Upload folder using huggingface_hub

.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 +1,210 @@
+---
+base_model: Kwaipilot/KAT-Dev
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Kwaipilot/KAT-Dev
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.17.1

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "Kwaipilot/KAT-Dev",
+  "bias": "none",
+  "corda_config": null,
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff8183048ce0476260ce58616f706fd9eae090a0da637d84be61531c359fabe5
+size 536991984

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

chat_template.jinja

@@ -0,0 +1,117 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\nYou are a helpful AI assistant that can interact with a computer to solve tasks." }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+{%- endif %}
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
+            {{- '\n' + message.content | trim + '\n' }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+            {%- if tool_call.arguments is defined %}
+                {%- for args_name, args_value in tool_call.arguments|items %}
+                    {{- '<parameter=' + args_name + '>\n' }}
+                    {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                    {{- args_value }}
+                    {{- '\n</parameter>\n' }}
+                {%- endfor %}
+            {%- endif %}
+            {{- '</function>\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28dd40af0826ebe3f2fd1658f148b6697445cf1c83056f3f2e8345971bee48d4
+size 1074500451

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89645f9f6a2a8823b334e0748e4f5ea683a27b3d02632f0a241397db55d82fad
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3c7a69618bda5187b8d1b5fb3e2d676f7cec37cd84f1914eda65964bafcd19
+size 1465

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 30,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.025078369905956112,
+      "grad_norm": 0.43725547194480896,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.9437,
+      "step": 2
+    },
+    {
+      "epoch": 0.050156739811912224,
+      "grad_norm": 0.6708689332008362,
+      "learning_rate": 2.4e-05,
+      "loss": 1.849,
+      "step": 4
+    },
+    {
+      "epoch": 0.07523510971786834,
+      "grad_norm": 0.3925197422504425,
+      "learning_rate": 4e-05,
+      "loss": 1.8725,
+      "step": 6
+    },
+    {
+      "epoch": 0.10031347962382445,
+      "grad_norm": 0.4107086956501007,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 1.7837,
+      "step": 8
+    },
+    {
+      "epoch": 0.12539184952978055,
+      "grad_norm": 0.5341728329658508,
+      "learning_rate": 7.2e-05,
+      "loss": 1.8033,
+      "step": 10
+    },
+    {
+      "epoch": 0.15047021943573669,
+      "grad_norm": 0.43938425183296204,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 1.5958,
+      "step": 12
+    },
+    {
+      "epoch": 0.1755485893416928,
+      "grad_norm": 0.3650668263435364,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 1.5566,
+      "step": 14
+    },
+    {
+      "epoch": 0.2006269592476489,
+      "grad_norm": 0.3861461877822876,
+      "learning_rate": 0.00012,
+      "loss": 1.3631,
+      "step": 16
+    },
+    {
+      "epoch": 0.22570532915360503,
+      "grad_norm": 0.3685659170150757,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 1.3227,
+      "step": 18
+    },
+    {
+      "epoch": 0.2507836990595611,
+      "grad_norm": 0.4720342457294464,
+      "learning_rate": 0.000152,
+      "loss": 1.1027,
+      "step": 20
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.40199315547943115,
+      "learning_rate": 0.000168,
+      "loss": 1.018,
+      "step": 22
+    },
+    {
+      "epoch": 0.30094043887147337,
+      "grad_norm": 0.22768579423427582,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.9077,
+      "step": 24
+    },
+    {
+      "epoch": 0.32601880877742945,
+      "grad_norm": 0.2388496696949005,
+      "learning_rate": 0.0002,
+      "loss": 0.7587,
+      "step": 26
+    },
+    {
+      "epoch": 0.3510971786833856,
+      "grad_norm": 0.19000130891799927,
+      "learning_rate": 0.0001998993710691824,
+      "loss": 0.7766,
+      "step": 28
+    },
+    {
+      "epoch": 0.3761755485893417,
+      "grad_norm": 0.1965627372264862,
+      "learning_rate": 0.0001997987421383648,
+      "loss": 0.7575,
+      "step": 30
+    },
+    {
+      "epoch": 0.4012539184952978,
+      "grad_norm": 0.18852603435516357,
+      "learning_rate": 0.00019969811320754718,
+      "loss": 0.8292,
+      "step": 32
+    },
+    {
+      "epoch": 0.4263322884012539,
+      "grad_norm": 0.16236507892608643,
+      "learning_rate": 0.00019959748427672956,
+      "loss": 0.7272,
+      "step": 34
+    },
+    {
+      "epoch": 0.45141065830721006,
+      "grad_norm": 0.14128465950489044,
+      "learning_rate": 0.00019949685534591195,
+      "loss": 0.751,
+      "step": 36
+    },
+    {
+      "epoch": 0.47648902821316613,
+      "grad_norm": 0.14623811841011047,
+      "learning_rate": 0.00019939622641509434,
+      "loss": 0.6661,
+      "step": 38
+    },
+    {
+      "epoch": 0.5015673981191222,
+      "grad_norm": 0.14945009350776672,
+      "learning_rate": 0.00019929559748427673,
+      "loss": 0.7435,
+      "step": 40
+    },
+    {
+      "epoch": 0.5266457680250783,
+      "grad_norm": 0.1485632061958313,
+      "learning_rate": 0.00019919496855345915,
+      "loss": 0.6466,
+      "step": 42
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.14336936175823212,
+      "learning_rate": 0.00019909433962264153,
+      "loss": 0.7,
+      "step": 44
+    },
+    {
+      "epoch": 0.5768025078369906,
+      "grad_norm": 0.1316949725151062,
+      "learning_rate": 0.0001989937106918239,
+      "loss": 0.6194,
+      "step": 46
+    },
+    {
+      "epoch": 0.6018808777429467,
+      "grad_norm": 0.14485935866832733,
+      "learning_rate": 0.00019889308176100629,
+      "loss": 0.8044,
+      "step": 48
+    },
+    {
+      "epoch": 0.6269592476489029,
+      "grad_norm": 0.12860289216041565,
+      "learning_rate": 0.00019879245283018867,
+      "loss": 0.5773,
+      "step": 50
+    },
+    {
+      "epoch": 0.6520376175548589,
+      "grad_norm": 0.16889798641204834,
+      "learning_rate": 0.0001986918238993711,
+      "loss": 0.7281,
+      "step": 52
+    },
+    {
+      "epoch": 0.677115987460815,
+      "grad_norm": 0.14104238152503967,
+      "learning_rate": 0.00019859119496855348,
+      "loss": 0.6654,
+      "step": 54
+    },
+    {
+      "epoch": 0.7021943573667712,
+      "grad_norm": 0.1515515297651291,
+      "learning_rate": 0.00019849056603773587,
+      "loss": 0.6833,
+      "step": 56
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.16043280065059662,
+      "learning_rate": 0.00019838993710691826,
+      "loss": 0.6599,
+      "step": 58
+    },
+    {
+      "epoch": 0.7523510971786834,
+      "grad_norm": 0.15895870327949524,
+      "learning_rate": 0.00019828930817610062,
+      "loss": 0.686,
+      "step": 60
+    },
+    {
+      "epoch": 0.7774294670846394,
+      "grad_norm": 0.3486965298652649,
+      "learning_rate": 0.00019818867924528303,
+      "loss": 0.6835,
+      "step": 62
+    },
+    {
+      "epoch": 0.8025078369905956,
+      "grad_norm": 0.1274975836277008,
+      "learning_rate": 0.00019808805031446542,
+      "loss": 0.5425,
+      "step": 64
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.1669531911611557,
+      "learning_rate": 0.0001979874213836478,
+      "loss": 0.766,
+      "step": 66
+    },
+    {
+      "epoch": 0.8526645768025078,
+      "grad_norm": 0.14856377243995667,
+      "learning_rate": 0.0001978867924528302,
+      "loss": 0.5993,
+      "step": 68
+    },
+    {
+      "epoch": 0.877742946708464,
+      "grad_norm": 0.13947483897209167,
+      "learning_rate": 0.0001977861635220126,
+      "loss": 0.7071,
+      "step": 70
+    },
+    {
+      "epoch": 0.9028213166144201,
+      "grad_norm": 0.15276968479156494,
+      "learning_rate": 0.00019768553459119498,
+      "loss": 0.687,
+      "step": 72
+    },
+    {
+      "epoch": 0.9278996865203761,
+      "grad_norm": 0.14595958590507507,
+      "learning_rate": 0.00019758490566037737,
+      "loss": 0.6495,
+      "step": 74
+    },
+    {
+      "epoch": 0.9529780564263323,
+      "grad_norm": 0.17588546872138977,
+      "learning_rate": 0.00019748427672955975,
+      "loss": 0.6584,
+      "step": 76
+    },
+    {
+      "epoch": 0.9780564263322884,
+      "grad_norm": 0.15688568353652954,
+      "learning_rate": 0.00019738364779874214,
+      "loss": 0.6769,
+      "step": 78
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.1879902333021164,
+      "learning_rate": 0.00019728301886792453,
+      "loss": 0.5924,
+      "step": 80
+    },
+    {
+      "epoch": 1.025078369905956,
+      "grad_norm": 0.15292422473430634,
+      "learning_rate": 0.00019718238993710695,
+      "loss": 0.5727,
+      "step": 82
+    },
+    {
+      "epoch": 1.0501567398119123,
+      "grad_norm": 0.14542542397975922,
+      "learning_rate": 0.00019708176100628934,
+      "loss": 0.5528,
+      "step": 84
+    },
+    {
+      "epoch": 1.0752351097178683,
+      "grad_norm": 0.15912258625030518,
+      "learning_rate": 0.0001969811320754717,
+      "loss": 0.5404,
+      "step": 86
+    },
+    {
+      "epoch": 1.1003134796238245,
+      "grad_norm": 0.16443438827991486,
+      "learning_rate": 0.00019688050314465409,
+      "loss": 0.544,
+      "step": 88
+    },
+    {
+      "epoch": 1.1253918495297806,
+      "grad_norm": 0.18315915763378143,
+      "learning_rate": 0.00019677987421383647,
+      "loss": 0.5768,
+      "step": 90
+    },
+    {
+      "epoch": 1.1504702194357366,
+      "grad_norm": 0.16878078877925873,
+      "learning_rate": 0.0001966792452830189,
+      "loss": 0.6918,
+      "step": 92
+    },
+    {
+      "epoch": 1.1755485893416928,
+      "grad_norm": 0.1652018129825592,
+      "learning_rate": 0.00019657861635220128,
+      "loss": 0.5903,
+      "step": 94
+    },
+    {
+      "epoch": 1.2006269592476488,
+      "grad_norm": 0.181439608335495,
+      "learning_rate": 0.00019647798742138367,
+      "loss": 0.5917,
+      "step": 96
+    },
+    {
+      "epoch": 1.225705329153605,
+      "grad_norm": 0.15887363255023956,
+      "learning_rate": 0.00019637735849056606,
+      "loss": 0.5631,
+      "step": 98
+    },
+    {
+      "epoch": 1.250783699059561,
+      "grad_norm": 0.16309796273708344,
+      "learning_rate": 0.00019627672955974842,
+      "loss": 0.6206,
+      "step": 100
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.19174307584762573,
+      "learning_rate": 0.00019617610062893083,
+      "loss": 0.5375,
+      "step": 102
+    },
+    {
+      "epoch": 1.3009404388714734,
+      "grad_norm": 0.2240614891052246,
+      "learning_rate": 0.00019607547169811322,
+      "loss": 0.6407,
+      "step": 104
+    },
+    {
+      "epoch": 1.3260188087774294,
+      "grad_norm": 0.1673874855041504,
+      "learning_rate": 0.0001959748427672956,
+      "loss": 0.631,
+      "step": 106
+    },
+    {
+      "epoch": 1.3510971786833856,
+      "grad_norm": 0.16143380105495453,
+      "learning_rate": 0.000195874213836478,
+      "loss": 0.4985,
+      "step": 108
+    },
+    {
+      "epoch": 1.3761755485893417,
+      "grad_norm": 0.18511593341827393,
+      "learning_rate": 0.0001957735849056604,
+      "loss": 0.5844,
+      "step": 110
+    },
+    {
+      "epoch": 1.4012539184952977,
+      "grad_norm": 0.15226313471794128,
+      "learning_rate": 0.00019567295597484278,
+      "loss": 0.5237,
+      "step": 112
+    },
+    {
+      "epoch": 1.426332288401254,
+      "grad_norm": 0.16536672413349152,
+      "learning_rate": 0.00019557232704402517,
+      "loss": 0.4945,
+      "step": 114
+    },
+    {
+      "epoch": 1.4514106583072102,
+      "grad_norm": 0.17802752554416656,
+      "learning_rate": 0.00019547169811320755,
+      "loss": 0.632,
+      "step": 116
+    },
+    {
+      "epoch": 1.4764890282131662,
+      "grad_norm": 0.18615730106830597,
+      "learning_rate": 0.00019537106918238994,
+      "loss": 0.6778,
+      "step": 118
+    },
+    {
+      "epoch": 1.5015673981191222,
+      "grad_norm": 0.16418549418449402,
+      "learning_rate": 0.00019527044025157233,
+      "loss": 0.6141,
+      "step": 120
+    },
+    {
+      "epoch": 1.5266457680250785,
+      "grad_norm": 0.16458265483379364,
+      "learning_rate": 0.00019516981132075475,
+      "loss": 0.5316,
+      "step": 122
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.15842436254024506,
+      "learning_rate": 0.0001950691823899371,
+      "loss": 0.4761,
+      "step": 124
+    },
+    {
+      "epoch": 1.5768025078369905,
+      "grad_norm": 0.15368856489658356,
+      "learning_rate": 0.0001949685534591195,
+      "loss": 0.471,
+      "step": 126
+    },
+    {
+      "epoch": 1.6018808777429467,
+      "grad_norm": 0.16104081273078918,
+      "learning_rate": 0.0001948679245283019,
+      "loss": 0.572,
+      "step": 128
+    },
+    {
+      "epoch": 1.626959247648903,
+      "grad_norm": 0.1696012020111084,
+      "learning_rate": 0.00019476729559748428,
+      "loss": 0.5293,
+      "step": 130
+    },
+    {
+      "epoch": 1.6520376175548588,
+      "grad_norm": 0.16601622104644775,
+      "learning_rate": 0.0001946666666666667,
+      "loss": 0.6569,
+      "step": 132
+    },
+    {
+      "epoch": 1.677115987460815,
+      "grad_norm": 0.15106241405010223,
+      "learning_rate": 0.00019456603773584908,
+      "loss": 0.5687,
+      "step": 134
+    },
+    {
+      "epoch": 1.7021943573667713,
+      "grad_norm": 0.18189087510108948,
+      "learning_rate": 0.00019446540880503147,
+      "loss": 0.4965,
+      "step": 136
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.15463034808635712,
+      "learning_rate": 0.00019436477987421383,
+      "loss": 0.6398,
+      "step": 138
+    },
+    {
+      "epoch": 1.7523510971786833,
+      "grad_norm": 0.17576032876968384,
+      "learning_rate": 0.00019426415094339622,
+      "loss": 0.6122,
+      "step": 140
+    },
+    {
+      "epoch": 1.7774294670846396,
+      "grad_norm": 0.14750592410564423,
+      "learning_rate": 0.00019416352201257863,
+      "loss": 0.5475,
+      "step": 142
+    },
+    {
+      "epoch": 1.8025078369905956,
+      "grad_norm": 0.15765072405338287,
+      "learning_rate": 0.00019406289308176102,
+      "loss": 0.443,
+      "step": 144
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 0.16872242093086243,
+      "learning_rate": 0.0001939622641509434,
+      "loss": 0.5061,
+      "step": 146
+    },
+    {
+      "epoch": 1.8526645768025078,
+      "grad_norm": 0.16207149624824524,
+      "learning_rate": 0.0001938616352201258,
+      "loss": 0.572,
+      "step": 148
+    },
+    {
+      "epoch": 1.877742946708464,
+      "grad_norm": 0.16720207035541534,
+      "learning_rate": 0.0001937610062893082,
+      "loss": 0.5329,
+      "step": 150
+    },
+    {
+      "epoch": 1.90282131661442,
+      "grad_norm": 0.1653318852186203,
+      "learning_rate": 0.00019366037735849058,
+      "loss": 0.5361,
+      "step": 152
+    },
+    {
+      "epoch": 1.9278996865203761,
+      "grad_norm": 0.1918332576751709,
+      "learning_rate": 0.00019355974842767297,
+      "loss": 0.6219,
+      "step": 154
+    },
+    {
+      "epoch": 1.9529780564263324,
+      "grad_norm": 0.1535947322845459,
+      "learning_rate": 0.00019345911949685536,
+      "loss": 0.586,
+      "step": 156
+    },
+    {
+      "epoch": 1.9780564263322884,
+      "grad_norm": 0.16222791373729706,
+      "learning_rate": 0.00019335849056603774,
+      "loss": 0.5228,
+      "step": 158
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.24010032415390015,
+      "learning_rate": 0.00019325786163522013,
+      "loss": 0.5218,
+      "step": 160
+    },
+    {
+      "epoch": 2.0250783699059562,
+      "grad_norm": 0.15844006836414337,
+      "learning_rate": 0.00019315723270440255,
+      "loss": 0.5111,
+      "step": 162
+    },
+    {
+      "epoch": 2.050156739811912,
+      "grad_norm": 0.1755230873823166,
+      "learning_rate": 0.0001930566037735849,
+      "loss": 0.6063,
+      "step": 164
+    },
+    {
+      "epoch": 2.0752351097178683,
+      "grad_norm": 0.2025759369134903,
+      "learning_rate": 0.0001929559748427673,
+      "loss": 0.5672,
+      "step": 166
+    },
+    {
+      "epoch": 2.1003134796238245,
+      "grad_norm": 0.2058378905057907,
+      "learning_rate": 0.0001928553459119497,
+      "loss": 0.4629,
+      "step": 168
+    },
+    {
+      "epoch": 2.1253918495297803,
+      "grad_norm": 0.1765381544828415,
+      "learning_rate": 0.00019275471698113208,
+      "loss": 0.5236,
+      "step": 170
+    },
+    {
+      "epoch": 2.1504702194357366,
+      "grad_norm": 0.20618358254432678,
+      "learning_rate": 0.0001926540880503145,
+      "loss": 0.5029,
+      "step": 172
+    },
+    {
+      "epoch": 2.175548589341693,
+      "grad_norm": 0.1737968772649765,
+      "learning_rate": 0.00019255345911949688,
+      "loss": 0.3964,
+      "step": 174
+    },
+    {
+      "epoch": 2.200626959247649,
+      "grad_norm": 0.20385882258415222,
+      "learning_rate": 0.00019245283018867927,
+      "loss": 0.5188,
+      "step": 176
+    },
+    {
+      "epoch": 2.225705329153605,
+      "grad_norm": 0.2051456868648529,
+      "learning_rate": 0.00019235220125786163,
+      "loss": 0.4548,
+      "step": 178
+    },
+    {
+      "epoch": 2.250783699059561,
+      "grad_norm": 0.18826241791248322,
+      "learning_rate": 0.00019225157232704402,
+      "loss": 0.4515,
+      "step": 180
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "grad_norm": 0.18653476238250732,
+      "learning_rate": 0.00019215094339622644,
+      "loss": 0.5373,
+      "step": 182
+    },
+    {
+      "epoch": 2.300940438871473,
+      "grad_norm": 0.179554283618927,
+      "learning_rate": 0.00019205031446540882,
+      "loss": 0.49,
+      "step": 184
+    },
+    {
+      "epoch": 2.3260188087774294,
+      "grad_norm": 0.18949083983898163,
+      "learning_rate": 0.0001919496855345912,
+      "loss": 0.4795,
+      "step": 186
+    },
+    {
+      "epoch": 2.3510971786833856,
+      "grad_norm": 0.21681569516658783,
+      "learning_rate": 0.0001918490566037736,
+      "loss": 0.4826,
+      "step": 188
+    },
+    {
+      "epoch": 2.376175548589342,
+      "grad_norm": 0.20997639000415802,
+      "learning_rate": 0.000191748427672956,
+      "loss": 0.3699,
+      "step": 190
+    },
+    {
+      "epoch": 2.4012539184952977,
+      "grad_norm": 0.3043127954006195,
+      "learning_rate": 0.00019164779874213838,
+      "loss": 0.5264,
+      "step": 192
+    },
+    {
+      "epoch": 2.426332288401254,
+      "grad_norm": 0.19533301889896393,
+      "learning_rate": 0.00019154716981132077,
+      "loss": 0.4243,
+      "step": 194
+    },
+    {
+      "epoch": 2.45141065830721,
+      "grad_norm": 0.20891591906547546,
+      "learning_rate": 0.00019144654088050316,
+      "loss": 0.4748,
+      "step": 196
+    },
+    {
+      "epoch": 2.476489028213166,
+      "grad_norm": 0.1940625011920929,
+      "learning_rate": 0.00019134591194968554,
+      "loss": 0.456,
+      "step": 198
+    },
+    {
+      "epoch": 2.501567398119122,
+      "grad_norm": 0.2169208973646164,
+      "learning_rate": 0.00019124528301886793,
+      "loss": 0.577,
+      "step": 200
+    },
+    {
+      "epoch": 2.5266457680250785,
+      "grad_norm": 0.21462920308113098,
+      "learning_rate": 0.00019114465408805032,
+      "loss": 0.3583,
+      "step": 202
+    },
+    {
+      "epoch": 2.5517241379310347,
+      "grad_norm": 0.22243842482566833,
+      "learning_rate": 0.0001910440251572327,
+      "loss": 0.5473,
+      "step": 204
+    },
+    {
+      "epoch": 2.5768025078369905,
+      "grad_norm": 0.20357415080070496,
+      "learning_rate": 0.0001909433962264151,
+      "loss": 0.5596,
+      "step": 206
+    },
+    {
+      "epoch": 2.6018808777429467,
+      "grad_norm": 0.21374137699604034,
+      "learning_rate": 0.0001908427672955975,
+      "loss": 0.6041,
+      "step": 208
+    },
+    {
+      "epoch": 2.626959247648903,
+      "grad_norm": 0.22612103819847107,
+      "learning_rate": 0.00019074213836477988,
+      "loss": 0.4825,
+      "step": 210
+    },
+    {
+      "epoch": 2.652037617554859,
+      "grad_norm": 0.182185098528862,
+      "learning_rate": 0.0001906415094339623,
+      "loss": 0.5961,
+      "step": 212
+    },
+    {
+      "epoch": 2.677115987460815,
+      "grad_norm": 0.21316243708133698,
+      "learning_rate": 0.00019054088050314468,
+      "loss": 0.4892,
+      "step": 214
+    },
+    {
+      "epoch": 2.7021943573667713,
+      "grad_norm": 0.20594292879104614,
+      "learning_rate": 0.00019044025157232704,
+      "loss": 0.5294,
+      "step": 216
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.18579436838626862,
+      "learning_rate": 0.00019033962264150943,
+      "loss": 0.4867,
+      "step": 218
+    },
+    {
+      "epoch": 2.7523510971786833,
+      "grad_norm": 0.20978513360023499,
+      "learning_rate": 0.00019023899371069182,
+      "loss": 0.5459,
+      "step": 220
+    },
+    {
+      "epoch": 2.7774294670846396,
+      "grad_norm": 0.20766879618167877,
+      "learning_rate": 0.00019013836477987424,
+      "loss": 0.4467,
+      "step": 222
+    },
+    {
+      "epoch": 2.8025078369905954,
+      "grad_norm": 0.2247876673936844,
+      "learning_rate": 0.00019003773584905662,
+      "loss": 0.4955,
+      "step": 224
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": 0.20031589269638062,
+      "learning_rate": 0.00018993710691823901,
+      "loss": 0.4274,
+      "step": 226
+    },
+    {
+      "epoch": 2.852664576802508,
+      "grad_norm": 0.22423385083675385,
+      "learning_rate": 0.0001898364779874214,
+      "loss": 0.4741,
+      "step": 228
+    },
+    {
+      "epoch": 2.877742946708464,
+      "grad_norm": 0.1920011192560196,
+      "learning_rate": 0.00018973584905660376,
+      "loss": 0.4802,
+      "step": 230
+    },
+    {
+      "epoch": 2.9028213166144203,
+      "grad_norm": 0.1996566653251648,
+      "learning_rate": 0.00018963522012578615,
+      "loss": 0.5204,
+      "step": 232
+    },
+    {
+      "epoch": 2.927899686520376,
+      "grad_norm": 0.18659324944019318,
+      "learning_rate": 0.00018953459119496857,
+      "loss": 0.563,
+      "step": 234
+    },
+    {
+      "epoch": 2.9529780564263324,
+      "grad_norm": 0.20645543932914734,
+      "learning_rate": 0.00018943396226415096,
+      "loss": 0.5968,
+      "step": 236
+    },
+    {
+      "epoch": 2.978056426332288,
+      "grad_norm": 0.20103755593299866,
+      "learning_rate": 0.00018933333333333335,
+      "loss": 0.4683,
+      "step": 238
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.26790672540664673,
+      "learning_rate": 0.00018923270440251573,
+      "loss": 0.4214,
+      "step": 240
+    },
+    {
+      "epoch": 3.0250783699059562,
+      "grad_norm": 0.24234965443611145,
+      "learning_rate": 0.00018913207547169812,
+      "loss": 0.4778,
+      "step": 242
+    },
+    {
+      "epoch": 3.050156739811912,
+      "grad_norm": 0.2758055031299591,
+      "learning_rate": 0.0001890314465408805,
+      "loss": 0.4029,
+      "step": 244
+    },
+    {
+      "epoch": 3.0752351097178683,
+      "grad_norm": 0.2382444590330124,
+      "learning_rate": 0.0001889308176100629,
+      "loss": 0.3801,
+      "step": 246
+    },
+    {
+      "epoch": 3.1003134796238245,
+      "grad_norm": 0.24490897357463837,
+      "learning_rate": 0.0001888301886792453,
+      "loss": 0.3975,
+      "step": 248
+    },
+    {
+      "epoch": 3.1253918495297803,
+      "grad_norm": 0.26239147782325745,
+      "learning_rate": 0.00018872955974842768,
+      "loss": 0.4038,
+      "step": 250
+    },
+    {
+      "epoch": 3.1504702194357366,
+      "grad_norm": 0.24605032801628113,
+      "learning_rate": 0.00018862893081761007,
+      "loss": 0.4364,
+      "step": 252
+    },
+    {
+      "epoch": 3.175548589341693,
+      "grad_norm": 0.28764280676841736,
+      "learning_rate": 0.00018852830188679248,
+      "loss": 0.3577,
+      "step": 254
+    },
+    {
+      "epoch": 3.200626959247649,
+      "grad_norm": 0.23804618418216705,
+      "learning_rate": 0.00018842767295597484,
+      "loss": 0.4155,
+      "step": 256
+    },
+    {
+      "epoch": 3.225705329153605,
+      "grad_norm": 0.25497862696647644,
+      "learning_rate": 0.00018832704402515723,
+      "loss": 0.4654,
+      "step": 258
+    },
+    {
+      "epoch": 3.250783699059561,
+      "grad_norm": 0.23537839949131012,
+      "learning_rate": 0.00018822641509433962,
+      "loss": 0.4144,
+      "step": 260
+    },
+    {
+      "epoch": 3.2758620689655173,
+      "grad_norm": 0.268036812543869,
+      "learning_rate": 0.000188125786163522,
+      "loss": 0.4546,
+      "step": 262
+    },
+    {
+      "epoch": 3.300940438871473,
+      "grad_norm": 0.25395911931991577,
+      "learning_rate": 0.00018802515723270443,
+      "loss": 0.4604,
+      "step": 264
+    },
+    {
+      "epoch": 3.3260188087774294,
+      "grad_norm": 0.3395281732082367,
+      "learning_rate": 0.00018792452830188681,
+      "loss": 0.5816,
+      "step": 266
+    },
+    {
+      "epoch": 3.3510971786833856,
+      "grad_norm": 0.258900910615921,
+      "learning_rate": 0.0001878238993710692,
+      "loss": 0.4415,
+      "step": 268
+    },
+    {
+      "epoch": 3.376175548589342,
+      "grad_norm": 0.24031828343868256,
+      "learning_rate": 0.00018772327044025156,
+      "loss": 0.469,
+      "step": 270
+    },
+    {
+      "epoch": 3.4012539184952977,
+      "grad_norm": 0.26624906063079834,
+      "learning_rate": 0.00018762264150943395,
+      "loss": 0.4304,
+      "step": 272
+    },
+    {
+      "epoch": 3.426332288401254,
+      "grad_norm": 0.2869020998477936,
+      "learning_rate": 0.00018752201257861637,
+      "loss": 0.4623,
+      "step": 274
+    },
+    {
+      "epoch": 3.45141065830721,
+      "grad_norm": 0.2383798062801361,
+      "learning_rate": 0.00018742138364779876,
+      "loss": 0.3973,
+      "step": 276
+    },
+    {
+      "epoch": 3.476489028213166,
+      "grad_norm": 0.25947991013526917,
+      "learning_rate": 0.00018732075471698115,
+      "loss": 0.4468,
+      "step": 278
+    },
+    {
+      "epoch": 3.501567398119122,
+      "grad_norm": 0.21950559318065643,
+      "learning_rate": 0.00018722012578616354,
+      "loss": 0.3432,
+      "step": 280
+    },
+    {
+      "epoch": 3.5266457680250785,
+      "grad_norm": 0.26003995537757874,
+      "learning_rate": 0.00018711949685534592,
+      "loss": 0.4664,
+      "step": 282
+    },
+    {
+      "epoch": 3.5517241379310347,
+      "grad_norm": 0.2847505807876587,
+      "learning_rate": 0.0001870188679245283,
+      "loss": 0.4583,
+      "step": 284
+    },
+    {
+      "epoch": 3.5768025078369905,
+      "grad_norm": 0.2824760973453522,
+      "learning_rate": 0.0001869182389937107,
+      "loss": 0.4735,
+      "step": 286
+    },
+    {
+      "epoch": 3.6018808777429467,
+      "grad_norm": 0.268838107585907,
+      "learning_rate": 0.0001868176100628931,
+      "loss": 0.4071,
+      "step": 288
+    },
+    {
+      "epoch": 3.626959247648903,
+      "grad_norm": 0.24519529938697815,
+      "learning_rate": 0.00018671698113207548,
+      "loss": 0.4178,
+      "step": 290
+    },
+    {
+      "epoch": 3.652037617554859,
+      "grad_norm": 0.24740180373191833,
+      "learning_rate": 0.00018661635220125787,
+      "loss": 0.4716,
+      "step": 292
+    },
+    {
+      "epoch": 3.677115987460815,
+      "grad_norm": 0.22623687982559204,
+      "learning_rate": 0.00018651572327044026,
+      "loss": 0.3645,
+      "step": 294
+    },
+    {
+      "epoch": 3.7021943573667713,
+      "grad_norm": 0.2554280459880829,
+      "learning_rate": 0.00018641509433962264,
+      "loss": 0.4044,
+      "step": 296
+    },
+    {
+      "epoch": 3.7272727272727275,
+      "grad_norm": 0.2251761108636856,
+      "learning_rate": 0.00018631446540880503,
+      "loss": 0.3663,
+      "step": 298
+    },
+    {
+      "epoch": 3.7523510971786833,
+      "grad_norm": 0.20053140819072723,
+      "learning_rate": 0.00018621383647798742,
+      "loss": 0.4342,
+      "step": 300
+    },
+    {
+      "epoch": 3.7774294670846396,
+      "grad_norm": 0.2692326605319977,
+      "learning_rate": 0.0001861132075471698,
+      "loss": 0.4268,
+      "step": 302
+    },
+    {
+      "epoch": 3.8025078369905954,
+      "grad_norm": 0.23218081891536713,
+      "learning_rate": 0.00018601257861635223,
+      "loss": 0.4848,
+      "step": 304
+    },
+    {
+      "epoch": 3.8275862068965516,
+      "grad_norm": 0.2571001648902893,
+      "learning_rate": 0.00018591194968553462,
+      "loss": 0.5391,
+      "step": 306
+    },
+    {
+      "epoch": 3.852664576802508,
+      "grad_norm": 0.20899826288223267,
+      "learning_rate": 0.00018581132075471698,
+      "loss": 0.4183,
+      "step": 308
+    },
+    {
+      "epoch": 3.877742946708464,
+      "grad_norm": 0.24893143773078918,
+      "learning_rate": 0.00018571069182389937,
+      "loss": 0.4314,
+      "step": 310
+    },
+    {
+      "epoch": 3.9028213166144203,
+      "grad_norm": 0.26598888635635376,
+      "learning_rate": 0.00018561006289308175,
+      "loss": 0.4182,
+      "step": 312
+    },
+    {
+      "epoch": 3.927899686520376,
+      "grad_norm": 0.24121470749378204,
+      "learning_rate": 0.00018550943396226417,
+      "loss": 0.4327,
+      "step": 314
+    },
+    {
+      "epoch": 3.9529780564263324,
+      "grad_norm": 0.2874317467212677,
+      "learning_rate": 0.00018540880503144656,
+      "loss": 0.4616,
+      "step": 316
+    },
+    {
+      "epoch": 3.978056426332288,
+      "grad_norm": 0.22735589742660522,
+      "learning_rate": 0.00018530817610062895,
+      "loss": 0.376,
+      "step": 318
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.3424147069454193,
+      "learning_rate": 0.00018520754716981134,
+      "loss": 0.537,
+      "step": 320
+    },
+    {
+      "epoch": 4.025078369905956,
+      "grad_norm": 0.27403339743614197,
+      "learning_rate": 0.0001851069182389937,
+      "loss": 0.3539,
+      "step": 322
+    },
+    {
+      "epoch": 4.0501567398119125,
+      "grad_norm": 0.33905503153800964,
+      "learning_rate": 0.0001850062893081761,
+      "loss": 0.3367,
+      "step": 324
+    },
+    {
+      "epoch": 4.075235109717869,
+      "grad_norm": 0.47853460907936096,
+      "learning_rate": 0.0001849056603773585,
+      "loss": 0.393,
+      "step": 326
+    },
+    {
+      "epoch": 4.100313479623824,
+      "grad_norm": 0.3133102059364319,
+      "learning_rate": 0.0001848050314465409,
+      "loss": 0.3762,
+      "step": 328
+    },
+    {
+      "epoch": 4.12539184952978,
+      "grad_norm": 0.22834369540214539,
+      "learning_rate": 0.00018470440251572328,
+      "loss": 0.3404,
+      "step": 330
+    },
+    {
+      "epoch": 4.150470219435737,
+      "grad_norm": 0.2537166476249695,
+      "learning_rate": 0.00018460377358490567,
+      "loss": 0.3582,
+      "step": 332
+    },
+    {
+      "epoch": 4.175548589341693,
+      "grad_norm": 0.35708144307136536,
+      "learning_rate": 0.00018450314465408806,
+      "loss": 0.369,
+      "step": 334
+    },
+    {
+      "epoch": 4.200626959247649,
+      "grad_norm": 0.3224405348300934,
+      "learning_rate": 0.00018440251572327045,
+      "loss": 0.3458,
+      "step": 336
+    },
+    {
+      "epoch": 4.225705329153605,
+      "grad_norm": 0.34621739387512207,
+      "learning_rate": 0.00018430188679245283,
+      "loss": 0.4176,
+      "step": 338
+    },
+    {
+      "epoch": 4.250783699059561,
+      "grad_norm": 0.24818404018878937,
+      "learning_rate": 0.00018420125786163522,
+      "loss": 0.3205,
+      "step": 340
+    },
+    {
+      "epoch": 4.275862068965517,
+      "grad_norm": 0.29599064588546753,
+      "learning_rate": 0.0001841006289308176,
+      "loss": 0.3696,
+      "step": 342
+    },
+    {
+      "epoch": 4.300940438871473,
+      "grad_norm": 0.2980504333972931,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.3256,
+      "step": 344
+    },
+    {
+      "epoch": 4.326018808777429,
+      "grad_norm": 0.35454604029655457,
+      "learning_rate": 0.0001838993710691824,
+      "loss": 0.4957,
+      "step": 346
+    },
+    {
+      "epoch": 4.351097178683386,
+      "grad_norm": 0.3497369885444641,
+      "learning_rate": 0.00018379874213836478,
+      "loss": 0.3941,
+      "step": 348
+    },
+    {
+      "epoch": 4.376175548589342,
+      "grad_norm": 0.32460692524909973,
+      "learning_rate": 0.00018369811320754717,
+      "loss": 0.3615,
+      "step": 350
+    },
+    {
+      "epoch": 4.401253918495298,
+      "grad_norm": 0.29358094930648804,
+      "learning_rate": 0.00018359748427672955,
+      "loss": 0.3749,
+      "step": 352
+    },
+    {
+      "epoch": 4.4263322884012535,
+      "grad_norm": 0.2807920575141907,
+      "learning_rate": 0.00018349685534591197,
+      "loss": 0.3575,
+      "step": 354
+    },
+    {
+      "epoch": 4.45141065830721,
+      "grad_norm": 0.2809455096721649,
+      "learning_rate": 0.00018339622641509436,
+      "loss": 0.3097,
+      "step": 356
+    },
+    {
+      "epoch": 4.476489028213166,
+      "grad_norm": 0.3250884413719177,
+      "learning_rate": 0.00018329559748427675,
+      "loss": 0.4113,
+      "step": 358
+    },
+    {
+      "epoch": 4.501567398119122,
+      "grad_norm": 0.29040804505348206,
+      "learning_rate": 0.0001831949685534591,
+      "loss": 0.4481,
+      "step": 360
+    },
+    {
+      "epoch": 4.5266457680250785,
+      "grad_norm": 0.3208359479904175,
+      "learning_rate": 0.0001830943396226415,
+      "loss": 0.4438,
+      "step": 362
+    },
+    {
+      "epoch": 4.551724137931035,
+      "grad_norm": 0.23080404102802277,
+      "learning_rate": 0.00018299371069182391,
+      "loss": 0.2099,
+      "step": 364
+    },
+    {
+      "epoch": 4.576802507836991,
+      "grad_norm": 0.2984071373939514,
+      "learning_rate": 0.0001828930817610063,
+      "loss": 0.3339,
+      "step": 366
+    },
+    {
+      "epoch": 4.601880877742946,
+      "grad_norm": 0.3299279808998108,
+      "learning_rate": 0.0001827924528301887,
+      "loss": 0.4208,
+      "step": 368
+    },
+    {
+      "epoch": 4.6269592476489025,
+      "grad_norm": 0.3243483006954193,
+      "learning_rate": 0.00018269182389937108,
+      "loss": 0.4165,
+      "step": 370
+    },
+    {
+      "epoch": 4.652037617554859,
+      "grad_norm": 0.29541853070259094,
+      "learning_rate": 0.00018259119496855347,
+      "loss": 0.3703,
+      "step": 372
+    },
+    {
+      "epoch": 4.677115987460815,
+      "grad_norm": 0.3010431230068207,
+      "learning_rate": 0.00018249056603773586,
+      "loss": 0.4034,
+      "step": 374
+    },
+    {
+      "epoch": 4.702194357366771,
+      "grad_norm": 0.2970607578754425,
+      "learning_rate": 0.00018238993710691825,
+      "loss": 0.3151,
+      "step": 376
+    },
+    {
+      "epoch": 4.7272727272727275,
+      "grad_norm": 0.2794083058834076,
+      "learning_rate": 0.00018228930817610063,
+      "loss": 0.3605,
+      "step": 378
+    },
+    {
+      "epoch": 4.752351097178684,
+      "grad_norm": 0.2949012219905853,
+      "learning_rate": 0.00018218867924528302,
+      "loss": 0.343,
+      "step": 380
+    },
+    {
+      "epoch": 4.777429467084639,
+      "grad_norm": 0.28160709142684937,
+      "learning_rate": 0.0001820880503144654,
+      "loss": 0.4515,
+      "step": 382
+    },
+    {
+      "epoch": 4.802507836990595,
+      "grad_norm": 0.296051561832428,
+      "learning_rate": 0.00018198742138364783,
+      "loss": 0.3908,
+      "step": 384
+    },
+    {
+      "epoch": 4.827586206896552,
+      "grad_norm": 0.26115506887435913,
+      "learning_rate": 0.0001818867924528302,
+      "loss": 0.3312,
+      "step": 386
+    },
+    {
+      "epoch": 4.852664576802508,
+      "grad_norm": 0.27632880210876465,
+      "learning_rate": 0.00018178616352201258,
+      "loss": 0.3179,
+      "step": 388
+    },
+    {
+      "epoch": 4.877742946708464,
+      "grad_norm": 0.2973230481147766,
+      "learning_rate": 0.00018168553459119497,
+      "loss": 0.382,
+      "step": 390
+    },
+    {
+      "epoch": 4.90282131661442,
+      "grad_norm": 0.2833520472049713,
+      "learning_rate": 0.00018158490566037736,
+      "loss": 0.3363,
+      "step": 392
+    },
+    {
+      "epoch": 4.927899686520377,
+      "grad_norm": 0.30823326110839844,
+      "learning_rate": 0.00018148427672955977,
+      "loss": 0.3234,
+      "step": 394
+    },
+    {
+      "epoch": 4.952978056426332,
+      "grad_norm": 0.2736763060092926,
+      "learning_rate": 0.00018138364779874216,
+      "loss": 0.415,
+      "step": 396
+    },
+    {
+      "epoch": 4.978056426332288,
+      "grad_norm": 0.2832898199558258,
+      "learning_rate": 0.00018128301886792455,
+      "loss": 0.3755,
+      "step": 398
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.3281781077384949,
+      "learning_rate": 0.0001811823899371069,
+      "loss": 0.2756,
+      "step": 400
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.25570189464994e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d7eeb34846922a2a7eebd5772ded3cd6debc410de201f3ffbbad85d6518c86c
+size 6161