Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ 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
+checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1795/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,59 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen3-1.7B
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: qwen3-1-7b_eqa_lora_sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen3-1-7b_eqa_lora_sft
+
+This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) on the energy_qa_alpaca dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.4
+- Pytorch 2.7.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-1.7B",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f79ac00559ca6230aa3a5a84363d3eb98ba32978abcbf28e1db0f3931bfdf8
+size 34916720

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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.029161804649267e+16,
+    "train_loss": 1.6974632034726793,
+    "train_runtime": 3260.2981,
+    "train_samples_per_second": 4.402,
+    "train_steps_per_second": 0.551
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-1.7B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-1000/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-1.7B",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a50b421fcd089011ecdb4dd0e14b52dcb4f2057260155df5bd0beb30691521
+size 34916720

checkpoint-1000/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
+}

checkpoint-1000/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4ad6a8fea67f6ccce80912ccf143fbc6580b722d970caec073736763037cee
+size 70059963

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250560ab3d528161ab3659b120def6e4a9ab4b457e3399603bbcfa40db3efc90
+size 14645

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7742f57d6748a994796e54556d7aa815c4953a13a94d3bf47d4e1c767c576e9
+size 1465

checkpoint-1000/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
+  }
+}

checkpoint-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-1000/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
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.557374764857521,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0027868738242876052,
+      "grad_norm": 3.341921806335449,
+      "learning_rate": 2.2222222222222225e-06,
+      "loss": 3.1415,
+      "step": 5
+    },
+    {
+      "epoch": 0.0055737476485752105,
+      "grad_norm": 3.4862101078033447,
+      "learning_rate": 5e-06,
+      "loss": 3.04,
+      "step": 10
+    },
+    {
+      "epoch": 0.008360621472862817,
+      "grad_norm": 3.363572597503662,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 3.019,
+      "step": 15
+    },
+    {
+      "epoch": 0.011147495297150421,
+      "grad_norm": 3.5916693210601807,
+      "learning_rate": 1.0555555555555555e-05,
+      "loss": 3.073,
+      "step": 20
+    },
+    {
+      "epoch": 0.013934369121438027,
+      "grad_norm": 3.8997910022735596,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 3.0359,
+      "step": 25
+    },
+    {
+      "epoch": 0.016721242945725634,
+      "grad_norm": 3.789405345916748,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 2.9568,
+      "step": 30
+    },
+    {
+      "epoch": 0.019508116770013236,
+      "grad_norm": 2.785924196243286,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 2.6633,
+      "step": 35
+    },
+    {
+      "epoch": 0.022294990594300842,
+      "grad_norm": 2.715925693511963,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 2.3416,
+      "step": 40
+    },
+    {
+      "epoch": 0.025081864418588447,
+      "grad_norm": 1.851042628288269,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 2.304,
+      "step": 45
+    },
+    {
+      "epoch": 0.027868738242876053,
+      "grad_norm": 1.1627306938171387,
+      "learning_rate": 2.7222222222222223e-05,
+      "loss": 2.0913,
+      "step": 50
+    },
+    {
+      "epoch": 0.03065561206716366,
+      "grad_norm": 0.8980898857116699,
+      "learning_rate": 3e-05,
+      "loss": 1.9108,
+      "step": 55
+    },
+    {
+      "epoch": 0.03344248589145127,
+      "grad_norm": 0.741324245929718,
+      "learning_rate": 3.277777777777778e-05,
+      "loss": 1.989,
+      "step": 60
+    },
+    {
+      "epoch": 0.03622935971573887,
+      "grad_norm": 0.6890819668769836,
+      "learning_rate": 3.555555555555556e-05,
+      "loss": 1.8792,
+      "step": 65
+    },
+    {
+      "epoch": 0.03901623354002647,
+      "grad_norm": 0.6898017525672913,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 1.7895,
+      "step": 70
+    },
+    {
+      "epoch": 0.04180310736431408,
+      "grad_norm": 0.6752148866653442,
+      "learning_rate": 4.111111111111111e-05,
+      "loss": 1.8742,
+      "step": 75
+    },
+    {
+      "epoch": 0.044589981188601684,
+      "grad_norm": 0.6477967500686646,
+      "learning_rate": 4.388888888888889e-05,
+      "loss": 1.7473,
+      "step": 80
+    },
+    {
+      "epoch": 0.04737685501288929,
+      "grad_norm": 0.6459152698516846,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.8558,
+      "step": 85
+    },
+    {
+      "epoch": 0.050163728837176895,
+      "grad_norm": 0.6237108707427979,
+      "learning_rate": 4.9444444444444446e-05,
+      "loss": 1.7931,
+      "step": 90
+    },
+    {
+      "epoch": 0.0529506026614645,
+      "grad_norm": 0.6388494968414307,
+      "learning_rate": 5.222222222222223e-05,
+      "loss": 1.7712,
+      "step": 95
+    },
+    {
+      "epoch": 0.055737476485752106,
+      "grad_norm": 0.686677098274231,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.7316,
+      "step": 100
+    },
+    {
+      "epoch": 0.05852435031003971,
+      "grad_norm": 0.612424910068512,
+      "learning_rate": 5.7777777777777776e-05,
+      "loss": 1.7602,
+      "step": 105
+    },
+    {
+      "epoch": 0.06131122413432732,
+      "grad_norm": 0.8961934447288513,
+      "learning_rate": 6.055555555555555e-05,
+      "loss": 1.8706,
+      "step": 110
+    },
+    {
+      "epoch": 0.06409809795861493,
+      "grad_norm": 0.7244030833244324,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 1.7701,
+      "step": 115
+    },
+    {
+      "epoch": 0.06688497178290254,
+      "grad_norm": 0.6804441809654236,
+      "learning_rate": 6.611111111111111e-05,
+      "loss": 1.7833,
+      "step": 120
+    },
+    {
+      "epoch": 0.06967184560719013,
+      "grad_norm": 0.6717159152030945,
+      "learning_rate": 6.88888888888889e-05,
+      "loss": 1.8445,
+      "step": 125
+    },
+    {
+      "epoch": 0.07245871943147773,
+      "grad_norm": 0.6639799475669861,
+      "learning_rate": 7.166666666666667e-05,
+      "loss": 1.7847,
+      "step": 130
+    },
+    {
+      "epoch": 0.07524559325576534,
+      "grad_norm": 0.7095969915390015,
+      "learning_rate": 7.444444444444444e-05,
+      "loss": 1.7281,
+      "step": 135
+    },
+    {
+      "epoch": 0.07803246708005294,
+      "grad_norm": 0.8189035654067993,
+      "learning_rate": 7.722222222222223e-05,
+      "loss": 1.7678,
+      "step": 140
+    },
+    {
+      "epoch": 0.08081934090434055,
+      "grad_norm": 0.6709702610969543,
+      "learning_rate": 8e-05,
+      "loss": 1.8645,
+      "step": 145
+    },
+    {
+      "epoch": 0.08360621472862816,
+      "grad_norm": 0.743190348148346,
+      "learning_rate": 8.277777777777778e-05,
+      "loss": 1.8086,
+      "step": 150
+    },
+    {
+      "epoch": 0.08639308855291576,
+      "grad_norm": 0.669023871421814,
+      "learning_rate": 8.555555555555556e-05,
+      "loss": 1.7844,
+      "step": 155
+    },
+    {
+      "epoch": 0.08917996237720337,
+      "grad_norm": 0.8071898221969604,
+      "learning_rate": 8.833333333333333e-05,
+      "loss": 1.7379,
+      "step": 160
+    },
+    {
+      "epoch": 0.09196683620149097,
+      "grad_norm": 0.7679445743560791,
+      "learning_rate": 9.111111111111112e-05,
+      "loss": 1.706,
+      "step": 165
+    },
+    {
+      "epoch": 0.09475371002577858,
+      "grad_norm": 0.7896930575370789,
+      "learning_rate": 9.388888888888889e-05,
+      "loss": 1.7752,
+      "step": 170
+    },
+    {
+      "epoch": 0.09754058385006618,
+      "grad_norm": 0.7258396744728088,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 1.7635,
+      "step": 175
+    },
+    {
+      "epoch": 0.10032745767435379,
+      "grad_norm": 0.8085169196128845,
+      "learning_rate": 9.944444444444446e-05,
+      "loss": 1.7449,
+      "step": 180
+    },
+    {
+      "epoch": 0.1031143314986414,
+      "grad_norm": 0.7673636674880981,
+      "learning_rate": 9.999848639521432e-05,
+      "loss": 1.7286,
+      "step": 185
+    },
+    {
+      "epoch": 0.105901205322929,
+      "grad_norm": 0.7478857040405273,
+      "learning_rate": 9.999233753283091e-05,
+      "loss": 1.7203,
+      "step": 190
+    },
+    {
+      "epoch": 0.1086880791472166,
+      "grad_norm": 0.8994764685630798,
+      "learning_rate": 9.998145939378577e-05,
+      "loss": 1.6964,
+      "step": 195
+    },
+    {
+      "epoch": 0.11147495297150421,
+      "grad_norm": 0.7851970791816711,
+      "learning_rate": 9.996585300715116e-05,
+      "loss": 1.7513,
+      "step": 200
+    },
+    {
+      "epoch": 0.11426182679579182,
+      "grad_norm": 0.7743813395500183,
+      "learning_rate": 9.994551984929175e-05,
+      "loss": 1.7099,
+      "step": 205
+    },
+    {
+      "epoch": 0.11704870062007942,
+      "grad_norm": 0.7080249786376953,
+      "learning_rate": 9.992046184372492e-05,
+      "loss": 1.7431,
+      "step": 210
+    },
+    {
+      "epoch": 0.11983557444436703,
+      "grad_norm": 0.744627058506012,
+      "learning_rate": 9.989068136093873e-05,
+      "loss": 1.7159,
+      "step": 215
+    },
+    {
+      "epoch": 0.12262244826865464,
+      "grad_norm": 0.7715389132499695,
+      "learning_rate": 9.985618121816779e-05,
+      "loss": 1.7696,
+      "step": 220
+    },
+    {
+      "epoch": 0.12540932209294225,
+      "grad_norm": 0.7663665413856506,
+      "learning_rate": 9.981696467912664e-05,
+      "loss": 1.7205,
+      "step": 225
+    },
+    {
+      "epoch": 0.12819619591722986,
+      "grad_norm": 0.7923425436019897,
+      "learning_rate": 9.97730354537011e-05,
+      "loss": 1.7136,
+      "step": 230
+    },
+    {
+      "epoch": 0.13098306974151747,
+      "grad_norm": 0.7929289937019348,
+      "learning_rate": 9.972439769759722e-05,
+      "loss": 1.6462,
+      "step": 235
+    },
+    {
+      "epoch": 0.13376994356580507,
+      "grad_norm": 0.845177948474884,
+      "learning_rate": 9.967105601194823e-05,
+      "loss": 1.8031,
+      "step": 240
+    },
+    {
+      "epoch": 0.13655681739009268,
+      "grad_norm": 0.7540026307106018,
+      "learning_rate": 9.961301544287922e-05,
+      "loss": 1.6899,
+      "step": 245
+    },
+    {
+      "epoch": 0.13934369121438026,
+      "grad_norm": 0.8806189894676208,
+      "learning_rate": 9.955028148102979e-05,
+      "loss": 1.6526,
+      "step": 250
+    },
+    {
+      "epoch": 0.14213056503866786,
+      "grad_norm": 0.8206574320793152,
+      "learning_rate": 9.948286006103466e-05,
+      "loss": 1.8233,
+      "step": 255
+    },
+    {
+      "epoch": 0.14491743886295547,
+      "grad_norm": 0.8984567523002625,
+      "learning_rate": 9.941075756096226e-05,
+      "loss": 1.7252,
+      "step": 260
+    },
+    {
+      "epoch": 0.14770431268724307,
+      "grad_norm": 0.7411919832229614,
+      "learning_rate": 9.933398080171123e-05,
+      "loss": 1.7339,
+      "step": 265
+    },
+    {
+      "epoch": 0.15049118651153068,
+      "grad_norm": 0.8030174970626831,
+      "learning_rate": 9.925253704636543e-05,
+      "loss": 1.6934,
+      "step": 270
+    },
+    {
+      "epoch": 0.15327806033581828,
+      "grad_norm": 0.7879084944725037,
+      "learning_rate": 9.916643399950656e-05,
+      "loss": 1.7197,
+      "step": 275
+    },
+    {
+      "epoch": 0.1560649341601059,
+      "grad_norm": 0.8534114956855774,
+      "learning_rate": 9.907567980648549e-05,
+      "loss": 1.6941,
+      "step": 280
+    },
+    {
+      "epoch": 0.1588518079843935,
+      "grad_norm": 0.74381023645401,
+      "learning_rate": 9.898028305265169e-05,
+      "loss": 1.7919,
+      "step": 285
+    },
+    {
+      "epoch": 0.1616386818086811,
+      "grad_norm": 0.8476956486701965,
+      "learning_rate": 9.888025276254096e-05,
+      "loss": 1.7417,
+      "step": 290
+    },
+    {
+      "epoch": 0.1644255556329687,
+      "grad_norm": 0.8212200403213501,
+      "learning_rate": 9.877559839902184e-05,
+      "loss": 1.7452,
+      "step": 295
+    },
+    {
+      "epoch": 0.1672124294572563,
+      "grad_norm": 0.8340197801589966,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 1.6687,
+      "step": 300
+    },
+    {
+      "epoch": 0.16999930328154392,
+      "grad_norm": 0.858363151550293,
+      "learning_rate": 9.855245748948326e-05,
+      "loss": 1.7669,
+      "step": 305
+    },
+    {
+      "epoch": 0.17278617710583152,
+      "grad_norm": 0.8392812013626099,
+      "learning_rate": 9.843399205260068e-05,
+      "loss": 1.736,
+      "step": 310
+    },
+    {
+      "epoch": 0.17557305093011913,
+      "grad_norm": 0.8345137238502502,
+      "learning_rate": 9.831094475858652e-05,
+      "loss": 1.7264,
+      "step": 315
+    },
+    {
+      "epoch": 0.17835992475440673,
+      "grad_norm": 0.8243482708930969,
+      "learning_rate": 9.818332724771857e-05,
+      "loss": 1.7748,
+      "step": 320
+    },
+    {
+      "epoch": 0.18114679857869434,
+      "grad_norm": 0.8255311846733093,
+      "learning_rate": 9.805115159261726e-05,
+      "loss": 1.6798,
+      "step": 325
+    },
+    {
+      "epoch": 0.18393367240298195,
+      "grad_norm": 0.8170781135559082,
+      "learning_rate": 9.791443029710361e-05,
+      "loss": 1.6542,
+      "step": 330
+    },
+    {
+      "epoch": 0.18672054622726955,
+      "grad_norm": 0.8476420044898987,
+      "learning_rate": 9.777317629501636e-05,
+      "loss": 1.6875,
+      "step": 335
+    },
+    {
+      "epoch": 0.18950742005155716,
+      "grad_norm": 0.7547033429145813,
+      "learning_rate": 9.762740294898846e-05,
+      "loss": 1.646,
+      "step": 340
+    },
+    {
+      "epoch": 0.19229429387584476,
+      "grad_norm": 0.826404869556427,
+      "learning_rate": 9.747712404918286e-05,
+      "loss": 1.6187,
+      "step": 345
+    },
+    {
+      "epoch": 0.19508116770013237,
+      "grad_norm": 0.964885950088501,
+      "learning_rate": 9.732235381198813e-05,
+      "loss": 1.7507,
+      "step": 350
+    },
+    {
+      "epoch": 0.19786804152441997,
+      "grad_norm": 0.8207951188087463,
+      "learning_rate": 9.716310687867342e-05,
+      "loss": 1.5745,
+      "step": 355
+    },
+    {
+      "epoch": 0.20065491534870758,
+      "grad_norm": 0.8143700361251831,
+      "learning_rate": 9.699939831400351e-05,
+      "loss": 1.7754,
+      "step": 360
+    },
+    {
+      "epoch": 0.20344178917299519,
+      "grad_norm": 0.811844527721405,
+      "learning_rate": 9.683124360481364e-05,
+      "loss": 1.6993,
+      "step": 365
+    },
+    {
+      "epoch": 0.2062286629972828,
+      "grad_norm": 0.8975111842155457,
+      "learning_rate": 9.665865865854445e-05,
+      "loss": 1.6901,
+      "step": 370
+    },
+    {
+      "epoch": 0.2090155368215704,
+      "grad_norm": 0.7903837561607361,
+      "learning_rate": 9.648165980173712e-05,
+      "loss": 1.6895,
+      "step": 375
+    },
+    {
+      "epoch": 0.211802410645858,
+      "grad_norm": 0.8718327879905701,
+      "learning_rate": 9.630026377848892e-05,
+      "loss": 1.6725,
+      "step": 380
+    },
+    {
+      "epoch": 0.2145892844701456,
+      "grad_norm": 0.8131148219108582,
+      "learning_rate": 9.611448774886924e-05,
+      "loss": 1.6874,
+      "step": 385
+    },
+    {
+      "epoch": 0.2173761582944332,
+      "grad_norm": 0.8331175446510315,
+      "learning_rate": 9.592434928729616e-05,
+      "loss": 1.7542,
+      "step": 390
+    },
+    {
+      "epoch": 0.22016303211872082,
+      "grad_norm": 0.792988121509552,
+      "learning_rate": 9.572986638087396e-05,
+      "loss": 1.7311,
+      "step": 395
+    },
+    {
+      "epoch": 0.22294990594300843,
+      "grad_norm": 0.7799636721611023,
+      "learning_rate": 9.553105742769154e-05,
+      "loss": 1.6567,
+      "step": 400
+    },
+    {
+      "epoch": 0.22573677976729603,
+      "grad_norm": 0.7864108085632324,
+      "learning_rate": 9.532794123508197e-05,
+      "loss": 1.5611,
+      "step": 405
+    },
+    {
+      "epoch": 0.22852365359158364,
+      "grad_norm": 0.8886444568634033,
+      "learning_rate": 9.512053701784329e-05,
+      "loss": 1.6995,
+      "step": 410
+    },
+    {
+      "epoch": 0.23131052741587124,
+      "grad_norm": 0.7999454736709595,
+      "learning_rate": 9.490886439642081e-05,
+      "loss": 1.6898,
+      "step": 415
+    },
+    {
+      "epoch": 0.23409740124015885,
+      "grad_norm": 0.7729182243347168,
+      "learning_rate": 9.469294339505098e-05,
+      "loss": 1.7204,
+      "step": 420
+    },
+    {
+      "epoch": 0.23688427506444645,
+      "grad_norm": 0.8300912380218506,
+      "learning_rate": 9.447279443986716e-05,
+      "loss": 1.6668,
+      "step": 425
+    },
+    {
+      "epoch": 0.23967114888873406,
+      "grad_norm": 0.840481698513031,
+      "learning_rate": 9.424843835696724e-05,
+      "loss": 1.704,
+      "step": 430
+    },
+    {
+      "epoch": 0.24245802271302166,
+      "grad_norm": 0.9396219253540039,
+      "learning_rate": 9.401989637044355e-05,
+      "loss": 1.6713,
+      "step": 435
+    },
+    {
+      "epoch": 0.24524489653730927,
+      "grad_norm": 0.8775554299354553,
+      "learning_rate": 9.3787190100375e-05,
+      "loss": 1.6883,
+      "step": 440
+    },
+    {
+      "epoch": 0.24803177036159688,
+      "grad_norm": 0.8623490333557129,
+      "learning_rate": 9.355034156078188e-05,
+      "loss": 1.6783,
+      "step": 445
+    },
+    {
+      "epoch": 0.2508186441858845,
+      "grad_norm": 0.806533694267273,
+      "learning_rate": 9.330937315754329e-05,
+      "loss": 1.6853,
+      "step": 450
+    },
+    {
+      "epoch": 0.2536055180101721,
+      "grad_norm": 0.8504590392112732,
+      "learning_rate": 9.306430768627753e-05,
+      "loss": 1.6594,
+      "step": 455
+    },
+    {
+      "epoch": 0.2563923918344597,
+      "grad_norm": 0.9382562637329102,
+      "learning_rate": 9.281516833018571e-05,
+      "loss": 1.6827,
+      "step": 460
+    },
+    {
+      "epoch": 0.2591792656587473,
+      "grad_norm": 0.821978747844696,
+      "learning_rate": 9.256197865785854e-05,
+      "loss": 1.752,
+      "step": 465
+    },
+    {
+      "epoch": 0.26196613948303493,
+      "grad_norm": 0.8061692714691162,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": 1.6773,
+      "step": 470
+    },
+    {
+      "epoch": 0.26475301330732254,
+      "grad_norm": 0.8759399652481079,
+      "learning_rate": 9.204354455239539e-05,
+      "loss": 1.7003,
+      "step": 475
+    },
+    {
+      "epoch": 0.26753988713161014,
+      "grad_norm": 0.8721809387207031,
+      "learning_rate": 9.177834916314165e-05,
+      "loss": 1.6898,
+      "step": 480
+    },
+    {
+      "epoch": 0.27032676095589775,
+      "grad_norm": 0.7904046773910522,
+      "learning_rate": 9.150920154077754e-05,
+      "loss": 1.6636,
+      "step": 485
+    },
+    {
+      "epoch": 0.27311363478018535,
+      "grad_norm": 0.8828450441360474,
+      "learning_rate": 9.123612714667634e-05,
+      "loss": 1.6945,
+      "step": 490
+    },
+    {
+      "epoch": 0.2759005086044729,
+      "grad_norm": 0.7389103174209595,
+      "learning_rate": 9.095915181368412e-05,
+      "loss": 1.7459,
+      "step": 495
+    },
+    {
+      "epoch": 0.2786873824287605,
+      "grad_norm": 0.975307285785675,
+      "learning_rate": 9.067830174367586e-05,
+      "loss": 1.7296,
+      "step": 500
+    },
+    {
+      "epoch": 0.2814742562530481,
+      "grad_norm": 0.812856137752533,
+      "learning_rate": 9.039360350507679e-05,
+      "loss": 1.696,
+      "step": 505
+    },
+    {
+      "epoch": 0.2842611300773357,
+      "grad_norm": 0.8609644770622253,
+      "learning_rate": 9.010508403034898e-05,
+      "loss": 1.6464,
+      "step": 510
+    },
+    {
+      "epoch": 0.2870480039016233,
+      "grad_norm": 0.8457721471786499,
+      "learning_rate": 8.98127706134436e-05,
+      "loss": 1.682,
+      "step": 515
+    },
+    {
+      "epoch": 0.28983487772591093,
+      "grad_norm": 0.8576518297195435,
+      "learning_rate": 8.951669090721881e-05,
+      "loss": 1.6784,
+      "step": 520
+    },
+    {
+      "epoch": 0.29262175155019854,
+      "grad_norm": 0.892368495464325,
+      "learning_rate": 8.921687292082393e-05,
+      "loss": 1.6283,
+      "step": 525
+    },
+    {
+      "epoch": 0.29540862537448614,
+      "grad_norm": 0.7966616749763489,
+      "learning_rate": 8.891334501704962e-05,
+      "loss": 1.6898,
+      "step": 530
+    },
+    {
+      "epoch": 0.29819549919877375,
+      "grad_norm": 0.9272663593292236,
+      "learning_rate": 8.86061359096449e-05,
+      "loss": 1.6205,
+      "step": 535
+    },
+    {
+      "epoch": 0.30098237302306136,
+      "grad_norm": 0.8790031671524048,
+      "learning_rate": 8.829527466060072e-05,
+      "loss": 1.5345,
+      "step": 540
+    },
+    {
+      "epoch": 0.30376924684734896,
+      "grad_norm": 0.8462222814559937,
+      "learning_rate": 8.798079067740077e-05,
+      "loss": 1.7664,
+      "step": 545
+    },
+    {
+      "epoch": 0.30655612067163657,
+      "grad_norm": 0.8935257792472839,
+      "learning_rate": 8.766271371023948e-05,
+      "loss": 1.6742,
+      "step": 550
+    },
+    {
+      "epoch": 0.3093429944959242,
+      "grad_norm": 0.9315011501312256,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 1.6154,
+      "step": 555
+    },
+    {
+      "epoch": 0.3121298683202118,
+      "grad_norm": 0.8667712807655334,
+      "learning_rate": 8.701590152144612e-05,
+      "loss": 1.6356,
+      "step": 560
+    },
+    {
+      "epoch": 0.3149167421444994,
+      "grad_norm": 0.9088530540466309,
+      "learning_rate": 8.668722748826693e-05,
+      "loss": 1.6645,
+      "step": 565
+    },
+    {
+      "epoch": 0.317703615968787,
+      "grad_norm": 0.8751830458641052,
+      "learning_rate": 8.635508284224371e-05,
+      "loss": 1.7629,
+      "step": 570
+    },
+    {
+      "epoch": 0.3204904897930746,
+      "grad_norm": 0.8768523335456848,
+      "learning_rate": 8.601949900427016e-05,
+      "loss": 1.631,
+      "step": 575
+    },
+    {
+      "epoch": 0.3232773636173622,
+      "grad_norm": 0.9074881672859192,
+      "learning_rate": 8.568050772058762e-05,
+      "loss": 1.6924,
+      "step": 580
+    },
+    {
+      "epoch": 0.3260642374416498,
+      "grad_norm": 0.9533477425575256,
+      "learning_rate": 8.533814105978191e-05,
+      "loss": 1.644,
+      "step": 585
+    },
+    {
+      "epoch": 0.3288511112659374,
+      "grad_norm": 0.8163946866989136,
+      "learning_rate": 8.499243140974966e-05,
+      "loss": 1.6587,
+      "step": 590
+    },
+    {
+      "epoch": 0.331637985090225,
+      "grad_norm": 0.8785070180892944,
+      "learning_rate": 8.464341147463431e-05,
+      "loss": 1.6666,
+      "step": 595
+    },
+    {
+      "epoch": 0.3344248589145126,
+      "grad_norm": 0.8283839821815491,
+      "learning_rate": 8.429111427173241e-05,
+      "loss": 1.5772,
+      "step": 600
+    },
+    {
+      "epoch": 0.33721173273880023,
+      "grad_norm": 0.8584945797920227,
+      "learning_rate": 8.393557312837018e-05,
+      "loss": 1.6317,
+      "step": 605
+    },
+    {
+      "epoch": 0.33999860656308784,
+      "grad_norm": 0.880062997341156,
+      "learning_rate": 8.357682167875062e-05,
+      "loss": 1.7025,
+      "step": 610
+    },
+    {
+      "epoch": 0.34278548038737544,
+      "grad_norm": 0.9203423261642456,
+      "learning_rate": 8.321489386077192e-05,
+      "loss": 1.6741,
+      "step": 615
+    },
+    {
+      "epoch": 0.34557235421166305,
+      "grad_norm": 0.917999804019928,
+      "learning_rate": 8.28498239128167e-05,
+      "loss": 1.6954,
+      "step": 620
+    },
+    {
+      "epoch": 0.34835922803595065,
+      "grad_norm": 0.8408088088035583,
+      "learning_rate": 8.248164637051321e-05,
+      "loss": 1.6443,
+      "step": 625
+    },
+    {
+      "epoch": 0.35114610186023826,
+      "grad_norm": 0.908991277217865,
+      "learning_rate": 8.211039606346826e-05,
+      "loss": 1.6907,
+      "step": 630
+    },
+    {
+      "epoch": 0.35393297568452586,
+      "grad_norm": 0.9045994877815247,
+      "learning_rate": 8.173610811197226e-05,
+      "loss": 1.66,
+      "step": 635
+    },
+    {
+      "epoch": 0.35671984950881347,
+      "grad_norm": 0.8032850623130798,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 1.6538,
+      "step": 640
+    },
+    {
+      "epoch": 0.3595067233331011,
+      "grad_norm": 0.9243664741516113,
+      "learning_rate": 8.097856119024545e-05,
+      "loss": 1.7321,
+      "step": 645
+    },
+    {
+      "epoch": 0.3622935971573887,
+      "grad_norm": 0.9106388092041016,
+      "learning_rate": 8.059537388397665e-05,
+      "loss": 1.6566,
+      "step": 650
+    },
+    {
+      "epoch": 0.3650804709816763,
+      "grad_norm": 0.9164809584617615,
+      "learning_rate": 8.020929225440137e-05,
+      "loss": 1.6663,
+      "step": 655
+    },
+    {
+      "epoch": 0.3678673448059639,
+      "grad_norm": 0.9171935319900513,
+      "learning_rate": 7.98203528248536e-05,
+      "loss": 1.6781,
+      "step": 660
+    },
+    {
+      "epoch": 0.3706542186302515,
+      "grad_norm": 0.8433538675308228,
+      "learning_rate": 7.942859238901528e-05,
+      "loss": 1.7255,
+      "step": 665
+    },
+    {
+      "epoch": 0.3734410924545391,
+      "grad_norm": 0.9780874252319336,
+      "learning_rate": 7.903404800743564e-05,
+      "loss": 1.722,
+      "step": 670
+    },
+    {
+      "epoch": 0.3762279662788267,
+      "grad_norm": 0.9980689287185669,
+      "learning_rate": 7.863675700402526e-05,
+      "loss": 1.6403,
+      "step": 675
+    },
+    {
+      "epoch": 0.3790148401031143,
+      "grad_norm": 0.843333899974823,
+      "learning_rate": 7.823675696252524e-05,
+      "loss": 1.7583,
+      "step": 680
+    },
+    {
+      "epoch": 0.3818017139274019,
+      "grad_norm": 0.8417442440986633,
+      "learning_rate": 7.783408572295174e-05,
+      "loss": 1.6938,
+      "step": 685
+    },
+    {
+      "epoch": 0.3845885877516895,
+      "grad_norm": 0.8940498232841492,
+      "learning_rate": 7.742878137801639e-05,
+      "loss": 1.6737,
+      "step": 690
+    },
+    {
+      "epoch": 0.38737546157597713,
+      "grad_norm": 0.8713932633399963,
+      "learning_rate": 7.702088226952258e-05,
+      "loss": 1.6435,
+      "step": 695
+    },
+    {
+      "epoch": 0.39016233540026474,
+      "grad_norm": 0.9215396046638489,
+      "learning_rate": 7.661042698473853e-05,
+      "loss": 1.5994,
+      "step": 700
+    },
+    {
+      "epoch": 0.39294920922455234,
+      "grad_norm": 0.8360981941223145,
+      "learning_rate": 7.619745435274667e-05,
+      "loss": 1.6511,
+      "step": 705
+    },
+    {
+      "epoch": 0.39573608304883995,
+      "grad_norm": 0.9177049398422241,
+      "learning_rate": 7.578200344077073e-05,
+      "loss": 1.6655,
+      "step": 710
+    },
+    {
+      "epoch": 0.39852295687312755,
+      "grad_norm": 0.8501256108283997,
+      "learning_rate": 7.536411355047964e-05,
+      "loss": 1.659,
+      "step": 715
+    },
+    {
+      "epoch": 0.40130983069741516,
+      "grad_norm": 0.8666147589683533,
+      "learning_rate": 7.494382421426984e-05,
+      "loss": 1.7046,
+      "step": 720
+    },
+    {
+      "epoch": 0.40409670452170277,
+      "grad_norm": 0.8096281290054321,
+      "learning_rate": 7.452117519152542e-05,
+      "loss": 1.6108,
+      "step": 725
+    },
+    {
+      "epoch": 0.40688357834599037,
+      "grad_norm": 1.0028629302978516,
+      "learning_rate": 7.409620646485685e-05,
+      "loss": 1.6302,
+      "step": 730
+    },
+    {
+      "epoch": 0.409670452170278,
+      "grad_norm": 0.8731248378753662,
+      "learning_rate": 7.36689582363187e-05,
+      "loss": 1.6784,
+      "step": 735
+    },
+    {
+      "epoch": 0.4124573259945656,
+      "grad_norm": 0.9034931659698486,
+      "learning_rate": 7.323947092360649e-05,
+      "loss": 1.5845,
+      "step": 740
+    },
+    {
+      "epoch": 0.4152441998188532,
+      "grad_norm": 0.9129267334938049,
+      "learning_rate": 7.280778515623314e-05,
+      "loss": 1.7366,
+      "step": 745
+    },
+    {
+      "epoch": 0.4180310736431408,
+      "grad_norm": 0.9088048338890076,
+      "learning_rate": 7.237394177168548e-05,
+      "loss": 1.7065,
+      "step": 750
+    },
+    {
+      "epoch": 0.4208179474674284,
+      "grad_norm": 0.9397730827331543,
+      "learning_rate": 7.193798181156095e-05,
+      "loss": 1.7012,
+      "step": 755
+    },
+    {
+      "epoch": 0.423604821291716,
+      "grad_norm": 0.9324731230735779,
+      "learning_rate": 7.149994651768514e-05,
+      "loss": 1.5474,
+      "step": 760
+    },
+    {
+      "epoch": 0.4263916951160036,
+      "grad_norm": 0.9360097646713257,
+      "learning_rate": 7.10598773282103e-05,
+      "loss": 1.6602,
+      "step": 765
+    },
+    {
+      "epoch": 0.4291785689402912,
+      "grad_norm": 0.9703853130340576,
+      "learning_rate": 7.061781587369519e-05,
+      "loss": 1.7305,
+      "step": 770
+    },
+    {
+      "epoch": 0.4319654427645788,
+      "grad_norm": 0.9043810367584229,
+      "learning_rate": 7.017380397316695e-05,
+      "loss": 1.6131,
+      "step": 775
+    },
+    {
+      "epoch": 0.4347523165888664,
+      "grad_norm": 0.8870768547058105,
+      "learning_rate": 6.972788363016497e-05,
+      "loss": 1.5668,
+      "step": 780
+    },
+    {
+      "epoch": 0.43753919041315403,
+      "grad_norm": 0.9383454918861389,
+      "learning_rate": 6.92800970287674e-05,
+      "loss": 1.6773,
+      "step": 785
+    },
+    {
+      "epoch": 0.44032606423744164,
+      "grad_norm": 0.8532437682151794,
+      "learning_rate": 6.883048652960038e-05,
+      "loss": 1.6602,
+      "step": 790
+    },
+    {
+      "epoch": 0.44311293806172924,
+      "grad_norm": 0.8915623426437378,
+      "learning_rate": 6.837909466583095e-05,
+      "loss": 1.6778,
+      "step": 795
+    },
+    {
+      "epoch": 0.44589981188601685,
+      "grad_norm": 0.840151846408844,
+      "learning_rate": 6.792596413914324e-05,
+      "loss": 1.5566,
+      "step": 800
+    },
+    {
+      "epoch": 0.44868668571030446,
+      "grad_norm": 0.8808228969573975,
+      "learning_rate": 6.747113781569892e-05,
+      "loss": 1.6819,
+      "step": 805
+    },
+    {
+      "epoch": 0.45147355953459206,
+      "grad_norm": 0.9224216938018799,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 1.7057,
+      "step": 810
+    },
+    {
+      "epoch": 0.45426043335887967,
+      "grad_norm": 1.0062270164489746,
+      "learning_rate": 6.655657004122916e-05,
+      "loss": 1.719,
+      "step": 815
+    },
+    {
+      "epoch": 0.4570473071831673,
+      "grad_norm": 0.9544162154197693,
+      "learning_rate": 6.60969151083432e-05,
+      "loss": 1.657,
+      "step": 820
+    },
+    {
+      "epoch": 0.4598341810074549,
+      "grad_norm": 0.8740416169166565,
+      "learning_rate": 6.563573740679496e-05,
+      "loss": 1.645,
+      "step": 825
+    },
+    {
+      "epoch": 0.4626210548317425,
+      "grad_norm": 0.8866944313049316,
+      "learning_rate": 6.517308056400917e-05,
+      "loss": 1.6446,
+      "step": 830
+    },
+    {
+      "epoch": 0.4654079286560301,
+      "grad_norm": 0.9224971532821655,
+      "learning_rate": 6.470898834733731e-05,
+      "loss": 1.6384,
+      "step": 835
+    },
+    {
+      "epoch": 0.4681948024803177,
+      "grad_norm": 0.8925870656967163,
+      "learning_rate": 6.42435046599173e-05,
+      "loss": 1.6455,
+      "step": 840
+    },
+    {
+      "epoch": 0.4709816763046053,
+      "grad_norm": 0.9226738810539246,
+      "learning_rate": 6.377667353652022e-05,
+      "loss": 1.6799,
+      "step": 845
+    },
+    {
+      "epoch": 0.4737685501288929,
+      "grad_norm": 0.9104128479957581,
+      "learning_rate": 6.330853913938466e-05,
+      "loss": 1.6267,
+      "step": 850
+    },
+    {
+      "epoch": 0.4765554239531805,
+      "grad_norm": 0.912969708442688,
+      "learning_rate": 6.283914575403888e-05,
+      "loss": 1.716,
+      "step": 855
+    },
+    {
+      "epoch": 0.4793422977774681,
+      "grad_norm": 0.9142662882804871,
+      "learning_rate": 6.236853778511156e-05,
+      "loss": 1.6619,
+      "step": 860
+    },
+    {
+      "epoch": 0.4821291716017557,
+      "grad_norm": 0.9380782842636108,
+      "learning_rate": 6.189675975213094e-05,
+      "loss": 1.6578,
+      "step": 865
+    },
+    {
+      "epoch": 0.48491604542604333,
+      "grad_norm": 0.9225218296051025,
+      "learning_rate": 6.142385628531342e-05,
+      "loss": 1.6891,
+      "step": 870
+    },
+    {
+      "epoch": 0.48770291925033094,
+      "grad_norm": 0.9732077121734619,
+      "learning_rate": 6.09498721213414e-05,
+      "loss": 1.6008,
+      "step": 875
+    },
+    {
+      "epoch": 0.49048979307461854,
+      "grad_norm": 0.9870405197143555,
+      "learning_rate": 6.047485209913137e-05,
+      "loss": 1.7372,
+      "step": 880
+    },
+    {
+      "epoch": 0.49327666689890615,
+      "grad_norm": 0.8708714246749878,
+      "learning_rate": 5.999884115559192e-05,
+      "loss": 1.6317,
+      "step": 885
+    },
+    {
+      "epoch": 0.49606354072319375,
+      "grad_norm": 0.8490287065505981,
+      "learning_rate": 5.952188432137293e-05,
+      "loss": 1.6514,
+      "step": 890
+    },
+    {
+      "epoch": 0.49885041454748136,
+      "grad_norm": 0.7740074992179871,
+      "learning_rate": 5.90440267166055e-05,
+      "loss": 1.6091,
+      "step": 895
+    },
+    {
+      "epoch": 0.501637288371769,
+      "grad_norm": 0.9218555092811584,
+      "learning_rate": 5.8565313546633684e-05,
+      "loss": 1.674,
+      "step": 900
+    },
+    {
+      "epoch": 0.5044241621960566,
+      "grad_norm": 0.8074113726615906,
+      "learning_rate": 5.8085790097738025e-05,
+      "loss": 1.6567,
+      "step": 905
+    },
+    {
+      "epoch": 0.5072110360203442,
+      "grad_norm": 0.9320290684700012,
+      "learning_rate": 5.7605501732851475e-05,
+      "loss": 1.6925,
+      "step": 910
+    },
+    {
+      "epoch": 0.5099979098446318,
+      "grad_norm": 0.8326326012611389,
+      "learning_rate": 5.712449388726807e-05,
+      "loss": 1.6909,
+      "step": 915
+    },
+    {
+      "epoch": 0.5127847836689194,
+      "grad_norm": 0.9022158980369568,
+      "learning_rate": 5.664281206434472e-05,
+      "loss": 1.6075,
+      "step": 920
+    },
+    {
+      "epoch": 0.515571657493207,
+      "grad_norm": 0.8791519999504089,
+      "learning_rate": 5.616050183119663e-05,
+      "loss": 1.7011,
+      "step": 925
+    },
+    {
+      "epoch": 0.5183585313174947,
+      "grad_norm": 0.876043438911438,
+      "learning_rate": 5.5677608814386616e-05,
+      "loss": 1.5478,
+      "step": 930
+    },
+    {
+      "epoch": 0.5211454051417822,
+      "grad_norm": 0.9437665939331055,
+      "learning_rate": 5.519417869560889e-05,
+      "loss": 1.6518,
+      "step": 935
+    },
+    {
+      "epoch": 0.5239322789660699,
+      "grad_norm": 0.9788090586662292,
+      "learning_rate": 5.471025720736747e-05,
+      "loss": 1.7146,
+      "step": 940
+    },
+    {
+      "epoch": 0.5267191527903574,
+      "grad_norm": 0.861488938331604,
+      "learning_rate": 5.422589012864996e-05,
+      "loss": 1.6805,
+      "step": 945
+    },
+    {
+      "epoch": 0.5295060266146451,
+      "grad_norm": 1.008576512336731,
+      "learning_rate": 5.3741123280596864e-05,
+      "loss": 1.6012,
+      "step": 950
+    },
+    {
+      "epoch": 0.5322929004389326,
+      "grad_norm": 0.9095168113708496,
+      "learning_rate": 5.325600252216685e-05,
+      "loss": 1.6477,
+      "step": 955
+    },
+    {
+      "epoch": 0.5350797742632203,
+      "grad_norm": 0.8760788440704346,
+      "learning_rate": 5.27705737457985e-05,
+      "loss": 1.5747,
+      "step": 960
+    },
+    {
+      "epoch": 0.5378666480875078,
+      "grad_norm": 0.9696391224861145,
+      "learning_rate": 5.228488287306896e-05,
+      "loss": 1.6249,
+      "step": 965
+    },
+    {
+      "epoch": 0.5406535219117955,
+      "grad_norm": 0.8726052641868591,
+      "learning_rate": 5.179897585034963e-05,
+      "loss": 1.6701,
+      "step": 970
+    },
+    {
+      "epoch": 0.543440395736083,
+      "grad_norm": 0.8699939846992493,
+      "learning_rate": 5.1312898644459776e-05,
+      "loss": 1.5395,
+      "step": 975
+    },
+    {
+      "epoch": 0.5462272695603707,
+      "grad_norm": 0.9301031827926636,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": 1.6724,
+      "step": 980
+    },
+    {
+      "epoch": 0.5490141433846583,
+      "grad_norm": 0.8767033815383911,
+      "learning_rate": 5.0340417626592016e-05,
+      "loss": 1.6492,
+      "step": 985
+    },
+    {
+      "epoch": 0.5518010172089458,
+      "grad_norm": 0.9239912629127502,
+      "learning_rate": 4.9854105811348216e-05,
+      "loss": 1.6705,
+      "step": 990
+    },
+    {
+      "epoch": 0.5545878910332335,
+      "grad_norm": 1.0233875513076782,
+      "learning_rate": 4.936780779769913e-05,
+      "loss": 1.6758,
+      "step": 995
+    },
+    {
+      "epoch": 0.557374764857521,
+      "grad_norm": 0.9696400165557861,
+      "learning_rate": 4.888156958945174e-05,
+      "loss": 1.6276,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1795,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.129724819300352e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be8c0fcf2f8a062ba98a621f2443fdb7418dd260bb1044a8c33b7c88ee37e698
+size 6161

checkpoint-1500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-1.7B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-1500/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-1.7B",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c04a325765a01f7b125d6e2f20caaa99cea617b1a72a99547992b7f207999e
+size 34916720

checkpoint-1500/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
+}

checkpoint-1500/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e943568edd259ae9bfd24c0034a5abf23be3372e0c4c7424c647162121b751e
+size 70059963

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250560ab3d528161ab3659b120def6e4a9ab4b457e3399603bbcfa40db3efc90
+size 14645

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ecf9f08b8ece20f8e38217288ba9577a3fcfff91bb28828bd121972f45e8e0
+size 1465

checkpoint-1500/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
+  }
+}

checkpoint-1500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-1500/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
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,2134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8360621472862816,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0027868738242876052,
+      "grad_norm": 3.341921806335449,
+      "learning_rate": 2.2222222222222225e-06,
+      "loss": 3.1415,
+      "step": 5
+    },
+    {
+      "epoch": 0.0055737476485752105,
+      "grad_norm": 3.4862101078033447,
+      "learning_rate": 5e-06,
+      "loss": 3.04,
+      "step": 10
+    },
+    {
+      "epoch": 0.008360621472862817,
+      "grad_norm": 3.363572597503662,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 3.019,
+      "step": 15
+    },
+    {
+      "epoch": 0.011147495297150421,
+      "grad_norm": 3.5916693210601807,
+      "learning_rate": 1.0555555555555555e-05,
+      "loss": 3.073,
+      "step": 20
+    },
+    {
+      "epoch": 0.013934369121438027,
+      "grad_norm": 3.8997910022735596,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 3.0359,
+      "step": 25
+    },
+    {
+      "epoch": 0.016721242945725634,
+      "grad_norm": 3.789405345916748,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 2.9568,
+      "step": 30
+    },
+    {
+      "epoch": 0.019508116770013236,
+      "grad_norm": 2.785924196243286,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 2.6633,
+      "step": 35
+    },
+    {
+      "epoch": 0.022294990594300842,
+      "grad_norm": 2.715925693511963,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 2.3416,
+      "step": 40
+    },
+    {
+      "epoch": 0.025081864418588447,
+      "grad_norm": 1.851042628288269,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 2.304,
+      "step": 45
+    },
+    {
+      "epoch": 0.027868738242876053,
+      "grad_norm": 1.1627306938171387,
+      "learning_rate": 2.7222222222222223e-05,
+      "loss": 2.0913,
+      "step": 50
+    },
+    {
+      "epoch": 0.03065561206716366,
+      "grad_norm": 0.8980898857116699,
+      "learning_rate": 3e-05,
+      "loss": 1.9108,
+      "step": 55
+    },
+    {
+      "epoch": 0.03344248589145127,
+      "grad_norm": 0.741324245929718,
+      "learning_rate": 3.277777777777778e-05,
+      "loss": 1.989,
+      "step": 60
+    },
+    {
+      "epoch": 0.03622935971573887,
+      "grad_norm": 0.6890819668769836,
+      "learning_rate": 3.555555555555556e-05,
+      "loss": 1.8792,
+      "step": 65
+    },
+    {
+      "epoch": 0.03901623354002647,
+      "grad_norm": 0.6898017525672913,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 1.7895,
+      "step": 70
+    },
+    {
+      "epoch": 0.04180310736431408,
+      "grad_norm": 0.6752148866653442,
+      "learning_rate": 4.111111111111111e-05,
+      "loss": 1.8742,
+      "step": 75
+    },
+    {
+      "epoch": 0.044589981188601684,
+      "grad_norm": 0.6477967500686646,
+      "learning_rate": 4.388888888888889e-05,
+      "loss": 1.7473,
+      "step": 80
+    },
+    {
+      "epoch": 0.04737685501288929,
+      "grad_norm": 0.6459152698516846,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.8558,
+      "step": 85
+    },
+    {
+      "epoch": 0.050163728837176895,
+      "grad_norm": 0.6237108707427979,
+      "learning_rate": 4.9444444444444446e-05,
+      "loss": 1.7931,
+      "step": 90
+    },
+    {
+      "epoch": 0.0529506026614645,
+      "grad_norm": 0.6388494968414307,
+      "learning_rate": 5.222222222222223e-05,
+      "loss": 1.7712,
+      "step": 95
+    },
+    {
+      "epoch": 0.055737476485752106,
+      "grad_norm": 0.686677098274231,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.7316,
+      "step": 100
+    },
+    {
+      "epoch": 0.05852435031003971,
+      "grad_norm": 0.612424910068512,
+      "learning_rate": 5.7777777777777776e-05,
+      "loss": 1.7602,
+      "step": 105
+    },
+    {
+      "epoch": 0.06131122413432732,
+      "grad_norm": 0.8961934447288513,
+      "learning_rate": 6.055555555555555e-05,
+      "loss": 1.8706,
+      "step": 110
+    },
+    {
+      "epoch": 0.06409809795861493,
+      "grad_norm": 0.7244030833244324,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 1.7701,
+      "step": 115
+    },
+    {
+      "epoch": 0.06688497178290254,
+      "grad_norm": 0.6804441809654236,
+      "learning_rate": 6.611111111111111e-05,
+      "loss": 1.7833,
+      "step": 120
+    },
+    {
+      "epoch": 0.06967184560719013,
+      "grad_norm": 0.6717159152030945,
+      "learning_rate": 6.88888888888889e-05,
+      "loss": 1.8445,
+      "step": 125
+    },
+    {
+      "epoch": 0.07245871943147773,
+      "grad_norm": 0.6639799475669861,
+      "learning_rate": 7.166666666666667e-05,
+      "loss": 1.7847,
+      "step": 130
+    },
+    {
+      "epoch": 0.07524559325576534,
+      "grad_norm": 0.7095969915390015,
+      "learning_rate": 7.444444444444444e-05,
+      "loss": 1.7281,
+      "step": 135
+    },
+    {
+      "epoch": 0.07803246708005294,
+      "grad_norm": 0.8189035654067993,
+      "learning_rate": 7.722222222222223e-05,
+      "loss": 1.7678,
+      "step": 140
+    },
+    {
+      "epoch": 0.08081934090434055,
+      "grad_norm": 0.6709702610969543,
+      "learning_rate": 8e-05,
+      "loss": 1.8645,
+      "step": 145
+    },
+    {
+      "epoch": 0.08360621472862816,
+      "grad_norm": 0.743190348148346,
+      "learning_rate": 8.277777777777778e-05,
+      "loss": 1.8086,
+      "step": 150
+    },
+    {
+      "epoch": 0.08639308855291576,
+      "grad_norm": 0.669023871421814,
+      "learning_rate": 8.555555555555556e-05,
+      "loss": 1.7844,
+      "step": 155
+    },
+    {
+      "epoch": 0.08917996237720337,
+      "grad_norm": 0.8071898221969604,
+      "learning_rate": 8.833333333333333e-05,
+      "loss": 1.7379,
+      "step": 160
+    },
+    {
+      "epoch": 0.09196683620149097,
+      "grad_norm": 0.7679445743560791,
+      "learning_rate": 9.111111111111112e-05,
+      "loss": 1.706,
+      "step": 165
+    },
+    {
+      "epoch": 0.09475371002577858,
+      "grad_norm": 0.7896930575370789,
+      "learning_rate": 9.388888888888889e-05,
+      "loss": 1.7752,
+      "step": 170
+    },
+    {
+      "epoch": 0.09754058385006618,
+      "grad_norm": 0.7258396744728088,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 1.7635,
+      "step": 175
+    },
+    {
+      "epoch": 0.10032745767435379,
+      "grad_norm": 0.8085169196128845,
+      "learning_rate": 9.944444444444446e-05,
+      "loss": 1.7449,
+      "step": 180
+    },
+    {
+      "epoch": 0.1031143314986414,
+      "grad_norm": 0.7673636674880981,
+      "learning_rate": 9.999848639521432e-05,
+      "loss": 1.7286,
+      "step": 185
+    },
+    {
+      "epoch": 0.105901205322929,
+      "grad_norm": 0.7478857040405273,
+      "learning_rate": 9.999233753283091e-05,
+      "loss": 1.7203,
+      "step": 190
+    },
+    {
+      "epoch": 0.1086880791472166,
+      "grad_norm": 0.8994764685630798,
+      "learning_rate": 9.998145939378577e-05,
+      "loss": 1.6964,
+      "step": 195
+    },
+    {
+      "epoch": 0.11147495297150421,
+      "grad_norm": 0.7851970791816711,
+      "learning_rate": 9.996585300715116e-05,
+      "loss": 1.7513,
+      "step": 200
+    },
+    {
+      "epoch": 0.11426182679579182,
+      "grad_norm": 0.7743813395500183,
+      "learning_rate": 9.994551984929175e-05,
+      "loss": 1.7099,
+      "step": 205
+    },
+    {
+      "epoch": 0.11704870062007942,
+      "grad_norm": 0.7080249786376953,
+      "learning_rate": 9.992046184372492e-05,
+      "loss": 1.7431,
+      "step": 210
+    },
+    {
+      "epoch": 0.11983557444436703,
+      "grad_norm": 0.744627058506012,
+      "learning_rate": 9.989068136093873e-05,
+      "loss": 1.7159,
+      "step": 215
+    },
+    {
+      "epoch": 0.12262244826865464,
+      "grad_norm": 0.7715389132499695,
+      "learning_rate": 9.985618121816779e-05,
+      "loss": 1.7696,
+      "step": 220
+    },
+    {
+      "epoch": 0.12540932209294225,
+      "grad_norm": 0.7663665413856506,
+      "learning_rate": 9.981696467912664e-05,
+      "loss": 1.7205,
+      "step": 225
+    },
+    {
+      "epoch": 0.12819619591722986,
+      "grad_norm": 0.7923425436019897,
+      "learning_rate": 9.97730354537011e-05,
+      "loss": 1.7136,
+      "step": 230
+    },
+    {
+      "epoch": 0.13098306974151747,
+      "grad_norm": 0.7929289937019348,
+      "learning_rate": 9.972439769759722e-05,
+      "loss": 1.6462,
+      "step": 235
+    },
+    {
+      "epoch": 0.13376994356580507,
+      "grad_norm": 0.845177948474884,
+      "learning_rate": 9.967105601194823e-05,
+      "loss": 1.8031,
+      "step": 240
+    },
+    {
+      "epoch": 0.13655681739009268,
+      "grad_norm": 0.7540026307106018,
+      "learning_rate": 9.961301544287922e-05,
+      "loss": 1.6899,
+      "step": 245
+    },
+    {
+      "epoch": 0.13934369121438026,
+      "grad_norm": 0.8806189894676208,
+      "learning_rate": 9.955028148102979e-05,
+      "loss": 1.6526,
+      "step": 250
+    },
+    {
+      "epoch": 0.14213056503866786,
+      "grad_norm": 0.8206574320793152,
+      "learning_rate": 9.948286006103466e-05,
+      "loss": 1.8233,
+      "step": 255
+    },
+    {
+      "epoch": 0.14491743886295547,
+      "grad_norm": 0.8984567523002625,
+      "learning_rate": 9.941075756096226e-05,
+      "loss": 1.7252,
+      "step": 260
+    },
+    {
+      "epoch": 0.14770431268724307,
+      "grad_norm": 0.7411919832229614,
+      "learning_rate": 9.933398080171123e-05,
+      "loss": 1.7339,
+      "step": 265
+    },
+    {
+      "epoch": 0.15049118651153068,
+      "grad_norm": 0.8030174970626831,
+      "learning_rate": 9.925253704636543e-05,
+      "loss": 1.6934,
+      "step": 270
+    },
+    {
+      "epoch": 0.15327806033581828,
+      "grad_norm": 0.7879084944725037,
+      "learning_rate": 9.916643399950656e-05,
+      "loss": 1.7197,
+      "step": 275
+    },
+    {
+      "epoch": 0.1560649341601059,
+      "grad_norm": 0.8534114956855774,
+      "learning_rate": 9.907567980648549e-05,
+      "loss": 1.6941,
+      "step": 280
+    },
+    {
+      "epoch": 0.1588518079843935,
+      "grad_norm": 0.74381023645401,
+      "learning_rate": 9.898028305265169e-05,
+      "loss": 1.7919,
+      "step": 285
+    },
+    {
+      "epoch": 0.1616386818086811,
+      "grad_norm": 0.8476956486701965,
+      "learning_rate": 9.888025276254096e-05,
+      "loss": 1.7417,
+      "step": 290
+    },
+    {
+      "epoch": 0.1644255556329687,
+      "grad_norm": 0.8212200403213501,
+      "learning_rate": 9.877559839902184e-05,
+      "loss": 1.7452,
+      "step": 295
+    },
+    {
+      "epoch": 0.1672124294572563,
+      "grad_norm": 0.8340197801589966,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 1.6687,
+      "step": 300
+    },
+    {
+      "epoch": 0.16999930328154392,
+      "grad_norm": 0.858363151550293,
+      "learning_rate": 9.855245748948326e-05,
+      "loss": 1.7669,
+      "step": 305
+    },
+    {
+      "epoch": 0.17278617710583152,
+      "grad_norm": 0.8392812013626099,
+      "learning_rate": 9.843399205260068e-05,
+      "loss": 1.736,
+      "step": 310
+    },
+    {
+      "epoch": 0.17557305093011913,
+      "grad_norm": 0.8345137238502502,
+      "learning_rate": 9.831094475858652e-05,
+      "loss": 1.7264,
+      "step": 315
+    },
+    {
+      "epoch": 0.17835992475440673,
+      "grad_norm": 0.8243482708930969,
+      "learning_rate": 9.818332724771857e-05,
+      "loss": 1.7748,
+      "step": 320
+    },
+    {
+      "epoch": 0.18114679857869434,
+      "grad_norm": 0.8255311846733093,
+      "learning_rate": 9.805115159261726e-05,
+      "loss": 1.6798,
+      "step": 325
+    },
+    {
+      "epoch": 0.18393367240298195,
+      "grad_norm": 0.8170781135559082,
+      "learning_rate": 9.791443029710361e-05,
+      "loss": 1.6542,
+      "step": 330
+    },
+    {
+      "epoch": 0.18672054622726955,
+      "grad_norm": 0.8476420044898987,
+      "learning_rate": 9.777317629501636e-05,
+      "loss": 1.6875,
+      "step": 335
+    },
+    {
+      "epoch": 0.18950742005155716,
+      "grad_norm": 0.7547033429145813,
+      "learning_rate": 9.762740294898846e-05,
+      "loss": 1.646,
+      "step": 340
+    },
+    {
+      "epoch": 0.19229429387584476,
+      "grad_norm": 0.826404869556427,
+      "learning_rate": 9.747712404918286e-05,
+      "loss": 1.6187,
+      "step": 345
+    },
+    {
+      "epoch": 0.19508116770013237,
+      "grad_norm": 0.964885950088501,
+      "learning_rate": 9.732235381198813e-05,
+      "loss": 1.7507,
+      "step": 350
+    },
+    {
+      "epoch": 0.19786804152441997,
+      "grad_norm": 0.8207951188087463,
+      "learning_rate": 9.716310687867342e-05,
+      "loss": 1.5745,
+      "step": 355
+    },
+    {
+      "epoch": 0.20065491534870758,
+      "grad_norm": 0.8143700361251831,
+      "learning_rate": 9.699939831400351e-05,
+      "loss": 1.7754,
+      "step": 360
+    },
+    {
+      "epoch": 0.20344178917299519,
+      "grad_norm": 0.811844527721405,
+      "learning_rate": 9.683124360481364e-05,
+      "loss": 1.6993,
+      "step": 365
+    },
+    {
+      "epoch": 0.2062286629972828,
+      "grad_norm": 0.8975111842155457,
+      "learning_rate": 9.665865865854445e-05,
+      "loss": 1.6901,
+      "step": 370
+    },
+    {
+      "epoch": 0.2090155368215704,
+      "grad_norm": 0.7903837561607361,
+      "learning_rate": 9.648165980173712e-05,
+      "loss": 1.6895,
+      "step": 375
+    },
+    {
+      "epoch": 0.211802410645858,
+      "grad_norm": 0.8718327879905701,
+      "learning_rate": 9.630026377848892e-05,
+      "loss": 1.6725,
+      "step": 380
+    },
+    {
+      "epoch": 0.2145892844701456,
+      "grad_norm": 0.8131148219108582,
+      "learning_rate": 9.611448774886924e-05,
+      "loss": 1.6874,
+      "step": 385
+    },
+    {
+      "epoch": 0.2173761582944332,
+      "grad_norm": 0.8331175446510315,
+      "learning_rate": 9.592434928729616e-05,
+      "loss": 1.7542,
+      "step": 390
+    },
+    {
+      "epoch": 0.22016303211872082,
+      "grad_norm": 0.792988121509552,
+      "learning_rate": 9.572986638087396e-05,
+      "loss": 1.7311,
+      "step": 395
+    },
+    {
+      "epoch": 0.22294990594300843,
+      "grad_norm": 0.7799636721611023,
+      "learning_rate": 9.553105742769154e-05,
+      "loss": 1.6567,
+      "step": 400
+    },
+    {
+      "epoch": 0.22573677976729603,
+      "grad_norm": 0.7864108085632324,
+      "learning_rate": 9.532794123508197e-05,
+      "loss": 1.5611,
+      "step": 405
+    },
+    {
+      "epoch": 0.22852365359158364,
+      "grad_norm": 0.8886444568634033,
+      "learning_rate": 9.512053701784329e-05,
+      "loss": 1.6995,
+      "step": 410
+    },
+    {
+      "epoch": 0.23131052741587124,
+      "grad_norm": 0.7999454736709595,
+      "learning_rate": 9.490886439642081e-05,
+      "loss": 1.6898,
+      "step": 415
+    },
+    {
+      "epoch": 0.23409740124015885,
+      "grad_norm": 0.7729182243347168,
+      "learning_rate": 9.469294339505098e-05,
+      "loss": 1.7204,
+      "step": 420
+    },
+    {
+      "epoch": 0.23688427506444645,
+      "grad_norm": 0.8300912380218506,
+      "learning_rate": 9.447279443986716e-05,
+      "loss": 1.6668,
+      "step": 425
+    },
+    {
+      "epoch": 0.23967114888873406,
+      "grad_norm": 0.840481698513031,
+      "learning_rate": 9.424843835696724e-05,
+      "loss": 1.704,
+      "step": 430
+    },
+    {
+      "epoch": 0.24245802271302166,
+      "grad_norm": 0.9396219253540039,
+      "learning_rate": 9.401989637044355e-05,
+      "loss": 1.6713,
+      "step": 435
+    },
+    {
+      "epoch": 0.24524489653730927,
+      "grad_norm": 0.8775554299354553,
+      "learning_rate": 9.3787190100375e-05,
+      "loss": 1.6883,
+      "step": 440
+    },
+    {
+      "epoch": 0.24803177036159688,
+      "grad_norm": 0.8623490333557129,
+      "learning_rate": 9.355034156078188e-05,
+      "loss": 1.6783,
+      "step": 445
+    },
+    {
+      "epoch": 0.2508186441858845,
+      "grad_norm": 0.806533694267273,
+      "learning_rate": 9.330937315754329e-05,
+      "loss": 1.6853,
+      "step": 450
+    },
+    {
+      "epoch": 0.2536055180101721,
+      "grad_norm": 0.8504590392112732,
+      "learning_rate": 9.306430768627753e-05,
+      "loss": 1.6594,
+      "step": 455
+    },
+    {
+      "epoch": 0.2563923918344597,
+      "grad_norm": 0.9382562637329102,
+      "learning_rate": 9.281516833018571e-05,
+      "loss": 1.6827,
+      "step": 460
+    },
+    {
+      "epoch": 0.2591792656587473,
+      "grad_norm": 0.821978747844696,
+      "learning_rate": 9.256197865785854e-05,
+      "loss": 1.752,
+      "step": 465
+    },
+    {
+      "epoch": 0.26196613948303493,
+      "grad_norm": 0.8061692714691162,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": 1.6773,
+      "step": 470
+    },
+    {
+      "epoch": 0.26475301330732254,
+      "grad_norm": 0.8759399652481079,
+      "learning_rate": 9.204354455239539e-05,
+      "loss": 1.7003,
+      "step": 475
+    },
+    {
+      "epoch": 0.26753988713161014,
+      "grad_norm": 0.8721809387207031,
+      "learning_rate": 9.177834916314165e-05,
+      "loss": 1.6898,
+      "step": 480
+    },
+    {
+      "epoch": 0.27032676095589775,
+      "grad_norm": 0.7904046773910522,
+      "learning_rate": 9.150920154077754e-05,
+      "loss": 1.6636,
+      "step": 485
+    },
+    {
+      "epoch": 0.27311363478018535,
+      "grad_norm": 0.8828450441360474,
+      "learning_rate": 9.123612714667634e-05,
+      "loss": 1.6945,
+      "step": 490
+    },
+    {
+      "epoch": 0.2759005086044729,
+      "grad_norm": 0.7389103174209595,
+      "learning_rate": 9.095915181368412e-05,
+      "loss": 1.7459,
+      "step": 495
+    },
+    {
+      "epoch": 0.2786873824287605,
+      "grad_norm": 0.975307285785675,
+      "learning_rate": 9.067830174367586e-05,
+      "loss": 1.7296,
+      "step": 500
+    },
+    {
+      "epoch": 0.2814742562530481,
+      "grad_norm": 0.812856137752533,
+      "learning_rate": 9.039360350507679e-05,
+      "loss": 1.696,
+      "step": 505
+    },
+    {
+      "epoch": 0.2842611300773357,
+      "grad_norm": 0.8609644770622253,
+      "learning_rate": 9.010508403034898e-05,
+      "loss": 1.6464,
+      "step": 510
+    },
+    {
+      "epoch": 0.2870480039016233,
+      "grad_norm": 0.8457721471786499,
+      "learning_rate": 8.98127706134436e-05,
+      "loss": 1.682,
+      "step": 515
+    },
+    {
+      "epoch": 0.28983487772591093,
+      "grad_norm": 0.8576518297195435,
+      "learning_rate": 8.951669090721881e-05,
+      "loss": 1.6784,
+      "step": 520
+    },
+    {
+      "epoch": 0.29262175155019854,
+      "grad_norm": 0.892368495464325,
+      "learning_rate": 8.921687292082393e-05,
+      "loss": 1.6283,
+      "step": 525
+    },
+    {
+      "epoch": 0.29540862537448614,
+      "grad_norm": 0.7966616749763489,
+      "learning_rate": 8.891334501704962e-05,
+      "loss": 1.6898,
+      "step": 530
+    },
+    {
+      "epoch": 0.29819549919877375,
+      "grad_norm": 0.9272663593292236,
+      "learning_rate": 8.86061359096449e-05,
+      "loss": 1.6205,
+      "step": 535
+    },
+    {
+      "epoch": 0.30098237302306136,
+      "grad_norm": 0.8790031671524048,
+      "learning_rate": 8.829527466060072e-05,
+      "loss": 1.5345,
+      "step": 540
+    },
+    {
+      "epoch": 0.30376924684734896,
+      "grad_norm": 0.8462222814559937,
+      "learning_rate": 8.798079067740077e-05,
+      "loss": 1.7664,
+      "step": 545
+    },
+    {
+      "epoch": 0.30655612067163657,
+      "grad_norm": 0.8935257792472839,
+      "learning_rate": 8.766271371023948e-05,
+      "loss": 1.6742,
+      "step": 550
+    },
+    {
+      "epoch": 0.3093429944959242,
+      "grad_norm": 0.9315011501312256,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 1.6154,
+      "step": 555
+    },
+    {
+      "epoch": 0.3121298683202118,
+      "grad_norm": 0.8667712807655334,
+      "learning_rate": 8.701590152144612e-05,
+      "loss": 1.6356,
+      "step": 560
+    },
+    {
+      "epoch": 0.3149167421444994,
+      "grad_norm": 0.9088530540466309,
+      "learning_rate": 8.668722748826693e-05,
+      "loss": 1.6645,
+      "step": 565
+    },
+    {
+      "epoch": 0.317703615968787,
+      "grad_norm": 0.8751830458641052,
+      "learning_rate": 8.635508284224371e-05,
+      "loss": 1.7629,
+      "step": 570
+    },
+    {
+      "epoch": 0.3204904897930746,
+      "grad_norm": 0.8768523335456848,
+      "learning_rate": 8.601949900427016e-05,
+      "loss": 1.631,
+      "step": 575
+    },
+    {
+      "epoch": 0.3232773636173622,
+      "grad_norm": 0.9074881672859192,
+      "learning_rate": 8.568050772058762e-05,
+      "loss": 1.6924,
+      "step": 580
+    },
+    {
+      "epoch": 0.3260642374416498,
+      "grad_norm": 0.9533477425575256,
+      "learning_rate": 8.533814105978191e-05,
+      "loss": 1.644,
+      "step": 585
+    },
+    {
+      "epoch": 0.3288511112659374,
+      "grad_norm": 0.8163946866989136,
+      "learning_rate": 8.499243140974966e-05,
+      "loss": 1.6587,
+      "step": 590
+    },
+    {
+      "epoch": 0.331637985090225,
+      "grad_norm": 0.8785070180892944,
+      "learning_rate": 8.464341147463431e-05,
+      "loss": 1.6666,
+      "step": 595
+    },
+    {
+      "epoch": 0.3344248589145126,
+      "grad_norm": 0.8283839821815491,
+      "learning_rate": 8.429111427173241e-05,
+      "loss": 1.5772,
+      "step": 600
+    },
+    {
+      "epoch": 0.33721173273880023,
+      "grad_norm": 0.8584945797920227,
+      "learning_rate": 8.393557312837018e-05,
+      "loss": 1.6317,
+      "step": 605
+    },
+    {
+      "epoch": 0.33999860656308784,
+      "grad_norm": 0.880062997341156,
+      "learning_rate": 8.357682167875062e-05,
+      "loss": 1.7025,
+      "step": 610
+    },
+    {
+      "epoch": 0.34278548038737544,
+      "grad_norm": 0.9203423261642456,
+      "learning_rate": 8.321489386077192e-05,
+      "loss": 1.6741,
+      "step": 615
+    },
+    {
+      "epoch": 0.34557235421166305,
+      "grad_norm": 0.917999804019928,
+      "learning_rate": 8.28498239128167e-05,
+      "loss": 1.6954,
+      "step": 620
+    },
+    {
+      "epoch": 0.34835922803595065,
+      "grad_norm": 0.8408088088035583,
+      "learning_rate": 8.248164637051321e-05,
+      "loss": 1.6443,
+      "step": 625
+    },
+    {
+      "epoch": 0.35114610186023826,
+      "grad_norm": 0.908991277217865,
+      "learning_rate": 8.211039606346826e-05,
+      "loss": 1.6907,
+      "step": 630
+    },
+    {
+      "epoch": 0.35393297568452586,
+      "grad_norm": 0.9045994877815247,
+      "learning_rate": 8.173610811197226e-05,
+      "loss": 1.66,
+      "step": 635
+    },
+    {
+      "epoch": 0.35671984950881347,
+      "grad_norm": 0.8032850623130798,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 1.6538,
+      "step": 640
+    },
+    {
+      "epoch": 0.3595067233331011,
+      "grad_norm": 0.9243664741516113,
+      "learning_rate": 8.097856119024545e-05,
+      "loss": 1.7321,
+      "step": 645
+    },
+    {
+      "epoch": 0.3622935971573887,
+      "grad_norm": 0.9106388092041016,
+      "learning_rate": 8.059537388397665e-05,
+      "loss": 1.6566,
+      "step": 650
+    },
+    {
+      "epoch": 0.3650804709816763,
+      "grad_norm": 0.9164809584617615,
+      "learning_rate": 8.020929225440137e-05,
+      "loss": 1.6663,
+      "step": 655
+    },
+    {
+      "epoch": 0.3678673448059639,
+      "grad_norm": 0.9171935319900513,
+      "learning_rate": 7.98203528248536e-05,
+      "loss": 1.6781,
+      "step": 660
+    },
+    {
+      "epoch": 0.3706542186302515,
+      "grad_norm": 0.8433538675308228,
+      "learning_rate": 7.942859238901528e-05,
+      "loss": 1.7255,
+      "step": 665
+    },
+    {
+      "epoch": 0.3734410924545391,
+      "grad_norm": 0.9780874252319336,
+      "learning_rate": 7.903404800743564e-05,
+      "loss": 1.722,
+      "step": 670
+    },
+    {
+      "epoch": 0.3762279662788267,
+      "grad_norm": 0.9980689287185669,
+      "learning_rate": 7.863675700402526e-05,
+      "loss": 1.6403,
+      "step": 675
+    },
+    {
+      "epoch": 0.3790148401031143,
+      "grad_norm": 0.843333899974823,
+      "learning_rate": 7.823675696252524e-05,
+      "loss": 1.7583,
+      "step": 680
+    },
+    {
+      "epoch": 0.3818017139274019,
+      "grad_norm": 0.8417442440986633,
+      "learning_rate": 7.783408572295174e-05,
+      "loss": 1.6938,
+      "step": 685
+    },
+    {
+      "epoch": 0.3845885877516895,
+      "grad_norm": 0.8940498232841492,
+      "learning_rate": 7.742878137801639e-05,
+      "loss": 1.6737,
+      "step": 690
+    },
+    {
+      "epoch": 0.38737546157597713,
+      "grad_norm": 0.8713932633399963,
+      "learning_rate": 7.702088226952258e-05,
+      "loss": 1.6435,
+      "step": 695
+    },
+    {
+      "epoch": 0.39016233540026474,
+      "grad_norm": 0.9215396046638489,
+      "learning_rate": 7.661042698473853e-05,
+      "loss": 1.5994,
+      "step": 700
+    },
+    {
+      "epoch": 0.39294920922455234,
+      "grad_norm": 0.8360981941223145,
+      "learning_rate": 7.619745435274667e-05,
+      "loss": 1.6511,
+      "step": 705
+    },
+    {
+      "epoch": 0.39573608304883995,
+      "grad_norm": 0.9177049398422241,
+      "learning_rate": 7.578200344077073e-05,
+      "loss": 1.6655,
+      "step": 710
+    },
+    {
+      "epoch": 0.39852295687312755,
+      "grad_norm": 0.8501256108283997,
+      "learning_rate": 7.536411355047964e-05,
+      "loss": 1.659,
+      "step": 715
+    },
+    {
+      "epoch": 0.40130983069741516,
+      "grad_norm": 0.8666147589683533,
+      "learning_rate": 7.494382421426984e-05,
+      "loss": 1.7046,
+      "step": 720
+    },
+    {
+      "epoch": 0.40409670452170277,
+      "grad_norm": 0.8096281290054321,
+      "learning_rate": 7.452117519152542e-05,
+      "loss": 1.6108,
+      "step": 725
+    },
+    {
+      "epoch": 0.40688357834599037,
+      "grad_norm": 1.0028629302978516,
+      "learning_rate": 7.409620646485685e-05,
+      "loss": 1.6302,
+      "step": 730
+    },
+    {
+      "epoch": 0.409670452170278,
+      "grad_norm": 0.8731248378753662,
+      "learning_rate": 7.36689582363187e-05,
+      "loss": 1.6784,
+      "step": 735
+    },
+    {
+      "epoch": 0.4124573259945656,
+      "grad_norm": 0.9034931659698486,
+      "learning_rate": 7.323947092360649e-05,
+      "loss": 1.5845,
+      "step": 740
+    },
+    {
+      "epoch": 0.4152441998188532,
+      "grad_norm": 0.9129267334938049,
+      "learning_rate": 7.280778515623314e-05,
+      "loss": 1.7366,
+      "step": 745
+    },
+    {
+      "epoch": 0.4180310736431408,
+      "grad_norm": 0.9088048338890076,
+      "learning_rate": 7.237394177168548e-05,
+      "loss": 1.7065,
+      "step": 750
+    },
+    {
+      "epoch": 0.4208179474674284,
+      "grad_norm": 0.9397730827331543,
+      "learning_rate": 7.193798181156095e-05,
+      "loss": 1.7012,
+      "step": 755
+    },
+    {
+      "epoch": 0.423604821291716,
+      "grad_norm": 0.9324731230735779,
+      "learning_rate": 7.149994651768514e-05,
+      "loss": 1.5474,
+      "step": 760
+    },
+    {
+      "epoch": 0.4263916951160036,
+      "grad_norm": 0.9360097646713257,
+      "learning_rate": 7.10598773282103e-05,
+      "loss": 1.6602,
+      "step": 765
+    },
+    {
+      "epoch": 0.4291785689402912,
+      "grad_norm": 0.9703853130340576,
+      "learning_rate": 7.061781587369519e-05,
+      "loss": 1.7305,
+      "step": 770
+    },
+    {
+      "epoch": 0.4319654427645788,
+      "grad_norm": 0.9043810367584229,
+      "learning_rate": 7.017380397316695e-05,
+      "loss": 1.6131,
+      "step": 775
+    },
+    {
+      "epoch": 0.4347523165888664,
+      "grad_norm": 0.8870768547058105,
+      "learning_rate": 6.972788363016497e-05,
+      "loss": 1.5668,
+      "step": 780
+    },
+    {
+      "epoch": 0.43753919041315403,
+      "grad_norm": 0.9383454918861389,
+      "learning_rate": 6.92800970287674e-05,
+      "loss": 1.6773,
+      "step": 785
+    },
+    {
+      "epoch": 0.44032606423744164,
+      "grad_norm": 0.8532437682151794,
+      "learning_rate": 6.883048652960038e-05,
+      "loss": 1.6602,
+      "step": 790
+    },
+    {
+      "epoch": 0.44311293806172924,
+      "grad_norm": 0.8915623426437378,
+      "learning_rate": 6.837909466583095e-05,
+      "loss": 1.6778,
+      "step": 795
+    },
+    {
+      "epoch": 0.44589981188601685,
+      "grad_norm": 0.840151846408844,
+      "learning_rate": 6.792596413914324e-05,
+      "loss": 1.5566,
+      "step": 800
+    },
+    {
+      "epoch": 0.44868668571030446,
+      "grad_norm": 0.8808228969573975,
+      "learning_rate": 6.747113781569892e-05,
+      "loss": 1.6819,
+      "step": 805
+    },
+    {
+      "epoch": 0.45147355953459206,
+      "grad_norm": 0.9224216938018799,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 1.7057,
+      "step": 810
+    },
+    {
+      "epoch": 0.45426043335887967,
+      "grad_norm": 1.0062270164489746,
+      "learning_rate": 6.655657004122916e-05,
+      "loss": 1.719,
+      "step": 815
+    },
+    {
+      "epoch": 0.4570473071831673,
+      "grad_norm": 0.9544162154197693,
+      "learning_rate": 6.60969151083432e-05,
+      "loss": 1.657,
+      "step": 820
+    },
+    {
+      "epoch": 0.4598341810074549,
+      "grad_norm": 0.8740416169166565,
+      "learning_rate": 6.563573740679496e-05,
+      "loss": 1.645,
+      "step": 825
+    },
+    {
+      "epoch": 0.4626210548317425,
+      "grad_norm": 0.8866944313049316,
+      "learning_rate": 6.517308056400917e-05,
+      "loss": 1.6446,
+      "step": 830
+    },
+    {
+      "epoch": 0.4654079286560301,
+      "grad_norm": 0.9224971532821655,
+      "learning_rate": 6.470898834733731e-05,
+      "loss": 1.6384,
+      "step": 835
+    },
+    {
+      "epoch": 0.4681948024803177,
+      "grad_norm": 0.8925870656967163,
+      "learning_rate": 6.42435046599173e-05,
+      "loss": 1.6455,
+      "step": 840
+    },
+    {
+      "epoch": 0.4709816763046053,
+      "grad_norm": 0.9226738810539246,
+      "learning_rate": 6.377667353652022e-05,
+      "loss": 1.6799,
+      "step": 845
+    },
+    {
+      "epoch": 0.4737685501288929,
+      "grad_norm": 0.9104128479957581,
+      "learning_rate": 6.330853913938466e-05,
+      "loss": 1.6267,
+      "step": 850
+    },
+    {
+      "epoch": 0.4765554239531805,
+      "grad_norm": 0.912969708442688,
+      "learning_rate": 6.283914575403888e-05,
+      "loss": 1.716,
+      "step": 855
+    },
+    {
+      "epoch": 0.4793422977774681,
+      "grad_norm": 0.9142662882804871,
+      "learning_rate": 6.236853778511156e-05,
+      "loss": 1.6619,
+      "step": 860
+    },
+    {
+      "epoch": 0.4821291716017557,
+      "grad_norm": 0.9380782842636108,
+      "learning_rate": 6.189675975213094e-05,
+      "loss": 1.6578,
+      "step": 865
+    },
+    {
+      "epoch": 0.48491604542604333,
+      "grad_norm": 0.9225218296051025,
+      "learning_rate": 6.142385628531342e-05,
+      "loss": 1.6891,
+      "step": 870
+    },
+    {
+      "epoch": 0.48770291925033094,
+      "grad_norm": 0.9732077121734619,
+      "learning_rate": 6.09498721213414e-05,
+      "loss": 1.6008,
+      "step": 875
+    },
+    {
+      "epoch": 0.49048979307461854,
+      "grad_norm": 0.9870405197143555,
+      "learning_rate": 6.047485209913137e-05,
+      "loss": 1.7372,
+      "step": 880
+    },
+    {
+      "epoch": 0.49327666689890615,
+      "grad_norm": 0.8708714246749878,
+      "learning_rate": 5.999884115559192e-05,
+      "loss": 1.6317,
+      "step": 885
+    },
+    {
+      "epoch": 0.49606354072319375,
+      "grad_norm": 0.8490287065505981,
+      "learning_rate": 5.952188432137293e-05,
+      "loss": 1.6514,
+      "step": 890
+    },
+    {
+      "epoch": 0.49885041454748136,
+      "grad_norm": 0.7740074992179871,
+      "learning_rate": 5.90440267166055e-05,
+      "loss": 1.6091,
+      "step": 895
+    },
+    {
+      "epoch": 0.501637288371769,
+      "grad_norm": 0.9218555092811584,
+      "learning_rate": 5.8565313546633684e-05,
+      "loss": 1.674,
+      "step": 900
+    },
+    {
+      "epoch": 0.5044241621960566,
+      "grad_norm": 0.8074113726615906,
+      "learning_rate": 5.8085790097738025e-05,
+      "loss": 1.6567,
+      "step": 905
+    },
+    {
+      "epoch": 0.5072110360203442,
+      "grad_norm": 0.9320290684700012,
+      "learning_rate": 5.7605501732851475e-05,
+      "loss": 1.6925,
+      "step": 910
+    },
+    {
+      "epoch": 0.5099979098446318,
+      "grad_norm": 0.8326326012611389,
+      "learning_rate": 5.712449388726807e-05,
+      "loss": 1.6909,
+      "step": 915
+    },
+    {
+      "epoch": 0.5127847836689194,
+      "grad_norm": 0.9022158980369568,
+      "learning_rate": 5.664281206434472e-05,
+      "loss": 1.6075,
+      "step": 920
+    },
+    {
+      "epoch": 0.515571657493207,
+      "grad_norm": 0.8791519999504089,
+      "learning_rate": 5.616050183119663e-05,
+      "loss": 1.7011,
+      "step": 925
+    },
+    {
+      "epoch": 0.5183585313174947,
+      "grad_norm": 0.876043438911438,
+      "learning_rate": 5.5677608814386616e-05,
+      "loss": 1.5478,
+      "step": 930
+    },
+    {
+      "epoch": 0.5211454051417822,
+      "grad_norm": 0.9437665939331055,
+      "learning_rate": 5.519417869560889e-05,
+      "loss": 1.6518,
+      "step": 935
+    },
+    {
+      "epoch": 0.5239322789660699,
+      "grad_norm": 0.9788090586662292,
+      "learning_rate": 5.471025720736747e-05,
+      "loss": 1.7146,
+      "step": 940
+    },
+    {
+      "epoch": 0.5267191527903574,
+      "grad_norm": 0.861488938331604,
+      "learning_rate": 5.422589012864996e-05,
+      "loss": 1.6805,
+      "step": 945
+    },
+    {
+      "epoch": 0.5295060266146451,
+      "grad_norm": 1.008576512336731,
+      "learning_rate": 5.3741123280596864e-05,
+      "loss": 1.6012,
+      "step": 950
+    },
+    {
+      "epoch": 0.5322929004389326,
+      "grad_norm": 0.9095168113708496,
+      "learning_rate": 5.325600252216685e-05,
+      "loss": 1.6477,
+      "step": 955
+    },
+    {
+      "epoch": 0.5350797742632203,
+      "grad_norm": 0.8760788440704346,
+      "learning_rate": 5.27705737457985e-05,
+      "loss": 1.5747,
+      "step": 960
+    },
+    {
+      "epoch": 0.5378666480875078,
+      "grad_norm": 0.9696391224861145,
+      "learning_rate": 5.228488287306896e-05,
+      "loss": 1.6249,
+      "step": 965
+    },
+    {
+      "epoch": 0.5406535219117955,
+      "grad_norm": 0.8726052641868591,
+      "learning_rate": 5.179897585034963e-05,
+      "loss": 1.6701,
+      "step": 970
+    },
+    {
+      "epoch": 0.543440395736083,
+      "grad_norm": 0.8699939846992493,
+      "learning_rate": 5.1312898644459776e-05,
+      "loss": 1.5395,
+      "step": 975
+    },
+    {
+      "epoch": 0.5462272695603707,
+      "grad_norm": 0.9301031827926636,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": 1.6724,
+      "step": 980
+    },
+    {
+      "epoch": 0.5490141433846583,
+      "grad_norm": 0.8767033815383911,
+      "learning_rate": 5.0340417626592016e-05,
+      "loss": 1.6492,
+      "step": 985
+    },
+    {
+      "epoch": 0.5518010172089458,
+      "grad_norm": 0.9239912629127502,
+      "learning_rate": 4.9854105811348216e-05,
+      "loss": 1.6705,
+      "step": 990
+    },
+    {
+      "epoch": 0.5545878910332335,
+      "grad_norm": 1.0233875513076782,
+      "learning_rate": 4.936780779769913e-05,
+      "loss": 1.6758,
+      "step": 995
+    },
+    {
+      "epoch": 0.557374764857521,
+      "grad_norm": 0.9696400165557861,
+      "learning_rate": 4.888156958945174e-05,
+      "loss": 1.6276,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5601616386818087,
+      "grad_norm": 0.9741013646125793,
+      "learning_rate": 4.839543718475543e-05,
+      "loss": 1.6241,
+      "step": 1005
+    },
+    {
+      "epoch": 0.5629485125060962,
+      "grad_norm": 0.9259172081947327,
+      "learning_rate": 4.790945657175061e-05,
+      "loss": 1.6596,
+      "step": 1010
+    },
+    {
+      "epoch": 0.5657353863303839,
+      "grad_norm": 0.9725984930992126,
+      "learning_rate": 4.742367372421811e-05,
+      "loss": 1.6663,
+      "step": 1015
+    },
+    {
+      "epoch": 0.5685222601546714,
+      "grad_norm": 1.0007803440093994,
+      "learning_rate": 4.69381345972302e-05,
+      "loss": 1.6159,
+      "step": 1020
+    },
+    {
+      "epoch": 0.5713091339789591,
+      "grad_norm": 0.9005650877952576,
+      "learning_rate": 4.6452885122803205e-05,
+      "loss": 1.5989,
+      "step": 1025
+    },
+    {
+      "epoch": 0.5740960078032467,
+      "grad_norm": 0.8858962655067444,
+      "learning_rate": 4.5967971205552194e-05,
+      "loss": 1.6609,
+      "step": 1030
+    },
+    {
+      "epoch": 0.5768828816275343,
+      "grad_norm": 0.945851743221283,
+      "learning_rate": 4.548343871834864e-05,
+      "loss": 1.6605,
+      "step": 1035
+    },
+    {
+      "epoch": 0.5796697554518219,
+      "grad_norm": 0.9151830077171326,
+      "learning_rate": 4.499933349798067e-05,
+      "loss": 1.678,
+      "step": 1040
+    },
+    {
+      "epoch": 0.5824566292761095,
+      "grad_norm": 0.9208435416221619,
+      "learning_rate": 4.451570134081694e-05,
+      "loss": 1.7427,
+      "step": 1045
+    },
+    {
+      "epoch": 0.5852435031003971,
+      "grad_norm": 0.9141213893890381,
+      "learning_rate": 4.403258799847433e-05,
+      "loss": 1.62,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5880303769246847,
+      "grad_norm": 1.0249472856521606,
+      "learning_rate": 4.3550039173489845e-05,
+      "loss": 1.634,
+      "step": 1055
+    },
+    {
+      "epoch": 0.5908172507489723,
+      "grad_norm": 0.8938164114952087,
+      "learning_rate": 4.306810051499708e-05,
+      "loss": 1.562,
+      "step": 1060
+    },
+    {
+      "epoch": 0.59360412457326,
+      "grad_norm": 1.0070486068725586,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": 1.6713,
+      "step": 1065
+    },
+    {
+      "epoch": 0.5963909983975475,
+      "grad_norm": 0.8382595777511597,
+      "learning_rate": 4.210623600109946e-05,
+      "loss": 1.5343,
+      "step": 1070
+    },
+    {
+      "epoch": 0.5991778722218352,
+      "grad_norm": 0.9747705459594727,
+      "learning_rate": 4.162640113810706e-05,
+      "loss": 1.67,
+      "step": 1075
+    },
+    {
+      "epoch": 0.6019647460461227,
+      "grad_norm": 0.9397943019866943,
+      "learning_rate": 4.114735841782347e-05,
+      "loss": 1.705,
+      "step": 1080
+    },
+    {
+      "epoch": 0.6047516198704104,
+      "grad_norm": 0.9868884086608887,
+      "learning_rate": 4.06691531577047e-05,
+      "loss": 1.6343,
+      "step": 1085
+    },
+    {
+      "epoch": 0.6075384936946979,
+      "grad_norm": 0.9283191561698914,
+      "learning_rate": 4.019183059598296e-05,
+      "loss": 1.6226,
+      "step": 1090
+    },
+    {
+      "epoch": 0.6103253675189856,
+      "grad_norm": 0.8564023971557617,
+      "learning_rate": 3.971543588738724e-05,
+      "loss": 1.6206,
+      "step": 1095
+    },
+    {
+      "epoch": 0.6131122413432731,
+      "grad_norm": 0.9272263050079346,
+      "learning_rate": 3.924001409887158e-05,
+      "loss": 1.5952,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6158991151675608,
+      "grad_norm": 0.9421799778938293,
+      "learning_rate": 3.87656102053517e-05,
+      "loss": 1.6356,
+      "step": 1105
+    },
+    {
+      "epoch": 0.6186859889918483,
+      "grad_norm": 0.918296217918396,
+      "learning_rate": 3.8292269085450474e-05,
+      "loss": 1.6143,
+      "step": 1110
+    },
+    {
+      "epoch": 0.621472862816136,
+      "grad_norm": 0.9440540671348572,
+      "learning_rate": 3.782003551725236e-05,
+      "loss": 1.6928,
+      "step": 1115
+    },
+    {
+      "epoch": 0.6242597366404236,
+      "grad_norm": 0.8987861275672913,
+      "learning_rate": 3.734895417406734e-05,
+      "loss": 1.6571,
+      "step": 1120
+    },
+    {
+      "epoch": 0.6270466104647112,
+      "grad_norm": 0.9039310216903687,
+      "learning_rate": 3.687906962020491e-05,
+      "loss": 1.6862,
+      "step": 1125
+    },
+    {
+      "epoch": 0.6298334842889988,
+      "grad_norm": 0.9794312119483948,
+      "learning_rate": 3.641042630675829e-05,
+      "loss": 1.6843,
+      "step": 1130
+    },
+    {
+      "epoch": 0.6326203581132864,
+      "grad_norm": 0.9151976704597473,
+      "learning_rate": 3.594306856739924e-05,
+      "loss": 1.602,
+      "step": 1135
+    },
+    {
+      "epoch": 0.635407231937574,
+      "grad_norm": 0.9147221446037292,
+      "learning_rate": 3.547704061418424e-05,
+      "loss": 1.6073,
+      "step": 1140
+    },
+    {
+      "epoch": 0.6381941057618616,
+      "grad_norm": 0.9955829977989197,
+      "learning_rate": 3.501238653337194e-05,
+      "loss": 1.6535,
+      "step": 1145
+    },
+    {
+      "epoch": 0.6409809795861492,
+      "grad_norm": 1.0493595600128174,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.6979,
+      "step": 1150
+    },
+    {
+      "epoch": 0.6437678534104369,
+      "grad_norm": 0.9534896016120911,
+      "learning_rate": 3.408737567998993e-05,
+      "loss": 1.5449,
+      "step": 1155
+    },
+    {
+      "epoch": 0.6465547272347244,
+      "grad_norm": 0.9850942492485046,
+      "learning_rate": 3.362710641347524e-05,
+      "loss": 1.6989,
+      "step": 1160
+    },
+    {
+      "epoch": 0.6493416010590121,
+      "grad_norm": 0.9439795017242432,
+      "learning_rate": 3.316838602319532e-05,
+      "loss": 1.6826,
+      "step": 1165
+    },
+    {
+      "epoch": 0.6521284748832996,
+      "grad_norm": 1.0012317895889282,
+      "learning_rate": 3.271125790411309e-05,
+      "loss": 1.524,
+      "step": 1170
+    },
+    {
+      "epoch": 0.6549153487075873,
+      "grad_norm": 0.9746808409690857,
+      "learning_rate": 3.225576530056264e-05,
+      "loss": 1.6796,
+      "step": 1175
+    },
+    {
+      "epoch": 0.6577022225318748,
+      "grad_norm": 0.8482115864753723,
+      "learning_rate": 3.180195130215824e-05,
+      "loss": 1.6443,
+      "step": 1180
+    },
+    {
+      "epoch": 0.6604890963561625,
+      "grad_norm": 1.0496842861175537,
+      "learning_rate": 3.1349858839717986e-05,
+      "loss": 1.586,
+      "step": 1185
+    },
+    {
+      "epoch": 0.66327597018045,
+      "grad_norm": 0.8761202692985535,
+      "learning_rate": 3.089953068120271e-05,
+      "loss": 1.5516,
+      "step": 1190
+    },
+    {
+      "epoch": 0.6660628440047377,
+      "grad_norm": 1.058709740638733,
+      "learning_rate": 3.0451009427669986e-05,
+      "loss": 1.611,
+      "step": 1195
+    },
+    {
+      "epoch": 0.6688497178290252,
+      "grad_norm": 0.9337294101715088,
+      "learning_rate": 3.000433750924414e-05,
+      "loss": 1.6324,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6716365916533129,
+      "grad_norm": 0.9224420785903931,
+      "learning_rate": 2.9559557181102315e-05,
+      "loss": 1.6494,
+      "step": 1205
+    },
+    {
+      "epoch": 0.6744234654776005,
+      "grad_norm": 1.1299585103988647,
+      "learning_rate": 2.911671051947722e-05,
+      "loss": 1.5891,
+      "step": 1210
+    },
+    {
+      "epoch": 0.6772103393018881,
+      "grad_norm": 0.9998091459274292,
+      "learning_rate": 2.867583941767657e-05,
+      "loss": 1.5622,
+      "step": 1215
+    },
+    {
+      "epoch": 0.6799972131261757,
+      "grad_norm": 0.9196699261665344,
+      "learning_rate": 2.823698558212009e-05,
+      "loss": 1.6298,
+      "step": 1220
+    },
+    {
+      "epoch": 0.6827840869504633,
+      "grad_norm": 0.9296634793281555,
+      "learning_rate": 2.7800190528394122e-05,
+      "loss": 1.6035,
+      "step": 1225
+    },
+    {
+      "epoch": 0.6855709607747509,
+      "grad_norm": 0.8991268873214722,
+      "learning_rate": 2.736549557732405e-05,
+      "loss": 1.5498,
+      "step": 1230
+    },
+    {
+      "epoch": 0.6883578345990385,
+      "grad_norm": 0.9545588493347168,
+      "learning_rate": 2.693294185106562e-05,
+      "loss": 1.7968,
+      "step": 1235
+    },
+    {
+      "epoch": 0.6911447084233261,
+      "grad_norm": 0.9947872757911682,
+      "learning_rate": 2.650257026921455e-05,
+      "loss": 1.673,
+      "step": 1240
+    },
+    {
+      "epoch": 0.6939315822476138,
+      "grad_norm": 1.013684630393982,
+      "learning_rate": 2.607442154493568e-05,
+      "loss": 1.6995,
+      "step": 1245
+    },
+    {
+      "epoch": 0.6967184560719013,
+      "grad_norm": 0.9432601928710938,
+      "learning_rate": 2.5648536181111438e-05,
+      "loss": 1.6238,
+      "step": 1250
+    },
+    {
+      "epoch": 0.699505329896189,
+      "grad_norm": 0.9840952157974243,
+      "learning_rate": 2.5224954466510274e-05,
+      "loss": 1.6116,
+      "step": 1255
+    },
+    {
+      "epoch": 0.7022922037204765,
+      "grad_norm": 0.9281061291694641,
+      "learning_rate": 2.480371647197538e-05,
+      "loss": 1.6705,
+      "step": 1260
+    },
+    {
+      "epoch": 0.7050790775447642,
+      "grad_norm": 0.9922870397567749,
+      "learning_rate": 2.438486204663391e-05,
+      "loss": 1.6893,
+      "step": 1265
+    },
+    {
+      "epoch": 0.7078659513690517,
+      "grad_norm": 0.9433642029762268,
+      "learning_rate": 2.3968430814127385e-05,
+      "loss": 1.674,
+      "step": 1270
+    },
+    {
+      "epoch": 0.7106528251933394,
+      "grad_norm": 0.9409830570220947,
+      "learning_rate": 2.3554462168863085e-05,
+      "loss": 1.6519,
+      "step": 1275
+    },
+    {
+      "epoch": 0.7134396990176269,
+      "grad_norm": 0.9217763543128967,
+      "learning_rate": 2.314299527228759e-05,
+      "loss": 1.6384,
+      "step": 1280
+    },
+    {
+      "epoch": 0.7162265728419146,
+      "grad_norm": 0.8798460364341736,
+      "learning_rate": 2.2734069049181882e-05,
+      "loss": 1.6243,
+      "step": 1285
+    },
+    {
+      "epoch": 0.7190134466662021,
+      "grad_norm": 0.9369103908538818,
+      "learning_rate": 2.2327722183979212e-05,
+      "loss": 1.6331,
+      "step": 1290
+    },
+    {
+      "epoch": 0.7218003204904898,
+      "grad_norm": 0.9402239918708801,
+      "learning_rate": 2.1923993117105462e-05,
+      "loss": 1.6124,
+      "step": 1295
+    },
+    {
+      "epoch": 0.7245871943147774,
+      "grad_norm": 1.0770180225372314,
+      "learning_rate": 2.1522920041342704e-05,
+      "loss": 1.6276,
+      "step": 1300
+    },
+    {
+      "epoch": 0.727374068139065,
+      "grad_norm": 0.9942741990089417,
+      "learning_rate": 2.1124540898216248e-05,
+      "loss": 1.6543,
+      "step": 1305
+    },
+    {
+      "epoch": 0.7301609419633526,
+      "grad_norm": 0.9097809195518494,
+      "learning_rate": 2.0728893374405166e-05,
+      "loss": 1.5341,
+      "step": 1310
+    },
+    {
+      "epoch": 0.7329478157876402,
+      "grad_norm": 0.9943116307258606,
+      "learning_rate": 2.033601489817738e-05,
+      "loss": 1.7465,
+      "step": 1315
+    },
+    {
+      "epoch": 0.7357346896119278,
+      "grad_norm": 0.9960694313049316,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 1.6835,
+      "step": 1320
+    },
+    {
+      "epoch": 0.7385215634362154,
+      "grad_norm": 0.9358818531036377,
+      "learning_rate": 1.9558713488267238e-05,
+      "loss": 1.6585,
+      "step": 1325
+    },
+    {
+      "epoch": 0.741308437260503,
+      "grad_norm": 0.9540205597877502,
+      "learning_rate": 1.917436408732208e-05,
+      "loss": 1.6298,
+      "step": 1330
+    },
+    {
+      "epoch": 0.7440953110847907,
+      "grad_norm": 1.0423612594604492,
+      "learning_rate": 1.8792930792478357e-05,
+      "loss": 1.6291,
+      "step": 1335
+    },
+    {
+      "epoch": 0.7468821849090782,
+      "grad_norm": 1.0178053379058838,
+      "learning_rate": 1.8414449687337464e-05,
+      "loss": 1.5844,
+      "step": 1340
+    },
+    {
+      "epoch": 0.7496690587333659,
+      "grad_norm": 0.9405874013900757,
+      "learning_rate": 1.8038956576223504e-05,
+      "loss": 1.5531,
+      "step": 1345
+    },
+    {
+      "epoch": 0.7524559325576534,
+      "grad_norm": 0.9561493396759033,
+      "learning_rate": 1.766648698079635e-05,
+      "loss": 1.6504,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7552428063819411,
+      "grad_norm": 0.9773407578468323,
+      "learning_rate": 1.7297076136691072e-05,
+      "loss": 1.7289,
+      "step": 1355
+    },
+    {
+      "epoch": 0.7580296802062286,
+      "grad_norm": 1.024316430091858,
+      "learning_rate": 1.6930758990184875e-05,
+      "loss": 1.6495,
+      "step": 1360
+    },
+    {
+      "epoch": 0.7608165540305163,
+      "grad_norm": 1.1461398601531982,
+      "learning_rate": 1.6567570194891024e-05,
+      "loss": 1.63,
+      "step": 1365
+    },
+    {
+      "epoch": 0.7636034278548038,
+      "grad_norm": 1.1386655569076538,
+      "learning_rate": 1.620754410848069e-05,
+      "loss": 1.647,
+      "step": 1370
+    },
+    {
+      "epoch": 0.7663903016790915,
+      "grad_norm": 0.9157811999320984,
+      "learning_rate": 1.5850714789432663e-05,
+      "loss": 1.659,
+      "step": 1375
+    },
+    {
+      "epoch": 0.769177175503379,
+      "grad_norm": 1.0108404159545898,
+      "learning_rate": 1.549711599381145e-05,
+      "loss": 1.6671,
+      "step": 1380
+    },
+    {
+      "epoch": 0.7719640493276667,
+      "grad_norm": 0.8621100783348083,
+      "learning_rate": 1.5146781172073959e-05,
+      "loss": 1.6478,
+      "step": 1385
+    },
+    {
+      "epoch": 0.7747509231519543,
+      "grad_norm": 0.957285463809967,
+      "learning_rate": 1.479974346590503e-05,
+      "loss": 1.6313,
+      "step": 1390
+    },
+    {
+      "epoch": 0.7775377969762419,
+      "grad_norm": 0.9681037068367004,
+      "learning_rate": 1.4456035705082349e-05,
+      "loss": 1.5881,
+      "step": 1395
+    },
+    {
+      "epoch": 0.7803246708005295,
+      "grad_norm": 0.9414888620376587,
+      "learning_rate": 1.4115690404370551e-05,
+      "loss": 1.6011,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7831115446248171,
+      "grad_norm": 0.9640589952468872,
+      "learning_rate": 1.3778739760445552e-05,
+      "loss": 1.623,
+      "step": 1405
+    },
+    {
+      "epoch": 0.7858984184491047,
+      "grad_norm": 0.9019273519515991,
+      "learning_rate": 1.344521564884858e-05,
+      "loss": 1.6779,
+      "step": 1410
+    },
+    {
+      "epoch": 0.7886852922733923,
+      "grad_norm": 0.9059531688690186,
+      "learning_rate": 1.3115149620970795e-05,
+      "loss": 1.6783,
+      "step": 1415
+    },
+    {
+      "epoch": 0.7914721660976799,
+      "grad_norm": 0.9945409297943115,
+      "learning_rate": 1.2788572901068552e-05,
+      "loss": 1.629,
+      "step": 1420
+    },
+    {
+      "epoch": 0.7942590399219676,
+      "grad_norm": 1.0185166597366333,
+      "learning_rate": 1.2465516383309551e-05,
+      "loss": 1.6547,
+      "step": 1425
+    },
+    {
+      "epoch": 0.7970459137462551,
+      "grad_norm": 1.0051592588424683,
+      "learning_rate": 1.2146010628850268e-05,
+      "loss": 1.7016,
+      "step": 1430
+    },
+    {
+      "epoch": 0.7998327875705428,
+      "grad_norm": 0.9881749749183655,
+      "learning_rate": 1.183008586294485e-05,
+      "loss": 1.5857,
+      "step": 1435
+    },
+    {
+      "epoch": 0.8026196613948303,
+      "grad_norm": 0.9611209630966187,
+      "learning_rate": 1.151777197208585e-05,
+      "loss": 1.6027,
+      "step": 1440
+    },
+    {
+      "epoch": 0.805406535219118,
+      "grad_norm": 1.0034438371658325,
+      "learning_rate": 1.1209098501176896e-05,
+      "loss": 1.6083,
+      "step": 1445
+    },
+    {
+      "epoch": 0.8081934090434055,
+      "grad_norm": 0.9777964949607849,
+      "learning_rate": 1.0904094650737795e-05,
+      "loss": 1.6016,
+      "step": 1450
+    },
+    {
+      "epoch": 0.8109802828676932,
+      "grad_norm": 1.0084513425827026,
+      "learning_rate": 1.0602789274142133e-05,
+      "loss": 1.6998,
+      "step": 1455
+    },
+    {
+      "epoch": 0.8137671566919807,
+      "grad_norm": 0.9777223467826843,
+      "learning_rate": 1.0305210874887766e-05,
+      "loss": 1.5668,
+      "step": 1460
+    },
+    {
+      "epoch": 0.8165540305162684,
+      "grad_norm": 0.9857009649276733,
+      "learning_rate": 1.0011387603900385e-05,
+      "loss": 1.5977,
+      "step": 1465
+    },
+    {
+      "epoch": 0.819340904340556,
+      "grad_norm": 1.0366628170013428,
+      "learning_rate": 9.7213472568704e-06,
+      "loss": 1.6536,
+      "step": 1470
+    },
+    {
+      "epoch": 0.8221277781648436,
+      "grad_norm": 0.9983012080192566,
+      "learning_rate": 9.435117271623566e-06,
+      "loss": 1.4905,
+      "step": 1475
+    },
+    {
+      "epoch": 0.8249146519891312,
+      "grad_norm": 1.042453646659851,
+      "learning_rate": 9.152724725525202e-06,
+      "loss": 1.636,
+      "step": 1480
+    },
+    {
+      "epoch": 0.8277015258134188,
+      "grad_norm": 0.945472776889801,
+      "learning_rate": 8.87419633291886e-06,
+      "loss": 1.651,
+      "step": 1485
+    },
+    {
+      "epoch": 0.8304883996377064,
+      "grad_norm": 1.0160605907440186,
+      "learning_rate": 8.599558442598998e-06,
+      "loss": 1.5852,
+      "step": 1490
+    },
+    {
+      "epoch": 0.833275273461994,
+      "grad_norm": 1.047103762626648,
+      "learning_rate": 8.328837035318448e-06,
+      "loss": 1.6926,
+      "step": 1495
+    },
+    {
+      "epoch": 0.8360621472862816,
+      "grad_norm": 0.9703435897827148,
+      "learning_rate": 8.06205772133063e-06,
+      "loss": 1.5367,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1795,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6954415082553344e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be8c0fcf2f8a062ba98a621f2443fdb7418dd260bb1044a8c33b7c88ee37e698
+size 6161

checkpoint-1795/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-1.7B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-1795/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-1.7B",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1795/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f79ac00559ca6230aa3a5a84363d3eb98ba32978abcbf28e1db0f3931bfdf8
+size 34916720

checkpoint-1795/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
+}

checkpoint-1795/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-1795/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92012cc24158d2ebdc67c0af4ab28995ab35e5d62e69eedef1939107a48c31c6
+size 70059963

checkpoint-1795/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250560ab3d528161ab3659b120def6e4a9ab4b457e3399603bbcfa40db3efc90
+size 14645

checkpoint-1795/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1eb2e719ba92d61c300d3b21bda51012661191790b1797109a6a81ec3f6ab06
+size 1465

checkpoint-1795/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
+  }
+}

checkpoint-1795/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-1795/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
+}

checkpoint-1795/trainer_state.json

@@ -0,0 +1,2547 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1795,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0027868738242876052,
+      "grad_norm": 3.341921806335449,
+      "learning_rate": 2.2222222222222225e-06,
+      "loss": 3.1415,
+      "step": 5
+    },
+    {
+      "epoch": 0.0055737476485752105,
+      "grad_norm": 3.4862101078033447,
+      "learning_rate": 5e-06,
+      "loss": 3.04,
+      "step": 10
+    },
+    {
+      "epoch": 0.008360621472862817,
+      "grad_norm": 3.363572597503662,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 3.019,
+      "step": 15
+    },
+    {
+      "epoch": 0.011147495297150421,
+      "grad_norm": 3.5916693210601807,
+      "learning_rate": 1.0555555555555555e-05,
+      "loss": 3.073,
+      "step": 20
+    },
+    {
+      "epoch": 0.013934369121438027,
+      "grad_norm": 3.8997910022735596,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 3.0359,
+      "step": 25
+    },
+    {
+      "epoch": 0.016721242945725634,
+      "grad_norm": 3.789405345916748,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 2.9568,
+      "step": 30
+    },
+    {
+      "epoch": 0.019508116770013236,
+      "grad_norm": 2.785924196243286,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 2.6633,
+      "step": 35
+    },
+    {
+      "epoch": 0.022294990594300842,
+      "grad_norm": 2.715925693511963,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 2.3416,
+      "step": 40
+    },
+    {
+      "epoch": 0.025081864418588447,
+      "grad_norm": 1.851042628288269,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 2.304,
+      "step": 45
+    },
+    {
+      "epoch": 0.027868738242876053,
+      "grad_norm": 1.1627306938171387,
+      "learning_rate": 2.7222222222222223e-05,
+      "loss": 2.0913,
+      "step": 50
+    },
+    {
+      "epoch": 0.03065561206716366,
+      "grad_norm": 0.8980898857116699,
+      "learning_rate": 3e-05,
+      "loss": 1.9108,
+      "step": 55
+    },
+    {
+      "epoch": 0.03344248589145127,
+      "grad_norm": 0.741324245929718,
+      "learning_rate": 3.277777777777778e-05,
+      "loss": 1.989,
+      "step": 60
+    },
+    {
+      "epoch": 0.03622935971573887,
+      "grad_norm": 0.6890819668769836,
+      "learning_rate": 3.555555555555556e-05,
+      "loss": 1.8792,
+      "step": 65
+    },
+    {
+      "epoch": 0.03901623354002647,
+      "grad_norm": 0.6898017525672913,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 1.7895,
+      "step": 70
+    },
+    {
+      "epoch": 0.04180310736431408,
+      "grad_norm": 0.6752148866653442,
+      "learning_rate": 4.111111111111111e-05,
+      "loss": 1.8742,
+      "step": 75
+    },
+    {
+      "epoch": 0.044589981188601684,
+      "grad_norm": 0.6477967500686646,
+      "learning_rate": 4.388888888888889e-05,
+      "loss": 1.7473,
+      "step": 80
+    },
+    {
+      "epoch": 0.04737685501288929,
+      "grad_norm": 0.6459152698516846,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.8558,
+      "step": 85
+    },
+    {
+      "epoch": 0.050163728837176895,
+      "grad_norm": 0.6237108707427979,
+      "learning_rate": 4.9444444444444446e-05,
+      "loss": 1.7931,
+      "step": 90
+    },
+    {
+      "epoch": 0.0529506026614645,
+      "grad_norm": 0.6388494968414307,
+      "learning_rate": 5.222222222222223e-05,
+      "loss": 1.7712,
+      "step": 95
+    },
+    {
+      "epoch": 0.055737476485752106,
+      "grad_norm": 0.686677098274231,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.7316,
+      "step": 100
+    },
+    {
+      "epoch": 0.05852435031003971,
+      "grad_norm": 0.612424910068512,
+      "learning_rate": 5.7777777777777776e-05,
+      "loss": 1.7602,
+      "step": 105
+    },
+    {
+      "epoch": 0.06131122413432732,
+      "grad_norm": 0.8961934447288513,
+      "learning_rate": 6.055555555555555e-05,
+      "loss": 1.8706,
+      "step": 110
+    },
+    {
+      "epoch": 0.06409809795861493,
+      "grad_norm": 0.7244030833244324,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 1.7701,
+      "step": 115
+    },
+    {
+      "epoch": 0.06688497178290254,
+      "grad_norm": 0.6804441809654236,
+      "learning_rate": 6.611111111111111e-05,
+      "loss": 1.7833,
+      "step": 120
+    },
+    {
+      "epoch": 0.06967184560719013,
+      "grad_norm": 0.6717159152030945,
+      "learning_rate": 6.88888888888889e-05,
+      "loss": 1.8445,
+      "step": 125
+    },
+    {
+      "epoch": 0.07245871943147773,
+      "grad_norm": 0.6639799475669861,
+      "learning_rate": 7.166666666666667e-05,
+      "loss": 1.7847,
+      "step": 130
+    },
+    {
+      "epoch": 0.07524559325576534,
+      "grad_norm": 0.7095969915390015,
+      "learning_rate": 7.444444444444444e-05,
+      "loss": 1.7281,
+      "step": 135
+    },
+    {
+      "epoch": 0.07803246708005294,
+      "grad_norm": 0.8189035654067993,
+      "learning_rate": 7.722222222222223e-05,
+      "loss": 1.7678,
+      "step": 140
+    },
+    {
+      "epoch": 0.08081934090434055,
+      "grad_norm": 0.6709702610969543,
+      "learning_rate": 8e-05,
+      "loss": 1.8645,
+      "step": 145
+    },
+    {
+      "epoch": 0.08360621472862816,
+      "grad_norm": 0.743190348148346,
+      "learning_rate": 8.277777777777778e-05,
+      "loss": 1.8086,
+      "step": 150
+    },
+    {
+      "epoch": 0.08639308855291576,
+      "grad_norm": 0.669023871421814,
+      "learning_rate": 8.555555555555556e-05,
+      "loss": 1.7844,
+      "step": 155
+    },
+    {
+      "epoch": 0.08917996237720337,
+      "grad_norm": 0.8071898221969604,
+      "learning_rate": 8.833333333333333e-05,
+      "loss": 1.7379,
+      "step": 160
+    },
+    {
+      "epoch": 0.09196683620149097,
+      "grad_norm": 0.7679445743560791,
+      "learning_rate": 9.111111111111112e-05,
+      "loss": 1.706,
+      "step": 165
+    },
+    {
+      "epoch": 0.09475371002577858,
+      "grad_norm": 0.7896930575370789,
+      "learning_rate": 9.388888888888889e-05,
+      "loss": 1.7752,
+      "step": 170
+    },
+    {
+      "epoch": 0.09754058385006618,
+      "grad_norm": 0.7258396744728088,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 1.7635,
+      "step": 175
+    },
+    {
+      "epoch": 0.10032745767435379,
+      "grad_norm": 0.8085169196128845,
+      "learning_rate": 9.944444444444446e-05,
+      "loss": 1.7449,
+      "step": 180
+    },
+    {
+      "epoch": 0.1031143314986414,
+      "grad_norm": 0.7673636674880981,
+      "learning_rate": 9.999848639521432e-05,
+      "loss": 1.7286,
+      "step": 185
+    },
+    {
+      "epoch": 0.105901205322929,
+      "grad_norm": 0.7478857040405273,
+      "learning_rate": 9.999233753283091e-05,
+      "loss": 1.7203,
+      "step": 190
+    },
+    {
+      "epoch": 0.1086880791472166,
+      "grad_norm": 0.8994764685630798,
+      "learning_rate": 9.998145939378577e-05,
+      "loss": 1.6964,
+      "step": 195
+    },
+    {
+      "epoch": 0.11147495297150421,
+      "grad_norm": 0.7851970791816711,
+      "learning_rate": 9.996585300715116e-05,
+      "loss": 1.7513,
+      "step": 200
+    },
+    {
+      "epoch": 0.11426182679579182,
+      "grad_norm": 0.7743813395500183,
+      "learning_rate": 9.994551984929175e-05,
+      "loss": 1.7099,
+      "step": 205
+    },
+    {
+      "epoch": 0.11704870062007942,
+      "grad_norm": 0.7080249786376953,
+      "learning_rate": 9.992046184372492e-05,
+      "loss": 1.7431,
+      "step": 210
+    },
+    {
+      "epoch": 0.11983557444436703,
+      "grad_norm": 0.744627058506012,
+      "learning_rate": 9.989068136093873e-05,
+      "loss": 1.7159,
+      "step": 215
+    },
+    {
+      "epoch": 0.12262244826865464,
+      "grad_norm": 0.7715389132499695,
+      "learning_rate": 9.985618121816779e-05,
+      "loss": 1.7696,
+      "step": 220
+    },
+    {
+      "epoch": 0.12540932209294225,
+      "grad_norm": 0.7663665413856506,
+      "learning_rate": 9.981696467912664e-05,
+      "loss": 1.7205,
+      "step": 225
+    },
+    {
+      "epoch": 0.12819619591722986,
+      "grad_norm": 0.7923425436019897,
+      "learning_rate": 9.97730354537011e-05,
+      "loss": 1.7136,
+      "step": 230
+    },
+    {
+      "epoch": 0.13098306974151747,
+      "grad_norm": 0.7929289937019348,
+      "learning_rate": 9.972439769759722e-05,
+      "loss": 1.6462,
+      "step": 235
+    },
+    {
+      "epoch": 0.13376994356580507,
+      "grad_norm": 0.845177948474884,
+      "learning_rate": 9.967105601194823e-05,
+      "loss": 1.8031,
+      "step": 240
+    },
+    {
+      "epoch": 0.13655681739009268,
+      "grad_norm": 0.7540026307106018,
+      "learning_rate": 9.961301544287922e-05,
+      "loss": 1.6899,
+      "step": 245
+    },
+    {
+      "epoch": 0.13934369121438026,
+      "grad_norm": 0.8806189894676208,
+      "learning_rate": 9.955028148102979e-05,
+      "loss": 1.6526,
+      "step": 250
+    },
+    {
+      "epoch": 0.14213056503866786,
+      "grad_norm": 0.8206574320793152,
+      "learning_rate": 9.948286006103466e-05,
+      "loss": 1.8233,
+      "step": 255
+    },
+    {
+      "epoch": 0.14491743886295547,
+      "grad_norm": 0.8984567523002625,
+      "learning_rate": 9.941075756096226e-05,
+      "loss": 1.7252,
+      "step": 260
+    },
+    {
+      "epoch": 0.14770431268724307,
+      "grad_norm": 0.7411919832229614,
+      "learning_rate": 9.933398080171123e-05,
+      "loss": 1.7339,
+      "step": 265
+    },
+    {
+      "epoch": 0.15049118651153068,
+      "grad_norm": 0.8030174970626831,
+      "learning_rate": 9.925253704636543e-05,
+      "loss": 1.6934,
+      "step": 270
+    },
+    {
+      "epoch": 0.15327806033581828,
+      "grad_norm": 0.7879084944725037,
+      "learning_rate": 9.916643399950656e-05,
+      "loss": 1.7197,
+      "step": 275
+    },
+    {
+      "epoch": 0.1560649341601059,
+      "grad_norm": 0.8534114956855774,
+      "learning_rate": 9.907567980648549e-05,
+      "loss": 1.6941,
+      "step": 280
+    },
+    {
+      "epoch": 0.1588518079843935,
+      "grad_norm": 0.74381023645401,
+      "learning_rate": 9.898028305265169e-05,
+      "loss": 1.7919,
+      "step": 285
+    },
+    {
+      "epoch": 0.1616386818086811,
+      "grad_norm": 0.8476956486701965,
+      "learning_rate": 9.888025276254096e-05,
+      "loss": 1.7417,
+      "step": 290
+    },
+    {
+      "epoch": 0.1644255556329687,
+      "grad_norm": 0.8212200403213501,
+      "learning_rate": 9.877559839902184e-05,
+      "loss": 1.7452,
+      "step": 295
+    },
+    {
+      "epoch": 0.1672124294572563,
+      "grad_norm": 0.8340197801589966,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 1.6687,
+      "step": 300
+    },
+    {
+      "epoch": 0.16999930328154392,
+      "grad_norm": 0.858363151550293,
+      "learning_rate": 9.855245748948326e-05,
+      "loss": 1.7669,
+      "step": 305
+    },
+    {
+      "epoch": 0.17278617710583152,
+      "grad_norm": 0.8392812013626099,
+      "learning_rate": 9.843399205260068e-05,
+      "loss": 1.736,
+      "step": 310
+    },
+    {
+      "epoch": 0.17557305093011913,
+      "grad_norm": 0.8345137238502502,
+      "learning_rate": 9.831094475858652e-05,
+      "loss": 1.7264,
+      "step": 315
+    },
+    {
+      "epoch": 0.17835992475440673,
+      "grad_norm": 0.8243482708930969,
+      "learning_rate": 9.818332724771857e-05,
+      "loss": 1.7748,
+      "step": 320
+    },
+    {
+      "epoch": 0.18114679857869434,
+      "grad_norm": 0.8255311846733093,
+      "learning_rate": 9.805115159261726e-05,
+      "loss": 1.6798,
+      "step": 325
+    },
+    {
+      "epoch": 0.18393367240298195,
+      "grad_norm": 0.8170781135559082,
+      "learning_rate": 9.791443029710361e-05,
+      "loss": 1.6542,
+      "step": 330
+    },
+    {
+      "epoch": 0.18672054622726955,
+      "grad_norm": 0.8476420044898987,
+      "learning_rate": 9.777317629501636e-05,
+      "loss": 1.6875,
+      "step": 335
+    },
+    {
+      "epoch": 0.18950742005155716,
+      "grad_norm": 0.7547033429145813,
+      "learning_rate": 9.762740294898846e-05,
+      "loss": 1.646,
+      "step": 340
+    },
+    {
+      "epoch": 0.19229429387584476,
+      "grad_norm": 0.826404869556427,
+      "learning_rate": 9.747712404918286e-05,
+      "loss": 1.6187,
+      "step": 345
+    },
+    {
+      "epoch": 0.19508116770013237,
+      "grad_norm": 0.964885950088501,
+      "learning_rate": 9.732235381198813e-05,
+      "loss": 1.7507,
+      "step": 350
+    },
+    {
+      "epoch": 0.19786804152441997,
+      "grad_norm": 0.8207951188087463,
+      "learning_rate": 9.716310687867342e-05,
+      "loss": 1.5745,
+      "step": 355
+    },
+    {
+      "epoch": 0.20065491534870758,
+      "grad_norm": 0.8143700361251831,
+      "learning_rate": 9.699939831400351e-05,
+      "loss": 1.7754,
+      "step": 360
+    },
+    {
+      "epoch": 0.20344178917299519,
+      "grad_norm": 0.811844527721405,
+      "learning_rate": 9.683124360481364e-05,
+      "loss": 1.6993,
+      "step": 365
+    },
+    {
+      "epoch": 0.2062286629972828,
+      "grad_norm": 0.8975111842155457,
+      "learning_rate": 9.665865865854445e-05,
+      "loss": 1.6901,
+      "step": 370
+    },
+    {
+      "epoch": 0.2090155368215704,
+      "grad_norm": 0.7903837561607361,
+      "learning_rate": 9.648165980173712e-05,
+      "loss": 1.6895,
+      "step": 375
+    },
+    {
+      "epoch": 0.211802410645858,
+      "grad_norm": 0.8718327879905701,
+      "learning_rate": 9.630026377848892e-05,
+      "loss": 1.6725,
+      "step": 380
+    },
+    {
+      "epoch": 0.2145892844701456,
+      "grad_norm": 0.8131148219108582,
+      "learning_rate": 9.611448774886924e-05,
+      "loss": 1.6874,
+      "step": 385
+    },
+    {
+      "epoch": 0.2173761582944332,
+      "grad_norm": 0.8331175446510315,
+      "learning_rate": 9.592434928729616e-05,
+      "loss": 1.7542,
+      "step": 390
+    },
+    {
+      "epoch": 0.22016303211872082,
+      "grad_norm": 0.792988121509552,
+      "learning_rate": 9.572986638087396e-05,
+      "loss": 1.7311,
+      "step": 395
+    },
+    {
+      "epoch": 0.22294990594300843,
+      "grad_norm": 0.7799636721611023,
+      "learning_rate": 9.553105742769154e-05,
+      "loss": 1.6567,
+      "step": 400
+    },
+    {
+      "epoch": 0.22573677976729603,
+      "grad_norm": 0.7864108085632324,
+      "learning_rate": 9.532794123508197e-05,
+      "loss": 1.5611,
+      "step": 405
+    },
+    {
+      "epoch": 0.22852365359158364,
+      "grad_norm": 0.8886444568634033,
+      "learning_rate": 9.512053701784329e-05,
+      "loss": 1.6995,
+      "step": 410
+    },
+    {
+      "epoch": 0.23131052741587124,
+      "grad_norm": 0.7999454736709595,
+      "learning_rate": 9.490886439642081e-05,
+      "loss": 1.6898,
+      "step": 415
+    },
+    {
+      "epoch": 0.23409740124015885,
+      "grad_norm": 0.7729182243347168,
+      "learning_rate": 9.469294339505098e-05,
+      "loss": 1.7204,
+      "step": 420
+    },
+    {
+      "epoch": 0.23688427506444645,
+      "grad_norm": 0.8300912380218506,
+      "learning_rate": 9.447279443986716e-05,
+      "loss": 1.6668,
+      "step": 425
+    },
+    {
+      "epoch": 0.23967114888873406,
+      "grad_norm": 0.840481698513031,
+      "learning_rate": 9.424843835696724e-05,
+      "loss": 1.704,
+      "step": 430
+    },
+    {
+      "epoch": 0.24245802271302166,
+      "grad_norm": 0.9396219253540039,
+      "learning_rate": 9.401989637044355e-05,
+      "loss": 1.6713,
+      "step": 435
+    },
+    {
+      "epoch": 0.24524489653730927,
+      "grad_norm": 0.8775554299354553,
+      "learning_rate": 9.3787190100375e-05,
+      "loss": 1.6883,
+      "step": 440
+    },
+    {
+      "epoch": 0.24803177036159688,
+      "grad_norm": 0.8623490333557129,
+      "learning_rate": 9.355034156078188e-05,
+      "loss": 1.6783,
+      "step": 445
+    },
+    {
+      "epoch": 0.2508186441858845,
+      "grad_norm": 0.806533694267273,
+      "learning_rate": 9.330937315754329e-05,
+      "loss": 1.6853,
+      "step": 450
+    },
+    {
+      "epoch": 0.2536055180101721,
+      "grad_norm": 0.8504590392112732,
+      "learning_rate": 9.306430768627753e-05,
+      "loss": 1.6594,
+      "step": 455
+    },
+    {
+      "epoch": 0.2563923918344597,
+      "grad_norm": 0.9382562637329102,
+      "learning_rate": 9.281516833018571e-05,
+      "loss": 1.6827,
+      "step": 460
+    },
+    {
+      "epoch": 0.2591792656587473,
+      "grad_norm": 0.821978747844696,
+      "learning_rate": 9.256197865785854e-05,
+      "loss": 1.752,
+      "step": 465
+    },
+    {
+      "epoch": 0.26196613948303493,
+      "grad_norm": 0.8061692714691162,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": 1.6773,
+      "step": 470
+    },
+    {
+      "epoch": 0.26475301330732254,
+      "grad_norm": 0.8759399652481079,
+      "learning_rate": 9.204354455239539e-05,
+      "loss": 1.7003,
+      "step": 475
+    },
+    {
+      "epoch": 0.26753988713161014,
+      "grad_norm": 0.8721809387207031,
+      "learning_rate": 9.177834916314165e-05,
+      "loss": 1.6898,
+      "step": 480
+    },
+    {
+      "epoch": 0.27032676095589775,
+      "grad_norm": 0.7904046773910522,
+      "learning_rate": 9.150920154077754e-05,
+      "loss": 1.6636,
+      "step": 485
+    },
+    {
+      "epoch": 0.27311363478018535,
+      "grad_norm": 0.8828450441360474,
+      "learning_rate": 9.123612714667634e-05,
+      "loss": 1.6945,
+      "step": 490
+    },
+    {
+      "epoch": 0.2759005086044729,
+      "grad_norm": 0.7389103174209595,
+      "learning_rate": 9.095915181368412e-05,
+      "loss": 1.7459,
+      "step": 495
+    },
+    {
+      "epoch": 0.2786873824287605,
+      "grad_norm": 0.975307285785675,
+      "learning_rate": 9.067830174367586e-05,
+      "loss": 1.7296,
+      "step": 500
+    },
+    {
+      "epoch": 0.2814742562530481,
+      "grad_norm": 0.812856137752533,
+      "learning_rate": 9.039360350507679e-05,
+      "loss": 1.696,
+      "step": 505
+    },
+    {
+      "epoch": 0.2842611300773357,
+      "grad_norm": 0.8609644770622253,
+      "learning_rate": 9.010508403034898e-05,
+      "loss": 1.6464,
+      "step": 510
+    },
+    {
+      "epoch": 0.2870480039016233,
+      "grad_norm": 0.8457721471786499,
+      "learning_rate": 8.98127706134436e-05,
+      "loss": 1.682,
+      "step": 515
+    },
+    {
+      "epoch": 0.28983487772591093,
+      "grad_norm": 0.8576518297195435,
+      "learning_rate": 8.951669090721881e-05,
+      "loss": 1.6784,
+      "step": 520
+    },
+    {
+      "epoch": 0.29262175155019854,
+      "grad_norm": 0.892368495464325,
+      "learning_rate": 8.921687292082393e-05,
+      "loss": 1.6283,
+      "step": 525
+    },
+    {
+      "epoch": 0.29540862537448614,
+      "grad_norm": 0.7966616749763489,
+      "learning_rate": 8.891334501704962e-05,
+      "loss": 1.6898,
+      "step": 530
+    },
+    {
+      "epoch": 0.29819549919877375,
+      "grad_norm": 0.9272663593292236,
+      "learning_rate": 8.86061359096449e-05,
+      "loss": 1.6205,
+      "step": 535
+    },
+    {
+      "epoch": 0.30098237302306136,
+      "grad_norm": 0.8790031671524048,
+      "learning_rate": 8.829527466060072e-05,
+      "loss": 1.5345,
+      "step": 540
+    },
+    {
+      "epoch": 0.30376924684734896,
+      "grad_norm": 0.8462222814559937,
+      "learning_rate": 8.798079067740077e-05,
+      "loss": 1.7664,
+      "step": 545
+    },
+    {
+      "epoch": 0.30655612067163657,
+      "grad_norm": 0.8935257792472839,
+      "learning_rate": 8.766271371023948e-05,
+      "loss": 1.6742,
+      "step": 550
+    },
+    {
+      "epoch": 0.3093429944959242,
+      "grad_norm": 0.9315011501312256,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 1.6154,
+      "step": 555
+    },
+    {
+      "epoch": 0.3121298683202118,
+      "grad_norm": 0.8667712807655334,
+      "learning_rate": 8.701590152144612e-05,
+      "loss": 1.6356,
+      "step": 560
+    },
+    {
+      "epoch": 0.3149167421444994,
+      "grad_norm": 0.9088530540466309,
+      "learning_rate": 8.668722748826693e-05,
+      "loss": 1.6645,
+      "step": 565
+    },
+    {
+      "epoch": 0.317703615968787,
+      "grad_norm": 0.8751830458641052,
+      "learning_rate": 8.635508284224371e-05,
+      "loss": 1.7629,
+      "step": 570
+    },
+    {
+      "epoch": 0.3204904897930746,
+      "grad_norm": 0.8768523335456848,
+      "learning_rate": 8.601949900427016e-05,
+      "loss": 1.631,
+      "step": 575
+    },
+    {
+      "epoch": 0.3232773636173622,
+      "grad_norm": 0.9074881672859192,
+      "learning_rate": 8.568050772058762e-05,
+      "loss": 1.6924,
+      "step": 580
+    },
+    {
+      "epoch": 0.3260642374416498,
+      "grad_norm": 0.9533477425575256,
+      "learning_rate": 8.533814105978191e-05,
+      "loss": 1.644,
+      "step": 585
+    },
+    {
+      "epoch": 0.3288511112659374,
+      "grad_norm": 0.8163946866989136,
+      "learning_rate": 8.499243140974966e-05,
+      "loss": 1.6587,
+      "step": 590
+    },
+    {
+      "epoch": 0.331637985090225,
+      "grad_norm": 0.8785070180892944,
+      "learning_rate": 8.464341147463431e-05,
+      "loss": 1.6666,
+      "step": 595
+    },
+    {
+      "epoch": 0.3344248589145126,
+      "grad_norm": 0.8283839821815491,
+      "learning_rate": 8.429111427173241e-05,
+      "loss": 1.5772,
+      "step": 600
+    },
+    {
+      "epoch": 0.33721173273880023,
+      "grad_norm": 0.8584945797920227,
+      "learning_rate": 8.393557312837018e-05,
+      "loss": 1.6317,
+      "step": 605
+    },
+    {
+      "epoch": 0.33999860656308784,
+      "grad_norm": 0.880062997341156,
+      "learning_rate": 8.357682167875062e-05,
+      "loss": 1.7025,
+      "step": 610
+    },
+    {
+      "epoch": 0.34278548038737544,
+      "grad_norm": 0.9203423261642456,
+      "learning_rate": 8.321489386077192e-05,
+      "loss": 1.6741,
+      "step": 615
+    },
+    {
+      "epoch": 0.34557235421166305,
+      "grad_norm": 0.917999804019928,
+      "learning_rate": 8.28498239128167e-05,
+      "loss": 1.6954,
+      "step": 620
+    },
+    {
+      "epoch": 0.34835922803595065,
+      "grad_norm": 0.8408088088035583,
+      "learning_rate": 8.248164637051321e-05,
+      "loss": 1.6443,
+      "step": 625
+    },
+    {
+      "epoch": 0.35114610186023826,
+      "grad_norm": 0.908991277217865,
+      "learning_rate": 8.211039606346826e-05,
+      "loss": 1.6907,
+      "step": 630
+    },
+    {
+      "epoch": 0.35393297568452586,
+      "grad_norm": 0.9045994877815247,
+      "learning_rate": 8.173610811197226e-05,
+      "loss": 1.66,
+      "step": 635
+    },
+    {
+      "epoch": 0.35671984950881347,
+      "grad_norm": 0.8032850623130798,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 1.6538,
+      "step": 640
+    },
+    {
+      "epoch": 0.3595067233331011,
+      "grad_norm": 0.9243664741516113,
+      "learning_rate": 8.097856119024545e-05,
+      "loss": 1.7321,
+      "step": 645
+    },
+    {
+      "epoch": 0.3622935971573887,
+      "grad_norm": 0.9106388092041016,
+      "learning_rate": 8.059537388397665e-05,
+      "loss": 1.6566,
+      "step": 650
+    },
+    {
+      "epoch": 0.3650804709816763,
+      "grad_norm": 0.9164809584617615,
+      "learning_rate": 8.020929225440137e-05,
+      "loss": 1.6663,
+      "step": 655
+    },
+    {
+      "epoch": 0.3678673448059639,
+      "grad_norm": 0.9171935319900513,
+      "learning_rate": 7.98203528248536e-05,
+      "loss": 1.6781,
+      "step": 660
+    },
+    {
+      "epoch": 0.3706542186302515,
+      "grad_norm": 0.8433538675308228,
+      "learning_rate": 7.942859238901528e-05,
+      "loss": 1.7255,
+      "step": 665
+    },
+    {
+      "epoch": 0.3734410924545391,
+      "grad_norm": 0.9780874252319336,
+      "learning_rate": 7.903404800743564e-05,
+      "loss": 1.722,
+      "step": 670
+    },
+    {
+      "epoch": 0.3762279662788267,
+      "grad_norm": 0.9980689287185669,
+      "learning_rate": 7.863675700402526e-05,
+      "loss": 1.6403,
+      "step": 675
+    },
+    {
+      "epoch": 0.3790148401031143,
+      "grad_norm": 0.843333899974823,
+      "learning_rate": 7.823675696252524e-05,
+      "loss": 1.7583,
+      "step": 680
+    },
+    {
+      "epoch": 0.3818017139274019,
+      "grad_norm": 0.8417442440986633,
+      "learning_rate": 7.783408572295174e-05,
+      "loss": 1.6938,
+      "step": 685
+    },
+    {
+      "epoch": 0.3845885877516895,
+      "grad_norm": 0.8940498232841492,
+      "learning_rate": 7.742878137801639e-05,
+      "loss": 1.6737,
+      "step": 690
+    },
+    {
+      "epoch": 0.38737546157597713,
+      "grad_norm": 0.8713932633399963,
+      "learning_rate": 7.702088226952258e-05,
+      "loss": 1.6435,
+      "step": 695
+    },
+    {
+      "epoch": 0.39016233540026474,
+      "grad_norm": 0.9215396046638489,
+      "learning_rate": 7.661042698473853e-05,
+      "loss": 1.5994,
+      "step": 700
+    },
+    {
+      "epoch": 0.39294920922455234,
+      "grad_norm": 0.8360981941223145,
+      "learning_rate": 7.619745435274667e-05,
+      "loss": 1.6511,
+      "step": 705
+    },
+    {
+      "epoch": 0.39573608304883995,
+      "grad_norm": 0.9177049398422241,
+      "learning_rate": 7.578200344077073e-05,
+      "loss": 1.6655,
+      "step": 710
+    },
+    {
+      "epoch": 0.39852295687312755,
+      "grad_norm": 0.8501256108283997,
+      "learning_rate": 7.536411355047964e-05,
+      "loss": 1.659,
+      "step": 715
+    },
+    {
+      "epoch": 0.40130983069741516,
+      "grad_norm": 0.8666147589683533,
+      "learning_rate": 7.494382421426984e-05,
+      "loss": 1.7046,
+      "step": 720
+    },
+    {
+      "epoch": 0.40409670452170277,
+      "grad_norm": 0.8096281290054321,
+      "learning_rate": 7.452117519152542e-05,
+      "loss": 1.6108,
+      "step": 725
+    },
+    {
+      "epoch": 0.40688357834599037,
+      "grad_norm": 1.0028629302978516,
+      "learning_rate": 7.409620646485685e-05,
+      "loss": 1.6302,
+      "step": 730
+    },
+    {
+      "epoch": 0.409670452170278,
+      "grad_norm": 0.8731248378753662,
+      "learning_rate": 7.36689582363187e-05,
+      "loss": 1.6784,
+      "step": 735
+    },
+    {
+      "epoch": 0.4124573259945656,
+      "grad_norm": 0.9034931659698486,
+      "learning_rate": 7.323947092360649e-05,
+      "loss": 1.5845,
+      "step": 740
+    },
+    {
+      "epoch": 0.4152441998188532,
+      "grad_norm": 0.9129267334938049,
+      "learning_rate": 7.280778515623314e-05,
+      "loss": 1.7366,
+      "step": 745
+    },
+    {
+      "epoch": 0.4180310736431408,
+      "grad_norm": 0.9088048338890076,
+      "learning_rate": 7.237394177168548e-05,
+      "loss": 1.7065,
+      "step": 750
+    },
+    {
+      "epoch": 0.4208179474674284,
+      "grad_norm": 0.9397730827331543,
+      "learning_rate": 7.193798181156095e-05,
+      "loss": 1.7012,
+      "step": 755
+    },
+    {
+      "epoch": 0.423604821291716,
+      "grad_norm": 0.9324731230735779,
+      "learning_rate": 7.149994651768514e-05,
+      "loss": 1.5474,
+      "step": 760
+    },
+    {
+      "epoch": 0.4263916951160036,
+      "grad_norm": 0.9360097646713257,
+      "learning_rate": 7.10598773282103e-05,
+      "loss": 1.6602,
+      "step": 765
+    },
+    {
+      "epoch": 0.4291785689402912,
+      "grad_norm": 0.9703853130340576,
+      "learning_rate": 7.061781587369519e-05,
+      "loss": 1.7305,
+      "step": 770
+    },
+    {
+      "epoch": 0.4319654427645788,
+      "grad_norm": 0.9043810367584229,
+      "learning_rate": 7.017380397316695e-05,
+      "loss": 1.6131,
+      "step": 775
+    },
+    {
+      "epoch": 0.4347523165888664,
+      "grad_norm": 0.8870768547058105,
+      "learning_rate": 6.972788363016497e-05,
+      "loss": 1.5668,
+      "step": 780
+    },
+    {
+      "epoch": 0.43753919041315403,
+      "grad_norm": 0.9383454918861389,
+      "learning_rate": 6.92800970287674e-05,
+      "loss": 1.6773,
+      "step": 785
+    },
+    {
+      "epoch": 0.44032606423744164,
+      "grad_norm": 0.8532437682151794,
+      "learning_rate": 6.883048652960038e-05,
+      "loss": 1.6602,
+      "step": 790
+    },
+    {
+      "epoch": 0.44311293806172924,
+      "grad_norm": 0.8915623426437378,
+      "learning_rate": 6.837909466583095e-05,
+      "loss": 1.6778,
+      "step": 795
+    },
+    {
+      "epoch": 0.44589981188601685,
+      "grad_norm": 0.840151846408844,
+      "learning_rate": 6.792596413914324e-05,
+      "loss": 1.5566,
+      "step": 800
+    },
+    {
+      "epoch": 0.44868668571030446,
+      "grad_norm": 0.8808228969573975,
+      "learning_rate": 6.747113781569892e-05,
+      "loss": 1.6819,
+      "step": 805
+    },
+    {
+      "epoch": 0.45147355953459206,
+      "grad_norm": 0.9224216938018799,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 1.7057,
+      "step": 810
+    },
+    {
+      "epoch": 0.45426043335887967,
+      "grad_norm": 1.0062270164489746,
+      "learning_rate": 6.655657004122916e-05,
+      "loss": 1.719,
+      "step": 815
+    },
+    {
+      "epoch": 0.4570473071831673,
+      "grad_norm": 0.9544162154197693,
+      "learning_rate": 6.60969151083432e-05,
+      "loss": 1.657,
+      "step": 820
+    },
+    {
+      "epoch": 0.4598341810074549,
+      "grad_norm": 0.8740416169166565,
+      "learning_rate": 6.563573740679496e-05,
+      "loss": 1.645,
+      "step": 825
+    },
+    {
+      "epoch": 0.4626210548317425,
+      "grad_norm": 0.8866944313049316,
+      "learning_rate": 6.517308056400917e-05,
+      "loss": 1.6446,
+      "step": 830
+    },
+    {
+      "epoch": 0.4654079286560301,
+      "grad_norm": 0.9224971532821655,
+      "learning_rate": 6.470898834733731e-05,
+      "loss": 1.6384,
+      "step": 835
+    },
+    {
+      "epoch": 0.4681948024803177,
+      "grad_norm": 0.8925870656967163,
+      "learning_rate": 6.42435046599173e-05,
+      "loss": 1.6455,
+      "step": 840
+    },
+    {
+      "epoch": 0.4709816763046053,
+      "grad_norm": 0.9226738810539246,
+      "learning_rate": 6.377667353652022e-05,
+      "loss": 1.6799,
+      "step": 845
+    },
+    {
+      "epoch": 0.4737685501288929,
+      "grad_norm": 0.9104128479957581,
+      "learning_rate": 6.330853913938466e-05,
+      "loss": 1.6267,
+      "step": 850
+    },
+    {
+      "epoch": 0.4765554239531805,
+      "grad_norm": 0.912969708442688,
+      "learning_rate": 6.283914575403888e-05,
+      "loss": 1.716,
+      "step": 855
+    },
+    {
+      "epoch": 0.4793422977774681,
+      "grad_norm": 0.9142662882804871,
+      "learning_rate": 6.236853778511156e-05,
+      "loss": 1.6619,
+      "step": 860
+    },
+    {
+      "epoch": 0.4821291716017557,
+      "grad_norm": 0.9380782842636108,
+      "learning_rate": 6.189675975213094e-05,
+      "loss": 1.6578,
+      "step": 865
+    },
+    {
+      "epoch": 0.48491604542604333,
+      "grad_norm": 0.9225218296051025,
+      "learning_rate": 6.142385628531342e-05,
+      "loss": 1.6891,
+      "step": 870
+    },
+    {
+      "epoch": 0.48770291925033094,
+      "grad_norm": 0.9732077121734619,
+      "learning_rate": 6.09498721213414e-05,
+      "loss": 1.6008,
+      "step": 875
+    },
+    {
+      "epoch": 0.49048979307461854,
+      "grad_norm": 0.9870405197143555,
+      "learning_rate": 6.047485209913137e-05,
+      "loss": 1.7372,
+      "step": 880
+    },
+    {
+      "epoch": 0.49327666689890615,
+      "grad_norm": 0.8708714246749878,
+      "learning_rate": 5.999884115559192e-05,
+      "loss": 1.6317,
+      "step": 885
+    },
+    {
+      "epoch": 0.49606354072319375,
+      "grad_norm": 0.8490287065505981,
+      "learning_rate": 5.952188432137293e-05,
+      "loss": 1.6514,
+      "step": 890
+    },
+    {
+      "epoch": 0.49885041454748136,
+      "grad_norm": 0.7740074992179871,
+      "learning_rate": 5.90440267166055e-05,
+      "loss": 1.6091,
+      "step": 895
+    },
+    {
+      "epoch": 0.501637288371769,
+      "grad_norm": 0.9218555092811584,
+      "learning_rate": 5.8565313546633684e-05,
+      "loss": 1.674,
+      "step": 900
+    },
+    {
+      "epoch": 0.5044241621960566,
+      "grad_norm": 0.8074113726615906,
+      "learning_rate": 5.8085790097738025e-05,
+      "loss": 1.6567,
+      "step": 905
+    },
+    {
+      "epoch": 0.5072110360203442,
+      "grad_norm": 0.9320290684700012,
+      "learning_rate": 5.7605501732851475e-05,
+      "loss": 1.6925,
+      "step": 910
+    },
+    {
+      "epoch": 0.5099979098446318,
+      "grad_norm": 0.8326326012611389,
+      "learning_rate": 5.712449388726807e-05,
+      "loss": 1.6909,
+      "step": 915
+    },
+    {
+      "epoch": 0.5127847836689194,
+      "grad_norm": 0.9022158980369568,
+      "learning_rate": 5.664281206434472e-05,
+      "loss": 1.6075,
+      "step": 920
+    },
+    {
+      "epoch": 0.515571657493207,
+      "grad_norm": 0.8791519999504089,
+      "learning_rate": 5.616050183119663e-05,
+      "loss": 1.7011,
+      "step": 925
+    },
+    {
+      "epoch": 0.5183585313174947,
+      "grad_norm": 0.876043438911438,
+      "learning_rate": 5.5677608814386616e-05,
+      "loss": 1.5478,
+      "step": 930
+    },
+    {
+      "epoch": 0.5211454051417822,
+      "grad_norm": 0.9437665939331055,
+      "learning_rate": 5.519417869560889e-05,
+      "loss": 1.6518,
+      "step": 935
+    },
+    {
+      "epoch": 0.5239322789660699,
+      "grad_norm": 0.9788090586662292,
+      "learning_rate": 5.471025720736747e-05,
+      "loss": 1.7146,
+      "step": 940
+    },
+    {
+      "epoch": 0.5267191527903574,
+      "grad_norm": 0.861488938331604,
+      "learning_rate": 5.422589012864996e-05,
+      "loss": 1.6805,
+      "step": 945
+    },
+    {
+      "epoch": 0.5295060266146451,
+      "grad_norm": 1.008576512336731,
+      "learning_rate": 5.3741123280596864e-05,
+      "loss": 1.6012,
+      "step": 950
+    },
+    {
+      "epoch": 0.5322929004389326,
+      "grad_norm": 0.9095168113708496,
+      "learning_rate": 5.325600252216685e-05,
+      "loss": 1.6477,
+      "step": 955
+    },
+    {
+      "epoch": 0.5350797742632203,
+      "grad_norm": 0.8760788440704346,
+      "learning_rate": 5.27705737457985e-05,
+      "loss": 1.5747,
+      "step": 960
+    },
+    {
+      "epoch": 0.5378666480875078,
+      "grad_norm": 0.9696391224861145,
+      "learning_rate": 5.228488287306896e-05,
+      "loss": 1.6249,
+      "step": 965
+    },
+    {
+      "epoch": 0.5406535219117955,
+      "grad_norm": 0.8726052641868591,
+      "learning_rate": 5.179897585034963e-05,
+      "loss": 1.6701,
+      "step": 970
+    },
+    {
+      "epoch": 0.543440395736083,
+      "grad_norm": 0.8699939846992493,
+      "learning_rate": 5.1312898644459776e-05,
+      "loss": 1.5395,
+      "step": 975
+    },
+    {
+      "epoch": 0.5462272695603707,
+      "grad_norm": 0.9301031827926636,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": 1.6724,
+      "step": 980
+    },
+    {
+      "epoch": 0.5490141433846583,
+      "grad_norm": 0.8767033815383911,
+      "learning_rate": 5.0340417626592016e-05,
+      "loss": 1.6492,
+      "step": 985
+    },
+    {
+      "epoch": 0.5518010172089458,
+      "grad_norm": 0.9239912629127502,
+      "learning_rate": 4.9854105811348216e-05,
+      "loss": 1.6705,
+      "step": 990
+    },
+    {
+      "epoch": 0.5545878910332335,
+      "grad_norm": 1.0233875513076782,
+      "learning_rate": 4.936780779769913e-05,
+      "loss": 1.6758,
+      "step": 995
+    },
+    {
+      "epoch": 0.557374764857521,
+      "grad_norm": 0.9696400165557861,
+      "learning_rate": 4.888156958945174e-05,
+      "loss": 1.6276,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5601616386818087,
+      "grad_norm": 0.9741013646125793,
+      "learning_rate": 4.839543718475543e-05,
+      "loss": 1.6241,
+      "step": 1005
+    },
+    {
+      "epoch": 0.5629485125060962,
+      "grad_norm": 0.9259172081947327,
+      "learning_rate": 4.790945657175061e-05,
+      "loss": 1.6596,
+      "step": 1010
+    },
+    {
+      "epoch": 0.5657353863303839,
+      "grad_norm": 0.9725984930992126,
+      "learning_rate": 4.742367372421811e-05,
+      "loss": 1.6663,
+      "step": 1015
+    },
+    {
+      "epoch": 0.5685222601546714,
+      "grad_norm": 1.0007803440093994,
+      "learning_rate": 4.69381345972302e-05,
+      "loss": 1.6159,
+      "step": 1020
+    },
+    {
+      "epoch": 0.5713091339789591,
+      "grad_norm": 0.9005650877952576,
+      "learning_rate": 4.6452885122803205e-05,
+      "loss": 1.5989,
+      "step": 1025
+    },
+    {
+      "epoch": 0.5740960078032467,
+      "grad_norm": 0.8858962655067444,
+      "learning_rate": 4.5967971205552194e-05,
+      "loss": 1.6609,
+      "step": 1030
+    },
+    {
+      "epoch": 0.5768828816275343,
+      "grad_norm": 0.945851743221283,
+      "learning_rate": 4.548343871834864e-05,
+      "loss": 1.6605,
+      "step": 1035
+    },
+    {
+      "epoch": 0.5796697554518219,
+      "grad_norm": 0.9151830077171326,
+      "learning_rate": 4.499933349798067e-05,
+      "loss": 1.678,
+      "step": 1040
+    },
+    {
+      "epoch": 0.5824566292761095,
+      "grad_norm": 0.9208435416221619,
+      "learning_rate": 4.451570134081694e-05,
+      "loss": 1.7427,
+      "step": 1045
+    },
+    {
+      "epoch": 0.5852435031003971,
+      "grad_norm": 0.9141213893890381,
+      "learning_rate": 4.403258799847433e-05,
+      "loss": 1.62,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5880303769246847,
+      "grad_norm": 1.0249472856521606,
+      "learning_rate": 4.3550039173489845e-05,
+      "loss": 1.634,
+      "step": 1055
+    },
+    {
+      "epoch": 0.5908172507489723,
+      "grad_norm": 0.8938164114952087,
+      "learning_rate": 4.306810051499708e-05,
+      "loss": 1.562,
+      "step": 1060
+    },
+    {
+      "epoch": 0.59360412457326,
+      "grad_norm": 1.0070486068725586,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": 1.6713,
+      "step": 1065
+    },
+    {
+      "epoch": 0.5963909983975475,
+      "grad_norm": 0.8382595777511597,
+      "learning_rate": 4.210623600109946e-05,
+      "loss": 1.5343,
+      "step": 1070
+    },
+    {
+      "epoch": 0.5991778722218352,
+      "grad_norm": 0.9747705459594727,
+      "learning_rate": 4.162640113810706e-05,
+      "loss": 1.67,
+      "step": 1075
+    },
+    {
+      "epoch": 0.6019647460461227,
+      "grad_norm": 0.9397943019866943,
+      "learning_rate": 4.114735841782347e-05,
+      "loss": 1.705,
+      "step": 1080
+    },
+    {
+      "epoch": 0.6047516198704104,
+      "grad_norm": 0.9868884086608887,
+      "learning_rate": 4.06691531577047e-05,
+      "loss": 1.6343,
+      "step": 1085
+    },
+    {
+      "epoch": 0.6075384936946979,
+      "grad_norm": 0.9283191561698914,
+      "learning_rate": 4.019183059598296e-05,
+      "loss": 1.6226,
+      "step": 1090
+    },
+    {
+      "epoch": 0.6103253675189856,
+      "grad_norm": 0.8564023971557617,
+      "learning_rate": 3.971543588738724e-05,
+      "loss": 1.6206,
+      "step": 1095
+    },
+    {
+      "epoch": 0.6131122413432731,
+      "grad_norm": 0.9272263050079346,
+      "learning_rate": 3.924001409887158e-05,
+      "loss": 1.5952,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6158991151675608,
+      "grad_norm": 0.9421799778938293,
+      "learning_rate": 3.87656102053517e-05,
+      "loss": 1.6356,
+      "step": 1105
+    },
+    {
+      "epoch": 0.6186859889918483,
+      "grad_norm": 0.918296217918396,
+      "learning_rate": 3.8292269085450474e-05,
+      "loss": 1.6143,
+      "step": 1110
+    },
+    {
+      "epoch": 0.621472862816136,
+      "grad_norm": 0.9440540671348572,
+      "learning_rate": 3.782003551725236e-05,
+      "loss": 1.6928,
+      "step": 1115
+    },
+    {
+      "epoch": 0.6242597366404236,
+      "grad_norm": 0.8987861275672913,
+      "learning_rate": 3.734895417406734e-05,
+      "loss": 1.6571,
+      "step": 1120
+    },
+    {
+      "epoch": 0.6270466104647112,
+      "grad_norm": 0.9039310216903687,
+      "learning_rate": 3.687906962020491e-05,
+      "loss": 1.6862,
+      "step": 1125
+    },
+    {
+      "epoch": 0.6298334842889988,
+      "grad_norm": 0.9794312119483948,
+      "learning_rate": 3.641042630675829e-05,
+      "loss": 1.6843,
+      "step": 1130
+    },
+    {
+      "epoch": 0.6326203581132864,
+      "grad_norm": 0.9151976704597473,
+      "learning_rate": 3.594306856739924e-05,
+      "loss": 1.602,
+      "step": 1135
+    },
+    {
+      "epoch": 0.635407231937574,
+      "grad_norm": 0.9147221446037292,
+      "learning_rate": 3.547704061418424e-05,
+      "loss": 1.6073,
+      "step": 1140
+    },
+    {
+      "epoch": 0.6381941057618616,
+      "grad_norm": 0.9955829977989197,
+      "learning_rate": 3.501238653337194e-05,
+      "loss": 1.6535,
+      "step": 1145
+    },
+    {
+      "epoch": 0.6409809795861492,
+      "grad_norm": 1.0493595600128174,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.6979,
+      "step": 1150
+    },
+    {
+      "epoch": 0.6437678534104369,
+      "grad_norm": 0.9534896016120911,
+      "learning_rate": 3.408737567998993e-05,
+      "loss": 1.5449,
+      "step": 1155
+    },
+    {
+      "epoch": 0.6465547272347244,
+      "grad_norm": 0.9850942492485046,
+      "learning_rate": 3.362710641347524e-05,
+      "loss": 1.6989,
+      "step": 1160
+    },
+    {
+      "epoch": 0.6493416010590121,
+      "grad_norm": 0.9439795017242432,
+      "learning_rate": 3.316838602319532e-05,
+      "loss": 1.6826,
+      "step": 1165
+    },
+    {
+      "epoch": 0.6521284748832996,
+      "grad_norm": 1.0012317895889282,
+      "learning_rate": 3.271125790411309e-05,
+      "loss": 1.524,
+      "step": 1170
+    },
+    {
+      "epoch": 0.6549153487075873,
+      "grad_norm": 0.9746808409690857,
+      "learning_rate": 3.225576530056264e-05,
+      "loss": 1.6796,
+      "step": 1175
+    },
+    {
+      "epoch": 0.6577022225318748,
+      "grad_norm": 0.8482115864753723,
+      "learning_rate": 3.180195130215824e-05,
+      "loss": 1.6443,
+      "step": 1180
+    },
+    {
+      "epoch": 0.6604890963561625,
+      "grad_norm": 1.0496842861175537,
+      "learning_rate": 3.1349858839717986e-05,
+      "loss": 1.586,
+      "step": 1185
+    },
+    {
+      "epoch": 0.66327597018045,
+      "grad_norm": 0.8761202692985535,
+      "learning_rate": 3.089953068120271e-05,
+      "loss": 1.5516,
+      "step": 1190
+    },
+    {
+      "epoch": 0.6660628440047377,
+      "grad_norm": 1.058709740638733,
+      "learning_rate": 3.0451009427669986e-05,
+      "loss": 1.611,
+      "step": 1195
+    },
+    {
+      "epoch": 0.6688497178290252,
+      "grad_norm": 0.9337294101715088,
+      "learning_rate": 3.000433750924414e-05,
+      "loss": 1.6324,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6716365916533129,
+      "grad_norm": 0.9224420785903931,
+      "learning_rate": 2.9559557181102315e-05,
+      "loss": 1.6494,
+      "step": 1205
+    },
+    {
+      "epoch": 0.6744234654776005,
+      "grad_norm": 1.1299585103988647,
+      "learning_rate": 2.911671051947722e-05,
+      "loss": 1.5891,
+      "step": 1210
+    },
+    {
+      "epoch": 0.6772103393018881,
+      "grad_norm": 0.9998091459274292,
+      "learning_rate": 2.867583941767657e-05,
+      "loss": 1.5622,
+      "step": 1215
+    },
+    {
+      "epoch": 0.6799972131261757,
+      "grad_norm": 0.9196699261665344,
+      "learning_rate": 2.823698558212009e-05,
+      "loss": 1.6298,
+      "step": 1220
+    },
+    {
+      "epoch": 0.6827840869504633,
+      "grad_norm": 0.9296634793281555,
+      "learning_rate": 2.7800190528394122e-05,
+      "loss": 1.6035,
+      "step": 1225
+    },
+    {
+      "epoch": 0.6855709607747509,
+      "grad_norm": 0.8991268873214722,
+      "learning_rate": 2.736549557732405e-05,
+      "loss": 1.5498,
+      "step": 1230
+    },
+    {
+      "epoch": 0.6883578345990385,
+      "grad_norm": 0.9545588493347168,
+      "learning_rate": 2.693294185106562e-05,
+      "loss": 1.7968,
+      "step": 1235
+    },
+    {
+      "epoch": 0.6911447084233261,
+      "grad_norm": 0.9947872757911682,
+      "learning_rate": 2.650257026921455e-05,
+      "loss": 1.673,
+      "step": 1240
+    },
+    {
+      "epoch": 0.6939315822476138,
+      "grad_norm": 1.013684630393982,
+      "learning_rate": 2.607442154493568e-05,
+      "loss": 1.6995,
+      "step": 1245
+    },
+    {
+      "epoch": 0.6967184560719013,
+      "grad_norm": 0.9432601928710938,
+      "learning_rate": 2.5648536181111438e-05,
+      "loss": 1.6238,
+      "step": 1250
+    },
+    {
+      "epoch": 0.699505329896189,
+      "grad_norm": 0.9840952157974243,
+      "learning_rate": 2.5224954466510274e-05,
+      "loss": 1.6116,
+      "step": 1255
+    },
+    {
+      "epoch": 0.7022922037204765,
+      "grad_norm": 0.9281061291694641,
+      "learning_rate": 2.480371647197538e-05,
+      "loss": 1.6705,
+      "step": 1260
+    },
+    {
+      "epoch": 0.7050790775447642,
+      "grad_norm": 0.9922870397567749,
+      "learning_rate": 2.438486204663391e-05,
+      "loss": 1.6893,
+      "step": 1265
+    },
+    {
+      "epoch": 0.7078659513690517,
+      "grad_norm": 0.9433642029762268,
+      "learning_rate": 2.3968430814127385e-05,
+      "loss": 1.674,
+      "step": 1270
+    },
+    {
+      "epoch": 0.7106528251933394,
+      "grad_norm": 0.9409830570220947,
+      "learning_rate": 2.3554462168863085e-05,
+      "loss": 1.6519,
+      "step": 1275
+    },
+    {
+      "epoch": 0.7134396990176269,
+      "grad_norm": 0.9217763543128967,
+      "learning_rate": 2.314299527228759e-05,
+      "loss": 1.6384,
+      "step": 1280
+    },
+    {
+      "epoch": 0.7162265728419146,
+      "grad_norm": 0.8798460364341736,
+      "learning_rate": 2.2734069049181882e-05,
+      "loss": 1.6243,
+      "step": 1285
+    },
+    {
+      "epoch": 0.7190134466662021,
+      "grad_norm": 0.9369103908538818,
+      "learning_rate": 2.2327722183979212e-05,
+      "loss": 1.6331,
+      "step": 1290
+    },
+    {
+      "epoch": 0.7218003204904898,
+      "grad_norm": 0.9402239918708801,
+      "learning_rate": 2.1923993117105462e-05,
+      "loss": 1.6124,
+      "step": 1295
+    },
+    {
+      "epoch": 0.7245871943147774,
+      "grad_norm": 1.0770180225372314,
+      "learning_rate": 2.1522920041342704e-05,
+      "loss": 1.6276,
+      "step": 1300
+    },
+    {
+      "epoch": 0.727374068139065,
+      "grad_norm": 0.9942741990089417,
+      "learning_rate": 2.1124540898216248e-05,
+      "loss": 1.6543,
+      "step": 1305
+    },
+    {
+      "epoch": 0.7301609419633526,
+      "grad_norm": 0.9097809195518494,
+      "learning_rate": 2.0728893374405166e-05,
+      "loss": 1.5341,
+      "step": 1310
+    },
+    {
+      "epoch": 0.7329478157876402,
+      "grad_norm": 0.9943116307258606,
+      "learning_rate": 2.033601489817738e-05,
+      "loss": 1.7465,
+      "step": 1315
+    },
+    {
+      "epoch": 0.7357346896119278,
+      "grad_norm": 0.9960694313049316,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 1.6835,
+      "step": 1320
+    },
+    {
+      "epoch": 0.7385215634362154,
+      "grad_norm": 0.9358818531036377,
+      "learning_rate": 1.9558713488267238e-05,
+      "loss": 1.6585,
+      "step": 1325
+    },
+    {
+      "epoch": 0.741308437260503,
+      "grad_norm": 0.9540205597877502,
+      "learning_rate": 1.917436408732208e-05,
+      "loss": 1.6298,
+      "step": 1330
+    },
+    {
+      "epoch": 0.7440953110847907,
+      "grad_norm": 1.0423612594604492,
+      "learning_rate": 1.8792930792478357e-05,
+      "loss": 1.6291,
+      "step": 1335
+    },
+    {
+      "epoch": 0.7468821849090782,
+      "grad_norm": 1.0178053379058838,
+      "learning_rate": 1.8414449687337464e-05,
+      "loss": 1.5844,
+      "step": 1340
+    },
+    {
+      "epoch": 0.7496690587333659,
+      "grad_norm": 0.9405874013900757,
+      "learning_rate": 1.8038956576223504e-05,
+      "loss": 1.5531,
+      "step": 1345
+    },
+    {
+      "epoch": 0.7524559325576534,
+      "grad_norm": 0.9561493396759033,
+      "learning_rate": 1.766648698079635e-05,
+      "loss": 1.6504,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7552428063819411,
+      "grad_norm": 0.9773407578468323,
+      "learning_rate": 1.7297076136691072e-05,
+      "loss": 1.7289,
+      "step": 1355
+    },
+    {
+      "epoch": 0.7580296802062286,
+      "grad_norm": 1.024316430091858,
+      "learning_rate": 1.6930758990184875e-05,
+      "loss": 1.6495,
+      "step": 1360
+    },
+    {
+      "epoch": 0.7608165540305163,
+      "grad_norm": 1.1461398601531982,
+      "learning_rate": 1.6567570194891024e-05,
+      "loss": 1.63,
+      "step": 1365
+    },
+    {
+      "epoch": 0.7636034278548038,
+      "grad_norm": 1.1386655569076538,
+      "learning_rate": 1.620754410848069e-05,
+      "loss": 1.647,
+      "step": 1370
+    },
+    {
+      "epoch": 0.7663903016790915,
+      "grad_norm": 0.9157811999320984,
+      "learning_rate": 1.5850714789432663e-05,
+      "loss": 1.659,
+      "step": 1375
+    },
+    {
+      "epoch": 0.769177175503379,
+      "grad_norm": 1.0108404159545898,
+      "learning_rate": 1.549711599381145e-05,
+      "loss": 1.6671,
+      "step": 1380
+    },
+    {
+      "epoch": 0.7719640493276667,
+      "grad_norm": 0.8621100783348083,
+      "learning_rate": 1.5146781172073959e-05,
+      "loss": 1.6478,
+      "step": 1385
+    },
+    {
+      "epoch": 0.7747509231519543,
+      "grad_norm": 0.957285463809967,
+      "learning_rate": 1.479974346590503e-05,
+      "loss": 1.6313,
+      "step": 1390
+    },
+    {
+      "epoch": 0.7775377969762419,
+      "grad_norm": 0.9681037068367004,
+      "learning_rate": 1.4456035705082349e-05,
+      "loss": 1.5881,
+      "step": 1395
+    },
+    {
+      "epoch": 0.7803246708005295,
+      "grad_norm": 0.9414888620376587,
+      "learning_rate": 1.4115690404370551e-05,
+      "loss": 1.6011,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7831115446248171,
+      "grad_norm": 0.9640589952468872,
+      "learning_rate": 1.3778739760445552e-05,
+      "loss": 1.623,
+      "step": 1405
+    },
+    {
+      "epoch": 0.7858984184491047,
+      "grad_norm": 0.9019273519515991,
+      "learning_rate": 1.344521564884858e-05,
+      "loss": 1.6779,
+      "step": 1410
+    },
+    {
+      "epoch": 0.7886852922733923,
+      "grad_norm": 0.9059531688690186,
+      "learning_rate": 1.3115149620970795e-05,
+      "loss": 1.6783,
+      "step": 1415
+    },
+    {
+      "epoch": 0.7914721660976799,
+      "grad_norm": 0.9945409297943115,
+      "learning_rate": 1.2788572901068552e-05,
+      "loss": 1.629,
+      "step": 1420
+    },
+    {
+      "epoch": 0.7942590399219676,
+      "grad_norm": 1.0185166597366333,
+      "learning_rate": 1.2465516383309551e-05,
+      "loss": 1.6547,
+      "step": 1425
+    },
+    {
+      "epoch": 0.7970459137462551,
+      "grad_norm": 1.0051592588424683,
+      "learning_rate": 1.2146010628850268e-05,
+      "loss": 1.7016,
+      "step": 1430
+    },
+    {
+      "epoch": 0.7998327875705428,
+      "grad_norm": 0.9881749749183655,
+      "learning_rate": 1.183008586294485e-05,
+      "loss": 1.5857,
+      "step": 1435
+    },
+    {
+      "epoch": 0.8026196613948303,
+      "grad_norm": 0.9611209630966187,
+      "learning_rate": 1.151777197208585e-05,
+      "loss": 1.6027,
+      "step": 1440
+    },
+    {
+      "epoch": 0.805406535219118,
+      "grad_norm": 1.0034438371658325,
+      "learning_rate": 1.1209098501176896e-05,
+      "loss": 1.6083,
+      "step": 1445
+    },
+    {
+      "epoch": 0.8081934090434055,
+      "grad_norm": 0.9777964949607849,
+      "learning_rate": 1.0904094650737795e-05,
+      "loss": 1.6016,
+      "step": 1450
+    },
+    {
+      "epoch": 0.8109802828676932,
+      "grad_norm": 1.0084513425827026,
+      "learning_rate": 1.0602789274142133e-05,
+      "loss": 1.6998,
+      "step": 1455
+    },
+    {
+      "epoch": 0.8137671566919807,
+      "grad_norm": 0.9777223467826843,
+      "learning_rate": 1.0305210874887766e-05,
+      "loss": 1.5668,
+      "step": 1460
+    },
+    {
+      "epoch": 0.8165540305162684,
+      "grad_norm": 0.9857009649276733,
+      "learning_rate": 1.0011387603900385e-05,
+      "loss": 1.5977,
+      "step": 1465
+    },
+    {
+      "epoch": 0.819340904340556,
+      "grad_norm": 1.0366628170013428,
+      "learning_rate": 9.7213472568704e-06,
+      "loss": 1.6536,
+      "step": 1470
+    },
+    {
+      "epoch": 0.8221277781648436,
+      "grad_norm": 0.9983012080192566,
+      "learning_rate": 9.435117271623566e-06,
+      "loss": 1.4905,
+      "step": 1475
+    },
+    {
+      "epoch": 0.8249146519891312,
+      "grad_norm": 1.042453646659851,
+      "learning_rate": 9.152724725525202e-06,
+      "loss": 1.636,
+      "step": 1480
+    },
+    {
+      "epoch": 0.8277015258134188,
+      "grad_norm": 0.945472776889801,
+      "learning_rate": 8.87419633291886e-06,
+      "loss": 1.651,
+      "step": 1485
+    },
+    {
+      "epoch": 0.8304883996377064,
+      "grad_norm": 1.0160605907440186,
+      "learning_rate": 8.599558442598998e-06,
+      "loss": 1.5852,
+      "step": 1490
+    },
+    {
+      "epoch": 0.833275273461994,
+      "grad_norm": 1.047103762626648,
+      "learning_rate": 8.328837035318448e-06,
+      "loss": 1.6926,
+      "step": 1495
+    },
+    {
+      "epoch": 0.8360621472862816,
+      "grad_norm": 0.9703435897827148,
+      "learning_rate": 8.06205772133063e-06,
+      "loss": 1.5367,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8388490211105692,
+      "grad_norm": 1.0638253688812256,
+      "learning_rate": 7.799245737966821e-06,
+      "loss": 1.5853,
+      "step": 1505
+    },
+    {
+      "epoch": 0.8416358949348568,
+      "grad_norm": 1.0305513143539429,
+      "learning_rate": 7.540425947248697e-06,
+      "loss": 1.6552,
+      "step": 1510
+    },
+    {
+      "epoch": 0.8444227687591445,
+      "grad_norm": 0.8863044381141663,
+      "learning_rate": 7.28562283353637e-06,
+      "loss": 1.627,
+      "step": 1515
+    },
+    {
+      "epoch": 0.847209642583432,
+      "grad_norm": 0.9131430387496948,
+      "learning_rate": 7.034860501212243e-06,
+      "loss": 1.6254,
+      "step": 1520
+    },
+    {
+      "epoch": 0.8499965164077197,
+      "grad_norm": 1.0161089897155762,
+      "learning_rate": 6.788162672400583e-06,
+      "loss": 1.7087,
+      "step": 1525
+    },
+    {
+      "epoch": 0.8527833902320072,
+      "grad_norm": 0.9403210878372192,
+      "learning_rate": 6.5455526847235825e-06,
+      "loss": 1.6491,
+      "step": 1530
+    },
+    {
+      "epoch": 0.8555702640562949,
+      "grad_norm": 0.9508659243583679,
+      "learning_rate": 6.307053489093506e-06,
+      "loss": 1.6222,
+      "step": 1535
+    },
+    {
+      "epoch": 0.8583571378805824,
+      "grad_norm": 0.9709882140159607,
+      "learning_rate": 6.072687647541553e-06,
+      "loss": 1.6431,
+      "step": 1540
+    },
+    {
+      "epoch": 0.8611440117048701,
+      "grad_norm": 0.9428046941757202,
+      "learning_rate": 5.842477331083518e-06,
+      "loss": 1.6559,
+      "step": 1545
+    },
+    {
+      "epoch": 0.8639308855291576,
+      "grad_norm": 0.9151241779327393,
+      "learning_rate": 5.616444317622388e-06,
+      "loss": 1.5556,
+      "step": 1550
+    },
+    {
+      "epoch": 0.8667177593534453,
+      "grad_norm": 0.9186306595802307,
+      "learning_rate": 5.394609989888161e-06,
+      "loss": 1.6637,
+      "step": 1555
+    },
+    {
+      "epoch": 0.8695046331777329,
+      "grad_norm": 1.1897034645080566,
+      "learning_rate": 5.176995333415019e-06,
+      "loss": 1.6557,
+      "step": 1560
+    },
+    {
+      "epoch": 0.8722915070020205,
+      "grad_norm": 1.0049179792404175,
+      "learning_rate": 4.963620934556168e-06,
+      "loss": 1.6551,
+      "step": 1565
+    },
+    {
+      "epoch": 0.8750783808263081,
+      "grad_norm": 0.9597494602203369,
+      "learning_rate": 4.754506978536227e-06,
+      "loss": 1.6064,
+      "step": 1570
+    },
+    {
+      "epoch": 0.8778652546505957,
+      "grad_norm": 0.8873302936553955,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 1.6245,
+      "step": 1575
+    },
+    {
+      "epoch": 0.8806521284748833,
+      "grad_norm": 0.8784957528114319,
+      "learning_rate": 4.3491391188503264e-06,
+      "loss": 1.6031,
+      "step": 1580
+    },
+    {
+      "epoch": 0.8834390022991709,
+      "grad_norm": 1.0219107866287231,
+      "learning_rate": 4.152923562996297e-06,
+      "loss": 1.5441,
+      "step": 1585
+    },
+    {
+      "epoch": 0.8862258761234585,
+      "grad_norm": 0.9388402700424194,
+      "learning_rate": 3.961045141977376e-06,
+      "loss": 1.6366,
+      "step": 1590
+    },
+    {
+      "epoch": 0.8890127499477462,
+      "grad_norm": 0.9844707250595093,
+      "learning_rate": 3.773522007498065e-06,
+      "loss": 1.6457,
+      "step": 1595
+    },
+    {
+      "epoch": 0.8917996237720337,
+      "grad_norm": 0.941916286945343,
+      "learning_rate": 3.590371899252659e-06,
+      "loss": 1.6043,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8945864975963214,
+      "grad_norm": 0.9494262337684631,
+      "learning_rate": 3.4116121432469615e-06,
+      "loss": 1.588,
+      "step": 1605
+    },
+    {
+      "epoch": 0.8973733714206089,
+      "grad_norm": 0.9501243233680725,
+      "learning_rate": 3.237259650159402e-06,
+      "loss": 1.6057,
+      "step": 1610
+    },
+    {
+      "epoch": 0.9001602452448966,
+      "grad_norm": 1.0099127292633057,
+      "learning_rate": 3.0673309137411564e-06,
+      "loss": 1.6564,
+      "step": 1615
+    },
+    {
+      "epoch": 0.9029471190691841,
+      "grad_norm": 1.011672854423523,
+      "learning_rate": 2.9018420092558786e-06,
+      "loss": 1.588,
+      "step": 1620
+    },
+    {
+      "epoch": 0.9057339928934718,
+      "grad_norm": 0.9527240991592407,
+      "learning_rate": 2.7408085919590264e-06,
+      "loss": 1.6918,
+      "step": 1625
+    },
+    {
+      "epoch": 0.9085208667177593,
+      "grad_norm": 0.9475979804992676,
+      "learning_rate": 2.584245895616788e-06,
+      "loss": 1.6399,
+      "step": 1630
+    },
+    {
+      "epoch": 0.911307740542047,
+      "grad_norm": 1.0325227975845337,
+      "learning_rate": 2.4321687310650487e-06,
+      "loss": 1.677,
+      "step": 1635
+    },
+    {
+      "epoch": 0.9140946143663345,
+      "grad_norm": 0.9847766757011414,
+      "learning_rate": 2.2845914848082127e-06,
+      "loss": 1.6693,
+      "step": 1640
+    },
+    {
+      "epoch": 0.9168814881906222,
+      "grad_norm": 1.0612833499908447,
+      "learning_rate": 2.1415281176583203e-06,
+      "loss": 1.6191,
+      "step": 1645
+    },
+    {
+      "epoch": 0.9196683620149098,
+      "grad_norm": 1.0091543197631836,
+      "learning_rate": 2.0029921634142632e-06,
+      "loss": 1.7255,
+      "step": 1650
+    },
+    {
+      "epoch": 0.9224552358391974,
+      "grad_norm": 1.0188473463058472,
+      "learning_rate": 1.8689967275815679e-06,
+      "loss": 1.6559,
+      "step": 1655
+    },
+    {
+      "epoch": 0.925242109663485,
+      "grad_norm": 0.9920323491096497,
+      "learning_rate": 1.7395544861325718e-06,
+      "loss": 1.6751,
+      "step": 1660
+    },
+    {
+      "epoch": 0.9280289834877726,
+      "grad_norm": 0.9998114705085754,
+      "learning_rate": 1.614677684307264e-06,
+      "loss": 1.6378,
+      "step": 1665
+    },
+    {
+      "epoch": 0.9308158573120602,
+      "grad_norm": 0.9813428521156311,
+      "learning_rate": 1.494378135454938e-06,
+      "loss": 1.633,
+      "step": 1670
+    },
+    {
+      "epoch": 0.9336027311363478,
+      "grad_norm": 0.9274668097496033,
+      "learning_rate": 1.3786672199165962e-06,
+      "loss": 1.6576,
+      "step": 1675
+    },
+    {
+      "epoch": 0.9363896049606354,
+      "grad_norm": 0.9314688444137573,
+      "learning_rate": 1.2675558839483848e-06,
+      "loss": 1.5988,
+      "step": 1680
+    },
+    {
+      "epoch": 0.939176478784923,
+      "grad_norm": 0.9858189225196838,
+      "learning_rate": 1.1610546386860988e-06,
+      "loss": 1.6311,
+      "step": 1685
+    },
+    {
+      "epoch": 0.9419633526092106,
+      "grad_norm": 1.005400538444519,
+      "learning_rate": 1.0591735591507946e-06,
+      "loss": 1.6264,
+      "step": 1690
+    },
+    {
+      "epoch": 0.9447502264334983,
+      "grad_norm": 1.0077372789382935,
+      "learning_rate": 9.619222832957243e-07,
+      "loss": 1.6273,
+      "step": 1695
+    },
+    {
+      "epoch": 0.9475371002577858,
+      "grad_norm": 0.9848856925964355,
+      "learning_rate": 8.693100110945484e-07,
+      "loss": 1.6123,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9503239740820735,
+      "grad_norm": 0.9205525517463684,
+      "learning_rate": 7.813455036710715e-07,
+      "loss": 1.6065,
+      "step": 1705
+    },
+    {
+      "epoch": 0.953110847906361,
+      "grad_norm": 0.9617009162902832,
+      "learning_rate": 6.980370824703763e-07,
+      "loss": 1.67,
+      "step": 1710
+    },
+    {
+      "epoch": 0.9558977217306487,
+      "grad_norm": 1.0937501192092896,
+      "learning_rate": 6.193926284716711e-07,
+      "loss": 1.5918,
+      "step": 1715
+    },
+    {
+      "epoch": 0.9586845955549362,
+      "grad_norm": 0.9189473986625671,
+      "learning_rate": 5.454195814427021e-07,
+      "loss": 1.6965,
+      "step": 1720
+    },
+    {
+      "epoch": 0.9614714693792239,
+      "grad_norm": 0.9764816761016846,
+      "learning_rate": 4.76124939235989e-07,
+      "loss": 1.5873,
+      "step": 1725
+    },
+    {
+      "epoch": 0.9642583432035114,
+      "grad_norm": 0.9174162149429321,
+      "learning_rate": 4.1151525712680996e-07,
+      "loss": 1.5511,
+      "step": 1730
+    },
+    {
+      "epoch": 0.9670452170277991,
+      "grad_norm": 1.0921601057052612,
+      "learning_rate": 3.515966471930643e-07,
+      "loss": 1.7006,
+      "step": 1735
+    },
+    {
+      "epoch": 0.9698320908520867,
+      "grad_norm": 0.9906566143035889,
+      "learning_rate": 2.963747777370907e-07,
+      "loss": 1.6587,
+      "step": 1740
+    },
+    {
+      "epoch": 0.9726189646763743,
+      "grad_norm": 1.0743408203125,
+      "learning_rate": 2.458548727494292e-07,
+      "loss": 1.5564,
+      "step": 1745
+    },
+    {
+      "epoch": 0.9754058385006619,
+      "grad_norm": 0.9558684229850769,
+      "learning_rate": 2.0004171141464467e-07,
+      "loss": 1.6312,
+      "step": 1750
+    },
+    {
+      "epoch": 0.9781927123249495,
+      "grad_norm": 1.00477135181427,
+      "learning_rate": 1.589396276591937e-07,
+      "loss": 1.613,
+      "step": 1755
+    },
+    {
+      "epoch": 0.9809795861492371,
+      "grad_norm": 1.034407615661621,
+      "learning_rate": 1.225525097414637e-07,
+      "loss": 1.5766,
+      "step": 1760
+    },
+    {
+      "epoch": 0.9837664599735247,
+      "grad_norm": 1.0314751863479614,
+      "learning_rate": 9.088379988392848e-08,
+      "loss": 1.6248,
+      "step": 1765
+    },
+    {
+      "epoch": 0.9865533337978123,
+      "grad_norm": 0.9959791302680969,
+      "learning_rate": 6.393649394749734e-08,
+      "loss": 1.6185,
+      "step": 1770
+    },
+    {
+      "epoch": 0.9893402076221,
+      "grad_norm": 1.0470571517944336,
+      "learning_rate": 4.171314114815306e-08,
+      "loss": 1.6926,
+      "step": 1775
+    },
+    {
+      "epoch": 0.9921270814463875,
+      "grad_norm": 1.0142252445220947,
+      "learning_rate": 2.4215843815733607e-08,
+      "loss": 1.5745,
+      "step": 1780
+    },
+    {
+      "epoch": 0.9949139552706752,
+      "grad_norm": 0.8373370170593262,
+      "learning_rate": 1.1446257195119048e-08,
+      "loss": 1.6419,
+      "step": 1785
+    },
+    {
+      "epoch": 0.9977008290949627,
+      "grad_norm": 1.0657517910003662,
+      "learning_rate": 3.4055892895901167e-09,
+      "loss": 1.6516,
+      "step": 1790
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.7746706008911133,
+      "learning_rate": 9.460074656963969e-11,
+      "loss": 1.7167,
+      "step": 1795
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1795,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.029161804649267e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}