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

@@ -1,3 +1,210 @@
----
-license: mit
----
+---
+base_model: unsloth/Qwen3-30B-A3B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-30B-A3B-Instruct
+- 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 0.18.0

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3MoeForCausalLM",
+    "parent_library": "transformers.models.qwen3_moe.modeling_qwen3_moe",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "/nfs/turbo/umms-drjieliu/usr/yctao/HF_HOME/hub/models--unsloth--Qwen3-30B-A3B-Instruct-2507/snapshots/41d47883cd854ab6d119fb7cba6e9ed3511886e2",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "o_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:f6a3f106d8961be61121e4d444043412ebc98b34c577e791402ba8bc6c90dd60
+size 3380768360

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 +1,86 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- 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:f7ab96ab8b195892e9f2377a0e2314c2d5e1c4381f840920f1e0b69f48cadd7d
+size 1757899449

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549120a950c76982ab0d4f8c41dd527a1f27618d6fa37025e7d2d0b403532834
+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": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256: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": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1189 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 165,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0060790273556231,
+      "grad_norm": 1.133876085281372,
+      "learning_rate": 0.0,
+      "loss": 2.3054,
+      "step": 1
+    },
+    {
+      "epoch": 0.0121580547112462,
+      "grad_norm": 1.1317460536956787,
+      "learning_rate": 4e-05,
+      "loss": 2.3129,
+      "step": 2
+    },
+    {
+      "epoch": 0.0182370820668693,
+      "grad_norm": 1.030227780342102,
+      "learning_rate": 8e-05,
+      "loss": 2.2997,
+      "step": 3
+    },
+    {
+      "epoch": 0.0243161094224924,
+      "grad_norm": 0.7727698087692261,
+      "learning_rate": 0.00012,
+      "loss": 2.0895,
+      "step": 4
+    },
+    {
+      "epoch": 0.030395136778115502,
+      "grad_norm": 0.6157111525535583,
+      "learning_rate": 0.00016,
+      "loss": 1.9285,
+      "step": 5
+    },
+    {
+      "epoch": 0.0364741641337386,
+      "grad_norm": 0.45515450835227966,
+      "learning_rate": 0.0002,
+      "loss": 1.6672,
+      "step": 6
+    },
+    {
+      "epoch": 0.0425531914893617,
+      "grad_norm": 0.3927247226238251,
+      "learning_rate": 0.0001999953280342959,
+      "loss": 1.4969,
+      "step": 7
+    },
+    {
+      "epoch": 0.0486322188449848,
+      "grad_norm": 0.36588212847709656,
+      "learning_rate": 0.00019998131257372876,
+      "loss": 1.3842,
+      "step": 8
+    },
+    {
+      "epoch": 0.0547112462006079,
+      "grad_norm": 0.29039424657821655,
+      "learning_rate": 0.0001999579549278937,
+      "loss": 1.2499,
+      "step": 9
+    },
+    {
+      "epoch": 0.060790273556231005,
+      "grad_norm": 0.279226690530777,
+      "learning_rate": 0.00019992525727931303,
+      "loss": 1.1685,
+      "step": 10
+    },
+    {
+      "epoch": 0.0668693009118541,
+      "grad_norm": 0.272398978471756,
+      "learning_rate": 0.00019988322268323268,
+      "loss": 1.0638,
+      "step": 11
+    },
+    {
+      "epoch": 0.0729483282674772,
+      "grad_norm": 0.24636079370975494,
+      "learning_rate": 0.0001998318550673364,
+      "loss": 0.9584,
+      "step": 12
+    },
+    {
+      "epoch": 0.0790273556231003,
+      "grad_norm": 0.22141209244728088,
+      "learning_rate": 0.00019977115923137912,
+      "loss": 0.9138,
+      "step": 13
+    },
+    {
+      "epoch": 0.0851063829787234,
+      "grad_norm": 0.17475497722625732,
+      "learning_rate": 0.00019970114084673796,
+      "loss": 0.8515,
+      "step": 14
+    },
+    {
+      "epoch": 0.0911854103343465,
+      "grad_norm": 0.15117621421813965,
+      "learning_rate": 0.0001996218064558829,
+      "loss": 0.8233,
+      "step": 15
+    },
+    {
+      "epoch": 0.0972644376899696,
+      "grad_norm": 0.11647526919841766,
+      "learning_rate": 0.00019953316347176488,
+      "loss": 0.8347,
+      "step": 16
+    },
+    {
+      "epoch": 0.1033434650455927,
+      "grad_norm": 0.10608438402414322,
+      "learning_rate": 0.00019943522017712358,
+      "loss": 0.7888,
+      "step": 17
+    },
+    {
+      "epoch": 0.1094224924012158,
+      "grad_norm": 0.10528700798749924,
+      "learning_rate": 0.0001993279857237133,
+      "loss": 0.7655,
+      "step": 18
+    },
+    {
+      "epoch": 0.11550151975683891,
+      "grad_norm": 0.09133293479681015,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 0.7585,
+      "step": 19
+    },
+    {
+      "epoch": 0.12158054711246201,
+      "grad_norm": 0.09861589223146439,
+      "learning_rate": 0.0001990856842874641,
+      "loss": 0.7616,
+      "step": 20
+    },
+    {
+      "epoch": 0.1276595744680851,
+      "grad_norm": 0.07328511029481888,
+      "learning_rate": 0.0001989506399451051,
+      "loss": 0.746,
+      "step": 21
+    },
+    {
+      "epoch": 0.1337386018237082,
+      "grad_norm": 0.08320208638906479,
+      "learning_rate": 0.00019880634972282166,
+      "loss": 0.729,
+      "step": 22
+    },
+    {
+      "epoch": 0.1398176291793313,
+      "grad_norm": 0.08053930848836899,
+      "learning_rate": 0.0001986528271029931,
+      "loss": 0.7052,
+      "step": 23
+    },
+    {
+      "epoch": 0.1458966565349544,
+      "grad_norm": 0.08553291857242584,
+      "learning_rate": 0.00019849008643066772,
+      "loss": 0.7167,
+      "step": 24
+    },
+    {
+      "epoch": 0.1519756838905775,
+      "grad_norm": 0.07856528460979462,
+      "learning_rate": 0.00019831814291222232,
+      "loss": 0.707,
+      "step": 25
+    },
+    {
+      "epoch": 0.1580547112462006,
+      "grad_norm": 0.0697573572397232,
+      "learning_rate": 0.00019813701261394136,
+      "loss": 0.706,
+      "step": 26
+    },
+    {
+      "epoch": 0.1641337386018237,
+      "grad_norm": 0.07752593606710434,
+      "learning_rate": 0.0001979467124605156,
+      "loss": 0.702,
+      "step": 27
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 0.06536618620157242,
+      "learning_rate": 0.0001977472602334609,
+      "loss": 0.6612,
+      "step": 28
+    },
+    {
+      "epoch": 0.1762917933130699,
+      "grad_norm": 0.061260443180799484,
+      "learning_rate": 0.0001975386745694565,
+      "loss": 0.6432,
+      "step": 29
+    },
+    {
+      "epoch": 0.182370820668693,
+      "grad_norm": 0.04959681257605553,
+      "learning_rate": 0.00019732097495860386,
+      "loss": 0.6545,
+      "step": 30
+    },
+    {
+      "epoch": 0.1884498480243161,
+      "grad_norm": 0.05118938162922859,
+      "learning_rate": 0.0001970941817426052,
+      "loss": 0.6564,
+      "step": 31
+    },
+    {
+      "epoch": 0.1945288753799392,
+      "grad_norm": 0.05098890885710716,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.6751,
+      "step": 32
+    },
+    {
+      "epoch": 0.2006079027355623,
+      "grad_norm": 0.049598027020692825,
+      "learning_rate": 0.00019661340010850026,
+      "loss": 0.6582,
+      "step": 33
+    },
+    {
+      "epoch": 0.2066869300911854,
+      "grad_norm": 0.052051279693841934,
+      "learning_rate": 0.00019635945661430006,
+      "loss": 0.6279,
+      "step": 34
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 0.04154731333255768,
+      "learning_rate": 0.00019609650935856844,
+      "loss": 0.6344,
+      "step": 35
+    },
+    {
+      "epoch": 0.2188449848024316,
+      "grad_norm": 0.045474398881196976,
+      "learning_rate": 0.00019582458291091663,
+      "loss": 0.6195,
+      "step": 36
+    },
+    {
+      "epoch": 0.22492401215805471,
+      "grad_norm": 0.04392531141638756,
+      "learning_rate": 0.00019554370267996538,
+      "loss": 0.6394,
+      "step": 37
+    },
+    {
+      "epoch": 0.23100303951367782,
+      "grad_norm": 0.04103963077068329,
+      "learning_rate": 0.0001952538949109708,
+      "loss": 0.6334,
+      "step": 38
+    },
+    {
+      "epoch": 0.23708206686930092,
+      "grad_norm": 0.042054690420627594,
+      "learning_rate": 0.00019495518668337201,
+      "loss": 0.6239,
+      "step": 39
+    },
+    {
+      "epoch": 0.24316109422492402,
+      "grad_norm": 0.0393654890358448,
+      "learning_rate": 0.00019464760590826098,
+      "loss": 0.6054,
+      "step": 40
+    },
+    {
+      "epoch": 0.24924012158054712,
+      "grad_norm": 0.042832907289266586,
+      "learning_rate": 0.0001943311813257743,
+      "loss": 0.5769,
+      "step": 41
+    },
+    {
+      "epoch": 0.2553191489361702,
+      "grad_norm": 0.03982216864824295,
+      "learning_rate": 0.00019400594250240798,
+      "loss": 0.5921,
+      "step": 42
+    },
+    {
+      "epoch": 0.2613981762917933,
+      "grad_norm": 0.03954484313726425,
+      "learning_rate": 0.0001936719198282545,
+      "loss": 0.5976,
+      "step": 43
+    },
+    {
+      "epoch": 0.2674772036474164,
+      "grad_norm": 0.042563363909721375,
+      "learning_rate": 0.00019332914451416347,
+      "loss": 0.6016,
+      "step": 44
+    },
+    {
+      "epoch": 0.2735562310030395,
+      "grad_norm": 0.04000777006149292,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 0.5822,
+      "step": 45
+    },
+    {
+      "epoch": 0.2796352583586626,
+      "grad_norm": 0.04084771126508713,
+      "learning_rate": 0.00019261746489577765,
+      "loss": 0.6122,
+      "step": 46
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.040883008390665054,
+      "learning_rate": 0.00019224862709033824,
+      "loss": 0.5898,
+      "step": 47
+    },
+    {
+      "epoch": 0.2917933130699088,
+      "grad_norm": 0.04313352331519127,
+      "learning_rate": 0.00019187116963645842,
+      "loss": 0.5852,
+      "step": 48
+    },
+    {
+      "epoch": 0.2978723404255319,
+      "grad_norm": 0.04391175135970116,
+      "learning_rate": 0.00019148512780350384,
+      "loss": 0.5901,
+      "step": 49
+    },
+    {
+      "epoch": 0.303951367781155,
+      "grad_norm": 0.041302260011434555,
+      "learning_rate": 0.0001910905376629585,
+      "loss": 0.5725,
+      "step": 50
+    },
+    {
+      "epoch": 0.3100303951367781,
+      "grad_norm": 0.044717274606227875,
+      "learning_rate": 0.00019068743608505455,
+      "loss": 0.5396,
+      "step": 51
+    },
+    {
+      "epoch": 0.3161094224924012,
+      "grad_norm": 0.04290296137332916,
+      "learning_rate": 0.0001902758607353269,
+      "loss": 0.5888,
+      "step": 52
+    },
+    {
+      "epoch": 0.3221884498480243,
+      "grad_norm": 0.04425125569105148,
+      "learning_rate": 0.0001898558500710939,
+      "loss": 0.5614,
+      "step": 53
+    },
+    {
+      "epoch": 0.3282674772036474,
+      "grad_norm": 0.047949157655239105,
+      "learning_rate": 0.00018942744333786397,
+      "loss": 0.5434,
+      "step": 54
+    },
+    {
+      "epoch": 0.3343465045592705,
+      "grad_norm": 0.0461716391146183,
+      "learning_rate": 0.0001889906805656684,
+      "loss": 0.5788,
+      "step": 55
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.04746852442622185,
+      "learning_rate": 0.000188545602565321,
+      "loss": 0.5431,
+      "step": 56
+    },
+    {
+      "epoch": 0.3465045592705167,
+      "grad_norm": 0.04825344309210777,
+      "learning_rate": 0.00018809225092460488,
+      "loss": 0.5372,
+      "step": 57
+    },
+    {
+      "epoch": 0.3525835866261398,
+      "grad_norm": 0.046712443232536316,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 0.5721,
+      "step": 58
+    },
+    {
+      "epoch": 0.3586626139817629,
+      "grad_norm": 0.045053232461214066,
+      "learning_rate": 0.00018716089693465696,
+      "loss": 0.5632,
+      "step": 59
+    },
+    {
+      "epoch": 0.364741641337386,
+      "grad_norm": 0.04859543964266777,
+      "learning_rate": 0.00018668298161050309,
+      "loss": 0.579,
+      "step": 60
+    },
+    {
+      "epoch": 0.3708206686930091,
+      "grad_norm": 0.05270425230264664,
+      "learning_rate": 0.00018619696668800492,
+      "loss": 0.5625,
+      "step": 61
+    },
+    {
+      "epoch": 0.3768996960486322,
+      "grad_norm": 0.05261973291635513,
+      "learning_rate": 0.00018570289758006346,
+      "loss": 0.5377,
+      "step": 62
+    },
+    {
+      "epoch": 0.3829787234042553,
+      "grad_norm": 0.04979139566421509,
+      "learning_rate": 0.0001852008204521572,
+      "loss": 0.5403,
+      "step": 63
+    },
+    {
+      "epoch": 0.3890577507598784,
+      "grad_norm": 0.05422956123948097,
+      "learning_rate": 0.0001846907822180286,
+      "loss": 0.5251,
+      "step": 64
+    },
+    {
+      "epoch": 0.3951367781155015,
+      "grad_norm": 0.057373154908418655,
+      "learning_rate": 0.00018417283053530044,
+      "loss": 0.5237,
+      "step": 65
+    },
+    {
+      "epoch": 0.4012158054711246,
+      "grad_norm": 0.054097920656204224,
+      "learning_rate": 0.00018364701380102266,
+      "loss": 0.5083,
+      "step": 66
+    },
+    {
+      "epoch": 0.4072948328267477,
+      "grad_norm": 0.05596352368593216,
+      "learning_rate": 0.0001831133811471503,
+      "loss": 0.5185,
+      "step": 67
+    },
+    {
+      "epoch": 0.4133738601823708,
+      "grad_norm": 0.054655492305755615,
+      "learning_rate": 0.0001825719824359524,
+      "loss": 0.5103,
+      "step": 68
+    },
+    {
+      "epoch": 0.4194528875379939,
+      "grad_norm": 0.056628547608852386,
+      "learning_rate": 0.0001820228682553533,
+      "loss": 0.5402,
+      "step": 69
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 0.058673664927482605,
+      "learning_rate": 0.00018146608991420534,
+      "loss": 0.5156,
+      "step": 70
+    },
+    {
+      "epoch": 0.4316109422492401,
+      "grad_norm": 0.0580279715359211,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.5077,
+      "step": 71
+    },
+    {
+      "epoch": 0.4376899696048632,
+      "grad_norm": 0.06008626148104668,
+      "learning_rate": 0.00018032974956148063,
+      "loss": 0.4982,
+      "step": 72
+    },
+    {
+      "epoch": 0.44376899696048633,
+      "grad_norm": 0.06102442368865013,
+      "learning_rate": 0.00017975029372876706,
+      "loss": 0.5117,
+      "step": 73
+    },
+    {
+      "epoch": 0.44984802431610943,
+      "grad_norm": 0.061185382306575775,
+      "learning_rate": 0.0001791633860833096,
+      "loss": 0.4933,
+      "step": 74
+    },
+    {
+      "epoch": 0.45592705167173253,
+      "grad_norm": 0.06262445449829102,
+      "learning_rate": 0.00017856908146535603,
+      "loss": 0.4907,
+      "step": 75
+    },
+    {
+      "epoch": 0.46200607902735563,
+      "grad_norm": 0.06194239482283592,
+      "learning_rate": 0.00017796743540632223,
+      "loss": 0.4722,
+      "step": 76
+    },
+    {
+      "epoch": 0.46808510638297873,
+      "grad_norm": 0.06256049871444702,
+      "learning_rate": 0.00017735850412360331,
+      "loss": 0.4935,
+      "step": 77
+    },
+    {
+      "epoch": 0.47416413373860183,
+      "grad_norm": 0.06734279543161392,
+      "learning_rate": 0.00017674234451532065,
+      "loss": 0.4767,
+      "step": 78
+    },
+    {
+      "epoch": 0.48024316109422494,
+      "grad_norm": 0.06772830337285995,
+      "learning_rate": 0.00017611901415500535,
+      "loss": 0.4915,
+      "step": 79
+    },
+    {
+      "epoch": 0.48632218844984804,
+      "grad_norm": 0.06995881348848343,
+      "learning_rate": 0.00017548857128621875,
+      "loss": 0.4723,
+      "step": 80
+    },
+    {
+      "epoch": 0.49240121580547114,
+      "grad_norm": 0.06601176410913467,
+      "learning_rate": 0.00017485107481711012,
+      "loss": 0.4831,
+      "step": 81
+    },
+    {
+      "epoch": 0.49848024316109424,
+      "grad_norm": 0.06836414337158203,
+      "learning_rate": 0.00017420658431491223,
+      "loss": 0.4585,
+      "step": 82
+    },
+    {
+      "epoch": 0.5045592705167173,
+      "grad_norm": 0.06948156654834747,
+      "learning_rate": 0.00017355516000037554,
+      "loss": 0.4624,
+      "step": 83
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "grad_norm": 0.06856788694858551,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 0.4497,
+      "step": 84
+    },
+    {
+      "epoch": 0.5167173252279635,
+      "grad_norm": 0.07304105907678604,
+      "learning_rate": 0.0001722317540510534,
+      "loss": 0.4697,
+      "step": 85
+    },
+    {
+      "epoch": 0.5227963525835866,
+      "grad_norm": 0.07297949492931366,
+      "learning_rate": 0.00017155989607441213,
+      "loss": 0.4376,
+      "step": 86
+    },
+    {
+      "epoch": 0.5288753799392097,
+      "grad_norm": 0.07408228516578674,
+      "learning_rate": 0.00017088135159016584,
+      "loss": 0.4493,
+      "step": 87
+    },
+    {
+      "epoch": 0.5349544072948328,
+      "grad_norm": 0.07207636535167694,
+      "learning_rate": 0.00017019618400104572,
+      "loss": 0.4612,
+      "step": 88
+    },
+    {
+      "epoch": 0.541033434650456,
+      "grad_norm": 0.07454758137464523,
+      "learning_rate": 0.00016950445732864127,
+      "loss": 0.4123,
+      "step": 89
+    },
+    {
+      "epoch": 0.547112462006079,
+      "grad_norm": 0.07566685974597931,
+      "learning_rate": 0.00016880623620741842,
+      "loss": 0.4632,
+      "step": 90
+    },
+    {
+      "epoch": 0.5531914893617021,
+      "grad_norm": 0.07650725543498993,
+      "learning_rate": 0.00016810158587867973,
+      "loss": 0.4153,
+      "step": 91
+    },
+    {
+      "epoch": 0.5592705167173252,
+      "grad_norm": 0.07634485512971878,
+      "learning_rate": 0.0001673905721844686,
+      "loss": 0.4402,
+      "step": 92
+    },
+    {
+      "epoch": 0.5653495440729484,
+      "grad_norm": 0.07571671158075333,
+      "learning_rate": 0.00016667326156141692,
+      "loss": 0.4308,
+      "step": 93
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.08016683161258698,
+      "learning_rate": 0.00016594972103453726,
+      "loss": 0.4213,
+      "step": 94
+    },
+    {
+      "epoch": 0.5775075987841946,
+      "grad_norm": 0.07403143495321274,
+      "learning_rate": 0.0001652200182109602,
+      "loss": 0.4485,
+      "step": 95
+    },
+    {
+      "epoch": 0.5835866261398176,
+      "grad_norm": 0.08598003536462784,
+      "learning_rate": 0.00016448422127361706,
+      "loss": 0.4044,
+      "step": 96
+    },
+    {
+      "epoch": 0.5896656534954408,
+      "grad_norm": 0.0837491899728775,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.3965,
+      "step": 97
+    },
+    {
+      "epoch": 0.5957446808510638,
+      "grad_norm": 0.08433262258768082,
+      "learning_rate": 0.00016299462063008272,
+      "loss": 0.4267,
+      "step": 98
+    },
+    {
+      "epoch": 0.601823708206687,
+      "grad_norm": 0.07738591730594635,
+      "learning_rate": 0.00016224095611115384,
+      "loss": 0.4175,
+      "step": 99
+    },
+    {
+      "epoch": 0.60790273556231,
+      "grad_norm": 0.08330941945314407,
+      "learning_rate": 0.00016148147583997812,
+      "loss": 0.4324,
+      "step": 100
+    },
+    {
+      "epoch": 0.6139817629179332,
+      "grad_norm": 0.08629601448774338,
+      "learning_rate": 0.00016071625078187114,
+      "loss": 0.3949,
+      "step": 101
+    },
+    {
+      "epoch": 0.6200607902735562,
+      "grad_norm": 0.08496759831905365,
+      "learning_rate": 0.0001599453524389374,
+      "loss": 0.4181,
+      "step": 102
+    },
+    {
+      "epoch": 0.6261398176291794,
+      "grad_norm": 0.08593132346868515,
+      "learning_rate": 0.00015916885284338937,
+      "loss": 0.3979,
+      "step": 103
+    },
+    {
+      "epoch": 0.6322188449848024,
+      "grad_norm": 0.08198531717061996,
+      "learning_rate": 0.00015838682455081657,
+      "loss": 0.396,
+      "step": 104
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 0.08349744975566864,
+      "learning_rate": 0.00015759934063340627,
+      "loss": 0.3773,
+      "step": 105
+    },
+    {
+      "epoch": 0.6443768996960486,
+      "grad_norm": 0.08445355296134949,
+      "learning_rate": 0.00015680647467311557,
+      "loss": 0.3946,
+      "step": 106
+    },
+    {
+      "epoch": 0.6504559270516718,
+      "grad_norm": 0.0808950737118721,
+      "learning_rate": 0.00015600830075479603,
+      "loss": 0.3926,
+      "step": 107
+    },
+    {
+      "epoch": 0.6565349544072948,
+      "grad_norm": 0.08728586137294769,
+      "learning_rate": 0.00015520489345927096,
+      "loss": 0.4248,
+      "step": 108
+    },
+    {
+      "epoch": 0.662613981762918,
+      "grad_norm": 0.08645470440387726,
+      "learning_rate": 0.00015439632785636706,
+      "loss": 0.4051,
+      "step": 109
+    },
+    {
+      "epoch": 0.668693009118541,
+      "grad_norm": 0.07910045236349106,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 0.4167,
+      "step": 110
+    },
+    {
+      "epoch": 0.6747720364741642,
+      "grad_norm": 0.08322255313396454,
+      "learning_rate": 0.0001527640244106133,
+      "loss": 0.3842,
+      "step": 111
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.07981768995523453,
+      "learning_rate": 0.00015194043908907775,
+      "loss": 0.3942,
+      "step": 112
+    },
+    {
+      "epoch": 0.6869300911854104,
+      "grad_norm": 0.08817645907402039,
+      "learning_rate": 0.00015111200048854056,
+      "loss": 0.3739,
+      "step": 113
+    },
+    {
+      "epoch": 0.6930091185410334,
+      "grad_norm": 0.09770014137029648,
+      "learning_rate": 0.00015027878601773633,
+      "loss": 0.3781,
+      "step": 114
+    },
+    {
+      "epoch": 0.6990881458966566,
+      "grad_norm": 0.09042941778898239,
+      "learning_rate": 0.0001494408735316537,
+      "loss": 0.3897,
+      "step": 115
+    },
+    {
+      "epoch": 0.7051671732522796,
+      "grad_norm": 0.08232049643993378,
+      "learning_rate": 0.0001485983413242606,
+      "loss": 0.3566,
+      "step": 116
+    },
+    {
+      "epoch": 0.7112462006079028,
+      "grad_norm": 0.08187402784824371,
+      "learning_rate": 0.00014775126812118864,
+      "loss": 0.3559,
+      "step": 117
+    },
+    {
+      "epoch": 0.7173252279635258,
+      "grad_norm": 0.08564823865890503,
+      "learning_rate": 0.00014689973307237687,
+      "loss": 0.37,
+      "step": 118
+    },
+    {
+      "epoch": 0.723404255319149,
+      "grad_norm": 0.09082309901714325,
+      "learning_rate": 0.00014604381574467615,
+      "loss": 0.3962,
+      "step": 119
+    },
+    {
+      "epoch": 0.729483282674772,
+      "grad_norm": 0.09014427661895752,
+      "learning_rate": 0.0001451835961144145,
+      "loss": 0.3391,
+      "step": 120
+    },
+    {
+      "epoch": 0.7355623100303952,
+      "grad_norm": 0.08382211625576019,
+      "learning_rate": 0.00014431915455992414,
+      "loss": 0.3547,
+      "step": 121
+    },
+    {
+      "epoch": 0.7416413373860182,
+      "grad_norm": 0.08397499471902847,
+      "learning_rate": 0.000143450571854031,
+      "loss": 0.3479,
+      "step": 122
+    },
+    {
+      "epoch": 0.7477203647416414,
+      "grad_norm": 0.08822325617074966,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.3824,
+      "step": 123
+    },
+    {
+      "epoch": 0.7537993920972644,
+      "grad_norm": 0.08629824221134186,
+      "learning_rate": 0.00014170130800648814,
+      "loss": 0.3548,
+      "step": 124
+    },
+    {
+      "epoch": 0.7598784194528876,
+      "grad_norm": 0.09454140067100525,
+      "learning_rate": 0.0001408207903148525,
+      "loss": 0.3524,
+      "step": 125
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 0.08818770945072174,
+      "learning_rate": 0.00013993645835656953,
+      "loss": 0.388,
+      "step": 126
+    },
+    {
+      "epoch": 0.7720364741641338,
+      "grad_norm": 0.08908054232597351,
+      "learning_rate": 0.0001390483947630109,
+      "loss": 0.3548,
+      "step": 127
+    },
+    {
+      "epoch": 0.7781155015197568,
+      "grad_norm": 0.08153887093067169,
+      "learning_rate": 0.00013815668251422952,
+      "loss": 0.3545,
+      "step": 128
+    },
+    {
+      "epoch": 0.78419452887538,
+      "grad_norm": 0.08948613703250885,
+      "learning_rate": 0.0001372614049312064,
+      "loss": 0.3483,
+      "step": 129
+    },
+    {
+      "epoch": 0.790273556231003,
+      "grad_norm": 0.08655694872140884,
+      "learning_rate": 0.0001363626456680647,
+      "loss": 0.321,
+      "step": 130
+    },
+    {
+      "epoch": 0.7963525835866262,
+      "grad_norm": 0.09818850457668304,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 0.3647,
+      "step": 131
+    },
+    {
+      "epoch": 0.8024316109422492,
+      "grad_norm": 0.0866372138261795,
+      "learning_rate": 0.00013455501833670088,
+      "loss": 0.3604,
+      "step": 132
+    },
+    {
+      "epoch": 0.8085106382978723,
+      "grad_norm": 0.09384460002183914,
+      "learning_rate": 0.0001336463191719367,
+      "loss": 0.357,
+      "step": 133
+    },
+    {
+      "epoch": 0.8145896656534954,
+      "grad_norm": 0.09135902673006058,
+      "learning_rate": 0.00013273447611818767,
+      "loss": 0.3406,
+      "step": 134
+    },
+    {
+      "epoch": 0.8206686930091185,
+      "grad_norm": 0.08802594989538193,
+      "learning_rate": 0.00013181957437744332,
+      "loss": 0.3548,
+      "step": 135
+    },
+    {
+      "epoch": 0.8267477203647416,
+      "grad_norm": 0.09025990217924118,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.3505,
+      "step": 136
+    },
+    {
+      "epoch": 0.8328267477203647,
+      "grad_norm": 0.09130747616291046,
+      "learning_rate": 0.00012998093706394675,
+      "loss": 0.3159,
+      "step": 137
+    },
+    {
+      "epoch": 0.8389057750759878,
+      "grad_norm": 0.09548977762460709,
+      "learning_rate": 0.00012905737329220392,
+      "loss": 0.3473,
+      "step": 138
+    },
+    {
+      "epoch": 0.8449848024316109,
+      "grad_norm": 0.08869072049856186,
+      "learning_rate": 0.00012813109441943166,
+      "loss": 0.3379,
+      "step": 139
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.09292670339345932,
+      "learning_rate": 0.00012720218699649243,
+      "loss": 0.3252,
+      "step": 140
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.08339939266443253,
+      "learning_rate": 0.0001262707378198587,
+      "loss": 0.2908,
+      "step": 141
+    },
+    {
+      "epoch": 0.8632218844984803,
+      "grad_norm": 0.0901230052113533,
+      "learning_rate": 0.00012533683392350263,
+      "loss": 0.3346,
+      "step": 142
+    },
+    {
+      "epoch": 0.8693009118541033,
+      "grad_norm": 0.09229591488838196,
+      "learning_rate": 0.00012440056257076375,
+      "loss": 0.3523,
+      "step": 143
+    },
+    {
+      "epoch": 0.8753799392097265,
+      "grad_norm": 0.09824731945991516,
+      "learning_rate": 0.00012346201124619502,
+      "loss": 0.3416,
+      "step": 144
+    },
+    {
+      "epoch": 0.8814589665653495,
+      "grad_norm": 0.09328845143318176,
+      "learning_rate": 0.00012252126764738844,
+      "loss": 0.3211,
+      "step": 145
+    },
+    {
+      "epoch": 0.8875379939209727,
+      "grad_norm": 0.09492561221122742,
+      "learning_rate": 0.00012157841967678063,
+      "loss": 0.3404,
+      "step": 146
+    },
+    {
+      "epoch": 0.8936170212765957,
+      "grad_norm": 0.09995546191930771,
+      "learning_rate": 0.00012063355543343924,
+      "loss": 0.3188,
+      "step": 147
+    },
+    {
+      "epoch": 0.8996960486322189,
+      "grad_norm": 0.09694822877645493,
+      "learning_rate": 0.00011968676320483103,
+      "loss": 0.3269,
+      "step": 148
+    },
+    {
+      "epoch": 0.9057750759878419,
+      "grad_norm": 0.11103739589452744,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 0.3228,
+      "step": 149
+    },
+    {
+      "epoch": 0.9118541033434651,
+      "grad_norm": 0.10173939168453217,
+      "learning_rate": 0.00011778774883416323,
+      "loss": 0.3033,
+      "step": 150
+    },
+    {
+      "epoch": 0.9179331306990881,
+      "grad_norm": 0.10053914040327072,
+      "learning_rate": 0.00011683570413470383,
+      "loss": 0.3357,
+      "step": 151
+    },
+    {
+      "epoch": 0.9240121580547113,
+      "grad_norm": 0.09117776155471802,
+      "learning_rate": 0.00011588208631859807,
+      "loss": 0.3288,
+      "step": 152
+    },
+    {
+      "epoch": 0.9300911854103343,
+      "grad_norm": 0.08972764015197754,
+      "learning_rate": 0.00011492698449124042,
+      "loss": 0.3134,
+      "step": 153
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.09842713177204132,
+      "learning_rate": 0.0001139704878966906,
+      "loss": 0.3258,
+      "step": 154
+    },
+    {
+      "epoch": 0.9422492401215805,
+      "grad_norm": 0.08585759252309799,
+      "learning_rate": 0.00011301268590933434,
+      "loss": 0.3121,
+      "step": 155
+    },
+    {
+      "epoch": 0.9483282674772037,
+      "grad_norm": 0.10005568712949753,
+      "learning_rate": 0.0001120536680255323,
+      "loss": 0.3199,
+      "step": 156
+    },
+    {
+      "epoch": 0.9544072948328267,
+      "grad_norm": 0.10690546780824661,
+      "learning_rate": 0.00011109352385525783,
+      "loss": 0.3008,
+      "step": 157
+    },
+    {
+      "epoch": 0.9604863221884499,
+      "grad_norm": 0.0924290269613266,
+      "learning_rate": 0.00011013234311372353,
+      "loss": 0.339,
+      "step": 158
+    },
+    {
+      "epoch": 0.9665653495440729,
+      "grad_norm": 0.09407492727041245,
+      "learning_rate": 0.00010917021561299863,
+      "loss": 0.3282,
+      "step": 159
+    },
+    {
+      "epoch": 0.9726443768996961,
+      "grad_norm": 0.09656916558742523,
+      "learning_rate": 0.00010820723125361684,
+      "loss": 0.285,
+      "step": 160
+    },
+    {
+      "epoch": 0.9787234042553191,
+      "grad_norm": 0.0891689881682396,
+      "learning_rate": 0.00010724348001617625,
+      "loss": 0.3134,
+      "step": 161
+    },
+    {
+      "epoch": 0.9848024316109423,
+      "grad_norm": 0.09076245874166489,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.3014,
+      "step": 162
+    },
+    {
+      "epoch": 0.9908814589665653,
+      "grad_norm": 0.09239046275615692,
+      "learning_rate": 0.00010531403717937887,
+      "loss": 0.2828,
+      "step": 163
+    },
+    {
+      "epoch": 0.9969604863221885,
+      "grad_norm": 0.10273317247629166,
+      "learning_rate": 0.00010434852586583736,
+      "loss": 0.3159,
+      "step": 164
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.1356026530265808,
+      "learning_rate": 0.00010338260822902167,
+      "loss": 0.2756,
+      "step": 165
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 330,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 15,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.452241334344024e+18,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92c755a6637946a23e7b7efa9b6819521969c1a52949f588079811b4baea0936
+size 6353