41764176417641763,
+      "grad_norm": 4.316523551940918,
+      "learning_rate": 9.800850721465334e-05,
+      "loss": 4.9625,
+      "step": 232
+    },
+    {
+      "epoch": 0.41944194419441944,
+      "grad_norm": 3.8222544193267822,
+      "learning_rate": 9.788299357366716e-05,
+      "loss": 4.843,
+      "step": 233
+    },
+    {
+      "epoch": 0.42124212421242124,
+      "grad_norm": 4.11749792098999,
+      "learning_rate": 9.775373001702998e-05,
+      "loss": 4.5882,
+      "step": 234
+    },
+    {
+      "epoch": 0.42304230423042305,
+      "grad_norm": 3.6795084476470947,
+      "learning_rate": 9.762072666790658e-05,
+      "loss": 5.2389,
+      "step": 235
+    },
+    {
+      "epoch": 0.42484248424842486,
+      "grad_norm": 3.996441602706909,
+      "learning_rate": 9.748399394234038e-05,
+      "loss": 4.6672,
+      "step": 236
+    },
+    {
+      "epoch": 0.42664266426642666,
+      "grad_norm": 4.023096561431885,
+      "learning_rate": 9.734354254843773e-05,
+      "loss": 5.3549,
+      "step": 237
+    },
+    {
+      "epoch": 0.42844284428442847,
+      "grad_norm": 4.174993515014648,
+      "learning_rate": 9.71993834855293e-05,
+      "loss": 5.1587,
+      "step": 238
+    },
+    {
+      "epoch": 0.4302430243024302,
+      "grad_norm": 4.372593879699707,
+      "learning_rate": 9.705152804330872e-05,
+      "loss": 5.6517,
+      "step": 239
+    },
+    {
+      "epoch": 0.43204320432043203,
+      "grad_norm": 4.535490989685059,
+      "learning_rate": 9.689998780094837e-05,
+      "loss": 5.4977,
+      "step": 240
+    },
+    {
+      "epoch": 0.43384338433843384,
+      "grad_norm": 4.093436241149902,
+      "learning_rate": 9.67447746261926e-05,
+      "loss": 4.3227,
+      "step": 241
+    },
+    {
+      "epoch": 0.43564356435643564,
+      "grad_norm": 4.311260223388672,
+      "learning_rate": 9.658590067442829e-05,
+      "loss": 5.137,
+      "step": 242
+    },
+    {
+      "epoch": 0.43744374437443745,
+      "grad_norm": 4.544931411743164,
+      "learning_rate": 9.6423378387733e-05,
+      "loss": 5.3618,
+      "step": 243
+    },
+    {
+      "epoch": 0.43924392439243926,
+      "grad_norm": 4.6238298416137695,
+      "learning_rate": 9.625722049390046e-05,
+      "loss": 5.7622,
+      "step": 244
+    },
+    {
+      "epoch": 0.44104410441044106,
+      "grad_norm": 4.168641567230225,
+      "learning_rate": 9.608744000544392e-05,
+      "loss": 5.2432,
+      "step": 245
+    },
+    {
+      "epoch": 0.44284428442844287,
+      "grad_norm": 4.634570598602295,
+      "learning_rate": 9.591405021857695e-05,
+      "loss": 5.8623,
+      "step": 246
+    },
+    {
+      "epoch": 0.4446444644464446,
+      "grad_norm": 4.366397380828857,
+      "learning_rate": 9.573706471217232e-05,
+      "loss": 5.4993,
+      "step": 247
+    },
+    {
+      "epoch": 0.4464446444644464,
+      "grad_norm": 4.067739963531494,
+      "learning_rate": 9.55564973466984e-05,
+      "loss": 5.6379,
+      "step": 248
+    },
+    {
+      "epoch": 0.44824482448244823,
+      "grad_norm": 3.8812038898468018,
+      "learning_rate": 9.537236226313389e-05,
+      "loss": 5.4358,
+      "step": 249
+    },
+    {
+      "epoch": 0.45004500450045004,
+      "grad_norm": 5.2032318115234375,
+      "learning_rate": 9.51846738818602e-05,
+      "loss": 5.2139,
+      "step": 250
+    },
+    {
+      "epoch": 0.45184518451845185,
+      "grad_norm": 64.75902557373047,
+      "learning_rate": 9.499344690153225e-05,
+      "loss": 6.1023,
+      "step": 251
+    },
+    {
+      "epoch": 0.45364536453645365,
+      "grad_norm": 35.30427932739258,
+      "learning_rate": 9.479869629792728e-05,
+      "loss": 3.4732,
+      "step": 252
+    },
+    {
+      "epoch": 0.45544554455445546,
+      "grad_norm": 4.7051496505737305,
+      "learning_rate": 9.460043732277213e-05,
+      "loss": 2.73,
+      "step": 253
+    },
+    {
+      "epoch": 0.45724572457245727,
+      "grad_norm": 3.9896416664123535,
+      "learning_rate": 9.439868550254869e-05,
+      "loss": 3.2622,
+      "step": 254
+    },
+    {
+      "epoch": 0.459045904590459,
+      "grad_norm": 3.751338005065918,
+      "learning_rate": 9.419345663727805e-05,
+      "loss": 3.0939,
+      "step": 255
+    },
+    {
+      "epoch": 0.4608460846084608,
+      "grad_norm": 3.8281116485595703,
+      "learning_rate": 9.398476679928313e-05,
+      "loss": 3.9917,
+      "step": 256
+    },
+    {
+      "epoch": 0.46264626462646263,
+      "grad_norm": 3.47261905670166,
+      "learning_rate": 9.377263233192992e-05,
+      "loss": 3.471,
+      "step": 257
+    },
+    {
+      "epoch": 0.46444644464446444,
+      "grad_norm": 3.8381025791168213,
+      "learning_rate": 9.355706984834763e-05,
+      "loss": 3.7771,
+      "step": 258
+    },
+    {
+      "epoch": 0.46624662466246625,
+      "grad_norm": 4.145185470581055,
+      "learning_rate": 9.333809623012763e-05,
+      "loss": 3.7653,
+      "step": 259
+    },
+    {
+      "epoch": 0.46804680468046805,
+      "grad_norm": 3.826444387435913,
+      "learning_rate": 9.311572862600139e-05,
+      "loss": 3.7425,
+      "step": 260
+    },
+    {
+      "epoch": 0.46984698469846986,
+      "grad_norm": 3.433979034423828,
+      "learning_rate": 9.288998445049746e-05,
+      "loss": 3.4126,
+      "step": 261
+    },
+    {
+      "epoch": 0.47164716471647167,
+      "grad_norm": 4.036341667175293,
+      "learning_rate": 9.266088138257768e-05,
+      "loss": 3.6221,
+      "step": 262
+    },
+    {
+      "epoch": 0.4734473447344735,
+      "grad_norm": 3.754890203475952,
+      "learning_rate": 9.24284373642527e-05,
+      "loss": 4.0088,
+      "step": 263
+    },
+    {
+      "epoch": 0.4752475247524752,
+      "grad_norm": 3.838566780090332,
+      "learning_rate": 9.219267059917682e-05,
+      "loss": 3.6828,
+      "step": 264
+    },
+    {
+      "epoch": 0.47704770477047703,
+      "grad_norm": 3.6993019580841064,
+      "learning_rate": 9.195359955122244e-05,
+      "loss": 3.7106,
+      "step": 265
+    },
+    {
+      "epoch": 0.47884788478847884,
+      "grad_norm": 3.721072196960449,
+      "learning_rate": 9.171124294303399e-05,
+      "loss": 3.9501,
+      "step": 266
+    },
+    {
+      "epoch": 0.48064806480648065,
+      "grad_norm": 3.40067982673645,
+      "learning_rate": 9.14656197545618e-05,
+      "loss": 3.6647,
+      "step": 267
+    },
+    {
+      "epoch": 0.48244824482448245,
+      "grad_norm": 4.225182056427002,
+      "learning_rate": 9.121674922157558e-05,
+      "loss": 4.2479,
+      "step": 268
+    },
+    {
+      "epoch": 0.48424842484248426,
+      "grad_norm": 3.574556589126587,
+      "learning_rate": 9.096465083415808e-05,
+      "loss": 4.3452,
+      "step": 269
+    },
+    {
+      "epoch": 0.48604860486048607,
+      "grad_norm": 3.840705394744873,
+      "learning_rate": 9.070934433517873e-05,
+      "loss": 4.7066,
+      "step": 270
+    },
+    {
+      "epoch": 0.4878487848784879,
+      "grad_norm": 3.4904778003692627,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.7437,
+      "step": 271
+    },
+    {
+      "epoch": 0.4896489648964896,
+      "grad_norm": 3.8224945068359375,
+      "learning_rate": 9.018918722864867e-05,
+      "loss": 4.1212,
+      "step": 272
+    },
+    {
+      "epoch": 0.49144914491449143,
+      "grad_norm": 4.084190368652344,
+      "learning_rate": 8.992437735675651e-05,
+      "loss": 3.883,
+      "step": 273
+    },
+    {
+      "epoch": 0.49324932493249324,
+      "grad_norm": 4.186155796051025,
+      "learning_rate": 8.965644084142932e-05,
+      "loss": 4.6328,
+      "step": 274
+    },
+    {
+      "epoch": 0.49504950495049505,
+      "grad_norm": 4.2307047843933105,
+      "learning_rate": 8.938539866588592e-05,
+      "loss": 3.9238,
+      "step": 275
+    },
+    {
+      "epoch": 0.49684968496849685,
+      "grad_norm": 4.097965717315674,
+      "learning_rate": 8.911127205656226e-05,
+      "loss": 4.4123,
+      "step": 276
+    },
+    {
+      "epoch": 0.49864986498649866,
+      "grad_norm": 3.495042562484741,
+      "learning_rate": 8.88340824814491e-05,
+      "loss": 3.8635,
+      "step": 277
+    },
+    {
+      "epoch": 0.5004500450045004,
+      "grad_norm": 3.689110517501831,
+      "learning_rate": 8.855385164841072e-05,
+      "loss": 4.6177,
+      "step": 278
+    },
+    {
+      "epoch": 0.5022502250225023,
+      "grad_norm": 3.6329872608184814,
+      "learning_rate": 8.82706015034849e-05,
+      "loss": 4.2534,
+      "step": 279
+    },
+    {
+      "epoch": 0.504050405040504,
+      "grad_norm": 3.8967461585998535,
+      "learning_rate": 8.798435422916425e-05,
+      "loss": 3.7907,
+      "step": 280
+    },
+    {
+      "epoch": 0.5058505850585059,
+      "grad_norm": 4.086053848266602,
+      "learning_rate": 8.769513224265904e-05,
+      "loss": 4.5879,
+      "step": 281
+    },
+    {
+      "epoch": 0.5076507650765076,
+      "grad_norm": 4.173221111297607,
+      "learning_rate": 8.740295819414155e-05,
+      "loss": 4.1702,
+      "step": 282
+    },
+    {
+      "epoch": 0.5094509450945095,
+      "grad_norm": 3.921698570251465,
+      "learning_rate": 8.710785496497225e-05,
+      "loss": 4.2377,
+      "step": 283
+    },
+    {
+      "epoch": 0.5112511251125113,
+      "grad_norm": 3.830862045288086,
+      "learning_rate": 8.680984566590793e-05,
+      "loss": 4.3651,
+      "step": 284
+    },
+    {
+      "epoch": 0.513051305130513,
+      "grad_norm": 3.77140212059021,
+      "learning_rate": 8.650895363529173e-05,
+      "loss": 4.4687,
+      "step": 285
+    },
+    {
+      "epoch": 0.5148514851485149,
+      "grad_norm": 3.5552985668182373,
+      "learning_rate": 8.620520243722541e-05,
+      "loss": 4.8082,
+      "step": 286
+    },
+    {
+      "epoch": 0.5166516651665166,
+      "grad_norm": 3.6477136611938477,
+      "learning_rate": 8.589861585972407e-05,
+      "loss": 5.2562,
+      "step": 287
+    },
+    {
+      "epoch": 0.5184518451845185,
+      "grad_norm": 4.382421493530273,
+      "learning_rate": 8.558921791285304e-05,
+      "loss": 5.0799,
+      "step": 288
+    },
+    {
+      "epoch": 0.5202520252025202,
+      "grad_norm": 4.065561294555664,
+      "learning_rate": 8.527703282684766e-05,
+      "loss": 4.9109,
+      "step": 289
+    },
+    {
+      "epoch": 0.5220522052205221,
+      "grad_norm": 3.5327258110046387,
+      "learning_rate": 8.496208505021571e-05,
+      "loss": 4.2811,
+      "step": 290
+    },
+    {
+      "epoch": 0.5238523852385238,
+      "grad_norm": 4.304015636444092,
+      "learning_rate": 8.464439924782271e-05,
+      "loss": 5.0544,
+      "step": 291
+    },
+    {
+      "epoch": 0.5256525652565257,
+      "grad_norm": 4.300441265106201,
+      "learning_rate": 8.432400029896028e-05,
+      "loss": 5.1385,
+      "step": 292
+    },
+    {
+      "epoch": 0.5274527452745275,
+      "grad_norm": 3.970590114593506,
+      "learning_rate": 8.400091329539784e-05,
+      "loss": 5.5669,
+      "step": 293
+    },
+    {
+      "epoch": 0.5292529252925292,
+      "grad_norm": 4.322851657867432,
+      "learning_rate": 8.367516353941751e-05,
+      "loss": 5.1609,
+      "step": 294
+    },
+    {
+      "epoch": 0.5310531053105311,
+      "grad_norm": 4.039634704589844,
+      "learning_rate": 8.334677654183254e-05,
+      "loss": 5.3988,
+      "step": 295
+    },
+    {
+      "epoch": 0.5328532853285328,
+      "grad_norm": 4.090119361877441,
+      "learning_rate": 8.301577801998954e-05,
+      "loss": 5.3261,
+      "step": 296
+    },
+    {
+      "epoch": 0.5346534653465347,
+      "grad_norm": 4.731489181518555,
+      "learning_rate": 8.26821938957544e-05,
+      "loss": 5.4674,
+      "step": 297
+    },
+    {
+      "epoch": 0.5364536453645364,
+      "grad_norm": 4.765017032623291,
+      "learning_rate": 8.234605029348223e-05,
+      "loss": 5.5113,
+      "step": 298
+    },
+    {
+      "epoch": 0.5382538253825383,
+      "grad_norm": 4.620230197906494,
+      "learning_rate": 8.200737353797149e-05,
+      "loss": 6.6506,
+      "step": 299
+    },
+    {
+      "epoch": 0.54005400540054,
+      "grad_norm": 4.256903648376465,
+      "learning_rate": 8.166619015240236e-05,
+      "loss": 5.401,
+      "step": 300
+    },
+    {
+      "epoch": 0.5418541854185418,
+      "grad_norm": 72.8096694946289,
+      "learning_rate": 8.132252685625958e-05,
+      "loss": 5.5679,
+      "step": 301
+    },
+    {
+      "epoch": 0.5436543654365437,
+      "grad_norm": 12.82461166381836,
+      "learning_rate": 8.097641056324004e-05,
+      "loss": 2.3965,
+      "step": 302
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 3.8120839595794678,
+      "learning_rate": 8.062786837914492e-05,
+      "loss": 2.5916,
+      "step": 303
+    },
+    {
+      "epoch": 0.5472547254725473,
+      "grad_norm": 4.205955505371094,
+      "learning_rate": 8.027692759975695e-05,
+      "loss": 3.1019,
+      "step": 304
+    },
+    {
+      "epoch": 0.549054905490549,
+      "grad_norm": 3.6653831005096436,
+      "learning_rate": 7.992361570870288e-05,
+      "loss": 3.0688,
+      "step": 305
+    },
+    {
+      "epoch": 0.5508550855085509,
+      "grad_norm": 3.9019699096679688,
+      "learning_rate": 7.956796037530099e-05,
+      "loss": 3.4956,
+      "step": 306
+    },
+    {
+      "epoch": 0.5526552655265526,
+      "grad_norm": 4.44380521774292,
+      "learning_rate": 7.920998945239427e-05,
+      "loss": 3.8163,
+      "step": 307
+    },
+    {
+      "epoch": 0.5544554455445545,
+      "grad_norm": 4.306615352630615,
+      "learning_rate": 7.884973097416908e-05,
+      "loss": 3.8254,
+      "step": 308
+    },
+    {
+      "epoch": 0.5562556255625563,
+      "grad_norm": 3.5584664344787598,
+      "learning_rate": 7.848721315395974e-05,
+      "loss": 3.9131,
+      "step": 309
+    },
+    {
+      "epoch": 0.558055805580558,
+      "grad_norm": 3.8743574619293213,
+      "learning_rate": 7.812246438203904e-05,
+      "loss": 3.7078,
+      "step": 310
+    },
+    {
+      "epoch": 0.5598559855985599,
+      "grad_norm": 3.7516815662384033,
+      "learning_rate": 7.775551322339476e-05,
+      "loss": 3.8186,
+      "step": 311
+    },
+    {
+      "epoch": 0.5616561656165616,
+      "grad_norm": 3.739532232284546,
+      "learning_rate": 7.738638841549277e-05,
+      "loss": 3.7782,
+      "step": 312
+    },
+    {
+      "epoch": 0.5634563456345635,
+      "grad_norm": 3.378246784210205,
+      "learning_rate": 7.701511886602643e-05,
+      "loss": 3.703,
+      "step": 313
+    },
+    {
+      "epoch": 0.5652565256525652,
+      "grad_norm": 3.18391752243042,
+      "learning_rate": 7.664173365065265e-05,
+      "loss": 3.7862,
+      "step": 314
+    },
+    {
+      "epoch": 0.5670567056705671,
+      "grad_norm": 3.660829782485962,
+      "learning_rate": 7.626626201071494e-05,
+      "loss": 4.0942,
+      "step": 315
+    },
+    {
+      "epoch": 0.5688568856885688,
+      "grad_norm": 3.49433970451355,
+      "learning_rate": 7.588873335095337e-05,
+      "loss": 4.4192,
+      "step": 316
+    },
+    {
+      "epoch": 0.5706570657065707,
+      "grad_norm": 3.631074905395508,
+      "learning_rate": 7.550917723720172e-05,
+      "loss": 4.0662,
+      "step": 317
+    },
+    {
+      "epoch": 0.5724572457245725,
+      "grad_norm": 3.1131577491760254,
+      "learning_rate": 7.512762339407214e-05,
+      "loss": 3.5052,
+      "step": 318
+    },
+    {
+      "epoch": 0.5742574257425742,
+      "grad_norm": 3.5523805618286133,
+      "learning_rate": 7.474410170262718e-05,
+      "loss": 4.2908,
+      "step": 319
+    },
+    {
+      "epoch": 0.5760576057605761,
+      "grad_norm": 3.9423253536224365,
+      "learning_rate": 7.435864219803983e-05,
+      "loss": 4.3511,
+      "step": 320
+    },
+    {
+      "epoch": 0.5778577857785778,
+      "grad_norm": 3.6397900581359863,
+      "learning_rate": 7.39712750672412e-05,
+      "loss": 4.0423,
+      "step": 321
+    },
+    {
+      "epoch": 0.5796579657965797,
+      "grad_norm": 3.341845750808716,
+      "learning_rate": 7.358203064655653e-05,
+      "loss": 4.0845,
+      "step": 322
+    },
+    {
+      "epoch": 0.5814581458145814,
+      "grad_norm": 3.8859944343566895,
+      "learning_rate": 7.31909394193294e-05,
+      "loss": 3.6363,
+      "step": 323
+    },
+    {
+      "epoch": 0.5832583258325833,
+      "grad_norm": 3.2730302810668945,
+      "learning_rate": 7.27980320135345e-05,
+      "loss": 3.9988,
+      "step": 324
+    },
+    {
+      "epoch": 0.585058505850585,
+      "grad_norm": 3.4280858039855957,
+      "learning_rate": 7.240333919937893e-05,
+      "loss": 3.9773,
+      "step": 325
+    },
+    {
+      "epoch": 0.5868586858685868,
+      "grad_norm": 3.675854444503784,
+      "learning_rate": 7.200689188689256e-05,
+      "loss": 4.4474,
+      "step": 326
+    },
+    {
+      "epoch": 0.5886588658865887,
+      "grad_norm": 3.922302007675171,
+      "learning_rate": 7.16087211235073e-05,
+      "loss": 4.1046,
+      "step": 327
+    },
+    {
+      "epoch": 0.5904590459045904,
+      "grad_norm": 4.065755367279053,
+      "learning_rate": 7.120885809162561e-05,
+      "loss": 4.6008,
+      "step": 328
+    },
+    {
+      "epoch": 0.5922592259225923,
+      "grad_norm": 4.271775722503662,
+      "learning_rate": 7.080733410617853e-05,
+      "loss": 4.2479,
+      "step": 329
+    },
+    {
+      "epoch": 0.594059405940594,
+      "grad_norm": 3.5132906436920166,
+      "learning_rate": 7.040418061217325e-05,
+      "loss": 4.0792,
+      "step": 330
+    },
+    {
+      "epoch": 0.5958595859585959,
+      "grad_norm": 3.62770676612854,
+      "learning_rate": 6.999942918223053e-05,
+      "loss": 4.6398,
+      "step": 331
+    },
+    {
+      "epoch": 0.5976597659765976,
+      "grad_norm": 3.656203508377075,
+      "learning_rate": 6.959311151411212e-05,
+      "loss": 4.2742,
+      "step": 332
+    },
+    {
+      "epoch": 0.5994599459945995,
+      "grad_norm": 4.29753303527832,
+      "learning_rate": 6.918525942823835e-05,
+      "loss": 4.6216,
+      "step": 333
+    },
+    {
+      "epoch": 0.6012601260126013,
+      "grad_norm": 3.8375144004821777,
+      "learning_rate": 6.87759048651962e-05,
+      "loss": 4.6474,
+      "step": 334
+    },
+    {
+      "epoch": 0.603060306030603,
+      "grad_norm": 3.9374406337738037,
+      "learning_rate": 6.836507988323784e-05,
+      "loss": 4.8221,
+      "step": 335
+    },
+    {
+      "epoch": 0.6048604860486049,
+      "grad_norm": 4.202131748199463,
+      "learning_rate": 6.795281665577003e-05,
+      "loss": 4.4779,
+      "step": 336
+    },
+    {
+      "epoch": 0.6066606660666066,
+      "grad_norm": 4.333240985870361,
+      "learning_rate": 6.753914746883451e-05,
+      "loss": 5.2416,
+      "step": 337
+    },
+    {
+      "epoch": 0.6084608460846085,
+      "grad_norm": 4.519970417022705,
+      "learning_rate": 6.712410471857955e-05,
+      "loss": 5.6601,
+      "step": 338
+    },
+    {
+      "epoch": 0.6102610261026102,
+      "grad_norm": 4.426661968231201,
+      "learning_rate": 6.67077209087228e-05,
+      "loss": 4.9072,
+      "step": 339
+    },
+    {
+      "epoch": 0.6120612061206121,
+      "grad_norm": 3.4359755516052246,
+      "learning_rate": 6.629002864800589e-05,
+      "loss": 4.8438,
+      "step": 340
+    },
+    {
+      "epoch": 0.6138613861386139,
+      "grad_norm": 3.7532505989074707,
+      "learning_rate": 6.587106064764064e-05,
+      "loss": 5.4166,
+      "step": 341
+    },
+    {
+      "epoch": 0.6156615661566157,
+      "grad_norm": 3.9281110763549805,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 4.7921,
+      "step": 342
+    },
+    {
+      "epoch": 0.6174617461746175,
+      "grad_norm": 3.9203011989593506,
+      "learning_rate": 6.502942876978524e-05,
+      "loss": 4.6832,
+      "step": 343
+    },
+    {
+      "epoch": 0.6192619261926192,
+      "grad_norm": 3.9752700328826904,
+      "learning_rate": 6.460683080397508e-05,
+      "loss": 5.1418,
+      "step": 344
+    },
+    {
+      "epoch": 0.6210621062106211,
+      "grad_norm": 3.637481451034546,
+      "learning_rate": 6.418308891671484e-05,
+      "loss": 4.8411,
+      "step": 345
+    },
+    {
+      "epoch": 0.6228622862286228,
+      "grad_norm": 3.9811997413635254,
+      "learning_rate": 6.375823629298765e-05,
+      "loss": 4.9951,
+      "step": 346
+    },
+    {
+      "epoch": 0.6246624662466247,
+      "grad_norm": 4.1592559814453125,
+      "learning_rate": 6.333230620476307e-05,
+      "loss": 5.9485,
+      "step": 347
+    },
+    {
+      "epoch": 0.6264626462646264,
+      "grad_norm": 3.6163744926452637,
+      "learning_rate": 6.29053320083913e-05,
+      "loss": 5.3969,
+      "step": 348
+    },
+    {
+      "epoch": 0.6282628262826283,
+      "grad_norm": 4.366085052490234,
+      "learning_rate": 6.247734714199105e-05,
+      "loss": 5.3296,
+      "step": 349
+    },
+    {
+      "epoch": 0.6300630063006301,
+      "grad_norm": 4.482414722442627,
+      "learning_rate": 6.204838512283072e-05,
+      "loss": 6.0348,
+      "step": 350
+    },
+    {
+      "epoch": 0.6318631863186318,
+      "grad_norm": 38.78593826293945,
+      "learning_rate": 6.161847954470365e-05,
+      "loss": 4.4123,
+      "step": 351
+    },
+    {
+      "epoch": 0.6336633663366337,
+      "grad_norm": 4.5870041847229,
+      "learning_rate": 6.118766407529713e-05,
+      "loss": 2.4915,
+      "step": 352
+    },
+    {
+      "epoch": 0.6354635463546354,
+      "grad_norm": 3.5220015048980713,
+      "learning_rate": 6.075597245355589e-05,
+      "loss": 2.8723,
+      "step": 353
+    },
+    {
+      "epoch": 0.6372637263726373,
+      "grad_norm": 3.2156431674957275,
+      "learning_rate": 6.03234384870397e-05,
+      "loss": 3.0837,
+      "step": 354
+    },
+    {
+      "epoch": 0.639063906390639,
+      "grad_norm": 3.223064422607422,
+      "learning_rate": 5.989009604927587e-05,
+      "loss": 2.9846,
+      "step": 355
+    },
+    {
+      "epoch": 0.6408640864086409,
+      "grad_norm": 3.5234880447387695,
+      "learning_rate": 5.9455979077106463e-05,
+      "loss": 3.4383,
+      "step": 356
+    },
+    {
+      "epoch": 0.6426642664266426,
+      "grad_norm": 3.648319721221924,
+      "learning_rate": 5.9021121568030514e-05,
+      "loss": 3.2179,
+      "step": 357
+    },
+    {
+      "epoch": 0.6444644464446445,
+      "grad_norm": 3.348188877105713,
+      "learning_rate": 5.8585557577541595e-05,
+      "loss": 3.2722,
+      "step": 358
+    },
+    {
+      "epoch": 0.6462646264626463,
+      "grad_norm": 3.6280741691589355,
+      "learning_rate": 5.814932121646074e-05,
+      "loss": 3.6418,
+      "step": 359
+    },
+    {
+      "epoch": 0.648064806480648,
+      "grad_norm": 3.3993427753448486,
+      "learning_rate": 5.771244664826512e-05,
+      "loss": 3.6959,
+      "step": 360
+    },
+    {
+      "epoch": 0.6498649864986499,
+      "grad_norm": 3.4230000972747803,
+      "learning_rate": 5.727496808641256e-05,
+      "loss": 3.5139,
+      "step": 361
+    },
+    {
+      "epoch": 0.6516651665166516,
+      "grad_norm": 3.6757190227508545,
+      "learning_rate": 5.6836919791662136e-05,
+      "loss": 4.1188,
+      "step": 362
+    },
+    {
+      "epoch": 0.6534653465346535,
+      "grad_norm": 3.232292413711548,
+      "learning_rate": 5.639833606939102e-05,
+      "loss": 3.7585,
+      "step": 363
+    },
+    {
+      "epoch": 0.6552655265526552,
+      "grad_norm": 3.3726987838745117,
+      "learning_rate": 5.595925126690801e-05,
+      "loss": 3.8637,
+      "step": 364
+    },
+    {
+      "epoch": 0.6570657065706571,
+      "grad_norm": 3.570510149002075,
+      "learning_rate": 5.55196997707635e-05,
+      "loss": 3.6172,
+      "step": 365
+    },
+    {
+      "epoch": 0.6588658865886589,
+      "grad_norm": 3.3099026679992676,
+      "learning_rate": 5.507971600405663e-05,
+      "loss": 4.0602,
+      "step": 366
+    },
+    {
+      "epoch": 0.6606660666066607,
+      "grad_norm": 3.730677843093872,
+      "learning_rate": 5.463933442373945e-05,
+      "loss": 4.0647,
+      "step": 367
+    },
+    {
+      "epoch": 0.6624662466246625,
+      "grad_norm": 3.8183600902557373,
+      "learning_rate": 5.419858951791842e-05,
+      "loss": 3.9943,
+      "step": 368
+    },
+    {
+      "epoch": 0.6642664266426642,
+      "grad_norm": 3.7817885875701904,
+      "learning_rate": 5.3757515803153546e-05,
+      "loss": 3.6044,
+      "step": 369
+    },
+    {
+      "epoch": 0.6660666066606661,
+      "grad_norm": 3.696652412414551,
+      "learning_rate": 5.3316147821755205e-05,
+      "loss": 3.8305,
+      "step": 370
+    },
+    {
+      "epoch": 0.6678667866786678,
+      "grad_norm": 3.8938591480255127,
+      "learning_rate": 5.2874520139079006e-05,
+      "loss": 4.1762,
+      "step": 371
+    },
+    {
+      "epoch": 0.6696669666966697,
+      "grad_norm": 3.8813014030456543,
+      "learning_rate": 5.2432667340818906e-05,
+      "loss": 4.0786,
+      "step": 372
+    },
+    {
+      "epoch": 0.6714671467146714,
+      "grad_norm": 3.655909299850464,
+      "learning_rate": 5.1990624030298506e-05,
+      "loss": 3.9051,
+      "step": 373
+    },
+    {
+      "epoch": 0.6732673267326733,
+      "grad_norm": 3.8451969623565674,
+      "learning_rate": 5.154842482576127e-05,
+      "loss": 4.1839,
+      "step": 374
+    },
+    {
+      "epoch": 0.6750675067506751,
+      "grad_norm": 4.180874824523926,
+      "learning_rate": 5.110610435765934e-05,
+      "loss": 4.0388,
+      "step": 375
+    },
+    {
+      "epoch": 0.6768676867686768,
+      "grad_norm": 3.5825304985046387,
+      "learning_rate": 5.0663697265941545e-05,
+      "loss": 4.1734,
+      "step": 376
+    },
+    {
+      "epoch": 0.6786678667866787,
+      "grad_norm": 3.780687093734741,
+      "learning_rate": 5.022123819734053e-05,
+      "loss": 4.3508,
+      "step": 377
+    },
+    {
+      "epoch": 0.6804680468046804,
+      "grad_norm": 3.889195203781128,
+      "learning_rate": 4.977876180265948e-05,
+      "loss": 4.1945,
+      "step": 378
+    },
+    {
+      "epoch": 0.6822682268226823,
+      "grad_norm": 3.726132869720459,
+      "learning_rate": 4.933630273405847e-05,
+      "loss": 3.8745,
+      "step": 379
+    },
+    {
+      "epoch": 0.684068406840684,
+      "grad_norm": 3.7415261268615723,
+      "learning_rate": 4.889389564234066e-05,
+      "loss": 4.2891,
+      "step": 380
+    },
+    {
+      "epoch": 0.6858685868586859,
+      "grad_norm": 3.6238245964050293,
+      "learning_rate": 4.845157517423874e-05,
+      "loss": 4.3567,
+      "step": 381
+    },
+    {
+      "epoch": 0.6876687668766877,
+      "grad_norm": 3.964704990386963,
+      "learning_rate": 4.8009375969701505e-05,
+      "loss": 4.5154,
+      "step": 382
+    },
+    {
+      "epoch": 0.6894689468946895,
+      "grad_norm": 3.337338447570801,
+      "learning_rate": 4.7567332659181106e-05,
+      "loss": 4.5835,
+      "step": 383
+    },
+    {
+      "epoch": 0.6912691269126913,
+      "grad_norm": 3.447648286819458,
+      "learning_rate": 4.7125479860921e-05,
+      "loss": 4.2734,
+      "step": 384
+    },
+    {
+      "epoch": 0.693069306930693,
+      "grad_norm": 4.408335208892822,
+      "learning_rate": 4.668385217824482e-05,
+      "loss": 4.8601,
+      "step": 385
+    },
+    {
+      "epoch": 0.6948694869486949,
+      "grad_norm": 3.683608293533325,
+      "learning_rate": 4.6242484196846465e-05,
+      "loss": 4.9472,
+      "step": 386
+    },
+    {
+      "epoch": 0.6966696669666966,
+      "grad_norm": 4.226807117462158,
+      "learning_rate": 4.5801410482081584e-05,
+      "loss": 4.6788,
+      "step": 387
+    },
+    {
+      "epoch": 0.6984698469846985,
+      "grad_norm": 3.806995391845703,
+      "learning_rate": 4.536066557626056e-05,
+      "loss": 4.9015,
+      "step": 388
+    },
+    {
+      "epoch": 0.7002700270027002,
+      "grad_norm": 3.541186571121216,
+      "learning_rate": 4.4920283995943383e-05,
+      "loss": 5.1853,
+      "step": 389
+    },
+    {
+      "epoch": 0.7020702070207021,
+      "grad_norm": 3.971658706665039,
+      "learning_rate": 4.448030022923652e-05,
+      "loss": 4.8798,
+      "step": 390
+    },
+    {
+      "epoch": 0.7038703870387039,
+      "grad_norm": 3.6937930583953857,
+      "learning_rate": 4.404074873309201e-05,
+      "loss": 4.9251,
+      "step": 391
+    },
+    {
+      "epoch": 0.7056705670567057,
+      "grad_norm": 4.2643723487854,
+      "learning_rate": 4.3601663930608995e-05,
+      "loss": 4.8249,
+      "step": 392
+    },
+    {
+      "epoch": 0.7074707470747075,
+      "grad_norm": 3.8684353828430176,
+      "learning_rate": 4.316308020833788e-05,
+      "loss": 5.6238,
+      "step": 393
+    },
+    {
+      "epoch": 0.7092709270927092,
+      "grad_norm": 3.8425145149230957,
+      "learning_rate": 4.272503191358743e-05,
+      "loss": 4.9036,
+      "step": 394
+    },
+    {
+      "epoch": 0.7110711071107111,
+      "grad_norm": 3.797442674636841,
+      "learning_rate": 4.228755335173488e-05,
+      "loss": 5.0452,
+      "step": 395
+    },
+    {
+      "epoch": 0.7128712871287128,
+      "grad_norm": 4.2270355224609375,
+      "learning_rate": 4.1850678783539265e-05,
+      "loss": 4.7575,
+      "step": 396
+    },
+    {
+      "epoch": 0.7146714671467147,
+      "grad_norm": 4.077787399291992,
+      "learning_rate": 4.141444242245841e-05,
+      "loss": 5.9227,
+      "step": 397
+    },
+    {
+      "epoch": 0.7164716471647165,
+      "grad_norm": 3.7013025283813477,
+      "learning_rate": 4.0978878431969484e-05,
+      "loss": 4.7173,
+      "step": 398
+    },
+    {
+      "epoch": 0.7182718271827183,
+      "grad_norm": 4.04628849029541,
+      "learning_rate": 4.054402092289354e-05,
+      "loss": 5.4247,
+      "step": 399
+    },
+    {
+      "epoch": 0.7200720072007201,
+      "grad_norm": 4.189887523651123,
+      "learning_rate": 4.0109903950724134e-05,
+      "loss": 5.3008,
+      "step": 400
+    },
+    {
+      "epoch": 0.7218721872187218,
+      "grad_norm": 20.025436401367188,
+      "learning_rate": 3.967656151296031e-05,
+      "loss": 3.8243,
+      "step": 401
+    },
+    {
+      "epoch": 0.7236723672367237,
+      "grad_norm": 4.733638286590576,
+      "learning_rate": 3.924402754644412e-05,
+      "loss": 2.4717,
+      "step": 402
+    },
+    {
+      "epoch": 0.7254725472547254,
+      "grad_norm": 3.5588278770446777,
+      "learning_rate": 3.881233592470287e-05,
+      "loss": 2.7574,
+      "step": 403
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 3.0511527061462402,
+      "learning_rate": 3.8381520455296364e-05,
+      "loss": 2.6524,
+      "step": 404
+    },
+    {
+      "epoch": 0.729072907290729,
+      "grad_norm": 3.7463011741638184,
+      "learning_rate": 3.7951614877169284e-05,
+      "loss": 3.2022,
+      "step": 405
+    },
+    {
+      "epoch": 0.7308730873087309,
+      "grad_norm": 3.974733829498291,
+      "learning_rate": 3.7522652858008964e-05,
+      "loss": 3.7213,
+      "step": 406
+    },
+    {
+      "epoch": 0.7326732673267327,
+      "grad_norm": 3.5178704261779785,
+      "learning_rate": 3.7094667991608704e-05,
+      "loss": 3.7185,
+      "step": 407
+    },
+    {
+      "epoch": 0.7344734473447345,
+      "grad_norm": 3.9185893535614014,
+      "learning_rate": 3.6667693795236946e-05,
+      "loss": 4.0272,
+      "step": 408
+    },
+    {
+      "epoch": 0.7362736273627363,
+      "grad_norm": 3.0775508880615234,
+      "learning_rate": 3.624176370701236e-05,
+      "loss": 3.0848,
+      "step": 409
+    },
+    {
+      "epoch": 0.738073807380738,
+      "grad_norm": 3.445986270904541,
+      "learning_rate": 3.581691108328517e-05,
+      "loss": 3.857,
+      "step": 410
+    },
+    {
+      "epoch": 0.7398739873987399,
+      "grad_norm": 3.1240127086639404,
+      "learning_rate": 3.5393169196024925e-05,
+      "loss": 3.0593,
+      "step": 411
+    },
+    {
+      "epoch": 0.7416741674167416,
+      "grad_norm": 3.4222195148468018,
+      "learning_rate": 3.4970571230214774e-05,
+      "loss": 3.551,
+      "step": 412
+    },
+    {
+      "epoch": 0.7434743474347435,
+      "grad_norm": 3.3344242572784424,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.6521,
+      "step": 413
+    },
+    {
+      "epoch": 0.7452745274527453,
+      "grad_norm": 3.6145176887512207,
+      "learning_rate": 3.412893935235936e-05,
+      "loss": 3.7669,
+      "step": 414
+    },
+    {
+      "epoch": 0.7470747074707471,
+      "grad_norm": 3.2903146743774414,
+      "learning_rate": 3.370997135199413e-05,
+      "loss": 3.333,
+      "step": 415
+    },
+    {
+      "epoch": 0.7488748874887489,
+      "grad_norm": 3.5195930004119873,
+      "learning_rate": 3.329227909127722e-05,
+      "loss": 4.2719,
+      "step": 416
+    },
+    {
+      "epoch": 0.7506750675067507,
+      "grad_norm": 3.5990970134735107,
+      "learning_rate": 3.287589528142048e-05,
+      "loss": 4.1684,
+      "step": 417
+    },
+    {
+      "epoch": 0.7524752475247525,
+      "grad_norm": 3.387673854827881,
+      "learning_rate": 3.24608525311655e-05,
+      "loss": 3.8335,
+      "step": 418
+    },
+    {
+      "epoch": 0.7542754275427542,
+      "grad_norm": 3.6439712047576904,
+      "learning_rate": 3.204718334422998e-05,
+      "loss": 4.3415,
+      "step": 419
+    },
+    {
+      "epoch": 0.7560756075607561,
+      "grad_norm": 3.3546173572540283,
+      "learning_rate": 3.1634920116762176e-05,
+      "loss": 3.8877,
+      "step": 420
+    },
+    {
+      "epoch": 0.7578757875787578,
+      "grad_norm": 3.6753296852111816,
+      "learning_rate": 3.122409513480381e-05,
+      "loss": 4.1525,
+      "step": 421
+    },
+    {
+      "epoch": 0.7596759675967597,
+      "grad_norm": 3.644063711166382,
+      "learning_rate": 3.081474057176164e-05,
+      "loss": 3.8885,
+      "step": 422
+    },
+    {
+      "epoch": 0.7614761476147615,
+      "grad_norm": 4.089780807495117,
+      "learning_rate": 3.040688848588788e-05,
+      "loss": 4.0093,
+      "step": 423
+    },
+    {
+      "epoch": 0.7632763276327633,
+      "grad_norm": 3.1043710708618164,
+      "learning_rate": 3.000057081776947e-05,
+      "loss": 4.0178,
+      "step": 424
+    },
+    {
+      "epoch": 0.7650765076507651,
+      "grad_norm": 3.322037935256958,
+      "learning_rate": 2.959581938782675e-05,
+      "loss": 4.1183,
+      "step": 425
+    },
+    {
+      "epoch": 0.7668766876687669,
+      "grad_norm": 3.9151599407196045,
+      "learning_rate": 2.9192665893821475e-05,
+      "loss": 4.2036,
+      "step": 426
+    },
+    {
+      "epoch": 0.7686768676867687,
+      "grad_norm": 3.6815481185913086,
+      "learning_rate": 2.8791141908374397e-05,
+      "loss": 4.7545,
+      "step": 427
+    },
+    {
+      "epoch": 0.7704770477047704,
+      "grad_norm": 4.053499698638916,
+      "learning_rate": 2.839127887649271e-05,
+      "loss": 4.0245,
+      "step": 428
+    },
+    {
+      "epoch": 0.7722772277227723,
+      "grad_norm": 3.4955430030822754,
+      "learning_rate": 2.7993108113107447e-05,
+      "loss": 3.901,
+      "step": 429
+    },
+    {
+      "epoch": 0.774077407740774,
+      "grad_norm": 3.2984628677368164,
+      "learning_rate": 2.7596660800621078e-05,
+      "loss": 3.9142,
+      "step": 430
+    },
+    {
+      "epoch": 0.7758775877587759,
+      "grad_norm": 3.7901782989501953,
+      "learning_rate": 2.7201967986465515e-05,
+      "loss": 3.669,
+      "step": 431
+    },
+    {
+      "epoch": 0.7776777677767777,
+      "grad_norm": 3.3658523559570312,
+      "learning_rate": 2.6809060580670607e-05,
+      "loss": 4.3362,
+      "step": 432
+    },
+    {
+      "epoch": 0.7794779477947795,
+      "grad_norm": 3.361583948135376,
+      "learning_rate": 2.6417969353443483e-05,
+      "loss": 4.4502,
+      "step": 433
+    },
+    {
+      "epoch": 0.7812781278127813,
+      "grad_norm": 3.271467924118042,
+      "learning_rate": 2.6028724932758813e-05,
+      "loss": 4.1924,
+      "step": 434
+    },
+    {
+      "epoch": 0.783078307830783,
+      "grad_norm": 3.368018627166748,
+      "learning_rate": 2.5641357801960187e-05,
+      "loss": 4.2437,
+      "step": 435
+    },
+    {
+      "epoch": 0.7848784878487849,
+      "grad_norm": 4.052670955657959,
+      "learning_rate": 2.525589829737284e-05,
+      "loss": 4.7636,
+      "step": 436
+    },
+    {
+      "epoch": 0.7866786678667866,
+      "grad_norm": 3.8365402221679688,
+      "learning_rate": 2.487237660592789e-05,
+      "loss": 4.259,
+      "step": 437
+    },
+    {
+      "epoch": 0.7884788478847885,
+      "grad_norm": 3.631394386291504,
+      "learning_rate": 2.44908227627983e-05,
+      "loss": 4.7527,
+      "step": 438
+    },
+    {
+      "epoch": 0.7902790279027903,
+      "grad_norm": 3.6414878368377686,
+      "learning_rate": 2.4111266649046647e-05,
+      "loss": 4.5161,
+      "step": 439
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 3.9235427379608154,
+      "learning_rate": 2.373373798928507e-05,
+      "loss": 4.7452,
+      "step": 440
+    },
+    {
+      "epoch": 0.7938793879387939,
+      "grad_norm": 3.502267599105835,
+      "learning_rate": 2.335826634934737e-05,
+      "loss": 4.2153,
+      "step": 441
+    },
+    {
+      "epoch": 0.7956795679567957,
+      "grad_norm": 3.719147205352783,
+      "learning_rate": 2.298488113397359e-05,
+      "loss": 4.7187,
+      "step": 442
+    },
+    {
+      "epoch": 0.7974797479747975,
+      "grad_norm": 4.110799789428711,
+      "learning_rate": 2.2613611584507228e-05,
+      "loss": 4.898,
+      "step": 443
+    },
+    {
+      "epoch": 0.7992799279927992,
+      "grad_norm": 3.9746625423431396,
+      "learning_rate": 2.2244486776605243e-05,
+      "loss": 5.2031,
+      "step": 444
+    },
+    {
+      "epoch": 0.8010801080108011,
+      "grad_norm": 3.9334423542022705,
+      "learning_rate": 2.187753561796097e-05,
+      "loss": 5.5832,
+      "step": 445
+    },
+    {
+      "epoch": 0.8028802880288028,
+      "grad_norm": 3.596407413482666,
+      "learning_rate": 2.1512786846040255e-05,
+      "loss": 5.0518,
+      "step": 446
+    },
+    {
+      "epoch": 0.8046804680468047,
+      "grad_norm": 3.7824950218200684,
+      "learning_rate": 2.1150269025830925e-05,
+      "loss": 5.0857,
+      "step": 447
+    },
+    {
+      "epoch": 0.8064806480648065,
+      "grad_norm": 3.96897292137146,
+      "learning_rate": 2.0790010547605743e-05,
+      "loss": 5.4674,
+      "step": 448
+    },
+    {
+      "epoch": 0.8082808280828083,
+      "grad_norm": 3.868983030319214,
+      "learning_rate": 2.0432039624699016e-05,
+      "loss": 5.3334,
+      "step": 449
+    },
+    {
+      "epoch": 0.8100810081008101,
+      "grad_norm": 4.298758029937744,
+      "learning_rate": 2.0076384291297134e-05,
+      "loss": 5.33,
+      "step": 450
+    },
+    {
+      "epoch": 0.8118811881188119,
+      "grad_norm": 14.23192024230957,
+      "learning_rate": 1.972307240024307e-05,
+      "loss": 3.0892,
+      "step": 451
+    },
+    {
+      "epoch": 0.8136813681368137,
+      "grad_norm": 4.406993865966797,
+      "learning_rate": 1.9372131620855095e-05,
+      "loss": 2.5208,
+      "step": 452
+    },
+    {
+      "epoch": 0.8154815481548154,
+      "grad_norm": 5.394495487213135,
+      "learning_rate": 1.9023589436759954e-05,
+      "loss": 2.8551,
+      "step": 453
+    },
+    {
+      "epoch": 0.8172817281728173,
+      "grad_norm": 3.0106537342071533,
+      "learning_rate": 1.867747314374041e-05,
+      "loss": 3.0363,
+      "step": 454
+    },
+    {
+      "epoch": 0.819081908190819,
+      "grad_norm": 2.969430685043335,
+      "learning_rate": 1.8333809847597642e-05,
+      "loss": 2.9957,
+      "step": 455
+    },
+    {
+      "epoch": 0.8208820882088209,
+      "grad_norm": 3.101269245147705,
+      "learning_rate": 1.7992626462028513e-05,
+      "loss": 3.0854,
+      "step": 456
+    },
+    {
+      "epoch": 0.8226822682268227,
+      "grad_norm": 3.125643730163574,
+      "learning_rate": 1.765394970651777e-05,
+      "loss": 3.2697,
+      "step": 457
+    },
+    {
+      "epoch": 0.8244824482448245,
+      "grad_norm": 3.0227460861206055,
+      "learning_rate": 1.7317806104245597e-05,
+      "loss": 3.4779,
+      "step": 458
+    },
+    {
+      "epoch": 0.8262826282628263,
+      "grad_norm": 3.203869342803955,
+      "learning_rate": 1.6984221980010455e-05,
+      "loss": 3.7277,
+      "step": 459
+    },
+    {
+      "epoch": 0.828082808280828,
+      "grad_norm": 3.483610153198242,
+      "learning_rate": 1.665322345816746e-05,
+      "loss": 3.8941,
+      "step": 460
+    },
+    {
+      "epoch": 0.8298829882988299,
+      "grad_norm": 3.1454741954803467,
+      "learning_rate": 1.6324836460582498e-05,
+      "loss": 3.883,
+      "step": 461
+    },
+    {
+      "epoch": 0.8316831683168316,
+      "grad_norm": 3.6109461784362793,
+      "learning_rate": 1.599908670460216e-05,
+      "loss": 3.2933,
+      "step": 462
+    },
+    {
+      "epoch": 0.8334833483348335,
+      "grad_norm": 3.4250762462615967,
+      "learning_rate": 1.5675999701039735e-05,
+      "loss": 3.628,
+      "step": 463
+    },
+    {
+      "epoch": 0.8352835283528353,
+      "grad_norm": 3.624478578567505,
+      "learning_rate": 1.535560075217731e-05,
+      "loss": 4.2137,
+      "step": 464
+    },
+    {
+      "epoch": 0.8370837083708371,
+      "grad_norm": 3.289508819580078,
+      "learning_rate": 1.5037914949784299e-05,
+      "loss": 3.5101,
+      "step": 465
+    },
+    {
+      "epoch": 0.8388838883888389,
+      "grad_norm": 3.1444578170776367,
+      "learning_rate": 1.4722967173152353e-05,
+      "loss": 4.0805,
+      "step": 466
+    },
+    {
+      "epoch": 0.8406840684068407,
+      "grad_norm": 2.974825143814087,
+      "learning_rate": 1.441078208714698e-05,
+      "loss": 3.5221,
+      "step": 467
+    },
+    {
+      "epoch": 0.8424842484248425,
+      "grad_norm": 3.4931812286376953,
+      "learning_rate": 1.4101384140275947e-05,
+      "loss": 3.6931,
+      "step": 468
+    },
+    {
+      "epoch": 0.8442844284428442,
+      "grad_norm": 3.261122703552246,
+      "learning_rate": 1.3794797562774598e-05,
+      "loss": 3.769,
+      "step": 469
+    },
+    {
+      "epoch": 0.8460846084608461,
+      "grad_norm": 3.2930214405059814,
+      "learning_rate": 1.3491046364708293e-05,
+      "loss": 3.6359,
+      "step": 470
+    },
+    {
+      "epoch": 0.8478847884788479,
+      "grad_norm": 3.166865587234497,
+      "learning_rate": 1.319015433409208e-05,
+      "loss": 4.2264,
+      "step": 471
+    },
+    {
+      "epoch": 0.8496849684968497,
+      "grad_norm": 3.187593936920166,
+      "learning_rate": 1.2892145035027758e-05,
+      "loss": 4.2423,
+      "step": 472
+    },
+    {
+      "epoch": 0.8514851485148515,
+      "grad_norm": 2.961714506149292,
+      "learning_rate": 1.2597041805858468e-05,
+      "loss": 3.7844,
+      "step": 473
+    },
+    {
+      "epoch": 0.8532853285328533,
+      "grad_norm": 3.1579463481903076,
+      "learning_rate": 1.2304867757340972e-05,
+      "loss": 3.9704,
+      "step": 474
+    },
+    {
+      "epoch": 0.8550855085508551,
+      "grad_norm": 3.4631705284118652,
+      "learning_rate": 1.2015645770835764e-05,
+      "loss": 3.943,
+      "step": 475
+    },
+    {
+      "epoch": 0.8568856885688569,
+      "grad_norm": 2.9861361980438232,
+      "learning_rate": 1.1729398496515126e-05,
+      "loss": 3.6184,
+      "step": 476
+    },
+    {
+      "epoch": 0.8586858685868587,
+      "grad_norm": 3.6547658443450928,
+      "learning_rate": 1.1446148351589297e-05,
+      "loss": 4.8532,
+      "step": 477
+    },
+    {
+      "epoch": 0.8604860486048604,
+      "grad_norm": 3.7734615802764893,
+      "learning_rate": 1.1165917518550911e-05,
+      "loss": 4.3348,
+      "step": 478
+    },
+    {
+      "epoch": 0.8622862286228623,
+      "grad_norm": 3.309903621673584,
+      "learning_rate": 1.0888727943437748e-05,
+      "loss": 4.2671,
+      "step": 479
+    },
+    {
+      "epoch": 0.8640864086408641,
+      "grad_norm": 3.503133535385132,
+      "learning_rate": 1.0614601334114099e-05,
+      "loss": 4.4343,
+      "step": 480
+    },
+    {
+      "epoch": 0.8658865886588659,
+      "grad_norm": 3.389491558074951,
+      "learning_rate": 1.0343559158570704e-05,
+      "loss": 4.7319,
+      "step": 481
+    },
+    {
+      "epoch": 0.8676867686768677,
+      "grad_norm": 3.3840572834014893,
+      "learning_rate": 1.0075622643243499e-05,
+      "loss": 4.5601,
+      "step": 482
+    },
+    {
+      "epoch": 0.8694869486948695,
+      "grad_norm": 3.25216007232666,
+      "learning_rate": 9.810812771351335e-06,
+      "loss": 4.2966,
+      "step": 483
+    },
+    {
+      "epoch": 0.8712871287128713,
+      "grad_norm": 3.635775089263916,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 4.7205,
+      "step": 484
+    },
+    {
+      "epoch": 0.873087308730873,
+      "grad_norm": 3.3356218338012695,
+      "learning_rate": 9.290655664821296e-06,
+      "loss": 4.9521,
+      "step": 485
+    },
+    {
+      "epoch": 0.8748874887488749,
+      "grad_norm": 3.6561996936798096,
+      "learning_rate": 9.035349165841923e-06,
+      "loss": 4.7275,
+      "step": 486
+    },
+    {
+      "epoch": 0.8766876687668766,
+      "grad_norm": 3.564394235610962,
+      "learning_rate": 8.783250778424428e-06,
+      "loss": 4.1435,
+      "step": 487
+    },
+    {
+      "epoch": 0.8784878487848785,
+      "grad_norm": 3.7181074619293213,
+      "learning_rate": 8.534380245438211e-06,
+      "loss": 5.1263,
+      "step": 488
+    },
+    {
+      "epoch": 0.8802880288028803,
+      "grad_norm": 3.6209585666656494,
+      "learning_rate": 8.288757056966018e-06,
+      "loss": 5.0345,
+      "step": 489
+    },
+    {
+      "epoch": 0.8820882088208821,
+      "grad_norm": 4.174393653869629,
+      "learning_rate": 8.046400448777574e-06,
+      "loss": 5.2958,
+      "step": 490
+    },
+    {
+      "epoch": 0.8838883888388839,
+      "grad_norm": 3.6721696853637695,
+      "learning_rate": 7.807329400823177e-06,
+      "loss": 5.1729,
+      "step": 491
+    },
+    {
+      "epoch": 0.8856885688568857,
+      "grad_norm": 3.6310222148895264,
+      "learning_rate": 7.571562635747304e-06,
+      "loss": 4.2984,
+      "step": 492
+    },
+    {
+      "epoch": 0.8874887488748875,
+      "grad_norm": 3.5798494815826416,
+      "learning_rate": 7.3391186174223245e-06,
+      "loss": 4.7273,
+      "step": 493
+    },
+    {
+      "epoch": 0.8892889288928892,
+      "grad_norm": 3.331014633178711,
+      "learning_rate": 7.1100155495025464e-06,
+      "loss": 5.1268,
+      "step": 494
+    },
+    {
+      "epoch": 0.8910891089108911,
+      "grad_norm": 3.6740384101867676,
+      "learning_rate": 6.8842713739986075e-06,
+      "loss": 5.3065,
+      "step": 495
+    },
+    {
+      "epoch": 0.8928892889288929,
+      "grad_norm": 3.8056387901306152,
+      "learning_rate": 6.661903769872363e-06,
+      "loss": 5.405,
+      "step": 496
+    },
+    {
+      "epoch": 0.8946894689468947,
+      "grad_norm": 3.7739763259887695,
+      "learning_rate": 6.442930151652371e-06,
+      "loss": 5.9443,
+      "step": 497
+    },
+    {
+      "epoch": 0.8964896489648965,
+      "grad_norm": 3.922481060028076,
+      "learning_rate": 6.227367668070083e-06,
+      "loss": 5.1865,
+      "step": 498
+    },
+    {
+      "epoch": 0.8982898289828983,
+      "grad_norm": 3.815195083618164,
+      "learning_rate": 6.015233200716874e-06,
+      "loss": 5.4361,
+      "step": 499
+    },
+    {
+      "epoch": 0.9000900090009001,
+      "grad_norm": 4.479306697845459,
+      "learning_rate": 5.806543362721945e-06,
+      "loss": 6.0537,
+      "step": 500
+    },
+    {
+      "epoch": 0.9018901890189019,
+      "grad_norm": 25.004121780395508,
+      "learning_rate": 5.601314497451316e-06,
+      "loss": 3.6237,
+      "step": 501
+    },
+    {
+      "epoch": 0.9036903690369037,
+      "grad_norm": 3.7974557876586914,
+      "learning_rate": 5.399562677227876e-06,
+      "loss": 2.1349,
+      "step": 502
+    },
+    {
+      "epoch": 0.9054905490549054,
+      "grad_norm": 3.4542431831359863,
+      "learning_rate": 5.201303702072724e-06,
+      "loss": 2.8379,
+      "step": 503
+    },
+    {
+      "epoch": 0.9072907290729073,
+      "grad_norm": 3.14579176902771,
+      "learning_rate": 5.006553098467764e-06,
+      "loss": 2.9554,
+      "step": 504
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 2.649793863296509,
+      "learning_rate": 4.8153261181398125e-06,
+      "loss": 2.2224,
+      "step": 505
+    },
+    {
+      "epoch": 0.9108910891089109,
+      "grad_norm": 3.07043719291687,
+      "learning_rate": 4.627637736866119e-06,
+      "loss": 3.5249,
+      "step": 506
+    },
+    {
+      "epoch": 0.9126912691269127,
+      "grad_norm": 3.646077871322632,
+      "learning_rate": 4.443502653301601e-06,
+      "loss": 3.5183,
+      "step": 507
+    },
+    {
+      "epoch": 0.9144914491449145,
+      "grad_norm": 3.1195287704467773,
+      "learning_rate": 4.262935287827696e-06,
+      "loss": 3.507,
+      "step": 508
+    },
+    {
+      "epoch": 0.9162916291629163,
+      "grad_norm": 3.2357397079467773,
+      "learning_rate": 4.085949781423048e-06,
+      "loss": 3.3765,
+      "step": 509
+    },
+    {
+      "epoch": 0.918091809180918,
+      "grad_norm": 3.1325178146362305,
+      "learning_rate": 3.912559994556086e-06,
+      "loss": 3.5724,
+      "step": 510
+    },
+    {
+      "epoch": 0.9198919891989199,
+      "grad_norm": 3.3491556644439697,
+      "learning_rate": 3.7427795060995306e-06,
+      "loss": 3.8159,
+      "step": 511
+    },
+    {
+      "epoch": 0.9216921692169217,
+      "grad_norm": 3.5712788105010986,
+      "learning_rate": 3.5766216122670003e-06,
+      "loss": 3.6621,
+      "step": 512
+    },
+    {
+      "epoch": 0.9234923492349235,
+      "grad_norm": 3.1630241870880127,
+      "learning_rate": 3.4140993255717126e-06,
+      "loss": 3.6589,
+      "step": 513
+    },
+    {
+      "epoch": 0.9252925292529253,
+      "grad_norm": 3.174769401550293,
+      "learning_rate": 3.2552253738074077e-06,
+      "loss": 3.8955,
+      "step": 514
+    },
+    {
+      "epoch": 0.9270927092709271,
+      "grad_norm": 3.325157880783081,
+      "learning_rate": 3.1000121990516274e-06,
+      "loss": 3.8899,
+      "step": 515
+    },
+    {
+      "epoch": 0.9288928892889289,
+      "grad_norm": 3.770094394683838,
+      "learning_rate": 2.9484719566912735e-06,
+      "loss": 4.0021,
+      "step": 516
+    },
+    {
+      "epoch": 0.9306930693069307,
+      "grad_norm": 3.7571139335632324,
+      "learning_rate": 2.800616514470694e-06,
+      "loss": 4.1601,
+      "step": 517
+    },
+    {
+      "epoch": 0.9324932493249325,
+      "grad_norm": 3.390287160873413,
+      "learning_rate": 2.656457451562283e-06,
+      "loss": 4.0102,
+      "step": 518
+    },
+    {
+      "epoch": 0.9342934293429342,
+      "grad_norm": 3.436528444290161,
+      "learning_rate": 2.5160060576596366e-06,
+      "loss": 4.2173,
+      "step": 519
+    },
+    {
+      "epoch": 0.9360936093609361,
+      "grad_norm": 2.9943151473999023,
+      "learning_rate": 2.3792733320934346e-06,
+      "loss": 3.7667,
+      "step": 520
+    },
+    {
+      "epoch": 0.9378937893789379,
+      "grad_norm": 3.1079506874084473,
+      "learning_rate": 2.2462699829700286e-06,
+      "loss": 3.9543,
+      "step": 521
+    },
+    {
+      "epoch": 0.9396939693969397,
+      "grad_norm": 3.511355400085449,
+      "learning_rate": 2.1170064263328514e-06,
+      "loss": 4.3681,
+      "step": 522
+    },
+    {
+      "epoch": 0.9414941494149415,
+      "grad_norm": 3.2926292419433594,
+      "learning_rate": 1.991492785346677e-06,
+      "loss": 4.2362,
+      "step": 523
+    },
+    {
+      "epoch": 0.9432943294329433,
+      "grad_norm": 3.607163667678833,
+      "learning_rate": 1.8697388895048518e-06,
+      "loss": 4.1022,
+      "step": 524
+    },
+    {
+      "epoch": 0.9450945094509451,
+      "grad_norm": 3.624814510345459,
+      "learning_rate": 1.7517542738595071e-06,
+      "loss": 3.7475,
+      "step": 525
+    },
+    {
+      "epoch": 0.946894689468947,
+      "grad_norm": 3.673523426055908,
+      "learning_rate": 1.637548178274806e-06,
+      "loss": 3.8728,
+      "step": 526
+    },
+    {
+      "epoch": 0.9486948694869487,
+      "grad_norm": 3.480508804321289,
+      "learning_rate": 1.5271295467033653e-06,
+      "loss": 4.1873,
+      "step": 527
+    },
+    {
+      "epoch": 0.9504950495049505,
+      "grad_norm": 3.1145169734954834,
+      "learning_rate": 1.42050702648579e-06,
+      "loss": 4.2106,
+      "step": 528
+    },
+    {
+      "epoch": 0.9522952295229523,
+      "grad_norm": 3.012479782104492,
+      "learning_rate": 1.3176889676734693e-06,
+      "loss": 4.4033,
+      "step": 529
+    },
+    {
+      "epoch": 0.9540954095409541,
+      "grad_norm": 3.321237564086914,
+      "learning_rate": 1.2186834223746612e-06,
+      "loss": 3.8453,
+      "step": 530
+    },
+    {
+      "epoch": 0.9558955895589559,
+      "grad_norm": 3.554750680923462,
+      "learning_rate": 1.1234981441239022e-06,
+      "loss": 4.2771,
+      "step": 531
+    },
+    {
+      "epoch": 0.9576957695769577,
+      "grad_norm": 3.595700979232788,
+      "learning_rate": 1.0321405872747603e-06,
+      "loss": 4.7381,
+      "step": 532
+    },
+    {
+      "epoch": 0.9594959495949595,
+      "grad_norm": 3.4314756393432617,
+      "learning_rate": 9.446179064161009e-07,
+      "loss": 4.7025,
+      "step": 533
+    },
+    {
+      "epoch": 0.9612961296129613,
+      "grad_norm": 3.4042766094207764,
+      "learning_rate": 8.609369558117531e-07,
+      "loss": 4.5694,
+      "step": 534
+    },
+    {
+      "epoch": 0.963096309630963,
+      "grad_norm": 3.677279472351074,
+      "learning_rate": 7.81104288863721e-07,
+      "loss": 4.4108,
+      "step": 535
+    },
+    {
+      "epoch": 0.9648964896489649,
+      "grad_norm": 4.0047712326049805,
+      "learning_rate": 7.051261575989787e-07,
+      "loss": 5.2683,
+      "step": 536
+    },
+    {
+      "epoch": 0.9666966696669667,
+      "grad_norm": 3.8668036460876465,
+      "learning_rate": 6.330085121798279e-07,
+      "loss": 5.0821,
+      "step": 537
+    },
+    {
+      "epoch": 0.9684968496849685,
+      "grad_norm": 3.524517297744751,
+      "learning_rate": 5.647570004379432e-07,
+      "loss": 4.7731,
+      "step": 538
+    },
+    {
+      "epoch": 0.9702970297029703,
+      "grad_norm": 4.2224955558776855,
+      "learning_rate": 5.003769674320369e-07,
+      "loss": 5.4911,
+      "step": 539
+    },
+    {
+      "epoch": 0.9720972097209721,
+      "grad_norm": 3.456015110015869,
+      "learning_rate": 4.3987345502927157e-07,
+      "loss": 4.9279,
+      "step": 540
+    },
+    {
+      "epoch": 0.9738973897389739,
+      "grad_norm": 4.04163122177124,
+      "learning_rate": 3.832512015104317e-07,
+      "loss": 4.8574,
+      "step": 541
+    },
+    {
+      "epoch": 0.9756975697569757,
+      "grad_norm": 3.488652467727661,
+      "learning_rate": 3.3051464119883136e-07,
+      "loss": 4.5105,
+      "step": 542
+    },
+    {
+      "epoch": 0.9774977497749775,
+      "grad_norm": 3.6072845458984375,
+      "learning_rate": 2.816679041130477e-07,
+      "loss": 5.0124,
+      "step": 543
+    },
+    {
+      "epoch": 0.9792979297929792,
+      "grad_norm": 3.613863229751587,
+      "learning_rate": 2.3671481564347397e-07,
+      "loss": 4.7951,
+      "step": 544
+    },
+    {
+      "epoch": 0.9810981098109811,
+      "grad_norm": 3.676605701446533,
+      "learning_rate": 1.9565889625275946e-07,
+      "loss": 5.7295,
+      "step": 545
+    },
+    {
+      "epoch": 0.9828982898289829,
+      "grad_norm": 3.8148982524871826,
+      "learning_rate": 1.5850336120007414e-07,
+      "loss": 5.0033,
+      "step": 546
+    },
+    {
+      "epoch": 0.9846984698469847,
+      "grad_norm": 3.664438486099243,
+      "learning_rate": 1.252511202893436e-07,
+      "loss": 4.9703,
+      "step": 547
+    },
+    {
+      "epoch": 0.9864986498649865,
+      "grad_norm": 3.756563663482666,
+      "learning_rate": 9.590477764135353e-08,
+      "loss": 5.3585,
+      "step": 548
+    },
+    {
+      "epoch": 0.9882988298829883,
+      "grad_norm": 3.9945781230926514,
+      "learning_rate": 7.046663148979616e-08,
+      "loss": 5.4977,
+      "step": 549
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "grad_norm": 4.365446090698242,
+      "learning_rate": 4.89386740013198e-08,
+      "loss": 5.6052,
+      "step": 550
+    },
+    {
+      "epoch": 0.991899189918992,
+      "grad_norm": 3.4431326389312744,
+      "learning_rate": 3.1322591119481436e-08,
+      "loss": 2.9021,
+      "step": 551
+    },
+    {
+      "epoch": 0.9936993699369937,
+      "grad_norm": 3.6631813049316406,
+      "learning_rate": 1.7619762432730113e-08,
+      "loss": 4.0126,
+      "step": 552
+    },
+    {
+      "epoch": 0.9954995499549955,
+      "grad_norm": 3.126596212387085,
+      "learning_rate": 7.831261066371109e-09,
+      "loss": 3.7145,
+      "step": 553
+    },
+    {
+      "epoch": 0.9972997299729973,
+      "grad_norm": 3.9898624420166016,
+      "learning_rate": 1.9578535984998705e-09,
+      "loss": 4.723,
+      "step": 554
+    },
+    {
+      "epoch": 0.9990999099909991,
+      "grad_norm": 3.7214019298553467,
+      "learning_rate": 0.0,
+      "loss": 5.0888,
+      "step": 555
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 555,
+  "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": 1.5203413975262822e+18,
+  "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:eeeaf8e5f0be26fe16c5007b59fb0963334c1291a87b55dacbc1fa339e139e35
+size 6840

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": false,
+  "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:eeeaf8e5f0be26fe16c5007b59fb0963334c1291a87b55dacbc1fa339e139e35
+size 6840