add: model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit
+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 0.14.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aaf872c4af1808c0ed87036889837257c873da907e3b65a77b0c05168bc34a2
+size 536991984

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57c4d05423a4b2b8412edc955c18aca639571b849ef9b6efe8a6a1e8cbba952c
+size 273683028

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf9097d4513154245c48236b6ec5137b7ee2a21c9f58f2cba798ea275c6026f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924d302abf5f685356e66110270e1f4d44c1c6f59465d461e888926b2dade607
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 131072,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2385 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.977777777777778,
+  "eval_steps": 500,
+  "global_step": 336,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008888888888888889,
+      "grad_norm": 0.12853842973709106,
+      "learning_rate": 4e-05,
+      "loss": 1.435,
+      "step": 1
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 0.1351887285709381,
+      "learning_rate": 8e-05,
+      "loss": 1.4834,
+      "step": 2
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 0.1353459358215332,
+      "learning_rate": 0.00012,
+      "loss": 1.4884,
+      "step": 3
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 0.15532286465168,
+      "learning_rate": 0.00016,
+      "loss": 1.4011,
+      "step": 4
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 0.18807101249694824,
+      "learning_rate": 0.0002,
+      "loss": 1.2824,
+      "step": 5
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.21187615394592285,
+      "learning_rate": 0.00019939577039274927,
+      "loss": 1.1333,
+      "step": 6
+    },
+    {
+      "epoch": 0.06222222222222222,
+      "grad_norm": 0.2363642305135727,
+      "learning_rate": 0.0001987915407854985,
+      "loss": 1.1263,
+      "step": 7
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.23471707105636597,
+      "learning_rate": 0.00019818731117824773,
+      "loss": 0.9295,
+      "step": 8
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.2460624724626541,
+      "learning_rate": 0.00019758308157099698,
+      "loss": 0.7405,
+      "step": 9
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.7134775519371033,
+      "learning_rate": 0.00019697885196374624,
+      "loss": 0.6167,
+      "step": 10
+    },
+    {
+      "epoch": 0.09777777777777778,
+      "grad_norm": 0.2952987551689148,
+      "learning_rate": 0.0001963746223564955,
+      "loss": 0.4617,
+      "step": 11
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.2638149559497833,
+      "learning_rate": 0.00019577039274924472,
+      "loss": 0.3641,
+      "step": 12
+    },
+    {
+      "epoch": 0.11555555555555555,
+      "grad_norm": 0.21738190948963165,
+      "learning_rate": 0.00019516616314199395,
+      "loss": 0.2669,
+      "step": 13
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 0.15935368835926056,
+      "learning_rate": 0.0001945619335347432,
+      "loss": 0.1899,
+      "step": 14
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.11436018347740173,
+      "learning_rate": 0.00019395770392749247,
+      "loss": 0.1529,
+      "step": 15
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 0.11110496520996094,
+      "learning_rate": 0.00019335347432024172,
+      "loss": 0.1928,
+      "step": 16
+    },
+    {
+      "epoch": 0.1511111111111111,
+      "grad_norm": 0.09791559725999832,
+      "learning_rate": 0.00019274924471299093,
+      "loss": 0.2024,
+      "step": 17
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.07391936331987381,
+      "learning_rate": 0.00019214501510574018,
+      "loss": 0.1278,
+      "step": 18
+    },
+    {
+      "epoch": 0.1688888888888889,
+      "grad_norm": 0.08692853152751923,
+      "learning_rate": 0.00019154078549848944,
+      "loss": 0.1588,
+      "step": 19
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.08260414749383926,
+      "learning_rate": 0.0001909365558912387,
+      "loss": 0.1765,
+      "step": 20
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 0.08524943888187408,
+      "learning_rate": 0.00019033232628398793,
+      "loss": 0.2432,
+      "step": 21
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 0.08510305732488632,
+      "learning_rate": 0.00018972809667673716,
+      "loss": 0.1527,
+      "step": 22
+    },
+    {
+      "epoch": 0.20444444444444446,
+      "grad_norm": 0.07516520470380783,
+      "learning_rate": 0.0001891238670694864,
+      "loss": 0.1394,
+      "step": 23
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.08073515444993973,
+      "learning_rate": 0.00018851963746223567,
+      "loss": 0.1754,
+      "step": 24
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.06894166767597198,
+      "learning_rate": 0.0001879154078549849,
+      "loss": 0.1352,
+      "step": 25
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 0.07681784778833389,
+      "learning_rate": 0.00018731117824773416,
+      "loss": 0.1514,
+      "step": 26
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.06964302062988281,
+      "learning_rate": 0.00018670694864048338,
+      "loss": 0.1408,
+      "step": 27
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 0.08564883470535278,
+      "learning_rate": 0.00018610271903323264,
+      "loss": 0.194,
+      "step": 28
+    },
+    {
+      "epoch": 0.2577777777777778,
+      "grad_norm": 0.07006793469190598,
+      "learning_rate": 0.0001854984894259819,
+      "loss": 0.1454,
+      "step": 29
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.07050830870866776,
+      "learning_rate": 0.00018489425981873113,
+      "loss": 0.134,
+      "step": 30
+    },
+    {
+      "epoch": 0.27555555555555555,
+      "grad_norm": 0.0687691867351532,
+      "learning_rate": 0.00018429003021148036,
+      "loss": 0.122,
+      "step": 31
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.8294079899787903,
+      "learning_rate": 0.00018368580060422961,
+      "loss": 0.1737,
+      "step": 32
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 0.0775313451886177,
+      "learning_rate": 0.00018308157099697887,
+      "loss": 0.1249,
+      "step": 33
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 0.08075764775276184,
+      "learning_rate": 0.0001824773413897281,
+      "loss": 0.1596,
+      "step": 34
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.09499762207269669,
+      "learning_rate": 0.00018187311178247736,
+      "loss": 0.1788,
+      "step": 35
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.09979691356420517,
+      "learning_rate": 0.00018126888217522659,
+      "loss": 0.1286,
+      "step": 36
+    },
+    {
+      "epoch": 0.3288888888888889,
+      "grad_norm": 0.1078299731016159,
+      "learning_rate": 0.00018066465256797584,
+      "loss": 0.1473,
+      "step": 37
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 0.11813590675592422,
+      "learning_rate": 0.0001800604229607251,
+      "loss": 0.1577,
+      "step": 38
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 0.12400685250759125,
+      "learning_rate": 0.00017945619335347433,
+      "loss": 0.1554,
+      "step": 39
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.13364343345165253,
+      "learning_rate": 0.00017885196374622359,
+      "loss": 0.1937,
+      "step": 40
+    },
+    {
+      "epoch": 0.36444444444444446,
+      "grad_norm": 0.1314571350812912,
+      "learning_rate": 0.00017824773413897281,
+      "loss": 0.1417,
+      "step": 41
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.14195436239242554,
+      "learning_rate": 0.00017764350453172207,
+      "loss": 0.1471,
+      "step": 42
+    },
+    {
+      "epoch": 0.38222222222222224,
+      "grad_norm": 0.14103101193904877,
+      "learning_rate": 0.0001770392749244713,
+      "loss": 0.1512,
+      "step": 43
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.15249131619930267,
+      "learning_rate": 0.00017643504531722056,
+      "loss": 0.1261,
+      "step": 44
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.16161827743053436,
+      "learning_rate": 0.0001758308157099698,
+      "loss": 0.1361,
+      "step": 45
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 0.15586595237255096,
+      "learning_rate": 0.00017522658610271904,
+      "loss": 0.1368,
+      "step": 46
+    },
+    {
+      "epoch": 0.4177777777777778,
+      "grad_norm": 0.14314575493335724,
+      "learning_rate": 0.00017462235649546827,
+      "loss": 0.1449,
+      "step": 47
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.11395762860774994,
+      "learning_rate": 0.00017401812688821753,
+      "loss": 0.1285,
+      "step": 48
+    },
+    {
+      "epoch": 0.43555555555555553,
+      "grad_norm": 0.09165538102388382,
+      "learning_rate": 0.0001734138972809668,
+      "loss": 0.1531,
+      "step": 49
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.08022209256887436,
+      "learning_rate": 0.00017280966767371602,
+      "loss": 0.1078,
+      "step": 50
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 0.08753547072410583,
+      "learning_rate": 0.00017220543806646527,
+      "loss": 0.1511,
+      "step": 51
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.09489995241165161,
+      "learning_rate": 0.0001716012084592145,
+      "loss": 0.1109,
+      "step": 52
+    },
+    {
+      "epoch": 0.4711111111111111,
+      "grad_norm": 0.09574859589338303,
+      "learning_rate": 0.00017099697885196376,
+      "loss": 0.112,
+      "step": 53
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.10898902267217636,
+      "learning_rate": 0.000170392749244713,
+      "loss": 0.1055,
+      "step": 54
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.1365131437778473,
+      "learning_rate": 0.00016978851963746225,
+      "loss": 0.1231,
+      "step": 55
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.13064222037792206,
+      "learning_rate": 0.00016918429003021147,
+      "loss": 0.1426,
+      "step": 56
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 0.15198342502117157,
+      "learning_rate": 0.00016858006042296073,
+      "loss": 0.1152,
+      "step": 57
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 0.14036396145820618,
+      "learning_rate": 0.00016797583081571,
+      "loss": 0.0877,
+      "step": 58
+    },
+    {
+      "epoch": 0.5244444444444445,
+      "grad_norm": 0.12717780470848083,
+      "learning_rate": 0.00016737160120845922,
+      "loss": 0.1527,
+      "step": 59
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.09991107136011124,
+      "learning_rate": 0.00016676737160120847,
+      "loss": 0.1184,
+      "step": 60
+    },
+    {
+      "epoch": 0.5422222222222223,
+      "grad_norm": 0.08420077711343765,
+      "learning_rate": 0.0001661631419939577,
+      "loss": 0.1162,
+      "step": 61
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 0.07980040460824966,
+      "learning_rate": 0.00016555891238670696,
+      "loss": 0.1154,
+      "step": 62
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.07247896492481232,
+      "learning_rate": 0.00016495468277945622,
+      "loss": 0.1431,
+      "step": 63
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.06688614189624786,
+      "learning_rate": 0.00016435045317220545,
+      "loss": 0.1054,
+      "step": 64
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.059071995317935944,
+      "learning_rate": 0.00016374622356495468,
+      "loss": 0.0957,
+      "step": 65
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.05386095494031906,
+      "learning_rate": 0.00016314199395770393,
+      "loss": 0.1225,
+      "step": 66
+    },
+    {
+      "epoch": 0.5955555555555555,
+      "grad_norm": 0.04684595763683319,
+      "learning_rate": 0.0001625377643504532,
+      "loss": 0.0944,
+      "step": 67
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.0526355542242527,
+      "learning_rate": 0.00016193353474320242,
+      "loss": 0.1067,
+      "step": 68
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.05670945346355438,
+      "learning_rate": 0.00016132930513595165,
+      "loss": 0.1201,
+      "step": 69
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.056082066148519516,
+      "learning_rate": 0.0001607250755287009,
+      "loss": 0.1068,
+      "step": 70
+    },
+    {
+      "epoch": 0.6311111111111111,
+      "grad_norm": 0.044239770621061325,
+      "learning_rate": 0.00016012084592145016,
+      "loss": 0.0701,
+      "step": 71
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.06141743063926697,
+      "learning_rate": 0.00015951661631419942,
+      "loss": 0.1047,
+      "step": 72
+    },
+    {
+      "epoch": 0.6488888888888888,
+      "grad_norm": 0.06362797319889069,
+      "learning_rate": 0.00015891238670694865,
+      "loss": 0.15,
+      "step": 73
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 0.057470619678497314,
+      "learning_rate": 0.00015830815709969788,
+      "loss": 0.1157,
+      "step": 74
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.057423558086156845,
+      "learning_rate": 0.00015770392749244713,
+      "loss": 0.1046,
+      "step": 75
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.052142687141895294,
+      "learning_rate": 0.0001570996978851964,
+      "loss": 0.0964,
+      "step": 76
+    },
+    {
+      "epoch": 0.6844444444444444,
+      "grad_norm": 0.06471661478281021,
+      "learning_rate": 0.00015649546827794562,
+      "loss": 0.188,
+      "step": 77
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.054023627191782,
+      "learning_rate": 0.00015589123867069485,
+      "loss": 0.1177,
+      "step": 78
+    },
+    {
+      "epoch": 0.7022222222222222,
+      "grad_norm": 0.051102183759212494,
+      "learning_rate": 0.0001552870090634441,
+      "loss": 0.1012,
+      "step": 79
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.06166974827647209,
+      "learning_rate": 0.00015468277945619336,
+      "loss": 0.1576,
+      "step": 80
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.049090635031461716,
+      "learning_rate": 0.00015407854984894262,
+      "loss": 0.1162,
+      "step": 81
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 0.05077630653977394,
+      "learning_rate": 0.00015347432024169185,
+      "loss": 0.0921,
+      "step": 82
+    },
+    {
+      "epoch": 0.7377777777777778,
+      "grad_norm": 0.0594823993742466,
+      "learning_rate": 0.00015287009063444108,
+      "loss": 0.0842,
+      "step": 83
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.049247365444898605,
+      "learning_rate": 0.00015226586102719034,
+      "loss": 0.087,
+      "step": 84
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.058970123529434204,
+      "learning_rate": 0.0001516616314199396,
+      "loss": 0.1541,
+      "step": 85
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 0.07077732682228088,
+      "learning_rate": 0.00015105740181268885,
+      "loss": 0.1124,
+      "step": 86
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.04939179867506027,
+      "learning_rate": 0.00015045317220543805,
+      "loss": 0.0978,
+      "step": 87
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.06014474108815193,
+      "learning_rate": 0.0001498489425981873,
+      "loss": 0.1195,
+      "step": 88
+    },
+    {
+      "epoch": 0.7911111111111111,
+      "grad_norm": 0.05583404749631882,
+      "learning_rate": 0.00014924471299093656,
+      "loss": 0.141,
+      "step": 89
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.053725555539131165,
+      "learning_rate": 0.00014864048338368582,
+      "loss": 0.1149,
+      "step": 90
+    },
+    {
+      "epoch": 0.8088888888888889,
+      "grad_norm": 0.044657181948423386,
+      "learning_rate": 0.00014803625377643505,
+      "loss": 0.0721,
+      "step": 91
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 0.06342475116252899,
+      "learning_rate": 0.00014743202416918428,
+      "loss": 0.1177,
+      "step": 92
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 0.056376609951257706,
+      "learning_rate": 0.00014682779456193354,
+      "loss": 0.0976,
+      "step": 93
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 0.05411997064948082,
+      "learning_rate": 0.0001462235649546828,
+      "loss": 0.1059,
+      "step": 94
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.056368228048086166,
+      "learning_rate": 0.00014561933534743205,
+      "loss": 0.1133,
+      "step": 95
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.05209295451641083,
+      "learning_rate": 0.00014501510574018128,
+      "loss": 0.0996,
+      "step": 96
+    },
+    {
+      "epoch": 0.8622222222222222,
+      "grad_norm": 0.054722413420677185,
+      "learning_rate": 0.0001444108761329305,
+      "loss": 0.1029,
+      "step": 97
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 0.05473008751869202,
+      "learning_rate": 0.00014380664652567977,
+      "loss": 0.1176,
+      "step": 98
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.05287059769034386,
+      "learning_rate": 0.00014320241691842902,
+      "loss": 0.0909,
+      "step": 99
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.04134868085384369,
+      "learning_rate": 0.00014259818731117825,
+      "loss": 0.0673,
+      "step": 100
+    },
+    {
+      "epoch": 0.8977777777777778,
+      "grad_norm": 0.048795074224472046,
+      "learning_rate": 0.00014199395770392748,
+      "loss": 0.0761,
+      "step": 101
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.06269072741270065,
+      "learning_rate": 0.00014138972809667674,
+      "loss": 0.1244,
+      "step": 102
+    },
+    {
+      "epoch": 0.9155555555555556,
+      "grad_norm": 0.05946790799498558,
+      "learning_rate": 0.000140785498489426,
+      "loss": 0.1307,
+      "step": 103
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.059073008596897125,
+      "learning_rate": 0.00014018126888217525,
+      "loss": 0.1274,
+      "step": 104
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.058441124856472015,
+      "learning_rate": 0.00013957703927492448,
+      "loss": 0.1185,
+      "step": 105
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 0.06066688522696495,
+      "learning_rate": 0.0001389728096676737,
+      "loss": 0.116,
+      "step": 106
+    },
+    {
+      "epoch": 0.9511111111111111,
+      "grad_norm": 0.05696433410048485,
+      "learning_rate": 0.00013836858006042297,
+      "loss": 0.0981,
+      "step": 107
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.04884543642401695,
+      "learning_rate": 0.00013776435045317222,
+      "loss": 0.0844,
+      "step": 108
+    },
+    {
+      "epoch": 0.9688888888888889,
+      "grad_norm": 0.05151006579399109,
+      "learning_rate": 0.00013716012084592145,
+      "loss": 0.1165,
+      "step": 109
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.048714157193899155,
+      "learning_rate": 0.0001365558912386707,
+      "loss": 0.0914,
+      "step": 110
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 0.05728358030319214,
+      "learning_rate": 0.00013595166163141994,
+      "loss": 0.096,
+      "step": 111
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.04793373495340347,
+      "learning_rate": 0.0001353474320241692,
+      "loss": 0.0732,
+      "step": 112
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0691237822175026,
+      "learning_rate": 0.00013474320241691845,
+      "loss": 0.0772,
+      "step": 113
+    },
+    {
+      "epoch": 1.008888888888889,
+      "grad_norm": 0.059231679886579514,
+      "learning_rate": 0.00013413897280966768,
+      "loss": 0.1035,
+      "step": 114
+    },
+    {
+      "epoch": 1.0177777777777777,
+      "grad_norm": 0.050710082054138184,
+      "learning_rate": 0.0001335347432024169,
+      "loss": 0.0927,
+      "step": 115
+    },
+    {
+      "epoch": 1.0266666666666666,
+      "grad_norm": 0.052448518574237823,
+      "learning_rate": 0.00013293051359516617,
+      "loss": 0.0927,
+      "step": 116
+    },
+    {
+      "epoch": 1.0355555555555556,
+      "grad_norm": 0.05111970752477646,
+      "learning_rate": 0.00013232628398791543,
+      "loss": 0.101,
+      "step": 117
+    },
+    {
+      "epoch": 1.0444444444444445,
+      "grad_norm": 0.050373584032058716,
+      "learning_rate": 0.00013172205438066465,
+      "loss": 0.0958,
+      "step": 118
+    },
+    {
+      "epoch": 1.0533333333333332,
+      "grad_norm": 0.053760871291160583,
+      "learning_rate": 0.0001311178247734139,
+      "loss": 0.1004,
+      "step": 119
+    },
+    {
+      "epoch": 1.0622222222222222,
+      "grad_norm": 0.050390031188726425,
+      "learning_rate": 0.00013051359516616314,
+      "loss": 0.098,
+      "step": 120
+    },
+    {
+      "epoch": 1.0711111111111111,
+      "grad_norm": 0.056723542511463165,
+      "learning_rate": 0.0001299093655589124,
+      "loss": 0.1019,
+      "step": 121
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.05544177070260048,
+      "learning_rate": 0.00012930513595166163,
+      "loss": 0.105,
+      "step": 122
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 0.05266315117478371,
+      "learning_rate": 0.00012870090634441088,
+      "loss": 0.0852,
+      "step": 123
+    },
+    {
+      "epoch": 1.0977777777777777,
+      "grad_norm": 0.05095309391617775,
+      "learning_rate": 0.0001280966767371601,
+      "loss": 0.0883,
+      "step": 124
+    },
+    {
+      "epoch": 1.1066666666666667,
+      "grad_norm": 0.052665866911411285,
+      "learning_rate": 0.00012749244712990937,
+      "loss": 0.0821,
+      "step": 125
+    },
+    {
+      "epoch": 1.1155555555555556,
+      "grad_norm": 0.05651025474071503,
+      "learning_rate": 0.00012688821752265863,
+      "loss": 0.0923,
+      "step": 126
+    },
+    {
+      "epoch": 1.1244444444444444,
+      "grad_norm": 0.053802527487277985,
+      "learning_rate": 0.00012628398791540786,
+      "loss": 0.0934,
+      "step": 127
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.04798378795385361,
+      "learning_rate": 0.0001256797583081571,
+      "loss": 0.0745,
+      "step": 128
+    },
+    {
+      "epoch": 1.1422222222222222,
+      "grad_norm": 0.04485182464122772,
+      "learning_rate": 0.00012507552870090634,
+      "loss": 0.0687,
+      "step": 129
+    },
+    {
+      "epoch": 1.1511111111111112,
+      "grad_norm": 0.05560389533638954,
+      "learning_rate": 0.0001244712990936556,
+      "loss": 0.1228,
+      "step": 130
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.053619932383298874,
+      "learning_rate": 0.00012386706948640483,
+      "loss": 0.1016,
+      "step": 131
+    },
+    {
+      "epoch": 1.1688888888888889,
+      "grad_norm": 0.061660535633563995,
+      "learning_rate": 0.00012326283987915408,
+      "loss": 0.1084,
+      "step": 132
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 0.05607709661126137,
+      "learning_rate": 0.00012265861027190334,
+      "loss": 0.1173,
+      "step": 133
+    },
+    {
+      "epoch": 1.1866666666666668,
+      "grad_norm": 0.06121942773461342,
+      "learning_rate": 0.00012205438066465258,
+      "loss": 0.1047,
+      "step": 134
+    },
+    {
+      "epoch": 1.1955555555555555,
+      "grad_norm": 0.058909133076667786,
+      "learning_rate": 0.00012145015105740183,
+      "loss": 0.0945,
+      "step": 135
+    },
+    {
+      "epoch": 1.2044444444444444,
+      "grad_norm": 0.04819121211767197,
+      "learning_rate": 0.00012084592145015106,
+      "loss": 0.0814,
+      "step": 136
+    },
+    {
+      "epoch": 1.2133333333333334,
+      "grad_norm": 0.052952077239751816,
+      "learning_rate": 0.0001202416918429003,
+      "loss": 0.0723,
+      "step": 137
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.059440117329359055,
+      "learning_rate": 0.00011963746223564956,
+      "loss": 0.1039,
+      "step": 138
+    },
+    {
+      "epoch": 1.231111111111111,
+      "grad_norm": 0.06102529540657997,
+      "learning_rate": 0.0001190332326283988,
+      "loss": 0.0946,
+      "step": 139
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.05853147804737091,
+      "learning_rate": 0.00011842900302114803,
+      "loss": 0.0928,
+      "step": 140
+    },
+    {
+      "epoch": 1.248888888888889,
+      "grad_norm": 0.05324235185980797,
+      "learning_rate": 0.00011782477341389729,
+      "loss": 0.0656,
+      "step": 141
+    },
+    {
+      "epoch": 1.2577777777777777,
+      "grad_norm": 0.060984380543231964,
+      "learning_rate": 0.00011722054380664653,
+      "loss": 0.114,
+      "step": 142
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.05423833429813385,
+      "learning_rate": 0.00011661631419939579,
+      "loss": 0.0758,
+      "step": 143
+    },
+    {
+      "epoch": 1.2755555555555556,
+      "grad_norm": 0.05878995731472969,
+      "learning_rate": 0.00011601208459214503,
+      "loss": 0.095,
+      "step": 144
+    },
+    {
+      "epoch": 1.2844444444444445,
+      "grad_norm": 0.05326640605926514,
+      "learning_rate": 0.00011540785498489426,
+      "loss": 0.0893,
+      "step": 145
+    },
+    {
+      "epoch": 1.2933333333333334,
+      "grad_norm": 0.045536670833826065,
+      "learning_rate": 0.00011480362537764352,
+      "loss": 0.0756,
+      "step": 146
+    },
+    {
+      "epoch": 1.3022222222222222,
+      "grad_norm": 0.06222836673259735,
+      "learning_rate": 0.00011419939577039276,
+      "loss": 0.0832,
+      "step": 147
+    },
+    {
+      "epoch": 1.3111111111111111,
+      "grad_norm": 0.05563228577375412,
+      "learning_rate": 0.00011359516616314202,
+      "loss": 0.0987,
+      "step": 148
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.05855840817093849,
+      "learning_rate": 0.00011299093655589123,
+      "loss": 0.1012,
+      "step": 149
+    },
+    {
+      "epoch": 1.3288888888888888,
+      "grad_norm": 0.06626389175653458,
+      "learning_rate": 0.00011238670694864049,
+      "loss": 0.1326,
+      "step": 150
+    },
+    {
+      "epoch": 1.3377777777777777,
+      "grad_norm": 0.050519317388534546,
+      "learning_rate": 0.00011178247734138973,
+      "loss": 0.0673,
+      "step": 151
+    },
+    {
+      "epoch": 1.3466666666666667,
+      "grad_norm": 0.057173047214746475,
+      "learning_rate": 0.00011117824773413899,
+      "loss": 0.0813,
+      "step": 152
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 0.04732273891568184,
+      "learning_rate": 0.00011057401812688822,
+      "loss": 0.0611,
+      "step": 153
+    },
+    {
+      "epoch": 1.3644444444444446,
+      "grad_norm": 0.058079130947589874,
+      "learning_rate": 0.00010996978851963746,
+      "loss": 0.111,
+      "step": 154
+    },
+    {
+      "epoch": 1.3733333333333333,
+      "grad_norm": 0.054955486208200455,
+      "learning_rate": 0.00010936555891238672,
+      "loss": 0.0819,
+      "step": 155
+    },
+    {
+      "epoch": 1.3822222222222222,
+      "grad_norm": 0.06241566315293312,
+      "learning_rate": 0.00010876132930513596,
+      "loss": 0.0897,
+      "step": 156
+    },
+    {
+      "epoch": 1.3911111111111112,
+      "grad_norm": 0.06284183263778687,
+      "learning_rate": 0.00010815709969788522,
+      "loss": 0.0995,
+      "step": 157
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.05234519764780998,
+      "learning_rate": 0.00010755287009063443,
+      "loss": 0.0886,
+      "step": 158
+    },
+    {
+      "epoch": 1.4088888888888889,
+      "grad_norm": 0.05802811682224274,
+      "learning_rate": 0.00010694864048338369,
+      "loss": 0.0867,
+      "step": 159
+    },
+    {
+      "epoch": 1.4177777777777778,
+      "grad_norm": 0.05341397225856781,
+      "learning_rate": 0.00010634441087613293,
+      "loss": 0.0822,
+      "step": 160
+    },
+    {
+      "epoch": 1.4266666666666667,
+      "grad_norm": 0.07113339751958847,
+      "learning_rate": 0.00010574018126888219,
+      "loss": 0.1002,
+      "step": 161
+    },
+    {
+      "epoch": 1.4355555555555555,
+      "grad_norm": 0.06063013896346092,
+      "learning_rate": 0.00010513595166163142,
+      "loss": 0.0981,
+      "step": 162
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.06280765682458878,
+      "learning_rate": 0.00010453172205438066,
+      "loss": 0.0872,
+      "step": 163
+    },
+    {
+      "epoch": 1.4533333333333334,
+      "grad_norm": 0.053992606699466705,
+      "learning_rate": 0.00010392749244712992,
+      "loss": 0.0811,
+      "step": 164
+    },
+    {
+      "epoch": 1.462222222222222,
+      "grad_norm": 0.06484760344028473,
+      "learning_rate": 0.00010332326283987916,
+      "loss": 0.1499,
+      "step": 165
+    },
+    {
+      "epoch": 1.471111111111111,
+      "grad_norm": 0.04423009976744652,
+      "learning_rate": 0.00010271903323262842,
+      "loss": 0.0587,
+      "step": 166
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.05195729061961174,
+      "learning_rate": 0.00010211480362537765,
+      "loss": 0.0756,
+      "step": 167
+    },
+    {
+      "epoch": 1.488888888888889,
+      "grad_norm": 0.07213317602872849,
+      "learning_rate": 0.00010151057401812689,
+      "loss": 0.1274,
+      "step": 168
+    },
+    {
+      "epoch": 1.4977777777777779,
+      "grad_norm": 0.07075338065624237,
+      "learning_rate": 0.00010090634441087615,
+      "loss": 0.1482,
+      "step": 169
+    },
+    {
+      "epoch": 1.5066666666666668,
+      "grad_norm": 0.05478464439511299,
+      "learning_rate": 0.00010030211480362539,
+      "loss": 0.0757,
+      "step": 170
+    },
+    {
+      "epoch": 1.5155555555555555,
+      "grad_norm": 0.05618472024798393,
+      "learning_rate": 9.969788519637463e-05,
+      "loss": 0.0809,
+      "step": 171
+    },
+    {
+      "epoch": 1.5244444444444445,
+      "grad_norm": 0.05127232149243355,
+      "learning_rate": 9.909365558912386e-05,
+      "loss": 0.0738,
+      "step": 172
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.05737868323922157,
+      "learning_rate": 9.848942598187312e-05,
+      "loss": 0.0944,
+      "step": 173
+    },
+    {
+      "epoch": 1.5422222222222222,
+      "grad_norm": 0.05908210948109627,
+      "learning_rate": 9.788519637462236e-05,
+      "loss": 0.0892,
+      "step": 174
+    },
+    {
+      "epoch": 1.551111111111111,
+      "grad_norm": 0.04666788876056671,
+      "learning_rate": 9.72809667673716e-05,
+      "loss": 0.059,
+      "step": 175
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.06086019426584244,
+      "learning_rate": 9.667673716012086e-05,
+      "loss": 0.0967,
+      "step": 176
+    },
+    {
+      "epoch": 1.568888888888889,
+      "grad_norm": 0.07607266306877136,
+      "learning_rate": 9.607250755287009e-05,
+      "loss": 0.1171,
+      "step": 177
+    },
+    {
+      "epoch": 1.5777777777777777,
+      "grad_norm": 0.05511125177145004,
+      "learning_rate": 9.546827794561935e-05,
+      "loss": 0.0803,
+      "step": 178
+    },
+    {
+      "epoch": 1.5866666666666667,
+      "grad_norm": 0.04639158770442009,
+      "learning_rate": 9.486404833836858e-05,
+      "loss": 0.0552,
+      "step": 179
+    },
+    {
+      "epoch": 1.5955555555555554,
+      "grad_norm": 0.06064977869391441,
+      "learning_rate": 9.425981873111783e-05,
+      "loss": 0.1009,
+      "step": 180
+    },
+    {
+      "epoch": 1.6044444444444443,
+      "grad_norm": 0.0693751648068428,
+      "learning_rate": 9.365558912386708e-05,
+      "loss": 0.1033,
+      "step": 181
+    },
+    {
+      "epoch": 1.6133333333333333,
+      "grad_norm": 0.060564182698726654,
+      "learning_rate": 9.305135951661632e-05,
+      "loss": 0.0783,
+      "step": 182
+    },
+    {
+      "epoch": 1.6222222222222222,
+      "grad_norm": 0.051936618983745575,
+      "learning_rate": 9.244712990936556e-05,
+      "loss": 0.0789,
+      "step": 183
+    },
+    {
+      "epoch": 1.6311111111111112,
+      "grad_norm": 0.0632539689540863,
+      "learning_rate": 9.184290030211481e-05,
+      "loss": 0.1033,
+      "step": 184
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.06275516003370285,
+      "learning_rate": 9.123867069486405e-05,
+      "loss": 0.0837,
+      "step": 185
+    },
+    {
+      "epoch": 1.6488888888888888,
+      "grad_norm": 0.07486943155527115,
+      "learning_rate": 9.063444108761329e-05,
+      "loss": 0.1463,
+      "step": 186
+    },
+    {
+      "epoch": 1.6577777777777778,
+      "grad_norm": 0.061665549874305725,
+      "learning_rate": 9.003021148036255e-05,
+      "loss": 0.0962,
+      "step": 187
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.058605264872312546,
+      "learning_rate": 8.942598187311179e-05,
+      "loss": 0.0903,
+      "step": 188
+    },
+    {
+      "epoch": 1.6755555555555555,
+      "grad_norm": 0.05885601043701172,
+      "learning_rate": 8.882175226586104e-05,
+      "loss": 0.0792,
+      "step": 189
+    },
+    {
+      "epoch": 1.6844444444444444,
+      "grad_norm": 0.06224210560321808,
+      "learning_rate": 8.821752265861028e-05,
+      "loss": 0.0985,
+      "step": 190
+    },
+    {
+      "epoch": 1.6933333333333334,
+      "grad_norm": 0.0739174336194992,
+      "learning_rate": 8.761329305135952e-05,
+      "loss": 0.1079,
+      "step": 191
+    },
+    {
+      "epoch": 1.7022222222222223,
+      "grad_norm": 0.06836007535457611,
+      "learning_rate": 8.700906344410877e-05,
+      "loss": 0.122,
+      "step": 192
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 0.06372584402561188,
+      "learning_rate": 8.640483383685801e-05,
+      "loss": 0.1006,
+      "step": 193
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.05704513192176819,
+      "learning_rate": 8.580060422960725e-05,
+      "loss": 0.0856,
+      "step": 194
+    },
+    {
+      "epoch": 1.728888888888889,
+      "grad_norm": 0.06607326865196228,
+      "learning_rate": 8.51963746223565e-05,
+      "loss": 0.0851,
+      "step": 195
+    },
+    {
+      "epoch": 1.7377777777777776,
+      "grad_norm": 0.06291351467370987,
+      "learning_rate": 8.459214501510574e-05,
+      "loss": 0.1026,
+      "step": 196
+    },
+    {
+      "epoch": 1.7466666666666666,
+      "grad_norm": 0.055036935955286026,
+      "learning_rate": 8.3987915407855e-05,
+      "loss": 0.0721,
+      "step": 197
+    },
+    {
+      "epoch": 1.7555555555555555,
+      "grad_norm": 0.06576612591743469,
+      "learning_rate": 8.338368580060424e-05,
+      "loss": 0.1199,
+      "step": 198
+    },
+    {
+      "epoch": 1.7644444444444445,
+      "grad_norm": 0.0656011551618576,
+      "learning_rate": 8.277945619335348e-05,
+      "loss": 0.0947,
+      "step": 199
+    },
+    {
+      "epoch": 1.7733333333333334,
+      "grad_norm": 0.05662452057003975,
+      "learning_rate": 8.217522658610272e-05,
+      "loss": 0.0783,
+      "step": 200
+    },
+    {
+      "epoch": 1.7822222222222224,
+      "grad_norm": 0.05521798133850098,
+      "learning_rate": 8.157099697885197e-05,
+      "loss": 0.0635,
+      "step": 201
+    },
+    {
+      "epoch": 1.791111111111111,
+      "grad_norm": 0.06891798228025436,
+      "learning_rate": 8.096676737160121e-05,
+      "loss": 0.1013,
+      "step": 202
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.06973979622125626,
+      "learning_rate": 8.036253776435045e-05,
+      "loss": 0.0787,
+      "step": 203
+    },
+    {
+      "epoch": 1.8088888888888888,
+      "grad_norm": 0.06616077572107315,
+      "learning_rate": 7.975830815709971e-05,
+      "loss": 0.0817,
+      "step": 204
+    },
+    {
+      "epoch": 1.8177777777777777,
+      "grad_norm": 0.06029290705919266,
+      "learning_rate": 7.915407854984894e-05,
+      "loss": 0.0806,
+      "step": 205
+    },
+    {
+      "epoch": 1.8266666666666667,
+      "grad_norm": 0.06291759759187698,
+      "learning_rate": 7.85498489425982e-05,
+      "loss": 0.087,
+      "step": 206
+    },
+    {
+      "epoch": 1.8355555555555556,
+      "grad_norm": 0.05678003653883934,
+      "learning_rate": 7.794561933534742e-05,
+      "loss": 0.0738,
+      "step": 207
+    },
+    {
+      "epoch": 1.8444444444444446,
+      "grad_norm": 0.05496233329176903,
+      "learning_rate": 7.734138972809668e-05,
+      "loss": 0.0835,
+      "step": 208
+    },
+    {
+      "epoch": 1.8533333333333335,
+      "grad_norm": 0.057058099657297134,
+      "learning_rate": 7.673716012084592e-05,
+      "loss": 0.0764,
+      "step": 209
+    },
+    {
+      "epoch": 1.8622222222222222,
+      "grad_norm": 0.05875209718942642,
+      "learning_rate": 7.613293051359517e-05,
+      "loss": 0.0734,
+      "step": 210
+    },
+    {
+      "epoch": 1.871111111111111,
+      "grad_norm": 0.06268563121557236,
+      "learning_rate": 7.552870090634442e-05,
+      "loss": 0.0791,
+      "step": 211
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.08160948008298874,
+      "learning_rate": 7.492447129909365e-05,
+      "loss": 0.1602,
+      "step": 212
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.06325849145650864,
+      "learning_rate": 7.432024169184291e-05,
+      "loss": 0.0955,
+      "step": 213
+    },
+    {
+      "epoch": 1.8977777777777778,
+      "grad_norm": 0.06835322082042694,
+      "learning_rate": 7.371601208459214e-05,
+      "loss": 0.1167,
+      "step": 214
+    },
+    {
+      "epoch": 1.9066666666666667,
+      "grad_norm": 0.06621617823839188,
+      "learning_rate": 7.31117824773414e-05,
+      "loss": 0.104,
+      "step": 215
+    },
+    {
+      "epoch": 1.9155555555555557,
+      "grad_norm": 0.0520428791642189,
+      "learning_rate": 7.250755287009064e-05,
+      "loss": 0.0595,
+      "step": 216
+    },
+    {
+      "epoch": 1.9244444444444444,
+      "grad_norm": 0.05874223634600639,
+      "learning_rate": 7.190332326283988e-05,
+      "loss": 0.0734,
+      "step": 217
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.06542330980300903,
+      "learning_rate": 7.129909365558913e-05,
+      "loss": 0.0957,
+      "step": 218
+    },
+    {
+      "epoch": 1.942222222222222,
+      "grad_norm": 0.05599142238497734,
+      "learning_rate": 7.069486404833837e-05,
+      "loss": 0.0804,
+      "step": 219
+    },
+    {
+      "epoch": 1.951111111111111,
+      "grad_norm": 0.058727771043777466,
+      "learning_rate": 7.009063444108763e-05,
+      "loss": 0.0812,
+      "step": 220
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.050783053040504456,
+      "learning_rate": 6.948640483383686e-05,
+      "loss": 0.073,
+      "step": 221
+    },
+    {
+      "epoch": 1.968888888888889,
+      "grad_norm": 0.058176856487989426,
+      "learning_rate": 6.888217522658611e-05,
+      "loss": 0.0941,
+      "step": 222
+    },
+    {
+      "epoch": 1.9777777777777779,
+      "grad_norm": 0.06019238755106926,
+      "learning_rate": 6.827794561933535e-05,
+      "loss": 0.0804,
+      "step": 223
+    },
+    {
+      "epoch": 1.9866666666666668,
+      "grad_norm": 0.052067600190639496,
+      "learning_rate": 6.76737160120846e-05,
+      "loss": 0.0664,
+      "step": 224
+    },
+    {
+      "epoch": 1.9955555555555555,
+      "grad_norm": 0.05987400561571121,
+      "learning_rate": 6.706948640483384e-05,
+      "loss": 0.087,
+      "step": 225
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.08068395406007767,
+      "learning_rate": 6.646525679758308e-05,
+      "loss": 0.0728,
+      "step": 226
+    },
+    {
+      "epoch": 2.008888888888889,
+      "grad_norm": 0.056796178221702576,
+      "learning_rate": 6.586102719033233e-05,
+      "loss": 0.0844,
+      "step": 227
+    },
+    {
+      "epoch": 2.017777777777778,
+      "grad_norm": 0.05155782401561737,
+      "learning_rate": 6.525679758308157e-05,
+      "loss": 0.0668,
+      "step": 228
+    },
+    {
+      "epoch": 2.026666666666667,
+      "grad_norm": 0.050025951117277145,
+      "learning_rate": 6.465256797583081e-05,
+      "loss": 0.0632,
+      "step": 229
+    },
+    {
+      "epoch": 2.0355555555555553,
+      "grad_norm": 0.06146937608718872,
+      "learning_rate": 6.404833836858006e-05,
+      "loss": 0.1061,
+      "step": 230
+    },
+    {
+      "epoch": 2.0444444444444443,
+      "grad_norm": 0.05745534226298332,
+      "learning_rate": 6.344410876132931e-05,
+      "loss": 0.0775,
+      "step": 231
+    },
+    {
+      "epoch": 2.0533333333333332,
+      "grad_norm": 0.058149635791778564,
+      "learning_rate": 6.283987915407856e-05,
+      "loss": 0.0812,
+      "step": 232
+    },
+    {
+      "epoch": 2.062222222222222,
+      "grad_norm": 0.052630528807640076,
+      "learning_rate": 6.22356495468278e-05,
+      "loss": 0.0715,
+      "step": 233
+    },
+    {
+      "epoch": 2.071111111111111,
+      "grad_norm": 0.053744129836559296,
+      "learning_rate": 6.163141993957704e-05,
+      "loss": 0.064,
+      "step": 234
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.05753091350197792,
+      "learning_rate": 6.102719033232629e-05,
+      "loss": 0.0769,
+      "step": 235
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 0.06525509059429169,
+      "learning_rate": 6.042296072507553e-05,
+      "loss": 0.0861,
+      "step": 236
+    },
+    {
+      "epoch": 2.097777777777778,
+      "grad_norm": 0.060992028564214706,
+      "learning_rate": 5.981873111782478e-05,
+      "loss": 0.0916,
+      "step": 237
+    },
+    {
+      "epoch": 2.1066666666666665,
+      "grad_norm": 0.05694571137428284,
+      "learning_rate": 5.9214501510574015e-05,
+      "loss": 0.0718,
+      "step": 238
+    },
+    {
+      "epoch": 2.1155555555555554,
+      "grad_norm": 0.06200471892952919,
+      "learning_rate": 5.8610271903323265e-05,
+      "loss": 0.0765,
+      "step": 239
+    },
+    {
+      "epoch": 2.1244444444444444,
+      "grad_norm": 0.07638643682003021,
+      "learning_rate": 5.8006042296072515e-05,
+      "loss": 0.1205,
+      "step": 240
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.05985346809029579,
+      "learning_rate": 5.740181268882176e-05,
+      "loss": 0.0633,
+      "step": 241
+    },
+    {
+      "epoch": 2.1422222222222222,
+      "grad_norm": 0.06811255216598511,
+      "learning_rate": 5.679758308157101e-05,
+      "loss": 0.0716,
+      "step": 242
+    },
+    {
+      "epoch": 2.151111111111111,
+      "grad_norm": 0.07051990926265717,
+      "learning_rate": 5.6193353474320244e-05,
+      "loss": 0.0985,
+      "step": 243
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.06572071462869644,
+      "learning_rate": 5.5589123867069494e-05,
+      "loss": 0.0645,
+      "step": 244
+    },
+    {
+      "epoch": 2.168888888888889,
+      "grad_norm": 0.06567268073558807,
+      "learning_rate": 5.498489425981873e-05,
+      "loss": 0.0602,
+      "step": 245
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 0.0646674782037735,
+      "learning_rate": 5.438066465256798e-05,
+      "loss": 0.0679,
+      "step": 246
+    },
+    {
+      "epoch": 2.1866666666666665,
+      "grad_norm": 0.06456337124109268,
+      "learning_rate": 5.3776435045317216e-05,
+      "loss": 0.0706,
+      "step": 247
+    },
+    {
+      "epoch": 2.1955555555555555,
+      "grad_norm": 0.07218114286661148,
+      "learning_rate": 5.3172205438066466e-05,
+      "loss": 0.076,
+      "step": 248
+    },
+    {
+      "epoch": 2.2044444444444444,
+      "grad_norm": 0.07510354369878769,
+      "learning_rate": 5.256797583081571e-05,
+      "loss": 0.0817,
+      "step": 249
+    },
+    {
+      "epoch": 2.2133333333333334,
+      "grad_norm": 0.07315120100975037,
+      "learning_rate": 5.196374622356496e-05,
+      "loss": 0.0725,
+      "step": 250
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.08618611097335815,
+      "learning_rate": 5.135951661631421e-05,
+      "loss": 0.099,
+      "step": 251
+    },
+    {
+      "epoch": 2.2311111111111113,
+      "grad_norm": 0.07698719948530197,
+      "learning_rate": 5.0755287009063445e-05,
+      "loss": 0.0878,
+      "step": 252
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.06022505462169647,
+      "learning_rate": 5.0151057401812695e-05,
+      "loss": 0.0558,
+      "step": 253
+    },
+    {
+      "epoch": 2.2488888888888887,
+      "grad_norm": 0.06770103424787521,
+      "learning_rate": 4.954682779456193e-05,
+      "loss": 0.0729,
+      "step": 254
+    },
+    {
+      "epoch": 2.2577777777777777,
+      "grad_norm": 0.08226872980594635,
+      "learning_rate": 4.894259818731118e-05,
+      "loss": 0.0953,
+      "step": 255
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.07327685505151749,
+      "learning_rate": 4.833836858006043e-05,
+      "loss": 0.088,
+      "step": 256
+    },
+    {
+      "epoch": 2.2755555555555556,
+      "grad_norm": 0.0711284875869751,
+      "learning_rate": 4.7734138972809674e-05,
+      "loss": 0.0689,
+      "step": 257
+    },
+    {
+      "epoch": 2.2844444444444445,
+      "grad_norm": 0.08122266829013824,
+      "learning_rate": 4.712990936555892e-05,
+      "loss": 0.1304,
+      "step": 258
+    },
+    {
+      "epoch": 2.2933333333333334,
+      "grad_norm": 0.06601269543170929,
+      "learning_rate": 4.652567975830816e-05,
+      "loss": 0.0544,
+      "step": 259
+    },
+    {
+      "epoch": 2.3022222222222224,
+      "grad_norm": 0.08035172522068024,
+      "learning_rate": 4.5921450151057403e-05,
+      "loss": 0.0809,
+      "step": 260
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 0.07023400068283081,
+      "learning_rate": 4.5317220543806646e-05,
+      "loss": 0.0719,
+      "step": 261
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.07323497533798218,
+      "learning_rate": 4.4712990936555896e-05,
+      "loss": 0.0757,
+      "step": 262
+    },
+    {
+      "epoch": 2.328888888888889,
+      "grad_norm": 0.0711096003651619,
+      "learning_rate": 4.410876132930514e-05,
+      "loss": 0.079,
+      "step": 263
+    },
+    {
+      "epoch": 2.3377777777777777,
+      "grad_norm": 0.08337131887674332,
+      "learning_rate": 4.350453172205438e-05,
+      "loss": 0.0863,
+      "step": 264
+    },
+    {
+      "epoch": 2.3466666666666667,
+      "grad_norm": 0.06306735426187515,
+      "learning_rate": 4.2900302114803626e-05,
+      "loss": 0.0544,
+      "step": 265
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 0.06520617753267288,
+      "learning_rate": 4.229607250755287e-05,
+      "loss": 0.0492,
+      "step": 266
+    },
+    {
+      "epoch": 2.3644444444444446,
+      "grad_norm": 0.07521840184926987,
+      "learning_rate": 4.169184290030212e-05,
+      "loss": 0.0817,
+      "step": 267
+    },
+    {
+      "epoch": 2.3733333333333335,
+      "grad_norm": 0.11388452351093292,
+      "learning_rate": 4.108761329305136e-05,
+      "loss": 0.1195,
+      "step": 268
+    },
+    {
+      "epoch": 2.3822222222222225,
+      "grad_norm": 0.0842316523194313,
+      "learning_rate": 4.0483383685800605e-05,
+      "loss": 0.0697,
+      "step": 269
+    },
+    {
+      "epoch": 2.391111111111111,
+      "grad_norm": 0.0726594477891922,
+      "learning_rate": 3.9879154078549855e-05,
+      "loss": 0.0685,
+      "step": 270
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.07490499317646027,
+      "learning_rate": 3.92749244712991e-05,
+      "loss": 0.0753,
+      "step": 271
+    },
+    {
+      "epoch": 2.408888888888889,
+      "grad_norm": 0.08467234671115875,
+      "learning_rate": 3.867069486404834e-05,
+      "loss": 0.0902,
+      "step": 272
+    },
+    {
+      "epoch": 2.417777777777778,
+      "grad_norm": 0.07775551825761795,
+      "learning_rate": 3.8066465256797584e-05,
+      "loss": 0.0749,
+      "step": 273
+    },
+    {
+      "epoch": 2.4266666666666667,
+      "grad_norm": 0.07680890709161758,
+      "learning_rate": 3.746223564954683e-05,
+      "loss": 0.0839,
+      "step": 274
+    },
+    {
+      "epoch": 2.4355555555555557,
+      "grad_norm": 0.07432601600885391,
+      "learning_rate": 3.685800604229607e-05,
+      "loss": 0.0718,
+      "step": 275
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.0697220042347908,
+      "learning_rate": 3.625377643504532e-05,
+      "loss": 0.0581,
+      "step": 276
+    },
+    {
+      "epoch": 2.453333333333333,
+      "grad_norm": 0.0710417628288269,
+      "learning_rate": 3.564954682779456e-05,
+      "loss": 0.0741,
+      "step": 277
+    },
+    {
+      "epoch": 2.462222222222222,
+      "grad_norm": 0.07673481106758118,
+      "learning_rate": 3.504531722054381e-05,
+      "loss": 0.0792,
+      "step": 278
+    },
+    {
+      "epoch": 2.471111111111111,
+      "grad_norm": 0.07718473672866821,
+      "learning_rate": 3.4441087613293056e-05,
+      "loss": 0.0786,
+      "step": 279
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.0753309354186058,
+      "learning_rate": 3.38368580060423e-05,
+      "loss": 0.0651,
+      "step": 280
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 0.06466688960790634,
+      "learning_rate": 3.323262839879154e-05,
+      "loss": 0.0662,
+      "step": 281
+    },
+    {
+      "epoch": 2.497777777777778,
+      "grad_norm": 0.06847023218870163,
+      "learning_rate": 3.2628398791540785e-05,
+      "loss": 0.0606,
+      "step": 282
+    },
+    {
+      "epoch": 2.506666666666667,
+      "grad_norm": 0.08267179876565933,
+      "learning_rate": 3.202416918429003e-05,
+      "loss": 0.0963,
+      "step": 283
+    },
+    {
+      "epoch": 2.5155555555555553,
+      "grad_norm": 0.07589060813188553,
+      "learning_rate": 3.141993957703928e-05,
+      "loss": 0.0811,
+      "step": 284
+    },
+    {
+      "epoch": 2.5244444444444447,
+      "grad_norm": 0.07186582684516907,
+      "learning_rate": 3.081570996978852e-05,
+      "loss": 0.0727,
+      "step": 285
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.06798484176397324,
+      "learning_rate": 3.0211480362537764e-05,
+      "loss": 0.0683,
+      "step": 286
+    },
+    {
+      "epoch": 2.542222222222222,
+      "grad_norm": 0.06041852384805679,
+      "learning_rate": 2.9607250755287007e-05,
+      "loss": 0.0549,
+      "step": 287
+    },
+    {
+      "epoch": 2.551111111111111,
+      "grad_norm": 0.07672443240880966,
+      "learning_rate": 2.9003021148036257e-05,
+      "loss": 0.0835,
+      "step": 288
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.06650765985250473,
+      "learning_rate": 2.8398791540785504e-05,
+      "loss": 0.0625,
+      "step": 289
+    },
+    {
+      "epoch": 2.568888888888889,
+      "grad_norm": 0.07676387578248978,
+      "learning_rate": 2.7794561933534747e-05,
+      "loss": 0.0804,
+      "step": 290
+    },
+    {
+      "epoch": 2.5777777777777775,
+      "grad_norm": 0.06516220420598984,
+      "learning_rate": 2.719033232628399e-05,
+      "loss": 0.0558,
+      "step": 291
+    },
+    {
+      "epoch": 2.586666666666667,
+      "grad_norm": 0.06658012419939041,
+      "learning_rate": 2.6586102719033233e-05,
+      "loss": 0.0656,
+      "step": 292
+    },
+    {
+      "epoch": 2.5955555555555554,
+      "grad_norm": 0.06700943410396576,
+      "learning_rate": 2.598187311178248e-05,
+      "loss": 0.0652,
+      "step": 293
+    },
+    {
+      "epoch": 2.6044444444444443,
+      "grad_norm": 0.08271019905805588,
+      "learning_rate": 2.5377643504531723e-05,
+      "loss": 0.0939,
+      "step": 294
+    },
+    {
+      "epoch": 2.6133333333333333,
+      "grad_norm": 0.06946663558483124,
+      "learning_rate": 2.4773413897280966e-05,
+      "loss": 0.0608,
+      "step": 295
+    },
+    {
+      "epoch": 2.6222222222222222,
+      "grad_norm": 0.06652197986841202,
+      "learning_rate": 2.4169184290030216e-05,
+      "loss": 0.063,
+      "step": 296
+    },
+    {
+      "epoch": 2.631111111111111,
+      "grad_norm": 0.05776477977633476,
+      "learning_rate": 2.356495468277946e-05,
+      "loss": 0.0519,
+      "step": 297
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.06055834889411926,
+      "learning_rate": 2.2960725075528702e-05,
+      "loss": 0.0587,
+      "step": 298
+    },
+    {
+      "epoch": 2.648888888888889,
+      "grad_norm": 0.0723641887307167,
+      "learning_rate": 2.2356495468277948e-05,
+      "loss": 0.0673,
+      "step": 299
+    },
+    {
+      "epoch": 2.6577777777777776,
+      "grad_norm": 0.06614179909229279,
+      "learning_rate": 2.175226586102719e-05,
+      "loss": 0.0609,
+      "step": 300
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.07408380508422852,
+      "learning_rate": 2.1148036253776434e-05,
+      "loss": 0.073,
+      "step": 301
+    },
+    {
+      "epoch": 2.6755555555555555,
+      "grad_norm": 0.08053004741668701,
+      "learning_rate": 2.054380664652568e-05,
+      "loss": 0.084,
+      "step": 302
+    },
+    {
+      "epoch": 2.6844444444444444,
+      "grad_norm": 0.061500728130340576,
+      "learning_rate": 1.9939577039274927e-05,
+      "loss": 0.0478,
+      "step": 303
+    },
+    {
+      "epoch": 2.6933333333333334,
+      "grad_norm": 0.06272031366825104,
+      "learning_rate": 1.933534743202417e-05,
+      "loss": 0.0557,
+      "step": 304
+    },
+    {
+      "epoch": 2.7022222222222223,
+      "grad_norm": 0.08150549232959747,
+      "learning_rate": 1.8731117824773413e-05,
+      "loss": 0.0878,
+      "step": 305
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 0.08058076351881027,
+      "learning_rate": 1.812688821752266e-05,
+      "loss": 0.0708,
+      "step": 306
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.07689347863197327,
+      "learning_rate": 1.7522658610271906e-05,
+      "loss": 0.0827,
+      "step": 307
+    },
+    {
+      "epoch": 2.728888888888889,
+      "grad_norm": 0.07880861312150955,
+      "learning_rate": 1.691842900302115e-05,
+      "loss": 0.1007,
+      "step": 308
+    },
+    {
+      "epoch": 2.7377777777777776,
+      "grad_norm": 0.0824202448129654,
+      "learning_rate": 1.6314199395770393e-05,
+      "loss": 0.0773,
+      "step": 309
+    },
+    {
+      "epoch": 2.7466666666666666,
+      "grad_norm": 0.07320031523704529,
+      "learning_rate": 1.570996978851964e-05,
+      "loss": 0.0742,
+      "step": 310
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 0.0690142959356308,
+      "learning_rate": 1.5105740181268882e-05,
+      "loss": 0.0557,
+      "step": 311
+    },
+    {
+      "epoch": 2.7644444444444445,
+      "grad_norm": 0.062487728893756866,
+      "learning_rate": 1.4501510574018129e-05,
+      "loss": 0.0624,
+      "step": 312
+    },
+    {
+      "epoch": 2.7733333333333334,
+      "grad_norm": 0.07230405509471893,
+      "learning_rate": 1.3897280966767373e-05,
+      "loss": 0.0713,
+      "step": 313
+    },
+    {
+      "epoch": 2.7822222222222224,
+      "grad_norm": 0.08470380306243896,
+      "learning_rate": 1.3293051359516617e-05,
+      "loss": 0.1038,
+      "step": 314
+    },
+    {
+      "epoch": 2.7911111111111113,
+      "grad_norm": 0.06646347045898438,
+      "learning_rate": 1.2688821752265861e-05,
+      "loss": 0.0612,
+      "step": 315
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.07566383481025696,
+      "learning_rate": 1.2084592145015108e-05,
+      "loss": 0.0645,
+      "step": 316
+    },
+    {
+      "epoch": 2.8088888888888888,
+      "grad_norm": 0.07404222339391708,
+      "learning_rate": 1.1480362537764351e-05,
+      "loss": 0.0677,
+      "step": 317
+    },
+    {
+      "epoch": 2.8177777777777777,
+      "grad_norm": 0.07574770599603653,
+      "learning_rate": 1.0876132930513596e-05,
+      "loss": 0.0828,
+      "step": 318
+    },
+    {
+      "epoch": 2.8266666666666667,
+      "grad_norm": 0.08625300973653793,
+      "learning_rate": 1.027190332326284e-05,
+      "loss": 0.0852,
+      "step": 319
+    },
+    {
+      "epoch": 2.8355555555555556,
+      "grad_norm": 0.0686657726764679,
+      "learning_rate": 9.667673716012085e-06,
+      "loss": 0.0584,
+      "step": 320
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 0.0677306279540062,
+      "learning_rate": 9.06344410876133e-06,
+      "loss": 0.0712,
+      "step": 321
+    },
+    {
+      "epoch": 2.8533333333333335,
+      "grad_norm": 0.06888636946678162,
+      "learning_rate": 8.459214501510575e-06,
+      "loss": 0.0703,
+      "step": 322
+    },
+    {
+      "epoch": 2.862222222222222,
+      "grad_norm": 0.06507274508476257,
+      "learning_rate": 7.85498489425982e-06,
+      "loss": 0.0594,
+      "step": 323
+    },
+    {
+      "epoch": 2.871111111111111,
+      "grad_norm": 0.07514124363660812,
+      "learning_rate": 7.250755287009064e-06,
+      "loss": 0.0753,
+      "step": 324
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.0745137482881546,
+      "learning_rate": 6.646525679758308e-06,
+      "loss": 0.0802,
+      "step": 325
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.07600755989551544,
+      "learning_rate": 6.042296072507554e-06,
+      "loss": 0.0763,
+      "step": 326
+    },
+    {
+      "epoch": 2.897777777777778,
+      "grad_norm": 0.05982338637113571,
+      "learning_rate": 5.438066465256798e-06,
+      "loss": 0.0496,
+      "step": 327
+    },
+    {
+      "epoch": 2.9066666666666667,
+      "grad_norm": 0.06928596645593643,
+      "learning_rate": 4.833836858006043e-06,
+      "loss": 0.0626,
+      "step": 328
+    },
+    {
+      "epoch": 2.9155555555555557,
+      "grad_norm": 0.06719228625297546,
+      "learning_rate": 4.229607250755287e-06,
+      "loss": 0.0644,
+      "step": 329
+    },
+    {
+      "epoch": 2.924444444444444,
+      "grad_norm": 0.06885026395320892,
+      "learning_rate": 3.625377643504532e-06,
+      "loss": 0.0723,
+      "step": 330
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.07556895166635513,
+      "learning_rate": 3.021148036253777e-06,
+      "loss": 0.0746,
+      "step": 331
+    },
+    {
+      "epoch": 2.942222222222222,
+      "grad_norm": 0.08047506213188171,
+      "learning_rate": 2.4169184290030213e-06,
+      "loss": 0.0876,
+      "step": 332
+    },
+    {
+      "epoch": 2.951111111111111,
+      "grad_norm": 0.08711687475442886,
+      "learning_rate": 1.812688821752266e-06,
+      "loss": 0.1013,
+      "step": 333
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.07905985414981842,
+      "learning_rate": 1.2084592145015106e-06,
+      "loss": 0.0794,
+      "step": 334
+    },
+    {
+      "epoch": 2.968888888888889,
+      "grad_norm": 0.0679263323545456,
+      "learning_rate": 6.042296072507553e-07,
+      "loss": 0.0551,
+      "step": 335
+    },
+    {
+      "epoch": 2.977777777777778,
+      "grad_norm": 0.07112424075603485,
+      "learning_rate": 0.0,
+      "loss": 0.0743,
+      "step": 336
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 336,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.934810290318336e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8646b79648aa1ac4da60ae4e96af1188fc44f7c5fc9d2cc0f8baeb7c9ff0ad24
+size 5560