upload first version

.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: Qwen/Qwen2.5-Coder-1.5B
+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 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_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 sha256:79cec2678902faf0b19ec5fbcbf3e658d1f8bdecc4f6107c7c11aef064d5ace6
+size 4372840

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,199 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_start|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation": true,
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1253 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 5555,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0288028802880288,
+      "grad_norm": 0.9036304950714111,
+      "learning_rate": 5.755395683453238e-07,
+      "loss": 1.0187,
+      "step": 32
+    },
+    {
+      "epoch": 0.0576057605760576,
+      "grad_norm": 2.02474045753479,
+      "learning_rate": 1.1510791366906476e-06,
+      "loss": 1.0342,
+      "step": 64
+    },
+    {
+      "epoch": 0.08640864086408641,
+      "grad_norm": 1.7671840190887451,
+      "learning_rate": 1.7266187050359715e-06,
+      "loss": 1.0534,
+      "step": 96
+    },
+    {
+      "epoch": 0.1152115211521152,
+      "grad_norm": 2.703395366668701,
+      "learning_rate": 2.302158273381295e-06,
+      "loss": 1.0047,
+      "step": 128
+    },
+    {
+      "epoch": 0.14401440144014402,
+      "grad_norm": 2.96386456489563,
+      "learning_rate": 2.877697841726619e-06,
+      "loss": 1.0125,
+      "step": 160
+    },
+    {
+      "epoch": 0.17281728172817282,
+      "grad_norm": 0.9527461528778076,
+      "learning_rate": 3.453237410071943e-06,
+      "loss": 0.9816,
+      "step": 192
+    },
+    {
+      "epoch": 0.20162016201620162,
+      "grad_norm": 2.197382926940918,
+      "learning_rate": 4.028776978417267e-06,
+      "loss": 1.05,
+      "step": 224
+    },
+    {
+      "epoch": 0.2304230423042304,
+      "grad_norm": 1.8034260272979736,
+      "learning_rate": 4.60431654676259e-06,
+      "loss": 0.8815,
+      "step": 256
+    },
+    {
+      "epoch": 0.25922592259225924,
+      "grad_norm": 2.3050363063812256,
+      "learning_rate": 5.179856115107914e-06,
+      "loss": 0.9027,
+      "step": 288
+    },
+    {
+      "epoch": 0.28802880288028804,
+      "grad_norm": 2.022681951522827,
+      "learning_rate": 5.755395683453238e-06,
+      "loss": 0.865,
+      "step": 320
+    },
+    {
+      "epoch": 0.31683168316831684,
+      "grad_norm": 1.3653255701065063,
+      "learning_rate": 6.330935251798561e-06,
+      "loss": 0.8724,
+      "step": 352
+    },
+    {
+      "epoch": 0.34563456345634563,
+      "grad_norm": 1.3452287912368774,
+      "learning_rate": 6.906474820143886e-06,
+      "loss": 0.8093,
+      "step": 384
+    },
+    {
+      "epoch": 0.37443744374437443,
+      "grad_norm": 1.9356400966644287,
+      "learning_rate": 7.48201438848921e-06,
+      "loss": 0.7579,
+      "step": 416
+    },
+    {
+      "epoch": 0.40324032403240323,
+      "grad_norm": 1.4237608909606934,
+      "learning_rate": 8.057553956834533e-06,
+      "loss": 0.7364,
+      "step": 448
+    },
+    {
+      "epoch": 0.43204320432043203,
+      "grad_norm": 1.9049218893051147,
+      "learning_rate": 8.633093525179856e-06,
+      "loss": 0.7033,
+      "step": 480
+    },
+    {
+      "epoch": 0.4608460846084608,
+      "grad_norm": 3.9214580059051514,
+      "learning_rate": 9.20863309352518e-06,
+      "loss": 0.696,
+      "step": 512
+    },
+    {
+      "epoch": 0.4896489648964896,
+      "grad_norm": 1.9122344255447388,
+      "learning_rate": 9.784172661870505e-06,
+      "loss": 0.697,
+      "step": 544
+    },
+    {
+      "epoch": 0.5184518451845185,
+      "grad_norm": 4.641770362854004,
+      "learning_rate": 9.999605063062183e-06,
+      "loss": 0.6691,
+      "step": 576
+    },
+    {
+      "epoch": 0.5472547254725473,
+      "grad_norm": 1.5034338235855103,
+      "learning_rate": 9.997330428740717e-06,
+      "loss": 0.6846,
+      "step": 608
+    },
+    {
+      "epoch": 0.5760576057605761,
+      "grad_norm": 1.306266188621521,
+      "learning_rate": 9.993034838418394e-06,
+      "loss": 0.6663,
+      "step": 640
+    },
+    {
+      "epoch": 0.6048604860486049,
+      "grad_norm": 4.800021648406982,
+      "learning_rate": 9.986720029262515e-06,
+      "loss": 0.6264,
+      "step": 672
+    },
+    {
+      "epoch": 0.6336633663366337,
+      "grad_norm": 1.366411566734314,
+      "learning_rate": 9.97838855502686e-06,
+      "loss": 0.6116,
+      "step": 704
+    },
+    {
+      "epoch": 0.6624662466246625,
+      "grad_norm": 1.8418484926223755,
+      "learning_rate": 9.968043785018917e-06,
+      "loss": 0.6244,
+      "step": 736
+    },
+    {
+      "epoch": 0.6912691269126913,
+      "grad_norm": 7.662785053253174,
+      "learning_rate": 9.955689902737327e-06,
+      "loss": 0.5972,
+      "step": 768
+    },
+    {
+      "epoch": 0.7200720072007201,
+      "grad_norm": 1.7773517370224,
+      "learning_rate": 9.941331904180025e-06,
+      "loss": 0.6061,
+      "step": 800
+    },
+    {
+      "epoch": 0.7488748874887489,
+      "grad_norm": 1.4460841417312622,
+      "learning_rate": 9.924975595823843e-06,
+      "loss": 0.5821,
+      "step": 832
+    },
+    {
+      "epoch": 0.7776777677767777,
+      "grad_norm": 2.224186897277832,
+      "learning_rate": 9.906627592276318e-06,
+      "loss": 0.6255,
+      "step": 864
+    },
+    {
+      "epoch": 0.8064806480648065,
+      "grad_norm": 1.6951428651809692,
+      "learning_rate": 9.886295313600703e-06,
+      "loss": 0.6272,
+      "step": 896
+    },
+    {
+      "epoch": 0.8352835283528353,
+      "grad_norm": 1.9330335855484009,
+      "learning_rate": 9.86398698231524e-06,
+      "loss": 0.5994,
+      "step": 928
+    },
+    {
+      "epoch": 0.8640864086408641,
+      "grad_norm": 1.4903757572174072,
+      "learning_rate": 9.839711620067906e-06,
+      "loss": 0.5589,
+      "step": 960
+    },
+    {
+      "epoch": 0.8928892889288929,
+      "grad_norm": 1.2906200885772705,
+      "learning_rate": 9.813479043988013e-06,
+      "loss": 0.5859,
+      "step": 992
+    },
+    {
+      "epoch": 0.9216921692169217,
+      "grad_norm": 1.8480700254440308,
+      "learning_rate": 9.785299862716072e-06,
+      "loss": 0.6045,
+      "step": 1024
+    },
+    {
+      "epoch": 0.9504950495049505,
+      "grad_norm": 1.5740501880645752,
+      "learning_rate": 9.755185472113595e-06,
+      "loss": 0.5862,
+      "step": 1056
+    },
+    {
+      "epoch": 0.9792979297929792,
+      "grad_norm": 2.271888017654419,
+      "learning_rate": 9.723148050654522e-06,
+      "loss": 0.5833,
+      "step": 1088
+    },
+    {
+      "epoch": 1.008100810081008,
+      "grad_norm": 0.8760111331939697,
+      "learning_rate": 9.689200554500162e-06,
+      "loss": 0.5658,
+      "step": 1120
+    },
+    {
+      "epoch": 1.036903690369037,
+      "grad_norm": 1.2301350831985474,
+      "learning_rate": 9.65335671225963e-06,
+      "loss": 0.5839,
+      "step": 1152
+    },
+    {
+      "epoch": 1.0657065706570656,
+      "grad_norm": 1.7237297296524048,
+      "learning_rate": 9.615631019437896e-06,
+      "loss": 0.5718,
+      "step": 1184
+    },
+    {
+      "epoch": 1.0945094509450946,
+      "grad_norm": 1.146071434020996,
+      "learning_rate": 9.576038732573702e-06,
+      "loss": 0.6036,
+      "step": 1216
+    },
+    {
+      "epoch": 1.1233123312331232,
+      "grad_norm": 1.4510979652404785,
+      "learning_rate": 9.53459586306971e-06,
+      "loss": 0.602,
+      "step": 1248
+    },
+    {
+      "epoch": 1.1521152115211521,
+      "grad_norm": 1.3618237972259521,
+      "learning_rate": 9.491319170717375e-06,
+      "loss": 0.5661,
+      "step": 1280
+    },
+    {
+      "epoch": 1.1809180918091808,
+      "grad_norm": 1.5930922031402588,
+      "learning_rate": 9.446226156919164e-06,
+      "loss": 0.5892,
+      "step": 1312
+    },
+    {
+      "epoch": 1.2097209720972097,
+      "grad_norm": 1.0816315412521362,
+      "learning_rate": 9.399335057610872e-06,
+      "loss": 0.5816,
+      "step": 1344
+    },
+    {
+      "epoch": 1.2385238523852384,
+      "grad_norm": 1.2080299854278564,
+      "learning_rate": 9.350664835886873e-06,
+      "loss": 0.5766,
+      "step": 1376
+    },
+    {
+      "epoch": 1.2673267326732673,
+      "grad_norm": 1.655219554901123,
+      "learning_rate": 9.300235174331309e-06,
+      "loss": 0.5925,
+      "step": 1408
+    },
+    {
+      "epoch": 1.296129612961296,
+      "grad_norm": 1.02821683883667,
+      "learning_rate": 9.248066467058315e-06,
+      "loss": 0.5726,
+      "step": 1440
+    },
+    {
+      "epoch": 1.324932493249325,
+      "grad_norm": 1.9538413286209106,
+      "learning_rate": 9.194179811464499e-06,
+      "loss": 0.5405,
+      "step": 1472
+    },
+    {
+      "epoch": 1.3537353735373538,
+      "grad_norm": 1.4714971780776978,
+      "learning_rate": 9.138596999696994e-06,
+      "loss": 0.5848,
+      "step": 1504
+    },
+    {
+      "epoch": 1.3825382538253825,
+      "grad_norm": 1.3316493034362793,
+      "learning_rate": 9.081340509840568e-06,
+      "loss": 0.5796,
+      "step": 1536
+    },
+    {
+      "epoch": 1.4113411341134112,
+      "grad_norm": 1.2864930629730225,
+      "learning_rate": 9.022433496827323e-06,
+      "loss": 0.5695,
+      "step": 1568
+    },
+    {
+      "epoch": 1.4401440144014401,
+      "grad_norm": 1.261751651763916,
+      "learning_rate": 8.961899783072673e-06,
+      "loss": 0.5779,
+      "step": 1600
+    },
+    {
+      "epoch": 1.468946894689469,
+      "grad_norm": 1.6343884468078613,
+      "learning_rate": 8.899763848841396e-06,
+      "loss": 0.6653,
+      "step": 1632
+    },
+    {
+      "epoch": 1.4977497749774977,
+      "grad_norm": 1.3842564821243286,
+      "learning_rate": 8.836050822347632e-06,
+      "loss": 0.6163,
+      "step": 1664
+    },
+    {
+      "epoch": 1.5265526552655264,
+      "grad_norm": 1.3212823867797852,
+      "learning_rate": 8.770786469592863e-06,
+      "loss": 0.5873,
+      "step": 1696
+    },
+    {
+      "epoch": 1.5553555355535553,
+      "grad_norm": 1.8528977632522583,
+      "learning_rate": 8.703997183945949e-06,
+      "loss": 0.5722,
+      "step": 1728
+    },
+    {
+      "epoch": 1.5841584158415842,
+      "grad_norm": 2.5258665084838867,
+      "learning_rate": 8.635709975469479e-06,
+      "loss": 0.5556,
+      "step": 1760
+    },
+    {
+      "epoch": 1.612961296129613,
+      "grad_norm": 1.2707765102386475,
+      "learning_rate": 8.565952459996684e-06,
+      "loss": 0.5536,
+      "step": 1792
+    },
+    {
+      "epoch": 1.6417641764176416,
+      "grad_norm": 1.631494164466858,
+      "learning_rate": 8.49475284796342e-06,
+      "loss": 0.5651,
+      "step": 1824
+    },
+    {
+      "epoch": 1.6705670567056705,
+      "grad_norm": 2.1226248741149902,
+      "learning_rate": 8.422139932999658e-06,
+      "loss": 0.5679,
+      "step": 1856
+    },
+    {
+      "epoch": 1.6993699369936994,
+      "grad_norm": 2.1261792182922363,
+      "learning_rate": 8.34814308028513e-06,
+      "loss": 0.5896,
+      "step": 1888
+    },
+    {
+      "epoch": 1.7281728172817283,
+      "grad_norm": 3.6276915073394775,
+      "learning_rate": 8.272792214673851e-06,
+      "loss": 0.5859,
+      "step": 1920
+    },
+    {
+      "epoch": 1.756975697569757,
+      "grad_norm": 1.1661372184753418,
+      "learning_rate": 8.19611780859229e-06,
+      "loss": 0.6355,
+      "step": 1952
+    },
+    {
+      "epoch": 1.7857785778577857,
+      "grad_norm": 1.1813215017318726,
+      "learning_rate": 8.118150869716101e-06,
+      "loss": 0.5659,
+      "step": 1984
+    },
+    {
+      "epoch": 1.8145814581458146,
+      "grad_norm": 1.6434768438339233,
+      "learning_rate": 8.038922928430408e-06,
+      "loss": 0.5681,
+      "step": 2016
+    },
+    {
+      "epoch": 1.8433843384338435,
+      "grad_norm": 2.215708017349243,
+      "learning_rate": 7.95846602507868e-06,
+      "loss": 0.5849,
+      "step": 2048
+    },
+    {
+      "epoch": 1.8721872187218722,
+      "grad_norm": 1.4538156986236572,
+      "learning_rate": 7.876812697005396e-06,
+      "loss": 0.5677,
+      "step": 2080
+    },
+    {
+      "epoch": 1.900990099009901,
+      "grad_norm": 1.8781392574310303,
+      "learning_rate": 7.79399596539771e-06,
+      "loss": 0.5612,
+      "step": 2112
+    },
+    {
+      "epoch": 1.9297929792979298,
+      "grad_norm": 2.6248340606689453,
+      "learning_rate": 7.710049321931453e-06,
+      "loss": 0.5578,
+      "step": 2144
+    },
+    {
+      "epoch": 1.9585958595859587,
+      "grad_norm": 2.893212080001831,
+      "learning_rate": 7.625006715226844e-06,
+      "loss": 0.5925,
+      "step": 2176
+    },
+    {
+      "epoch": 1.9873987398739874,
+      "grad_norm": 1.3693437576293945,
+      "learning_rate": 7.538902537119445e-06,
+      "loss": 0.5519,
+      "step": 2208
+    },
+    {
+      "epoch": 2.016201620162016,
+      "grad_norm": 0.9655335545539856,
+      "learning_rate": 7.451771608751854e-06,
+      "loss": 0.5848,
+      "step": 2240
+    },
+    {
+      "epoch": 2.045004500450045,
+      "grad_norm": 1.7546676397323608,
+      "learning_rate": 7.3636491664917746e-06,
+      "loss": 0.5676,
+      "step": 2272
+    },
+    {
+      "epoch": 2.073807380738074,
+      "grad_norm": 1.35713791847229,
+      "learning_rate": 7.274570847682192e-06,
+      "loss": 0.5995,
+      "step": 2304
+    },
+    {
+      "epoch": 2.102610261026103,
+      "grad_norm": 1.368743896484375,
+      "learning_rate": 7.184572676229373e-06,
+      "loss": 0.5532,
+      "step": 2336
+    },
+    {
+      "epoch": 2.1314131413141313,
+      "grad_norm": 1.5946100950241089,
+      "learning_rate": 7.093691048034539e-06,
+      "loss": 0.5732,
+      "step": 2368
+    },
+    {
+      "epoch": 2.16021602160216,
+      "grad_norm": 1.4962303638458252,
+      "learning_rate": 7.001962716275111e-06,
+      "loss": 0.6021,
+      "step": 2400
+    },
+    {
+      "epoch": 2.189018901890189,
+      "grad_norm": 2.6867597103118896,
+      "learning_rate": 6.909424776541456e-06,
+      "loss": 0.5429,
+      "step": 2432
+    },
+    {
+      "epoch": 2.217821782178218,
+      "grad_norm": 1.6566091775894165,
+      "learning_rate": 6.816114651835171e-06,
+      "loss": 0.5284,
+      "step": 2464
+    },
+    {
+      "epoch": 2.2466246624662465,
+      "grad_norm": 1.1805468797683716,
+      "learning_rate": 6.7220700774349524e-06,
+      "loss": 0.5797,
+      "step": 2496
+    },
+    {
+      "epoch": 2.2754275427542754,
+      "grad_norm": 1.6449726819992065,
+      "learning_rate": 6.627329085636178e-06,
+      "loss": 0.5624,
+      "step": 2528
+    },
+    {
+      "epoch": 2.3042304230423043,
+      "grad_norm": 1.2300235033035278,
+      "learning_rate": 6.531929990370387e-06,
+      "loss": 0.5629,
+      "step": 2560
+    },
+    {
+      "epoch": 2.333033303330333,
+      "grad_norm": 1.2485629320144653,
+      "learning_rate": 6.43591137171084e-06,
+      "loss": 0.561,
+      "step": 2592
+    },
+    {
+      "epoch": 2.3618361836183617,
+      "grad_norm": 1.2627168893814087,
+      "learning_rate": 6.3393120602704675e-06,
+      "loss": 0.5707,
+      "step": 2624
+    },
+    {
+      "epoch": 2.3906390639063906,
+      "grad_norm": 1.8480335474014282,
+      "learning_rate": 6.242171121498498e-06,
+      "loss": 0.5759,
+      "step": 2656
+    },
+    {
+      "epoch": 2.4194419441944195,
+      "grad_norm": 1.5584763288497925,
+      "learning_rate": 6.144527839882107e-06,
+      "loss": 0.5641,
+      "step": 2688
+    },
+    {
+      "epoch": 2.4482448244824484,
+      "grad_norm": 1.1628447771072388,
+      "learning_rate": 6.046421703059493e-06,
+      "loss": 0.5853,
+      "step": 2720
+    },
+    {
+      "epoch": 2.477047704770477,
+      "grad_norm": 1.420699119567871,
+      "learning_rate": 5.9478923858507955e-06,
+      "loss": 0.5572,
+      "step": 2752
+    },
+    {
+      "epoch": 2.5058505850585058,
+      "grad_norm": 1.5408899784088135,
+      "learning_rate": 5.848979734213309e-06,
+      "loss": 0.5835,
+      "step": 2784
+    },
+    {
+      "epoch": 2.5346534653465347,
+      "grad_norm": 3.342973470687866,
+      "learning_rate": 5.74972374912751e-06,
+      "loss": 0.5648,
+      "step": 2816
+    },
+    {
+      "epoch": 2.5634563456345636,
+      "grad_norm": 1.3234657049179077,
+      "learning_rate": 5.650164570420358e-06,
+      "loss": 0.5838,
+      "step": 2848
+    },
+    {
+      "epoch": 2.592259225922592,
+      "grad_norm": 3.896916627883911,
+      "learning_rate": 5.5503424605324715e-06,
+      "loss": 0.5716,
+      "step": 2880
+    },
+    {
+      "epoch": 2.621062106210621,
+      "grad_norm": 1.4137349128723145,
+      "learning_rate": 5.450297788235718e-06,
+      "loss": 0.5895,
+      "step": 2912
+    },
+    {
+      "epoch": 2.64986498649865,
+      "grad_norm": 1.852388620376587,
+      "learning_rate": 5.350071012307776e-06,
+      "loss": 0.5525,
+      "step": 2944
+    },
+    {
+      "epoch": 2.678667866786679,
+      "grad_norm": 1.226164698600769,
+      "learning_rate": 5.24970266517034e-06,
+      "loss": 0.5549,
+      "step": 2976
+    },
+    {
+      "epoch": 2.7074707470747077,
+      "grad_norm": 1.257299542427063,
+      "learning_rate": 5.149233336497501e-06,
+      "loss": 0.5797,
+      "step": 3008
+    },
+    {
+      "epoch": 2.736273627362736,
+      "grad_norm": 1.4466633796691895,
+      "learning_rate": 5.048703656801004e-06,
+      "loss": 0.5629,
+      "step": 3040
+    },
+    {
+      "epoch": 2.765076507650765,
+      "grad_norm": 2.2335245609283447,
+      "learning_rate": 4.948154280998981e-06,
+      "loss": 0.5626,
+      "step": 3072
+    },
+    {
+      "epoch": 2.793879387938794,
+      "grad_norm": 1.4836534261703491,
+      "learning_rate": 4.847625871974807e-06,
+      "loss": 0.5659,
+      "step": 3104
+    },
+    {
+      "epoch": 2.8226822682268224,
+      "grad_norm": 1.282368540763855,
+      "learning_rate": 4.747159084132742e-06,
+      "loss": 0.5957,
+      "step": 3136
+    },
+    {
+      "epoch": 2.8514851485148514,
+      "grad_norm": 1.2289072275161743,
+      "learning_rate": 4.646794546957001e-06,
+      "loss": 0.5754,
+      "step": 3168
+    },
+    {
+      "epoch": 2.8802880288028803,
+      "grad_norm": 1.3047752380371094,
+      "learning_rate": 4.546572848580907e-06,
+      "loss": 0.6166,
+      "step": 3200
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 1.365952730178833,
+      "learning_rate": 4.446534519372744e-06,
+      "loss": 0.5474,
+      "step": 3232
+    },
+    {
+      "epoch": 2.937893789378938,
+      "grad_norm": 1.4504116773605347,
+      "learning_rate": 4.34672001554501e-06,
+      "loss": 0.564,
+      "step": 3264
+    },
+    {
+      "epoch": 2.9666966696669665,
+      "grad_norm": 2.4160330295562744,
+      "learning_rate": 4.247169702793625e-06,
+      "loss": 0.5578,
+      "step": 3296
+    },
+    {
+      "epoch": 2.9954995499549955,
+      "grad_norm": 1.876542568206787,
+      "learning_rate": 4.1479238399737485e-06,
+      "loss": 0.5885,
+      "step": 3328
+    },
+    {
+      "epoch": 3.0243024302430244,
+      "grad_norm": 2.028958320617676,
+      "learning_rate": 4.049022562818829e-06,
+      "loss": 0.5875,
+      "step": 3360
+    },
+    {
+      "epoch": 3.0531053105310533,
+      "grad_norm": 1.76653254032135,
+      "learning_rate": 3.950505867709418e-06,
+      "loss": 0.5559,
+      "step": 3392
+    },
+    {
+      "epoch": 3.0819081908190817,
+      "grad_norm": 1.768809199333191,
+      "learning_rate": 3.852413595498343e-06,
+      "loss": 0.5792,
+      "step": 3424
+    },
+    {
+      "epoch": 3.1107110711071106,
+      "grad_norm": 1.5263768434524536,
+      "learning_rate": 3.7547854153987973e-06,
+      "loss": 0.5742,
+      "step": 3456
+    },
+    {
+      "epoch": 3.1395139513951396,
+      "grad_norm": 1.5573300123214722,
+      "learning_rate": 3.6576608089418188e-06,
+      "loss": 0.5664,
+      "step": 3488
+    },
+    {
+      "epoch": 3.1683168316831685,
+      "grad_norm": 1.0428520441055298,
+      "learning_rate": 3.561079054009678e-06,
+      "loss": 0.5434,
+      "step": 3520
+    },
+    {
+      "epoch": 3.197119711971197,
+      "grad_norm": 1.465216875076294,
+      "learning_rate": 3.4650792089516238e-06,
+      "loss": 0.5603,
+      "step": 3552
+    },
+    {
+      "epoch": 3.225922592259226,
+      "grad_norm": 1.1263318061828613,
+      "learning_rate": 3.3697000967884107e-06,
+      "loss": 0.5636,
+      "step": 3584
+    },
+    {
+      "epoch": 3.2547254725472547,
+      "grad_norm": 1.6343493461608887,
+      "learning_rate": 3.274980289511995e-06,
+      "loss": 0.5797,
+      "step": 3616
+    },
+    {
+      "epoch": 3.2835283528352837,
+      "grad_norm": 2.2945406436920166,
+      "learning_rate": 3.1809580924867358e-06,
+      "loss": 0.5638,
+      "step": 3648
+    },
+    {
+      "epoch": 3.312331233123312,
+      "grad_norm": 1.1425927877426147,
+      "learning_rate": 3.087671528958445e-06,
+      "loss": 0.559,
+      "step": 3680
+    },
+    {
+      "epoch": 3.341134113411341,
+      "grad_norm": 1.1738224029541016,
+      "learning_rate": 2.9951583246775147e-06,
+      "loss": 0.5947,
+      "step": 3712
+    },
+    {
+      "epoch": 3.36993699369937,
+      "grad_norm": 1.0960267782211304,
+      "learning_rate": 2.9034558926423427e-06,
+      "loss": 0.5609,
+      "step": 3744
+    },
+    {
+      "epoch": 3.398739873987399,
+      "grad_norm": 2.027769088745117,
+      "learning_rate": 2.812601317969266e-06,
+      "loss": 0.5932,
+      "step": 3776
+    },
+    {
+      "epoch": 3.4275427542754278,
+      "grad_norm": 1.8806779384613037,
+      "learning_rate": 2.7226313428950703e-06,
+      "loss": 0.546,
+      "step": 3808
+    },
+    {
+      "epoch": 3.4563456345634562,
+      "grad_norm": 1.778334617614746,
+      "learning_rate": 2.633582351918156e-06,
+      "loss": 0.5645,
+      "step": 3840
+    },
+    {
+      "epoch": 3.485148514851485,
+      "grad_norm": 1.2001926898956299,
+      "learning_rate": 2.545490357084409e-06,
+      "loss": 0.5634,
+      "step": 3872
+    },
+    {
+      "epoch": 3.513951395139514,
+      "grad_norm": 3.2067384719848633,
+      "learning_rate": 2.4583909834236563e-06,
+      "loss": 0.5409,
+      "step": 3904
+    },
+    {
+      "epoch": 3.5427542754275425,
+      "grad_norm": 2.1273581981658936,
+      "learning_rate": 2.372319454542659e-06,
+      "loss": 0.5632,
+      "step": 3936
+    },
+    {
+      "epoch": 3.5715571557155714,
+      "grad_norm": 1.4944703578948975,
+      "learning_rate": 2.28731057838043e-06,
+      "loss": 0.5438,
+      "step": 3968
+    },
+    {
+      "epoch": 3.6003600360036003,
+      "grad_norm": 1.5785070657730103,
+      "learning_rate": 2.203398733131661e-06,
+      "loss": 0.5491,
+      "step": 4000
+    },
+    {
+      "epoch": 3.6291629162916292,
+      "grad_norm": 1.9863430261611938,
+      "learning_rate": 2.120617853343926e-06,
+      "loss": 0.5681,
+      "step": 4032
+    },
+    {
+      "epoch": 3.657965796579658,
+      "grad_norm": 1.9844887256622314,
+      "learning_rate": 2.0390014161943224e-06,
+      "loss": 0.55,
+      "step": 4064
+    },
+    {
+      "epoch": 3.6867686768676866,
+      "grad_norm": 1.2234737873077393,
+      "learning_rate": 1.958582427951051e-06,
+      "loss": 0.5517,
+      "step": 4096
+    },
+    {
+      "epoch": 3.7155715571557155,
+      "grad_norm": 1.3753498792648315,
+      "learning_rate": 1.8793934106254557e-06,
+      "loss": 0.5613,
+      "step": 4128
+    },
+    {
+      "epoch": 3.7443744374437444,
+      "grad_norm": 1.6427245140075684,
+      "learning_rate": 1.8014663888198763e-06,
+      "loss": 0.5548,
+      "step": 4160
+    },
+    {
+      "epoch": 3.7731773177317733,
+      "grad_norm": 2.217555522918701,
+      "learning_rate": 1.7248328767766875e-06,
+      "loss": 0.5803,
+      "step": 4192
+    },
+    {
+      "epoch": 3.801980198019802,
+      "grad_norm": 1.24624764919281,
+      "learning_rate": 1.6495238656337076e-06,
+      "loss": 0.6296,
+      "step": 4224
+    },
+    {
+      "epoch": 3.8307830783078307,
+      "grad_norm": 1.3684077262878418,
+      "learning_rate": 1.575569810891156e-06,
+      "loss": 0.5865,
+      "step": 4256
+    },
+    {
+      "epoch": 3.8595859585958596,
+      "grad_norm": 2.7931735515594482,
+      "learning_rate": 1.503000620095244e-06,
+      "loss": 0.5758,
+      "step": 4288
+    },
+    {
+      "epoch": 3.8883888388838885,
+      "grad_norm": 1.8946348428726196,
+      "learning_rate": 1.4318456407433434e-06,
+      "loss": 0.563,
+      "step": 4320
+    },
+    {
+      "epoch": 3.9171917191719174,
+      "grad_norm": 1.750241756439209,
+      "learning_rate": 1.3621336484156456e-06,
+      "loss": 0.5692,
+      "step": 4352
+    },
+    {
+      "epoch": 3.945994599459946,
+      "grad_norm": 1.4938685894012451,
+      "learning_rate": 1.2938928351381224e-06,
+      "loss": 0.5379,
+      "step": 4384
+    },
+    {
+      "epoch": 3.974797479747975,
+      "grad_norm": 4.275557041168213,
+      "learning_rate": 1.2271507979814624e-06,
+      "loss": 0.534,
+      "step": 4416
+    },
+    {
+      "epoch": 4.003600360036003,
+      "grad_norm": 1.308555245399475,
+      "learning_rate": 1.1619345279006212e-06,
+      "loss": 0.5957,
+      "step": 4448
+    },
+    {
+      "epoch": 4.032403240324032,
+      "grad_norm": 1.5460844039916992,
+      "learning_rate": 1.0982703988194876e-06,
+      "loss": 0.5711,
+      "step": 4480
+    },
+    {
+      "epoch": 4.061206120612061,
+      "grad_norm": 1.5028718709945679,
+      "learning_rate": 1.0361841569650816e-06,
+      "loss": 0.5848,
+      "step": 4512
+    },
+    {
+      "epoch": 4.09000900090009,
+      "grad_norm": 1.7333652973175049,
+      "learning_rate": 9.75700910455592e-07,
+      "loss": 0.5748,
+      "step": 4544
+    },
+    {
+      "epoch": 4.118811881188119,
+      "grad_norm": 1.941709041595459,
+      "learning_rate": 9.168451191464822e-07,
+      "loss": 0.5728,
+      "step": 4576
+    },
+    {
+      "epoch": 4.147614761476148,
+      "grad_norm": 1.418080449104309,
+      "learning_rate": 8.596405847387462e-07,
+      "loss": 0.5787,
+      "step": 4608
+    },
+    {
+      "epoch": 4.176417641764177,
+      "grad_norm": 1.187457799911499,
+      "learning_rate": 8.041104411533329e-07,
+      "loss": 0.5324,
+      "step": 4640
+    },
+    {
+      "epoch": 4.205220522052206,
+      "grad_norm": 1.3761279582977295,
+      "learning_rate": 7.502771451756197e-07,
+      "loss": 0.5721,
+      "step": 4672
+    },
+    {
+      "epoch": 4.234023402340234,
+      "grad_norm": 0.9498482942581177,
+      "learning_rate": 6.981624673737336e-07,
+      "loss": 0.5712,
+      "step": 4704
+    },
+    {
+      "epoch": 4.262826282628263,
+      "grad_norm": 1.5619556903839111,
+      "learning_rate": 6.477874832943781e-07,
+      "loss": 0.5483,
+      "step": 4736
+    },
+    {
+      "epoch": 4.2916291629162915,
+      "grad_norm": 1.354587435722351,
+      "learning_rate": 5.991725649397279e-07,
+      "loss": 0.5314,
+      "step": 4768
+    },
+    {
+      "epoch": 4.32043204320432,
+      "grad_norm": 1.8367897272109985,
+      "learning_rate": 5.523373725288506e-07,
+      "loss": 0.5895,
+      "step": 4800
+    },
+    {
+      "epoch": 4.349234923492349,
+      "grad_norm": 1.9770034551620483,
+      "learning_rate": 5.073008465469731e-07,
+      "loss": 0.5482,
+      "step": 4832
+    },
+    {
+      "epoch": 4.378037803780378,
+      "grad_norm": 1.3692898750305176,
+      "learning_rate": 4.640812000858108e-07,
+      "loss": 0.5754,
+      "step": 4864
+    },
+    {
+      "epoch": 4.406840684068407,
+      "grad_norm": 1.9973537921905518,
+      "learning_rate": 4.226959114780699e-07,
+      "loss": 0.5309,
+      "step": 4896
+    },
+    {
+      "epoch": 4.435643564356436,
+      "grad_norm": 1.6791578531265259,
+      "learning_rate": 3.831617172290808e-07,
+      "loss": 0.5791,
+      "step": 4928
+    },
+    {
+      "epoch": 4.464446444644464,
+      "grad_norm": 1.2366864681243896,
+      "learning_rate": 3.454946052484376e-07,
+      "loss": 0.5401,
+      "step": 4960
+    },
+    {
+      "epoch": 4.493249324932493,
+      "grad_norm": 1.513241171836853,
+      "learning_rate": 3.0970980838437416e-07,
+      "loss": 0.5923,
+      "step": 4992
+    },
+    {
+      "epoch": 4.522052205220522,
+      "grad_norm": 1.3842517137527466,
+      "learning_rate": 2.758217982634903e-07,
+      "loss": 0.5654,
+      "step": 5024
+    },
+    {
+      "epoch": 4.550855085508551,
+      "grad_norm": 1.9963948726654053,
+      "learning_rate": 2.4384427943832335e-07,
+      "loss": 0.5736,
+      "step": 5056
+    },
+    {
+      "epoch": 4.57965796579658,
+      "grad_norm": 1.2688953876495361,
+      "learning_rate": 2.1379018384513116e-07,
+      "loss": 0.5604,
+      "step": 5088
+    },
+    {
+      "epoch": 4.608460846084609,
+      "grad_norm": 1.2119768857955933,
+      "learning_rate": 1.856716655741242e-07,
+      "loss": 0.561,
+      "step": 5120
+    },
+    {
+      "epoch": 4.6372637263726375,
+      "grad_norm": 1.7336974143981934,
+      "learning_rate": 1.5950009595426474e-07,
+      "loss": 0.579,
+      "step": 5152
+    },
+    {
+      "epoch": 4.666066606660666,
+      "grad_norm": 3.910386562347412,
+      "learning_rate": 1.3528605895461734e-07,
+      "loss": 0.5591,
+      "step": 5184
+    },
+    {
+      "epoch": 4.694869486948695,
+      "grad_norm": 1.0510704517364502,
+      "learning_rate": 1.130393469041241e-07,
+      "loss": 0.5636,
+      "step": 5216
+    },
+    {
+      "epoch": 4.723672367236723,
+      "grad_norm": 1.8472617864608765,
+      "learning_rate": 9.27689565315093e-08,
+      "loss": 0.5553,
+      "step": 5248
+    },
+    {
+      "epoch": 4.752475247524752,
+      "grad_norm": 1.5597736835479736,
+      "learning_rate": 7.448308532694237e-08,
+      "loss": 0.5721,
+      "step": 5280
+    },
+    {
+      "epoch": 4.781278127812781,
+      "grad_norm": 1.633854627609253,
+      "learning_rate": 5.8189128226913695e-08,
+      "loss": 0.5994,
+      "step": 5312
+    },
+    {
+      "epoch": 4.81008100810081,
+      "grad_norm": 4.339478015899658,
+      "learning_rate": 4.389367462367011e-08,
+      "loss": 0.5648,
+      "step": 5344
+    },
+    {
+      "epoch": 4.838883888388839,
+      "grad_norm": 2.3053483963012695,
+      "learning_rate": 3.160250570041601e-08,
+      "loss": 0.5796,
+      "step": 5376
+    },
+    {
+      "epoch": 4.867686768676868,
+      "grad_norm": 1.711835503578186,
+      "learning_rate": 2.1320592093364013e-08,
+      "loss": 0.5467,
+      "step": 5408
+    },
+    {
+      "epoch": 4.896489648964897,
+      "grad_norm": 1.162542700767517,
+      "learning_rate": 1.305209188157186e-08,
+      "loss": 0.5602,
+      "step": 5440
+    },
+    {
+      "epoch": 4.925292529252925,
+      "grad_norm": 1.5160582065582275,
+      "learning_rate": 6.8003489053886094e-09,
+      "loss": 0.5406,
+      "step": 5472
+    },
+    {
+      "epoch": 4.954095409540954,
+      "grad_norm": 1.8680617809295654,
+      "learning_rate": 2.5678914141791243e-09,
+      "loss": 0.553,
+      "step": 5504
+    },
+    {
+      "epoch": 4.982898289828983,
+      "grad_norm": 1.2880302667617798,
+      "learning_rate": 3.564310438830543e-10,
+      "loss": 0.5609,
+      "step": 5536
+    },
+    {
+      "epoch": 5.0,
+      "step": 5555,
+      "total_flos": 5.796630098241126e+16,
+      "train_loss": 0.6057587686258861,
+      "train_runtime": 1046.8819,
+      "train_samples_per_second": 10.612,
+      "train_steps_per_second": 5.306
+    }
+  ],
+  "logging_steps": 32,
+  "max_steps": 5555,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 5.796630098241126e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ed7c05c8980ab7140ec4027f5fe0f250ca91461e46d05f59f2a082c0e8acab7
+size 5432