Upload merged Qwen3-4B-Instruct-2507 model (auto-generated README)

.gitattributes

@@ -33,3 +33,6 @@ 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-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1506/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,72 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+datasets:
+- u-10bei/sft_alfworld_trajectory_dataset_v5
+- u-10bei/dbbench_sft_dataset_react
+- u-10bei/dbbench_sft_dataset_react_v2
+- u-10bei/dbbench_sft_dataset_react_v3
+- u-10bei/dbbench_sft_dataset_react_v4
+language:
+- en
+license: apache-2.0
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- lora
+- agent
+- tool-use
+- alfworld
+- dbbench
+---
+
+# Qwen3-4B ALFWorld+DBBench Mixed LoRA Adapter (r=64)
+
+This repository provides a **LoRA adapter** fine-tuned from
+**Qwen/Qwen3-4B-Instruct-2507** using **LoRA + Unsloth**.
+
+This repository contains **LoRA adapter weights only**.
+The base model must be loaded separately.
+
+## Training Objective
+
+This adapter is trained to improve **multi-turn agent task performance**
+on ALFWorld (household tasks) and DBBench (database operations).
+
+Loss is applied to **all assistant turns** in the multi-turn trajectory,
+enabling the model to learn environment observation, action selection,
+tool use, and recovery from errors.
+
+## Training Configuration
+
+- Base model: Qwen/Qwen3-4B-Instruct-2507
+- Method: LoRA (full precision base)
+- Max sequence length: 2048
+- Epochs: 3
+- Learning rate: 2e-04
+- LoRA: r=64, alpha=128
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+base = "Qwen/Qwen3-4B-Instruct-2507"
+adapter = "your_id/your-repo"
+
+tokenizer = AutoTokenizer.from_pretrained(base)
+model = AutoModelForCausalLM.from_pretrained(
+    base,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+model = PeftModel.from_pretrained(model, adapter)
+```
+
+## Sources & Terms (IMPORTANT)
+
+Training data: u-10bei/sft_alfworld_trajectory_dataset_v5 + u-10bei/dbbench_sft_dataset_react v1-v4 (weak categories only)
+
+Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
+Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "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": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0c064570a762cc303647cc94c60408cc6ab6fd213dc61a3c574df9efd5fea9
+size 528550256

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,86 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen3-4B-Instruct-2507
+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 0.13.2

checkpoint-1500/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "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": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "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:fea45b35412f87d2be5e01d215c397f17d6370f4993cfc8f5709d82cc756b034
+size 528550256

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 +1,86 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7abcdde389d19bdb4ec865ea65ec839c83a7b3414b8269904c0707964d787f9
+size 1057397963

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aa9ba6f2dfc92a964250f44b423fc475d3213d62a9b60120603ece4ce5b1acb
+size 14645

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:447b4c3a7295b83e4e7652770c31f15a8805b40bf9360720bfeaf9cf33f50b53
+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": "<|vision_pad|>",
+    "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": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,1484 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9895261845386534,
+  "eval_steps": 30,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0199501246882793,
+      "grad_norm": 9.905351638793945,
+      "learning_rate": 1.1920529801324503e-05,
+      "loss": 2.4681,
+      "step": 10
+    },
+    {
+      "epoch": 0.0399002493765586,
+      "grad_norm": 1.0738855600357056,
+      "learning_rate": 2.5165562913907287e-05,
+      "loss": 1.192,
+      "step": 20
+    },
+    {
+      "epoch": 0.059850374064837904,
+      "grad_norm": 0.9622387290000916,
+      "learning_rate": 3.841059602649007e-05,
+      "loss": 0.651,
+      "step": 30
+    },
+    {
+      "epoch": 0.059850374064837904,
+      "eval_loss": 0.5571362376213074,
+      "eval_runtime": 48.7371,
+      "eval_samples_per_second": 4.329,
+      "eval_steps_per_second": 2.175,
+      "step": 30
+    },
+    {
+      "epoch": 0.0798004987531172,
+      "grad_norm": 0.6049273610115051,
+      "learning_rate": 5.165562913907285e-05,
+      "loss": 0.5074,
+      "step": 40
+    },
+    {
+      "epoch": 0.09975062344139651,
+      "grad_norm": 0.6833104491233826,
+      "learning_rate": 6.490066225165563e-05,
+      "loss": 0.3756,
+      "step": 50
+    },
+    {
+      "epoch": 0.11970074812967581,
+      "grad_norm": 0.5208126902580261,
+      "learning_rate": 7.814569536423842e-05,
+      "loss": 0.3065,
+      "step": 60
+    },
+    {
+      "epoch": 0.11970074812967581,
+      "eval_loss": 0.25738316774368286,
+      "eval_runtime": 48.1494,
+      "eval_samples_per_second": 4.382,
+      "eval_steps_per_second": 2.201,
+      "step": 60
+    },
+    {
+      "epoch": 0.1396508728179551,
+      "grad_norm": 0.5192306041717529,
+      "learning_rate": 9.13907284768212e-05,
+      "loss": 0.2578,
+      "step": 70
+    },
+    {
+      "epoch": 0.1596009975062344,
+      "grad_norm": 0.5098096132278442,
+      "learning_rate": 0.00010463576158940399,
+      "loss": 0.2096,
+      "step": 80
+    },
+    {
+      "epoch": 0.17955112219451372,
+      "grad_norm": 0.5306766629219055,
+      "learning_rate": 0.00011788079470198677,
+      "loss": 0.1899,
+      "step": 90
+    },
+    {
+      "epoch": 0.17955112219451372,
+      "eval_loss": 0.1828010529279709,
+      "eval_runtime": 48.0843,
+      "eval_samples_per_second": 4.388,
+      "eval_steps_per_second": 2.204,
+      "step": 90
+    },
+    {
+      "epoch": 0.19950124688279303,
+      "grad_norm": 0.3457268178462982,
+      "learning_rate": 0.00013112582781456955,
+      "loss": 0.1848,
+      "step": 100
+    },
+    {
+      "epoch": 0.2194513715710723,
+      "grad_norm": 0.47407814860343933,
+      "learning_rate": 0.00014437086092715232,
+      "loss": 0.1736,
+      "step": 110
+    },
+    {
+      "epoch": 0.23940149625935161,
+      "grad_norm": 0.3515409827232361,
+      "learning_rate": 0.00015761589403973512,
+      "loss": 0.1676,
+      "step": 120
+    },
+    {
+      "epoch": 0.23940149625935161,
+      "eval_loss": 0.1554146409034729,
+      "eval_runtime": 48.3317,
+      "eval_samples_per_second": 4.366,
+      "eval_steps_per_second": 2.193,
+      "step": 120
+    },
+    {
+      "epoch": 0.2593516209476309,
+      "grad_norm": 0.4131653904914856,
+      "learning_rate": 0.0001708609271523179,
+      "loss": 0.1643,
+      "step": 130
+    },
+    {
+      "epoch": 0.2793017456359102,
+      "grad_norm": 0.7977883219718933,
+      "learning_rate": 0.0001841059602649007,
+      "loss": 0.1543,
+      "step": 140
+    },
+    {
+      "epoch": 0.29925187032418954,
+      "grad_norm": 0.32713833451271057,
+      "learning_rate": 0.00019735099337748346,
+      "loss": 0.1569,
+      "step": 150
+    },
+    {
+      "epoch": 0.29925187032418954,
+      "eval_loss": 0.14544202387332916,
+      "eval_runtime": 48.2076,
+      "eval_samples_per_second": 4.377,
+      "eval_steps_per_second": 2.199,
+      "step": 150
+    },
+    {
+      "epoch": 0.3192019950124688,
+      "grad_norm": 0.3618054986000061,
+      "learning_rate": 0.00019998279880250371,
+      "loss": 0.1661,
+      "step": 160
+    },
+    {
+      "epoch": 0.33915211970074816,
+      "grad_norm": 0.5105156302452087,
+      "learning_rate": 0.0001999129290795728,
+      "loss": 0.1542,
+      "step": 170
+    },
+    {
+      "epoch": 0.35910224438902744,
+      "grad_norm": 0.3221360445022583,
+      "learning_rate": 0.00019978935328445287,
+      "loss": 0.1437,
+      "step": 180
+    },
+    {
+      "epoch": 0.35910224438902744,
+      "eval_loss": 0.1328973025083542,
+      "eval_runtime": 48.1577,
+      "eval_samples_per_second": 4.381,
+      "eval_steps_per_second": 2.201,
+      "step": 180
+    },
+    {
+      "epoch": 0.3790523690773067,
+      "grad_norm": 0.39137646555900574,
+      "learning_rate": 0.000199612137842687,
+      "loss": 0.1511,
+      "step": 190
+    },
+    {
+      "epoch": 0.39900249376558605,
+      "grad_norm": 0.29165342450141907,
+      "learning_rate": 0.00019938137801267064,
+      "loss": 0.1456,
+      "step": 200
+    },
+    {
+      "epoch": 0.41895261845386533,
+      "grad_norm": 0.2816756069660187,
+      "learning_rate": 0.0001990971978344475,
+      "loss": 0.1271,
+      "step": 210
+    },
+    {
+      "epoch": 0.41895261845386533,
+      "eval_loss": 0.13140253722667694,
+      "eval_runtime": 47.9806,
+      "eval_samples_per_second": 4.398,
+      "eval_steps_per_second": 2.209,
+      "step": 210
+    },
+    {
+      "epoch": 0.4389027431421446,
+      "grad_norm": 0.6542349457740784,
+      "learning_rate": 0.00019875975006303435,
+      "loss": 0.1409,
+      "step": 220
+    },
+    {
+      "epoch": 0.45885286783042395,
+      "grad_norm": 0.2651802599430084,
+      "learning_rate": 0.00019836921608631114,
+      "loss": 0.1474,
+      "step": 230
+    },
+    {
+      "epoch": 0.47880299251870323,
+      "grad_norm": 0.2070140242576599,
+      "learning_rate": 0.00019792580582751935,
+      "loss": 0.1369,
+      "step": 240
+    },
+    {
+      "epoch": 0.47880299251870323,
+      "eval_loss": 0.12214324623346329,
+      "eval_runtime": 48.2216,
+      "eval_samples_per_second": 4.376,
+      "eval_steps_per_second": 2.198,
+      "step": 240
+    },
+    {
+      "epoch": 0.49875311720698257,
+      "grad_norm": 0.16217675805091858,
+      "learning_rate": 0.00019742975763242248,
+      "loss": 0.1342,
+      "step": 250
+    },
+    {
+      "epoch": 0.5187032418952618,
+      "grad_norm": 0.17511174082756042,
+      "learning_rate": 0.00019688133814118843,
+      "loss": 0.1233,
+      "step": 260
+    },
+    {
+      "epoch": 0.5386533665835411,
+      "grad_norm": 0.16075153648853302,
+      "learning_rate": 0.0001962808421450624,
+      "loss": 0.1333,
+      "step": 270
+    },
+    {
+      "epoch": 0.5386533665835411,
+      "eval_loss": 0.11943639069795609,
+      "eval_runtime": 48.0763,
+      "eval_samples_per_second": 4.389,
+      "eval_steps_per_second": 2.205,
+      "step": 270
+    },
+    {
+      "epoch": 0.5586034912718204,
+      "grad_norm": 0.1652883142232895,
+      "learning_rate": 0.00019562859242790853,
+      "loss": 0.1308,
+      "step": 280
+    },
+    {
+      "epoch": 0.5785536159600998,
+      "grad_norm": 0.2698552906513214,
+      "learning_rate": 0.00019492493959270398,
+      "loss": 0.1378,
+      "step": 290
+    },
+    {
+      "epoch": 0.5985037406483791,
+      "grad_norm": 0.11757837980985641,
+      "learning_rate": 0.00019417026187307985,
+      "loss": 0.1186,
+      "step": 300
+    },
+    {
+      "epoch": 0.5985037406483791,
+      "eval_loss": 0.11812838912010193,
+      "eval_runtime": 48.1525,
+      "eval_samples_per_second": 4.382,
+      "eval_steps_per_second": 2.201,
+      "step": 300
+    },
+    {
+      "epoch": 0.6184538653366584,
+      "grad_norm": 0.1514044553041458,
+      "learning_rate": 0.00019336496493000985,
+      "loss": 0.1329,
+      "step": 310
+    },
+    {
+      "epoch": 0.6384039900249376,
+      "grad_norm": 0.1278185248374939,
+      "learning_rate": 0.00019250948163375563,
+      "loss": 0.1311,
+      "step": 320
+    },
+    {
+      "epoch": 0.6583541147132169,
+      "grad_norm": 0.14280234277248383,
+      "learning_rate": 0.00019160427183118674,
+      "loss": 0.1281,
+      "step": 330
+    },
+    {
+      "epoch": 0.6583541147132169,
+      "eval_loss": 0.11799625307321548,
+      "eval_runtime": 48.1223,
+      "eval_samples_per_second": 4.385,
+      "eval_steps_per_second": 2.203,
+      "step": 330
+    },
+    {
+      "epoch": 0.6783042394014963,
+      "grad_norm": 0.141315296292305,
+      "learning_rate": 0.0001906498220985997,
+      "loss": 0.1131,
+      "step": 340
+    },
+    {
+      "epoch": 0.6982543640897756,
+      "grad_norm": 0.11978308856487274,
+      "learning_rate": 0.0001896466454801692,
+      "loss": 0.1294,
+      "step": 350
+    },
+    {
+      "epoch": 0.7182044887780549,
+      "grad_norm": 0.2772483825683594,
+      "learning_rate": 0.00018859528121217204,
+      "loss": 0.1297,
+      "step": 360
+    },
+    {
+      "epoch": 0.7182044887780549,
+      "eval_loss": 0.11690443754196167,
+      "eval_runtime": 48.1421,
+      "eval_samples_per_second": 4.383,
+      "eval_steps_per_second": 2.202,
+      "step": 360
+    },
+    {
+      "epoch": 0.7381546134663342,
+      "grad_norm": 0.13961242139339447,
+      "learning_rate": 0.00018749629443313233,
+      "loss": 0.1249,
+      "step": 370
+    },
+    {
+      "epoch": 0.7581047381546134,
+      "grad_norm": 0.17335286736488342,
+      "learning_rate": 0.0001863502758800431,
+      "loss": 0.1255,
+      "step": 380
+    },
+    {
+      "epoch": 0.7780548628428927,
+      "grad_norm": 0.15879972279071808,
+      "learning_rate": 0.00018515784157082822,
+      "loss": 0.1175,
+      "step": 390
+    },
+    {
+      "epoch": 0.7780548628428927,
+      "eval_loss": 0.11526743322610855,
+      "eval_runtime": 48.2061,
+      "eval_samples_per_second": 4.377,
+      "eval_steps_per_second": 2.199,
+      "step": 390
+    },
+    {
+      "epoch": 0.7980049875311721,
+      "grad_norm": 0.11807694286108017,
+      "learning_rate": 0.00018391963247321513,
+      "loss": 0.1178,
+      "step": 400
+    },
+    {
+      "epoch": 0.8179551122194514,
+      "grad_norm": 0.11275653541088104,
+      "learning_rate": 0.00018263631416019617,
+      "loss": 0.1195,
+      "step": 410
+    },
+    {
+      "epoch": 0.8379052369077307,
+      "grad_norm": 0.12657803297042847,
+      "learning_rate": 0.000181308576452264,
+      "loss": 0.1182,
+      "step": 420
+    },
+    {
+      "epoch": 0.8379052369077307,
+      "eval_loss": 0.11410157382488251,
+      "eval_runtime": 48.3064,
+      "eval_samples_per_second": 4.368,
+      "eval_steps_per_second": 2.194,
+      "step": 420
+    },
+    {
+      "epoch": 0.85785536159601,
+      "grad_norm": 0.15267746150493622,
+      "learning_rate": 0.00017993713304661322,
+      "loss": 0.1216,
+      "step": 430
+    },
+    {
+      "epoch": 0.8778054862842892,
+      "grad_norm": 0.11593750864267349,
+      "learning_rate": 0.00017852272113350767,
+      "loss": 0.1329,
+      "step": 440
+    },
+    {
+      "epoch": 0.8977556109725686,
+      "grad_norm": 0.12276951223611832,
+      "learning_rate": 0.0001770661010000194,
+      "loss": 0.1189,
+      "step": 450
+    },
+    {
+      "epoch": 0.8977556109725686,
+      "eval_loss": 0.11431698501110077,
+      "eval_runtime": 48.1715,
+      "eval_samples_per_second": 4.38,
+      "eval_steps_per_second": 2.2,
+      "step": 450
+    },
+    {
+      "epoch": 0.9177057356608479,
+      "grad_norm": 0.11874907463788986,
+      "learning_rate": 0.00017556805562135255,
+      "loss": 0.1313,
+      "step": 460
+    },
+    {
+      "epoch": 0.9376558603491272,
+      "grad_norm": 0.22391599416732788,
+      "learning_rate": 0.00017402939023997157,
+      "loss": 0.1127,
+      "step": 470
+    },
+    {
+      "epoch": 0.9576059850374065,
+      "grad_norm": 0.09968144446611404,
+      "learning_rate": 0.00017245093193276047,
+      "loss": 0.118,
+      "step": 480
+    },
+    {
+      "epoch": 0.9576059850374065,
+      "eval_loss": 0.11578261852264404,
+      "eval_runtime": 48.1681,
+      "eval_samples_per_second": 4.38,
+      "eval_steps_per_second": 2.201,
+      "step": 480
+    },
+    {
+      "epoch": 0.9775561097256857,
+      "grad_norm": 0.09711634367704391,
+      "learning_rate": 0.00017083352916644494,
+      "loss": 0.1184,
+      "step": 490
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "grad_norm": 0.0991770550608635,
+      "learning_rate": 0.0001691780513415173,
+      "loss": 0.1215,
+      "step": 500
+    },
+    {
+      "epoch": 1.0159600997506235,
+      "grad_norm": 0.09751348197460175,
+      "learning_rate": 0.00016748538832490857,
+      "loss": 0.1206,
+      "step": 510
+    },
+    {
+      "epoch": 1.0159600997506235,
+      "eval_loss": 0.1116185411810875,
+      "eval_runtime": 48.1046,
+      "eval_samples_per_second": 4.386,
+      "eval_steps_per_second": 2.204,
+      "step": 510
+    },
+    {
+      "epoch": 1.0359102244389027,
+      "grad_norm": 0.10556904226541519,
+      "learning_rate": 0.0001657564499716595,
+      "loss": 0.1135,
+      "step": 520
+    },
+    {
+      "epoch": 1.055860349127182,
+      "grad_norm": 0.15284962952136993,
+      "learning_rate": 0.00016399216563584736,
+      "loss": 0.1218,
+      "step": 530
+    },
+    {
+      "epoch": 1.0758104738154612,
+      "grad_norm": 0.09085577726364136,
+      "learning_rate": 0.00016219348367103132,
+      "loss": 0.1171,
+      "step": 540
+    },
+    {
+      "epoch": 1.0758104738154612,
+      "eval_loss": 0.11126323789358139,
+      "eval_runtime": 48.6749,
+      "eval_samples_per_second": 4.335,
+      "eval_steps_per_second": 2.178,
+      "step": 540
+    },
+    {
+      "epoch": 1.0957605985037406,
+      "grad_norm": 0.12901732325553894,
+      "learning_rate": 0.00016036137092048525,
+      "loss": 0.1188,
+      "step": 550
+    },
+    {
+      "epoch": 1.11571072319202,
+      "grad_norm": 0.09154735505580902,
+      "learning_rate": 0.0001584968121974915,
+      "loss": 0.1232,
+      "step": 560
+    },
+    {
+      "epoch": 1.1356608478802992,
+      "grad_norm": 0.10134833306074142,
+      "learning_rate": 0.00015660080975597553,
+      "loss": 0.1205,
+      "step": 570
+    },
+    {
+      "epoch": 1.1356608478802992,
+      "eval_loss": 0.11302559077739716,
+      "eval_runtime": 48.709,
+      "eval_samples_per_second": 4.332,
+      "eval_steps_per_second": 2.176,
+      "step": 570
+    },
+    {
+      "epoch": 1.1556109725685786,
+      "grad_norm": 0.14130111038684845,
+      "learning_rate": 0.00015467438275176568,
+      "loss": 0.1214,
+      "step": 580
+    },
+    {
+      "epoch": 1.1755610972568578,
+      "grad_norm": 0.1193675845861435,
+      "learning_rate": 0.0001527185666947675,
+      "loss": 0.1173,
+      "step": 590
+    },
+    {
+      "epoch": 1.1955112219451371,
+      "grad_norm": 0.06070871651172638,
+      "learning_rate": 0.00015073441289234745,
+      "loss": 0.1189,
+      "step": 600
+    },
+    {
+      "epoch": 1.1955112219451371,
+      "eval_loss": 0.11231612414121628,
+      "eval_runtime": 48.6333,
+      "eval_samples_per_second": 4.339,
+      "eval_steps_per_second": 2.18,
+      "step": 600
+    },
+    {
+      "epoch": 1.2154613466334165,
+      "grad_norm": 0.08564524352550507,
+      "learning_rate": 0.00014872298788422497,
+      "loss": 0.1194,
+      "step": 610
+    },
+    {
+      "epoch": 1.2354114713216957,
+      "grad_norm": 0.1110881119966507,
+      "learning_rate": 0.00014668537286917664,
+      "loss": 0.117,
+      "step": 620
+    },
+    {
+      "epoch": 1.255361596009975,
+      "grad_norm": 0.10232548415660858,
+      "learning_rate": 0.00014462266312386085,
+      "loss": 0.1235,
+      "step": 630
+    },
+    {
+      "epoch": 1.255361596009975,
+      "eval_loss": 0.11166342347860336,
+      "eval_runtime": 48.6028,
+      "eval_samples_per_second": 4.341,
+      "eval_steps_per_second": 2.181,
+      "step": 630
+    },
+    {
+      "epoch": 1.2753117206982543,
+      "grad_norm": 0.08676601946353912,
+      "learning_rate": 0.00014253596741407507,
+      "loss": 0.1281,
+      "step": 640
+    },
+    {
+      "epoch": 1.2952618453865337,
+      "grad_norm": 0.09077729284763336,
+      "learning_rate": 0.0001404264073987623,
+      "loss": 0.1242,
+      "step": 650
+    },
+    {
+      "epoch": 1.315211970074813,
+      "grad_norm": 0.3734651505947113,
+      "learning_rate": 0.00013829511702708727,
+      "loss": 0.1137,
+      "step": 660
+    },
+    {
+      "epoch": 1.315211970074813,
+      "eval_loss": 0.11021307855844498,
+      "eval_runtime": 48.6287,
+      "eval_samples_per_second": 4.339,
+      "eval_steps_per_second": 2.18,
+      "step": 660
+    },
+    {
+      "epoch": 1.3351620947630922,
+      "grad_norm": 0.09780021756887436,
+      "learning_rate": 0.00013614324192890592,
+      "loss": 0.1219,
+      "step": 670
+    },
+    {
+      "epoch": 1.3551122194513716,
+      "grad_norm": 0.09793366491794586,
+      "learning_rate": 0.00013397193879895671,
+      "loss": 0.1046,
+      "step": 680
+    },
+    {
+      "epoch": 1.3750623441396508,
+      "grad_norm": 0.11061827093362808,
+      "learning_rate": 0.00013178237477510374,
+      "loss": 0.1174,
+      "step": 690
+    },
+    {
+      "epoch": 1.3750623441396508,
+      "eval_loss": 0.1095186397433281,
+      "eval_runtime": 48.691,
+      "eval_samples_per_second": 4.333,
+      "eval_steps_per_second": 2.177,
+      "step": 690
+    },
+    {
+      "epoch": 1.3950124688279302,
+      "grad_norm": 0.11096978187561035,
+      "learning_rate": 0.0001295757268109666,
+      "loss": 0.1071,
+      "step": 700
+    },
+    {
+      "epoch": 1.4149625935162096,
+      "grad_norm": 0.10013638436794281,
+      "learning_rate": 0.0001273531810432741,
+      "loss": 0.1262,
+      "step": 710
+    },
+    {
+      "epoch": 1.4349127182044887,
+      "grad_norm": 0.12431971728801727,
+      "learning_rate": 0.00012511593215428141,
+      "loss": 0.1098,
+      "step": 720
+    },
+    {
+      "epoch": 1.4349127182044887,
+      "eval_loss": 0.10981423407793045,
+      "eval_runtime": 48.7018,
+      "eval_samples_per_second": 4.332,
+      "eval_steps_per_second": 2.177,
+      "step": 720
+    },
+    {
+      "epoch": 1.4548628428927681,
+      "grad_norm": 0.13086780905723572,
+      "learning_rate": 0.0001228651827295943,
+      "loss": 0.1142,
+      "step": 730
+    },
+    {
+      "epoch": 1.4748129675810473,
+      "grad_norm": 0.08466003090143204,
+      "learning_rate": 0.00012060214261174465,
+      "loss": 0.1144,
+      "step": 740
+    },
+    {
+      "epoch": 1.4947630922693267,
+      "grad_norm": 0.11653965711593628,
+      "learning_rate": 0.00011832802824986523,
+      "loss": 0.1183,
+      "step": 750
+    },
+    {
+      "epoch": 1.4947630922693267,
+      "eval_loss": 0.10894475877285004,
+      "eval_runtime": 48.6934,
+      "eval_samples_per_second": 4.333,
+      "eval_steps_per_second": 2.177,
+      "step": 750
+    },
+    {
+      "epoch": 1.514713216957606,
+      "grad_norm": 0.11816778779029846,
+      "learning_rate": 0.00011604406204581346,
+      "loss": 0.13,
+      "step": 760
+    },
+    {
+      "epoch": 1.5346633416458852,
+      "grad_norm": 0.09233927726745605,
+      "learning_rate": 0.00011375147169709519,
+      "loss": 0.109,
+      "step": 770
+    },
+    {
+      "epoch": 1.5546134663341646,
+      "grad_norm": 0.08808460831642151,
+      "learning_rate": 0.00011145148953694195,
+      "loss": 0.1145,
+      "step": 780
+    },
+    {
+      "epoch": 1.5546134663341646,
+      "eval_loss": 0.10957030206918716,
+      "eval_runtime": 48.6129,
+      "eval_samples_per_second": 4.34,
+      "eval_steps_per_second": 2.18,
+      "step": 780
+    },
+    {
+      "epoch": 1.5745635910224438,
+      "grad_norm": 0.0909830778837204,
+      "learning_rate": 0.00010914535187189654,
+      "loss": 0.1115,
+      "step": 790
+    },
+    {
+      "epoch": 1.5945137157107232,
+      "grad_norm": 0.08932233601808548,
+      "learning_rate": 0.00010683429831726252,
+      "loss": 0.1191,
+      "step": 800
+    },
+    {
+      "epoch": 1.6144638403990026,
+      "grad_norm": 0.08355925977230072,
+      "learning_rate": 0.0001045195711307756,
+      "loss": 0.1127,
+      "step": 810
+    },
+    {
+      "epoch": 1.6144638403990026,
+      "eval_loss": 0.10913572460412979,
+      "eval_runtime": 48.4393,
+      "eval_samples_per_second": 4.356,
+      "eval_steps_per_second": 2.188,
+      "step": 810
+    },
+    {
+      "epoch": 1.6344139650872818,
+      "grad_norm": 0.06819329410791397,
+      "learning_rate": 0.00010220241454485406,
+      "loss": 0.1098,
+      "step": 820
+    },
+    {
+      "epoch": 1.654364089775561,
+      "grad_norm": 0.6049116849899292,
+      "learning_rate": 9.988407409778838e-05,
+      "loss": 0.1141,
+      "step": 830
+    },
+    {
+      "epoch": 1.6743142144638403,
+      "grad_norm": 0.07323434203863144,
+      "learning_rate": 9.756579596422839e-05,
+      "loss": 0.1049,
+      "step": 840
+    },
+    {
+      "epoch": 1.6743142144638403,
+      "eval_loss": 0.10999356210231781,
+      "eval_runtime": 48.6539,
+      "eval_samples_per_second": 4.337,
+      "eval_steps_per_second": 2.179,
+      "step": 840
+    },
+    {
+      "epoch": 1.6942643391521197,
+      "grad_norm": 0.10413742810487747,
+      "learning_rate": 9.524882628532858e-05,
+      "loss": 0.1158,
+      "step": 850
+    },
+    {
+      "epoch": 1.714214463840399,
+      "grad_norm": 0.08523685485124588,
+      "learning_rate": 9.293441049891148e-05,
+      "loss": 0.115,
+      "step": 860
+    },
+    {
+      "epoch": 1.7341645885286783,
+      "grad_norm": 0.12683580815792084,
+      "learning_rate": 9.062379267000898e-05,
+      "loss": 0.1185,
+      "step": 870
+    },
+    {
+      "epoch": 1.7341645885286783,
+      "eval_loss": 0.10940343141555786,
+      "eval_runtime": 48.6011,
+      "eval_samples_per_second": 4.341,
+      "eval_steps_per_second": 2.181,
+      "step": 870
+    },
+    {
+      "epoch": 1.7541147132169574,
+      "grad_norm": 0.10133107006549835,
+      "learning_rate": 8.831821482214159e-05,
+      "loss": 0.1194,
+      "step": 880
+    },
+    {
+      "epoch": 1.7740648379052368,
+      "grad_norm": 0.08002304285764694,
+      "learning_rate": 8.601891626969514e-05,
+      "loss": 0.1178,
+      "step": 890
+    },
+    {
+      "epoch": 1.7940149625935162,
+      "grad_norm": 0.0782008096575737,
+      "learning_rate": 8.372713295175352e-05,
+      "loss": 0.1162,
+      "step": 900
+    },
+    {
+      "epoch": 1.7940149625935162,
+      "eval_loss": 0.10899555683135986,
+      "eval_runtime": 48.522,
+      "eval_samples_per_second": 4.349,
+      "eval_steps_per_second": 2.185,
+      "step": 900
+    },
+    {
+      "epoch": 1.8139650872817956,
+      "grad_norm": 0.08133247494697571,
+      "learning_rate": 8.14440967677461e-05,
+      "loss": 0.1234,
+      "step": 910
+    },
+    {
+      "epoch": 1.8339152119700748,
+      "grad_norm": 0.08592060953378677,
+      "learning_rate": 7.917103491526617e-05,
+      "loss": 0.1073,
+      "step": 920
+    },
+    {
+      "epoch": 1.853865336658354,
+      "grad_norm": 0.07544530183076859,
+      "learning_rate": 7.690916923041708e-05,
+      "loss": 0.1072,
+      "step": 930
+    },
+    {
+      "epoch": 1.853865336658354,
+      "eval_loss": 0.10886865854263306,
+      "eval_runtime": 48.4695,
+      "eval_samples_per_second": 4.353,
+      "eval_steps_per_second": 2.187,
+      "step": 930
+    },
+    {
+      "epoch": 1.8738154613466333,
+      "grad_norm": 0.10101612657308578,
+      "learning_rate": 7.465971553104014e-05,
+      "loss": 0.1109,
+      "step": 940
+    },
+    {
+      "epoch": 1.8937655860349127,
+      "grad_norm": 0.07430823147296906,
+      "learning_rate": 7.242388296317757e-05,
+      "loss": 0.108,
+      "step": 950
+    },
+    {
+      "epoch": 1.9137157107231921,
+      "grad_norm": 0.0772905945777893,
+      "learning_rate": 7.020287335112179e-05,
+      "loss": 0.1087,
+      "step": 960
+    },
+    {
+      "epoch": 1.9137157107231921,
+      "eval_loss": 0.10754832625389099,
+      "eval_runtime": 48.5946,
+      "eval_samples_per_second": 4.342,
+      "eval_steps_per_second": 2.181,
+      "step": 960
+    },
+    {
+      "epoch": 1.9336658354114713,
+      "grad_norm": 0.08496296405792236,
+      "learning_rate": 6.799788055140025e-05,
+      "loss": 0.1203,
+      "step": 970
+    },
+    {
+      "epoch": 1.9536159600997505,
+      "grad_norm": 0.07446739822626114,
+      "learning_rate": 6.58100898110432e-05,
+      "loss": 0.1158,
+      "step": 980
+    },
+    {
+      "epoch": 1.9735660847880299,
+      "grad_norm": 0.08105003088712692,
+      "learning_rate": 6.364067713047943e-05,
+      "loss": 0.1184,
+      "step": 990
+    },
+    {
+      "epoch": 1.9735660847880299,
+      "eval_loss": 0.1074095070362091,
+      "eval_runtime": 48.6824,
+      "eval_samples_per_second": 4.334,
+      "eval_steps_per_second": 2.177,
+      "step": 990
+    },
+    {
+      "epoch": 1.9935162094763093,
+      "grad_norm": 0.08692453801631927,
+      "learning_rate": 6.149080863140208e-05,
+      "loss": 0.1145,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0119700748129676,
+      "grad_norm": 0.0745435431599617,
+      "learning_rate": 5.9361639929944867e-05,
+      "loss": 0.1081,
+      "step": 1010
+    },
+    {
+      "epoch": 2.031920199501247,
+      "grad_norm": 0.08805131912231445,
+      "learning_rate": 5.7254315515505105e-05,
+      "loss": 0.1092,
+      "step": 1020
+    },
+    {
+      "epoch": 2.031920199501247,
+      "eval_loss": 0.10798249393701553,
+      "eval_runtime": 48.9954,
+      "eval_samples_per_second": 4.307,
+      "eval_steps_per_second": 2.163,
+      "step": 1020
+    },
+    {
+      "epoch": 2.051870324189526,
+      "grad_norm": 0.08542945981025696,
+      "learning_rate": 5.5169968135547655e-05,
+      "loss": 0.1185,
+      "step": 1030
+    },
+    {
+      "epoch": 2.0718204488778054,
+      "grad_norm": 0.08667082339525223,
+      "learning_rate": 5.310971818672077e-05,
+      "loss": 0.1107,
+      "step": 1040
+    },
+    {
+      "epoch": 2.0917705735660848,
+      "grad_norm": 0.0777161717414856,
+      "learning_rate": 5.1074673112610584e-05,
+      "loss": 0.1082,
+      "step": 1050
+    },
+    {
+      "epoch": 2.0917705735660848,
+      "eval_loss": 0.10762733221054077,
+      "eval_runtime": 49.1196,
+      "eval_samples_per_second": 4.296,
+      "eval_steps_per_second": 2.158,
+      "step": 1050
+    },
+    {
+      "epoch": 2.111720698254364,
+      "grad_norm": 0.06888756155967712,
+      "learning_rate": 4.906592680845829e-05,
+      "loss": 0.1075,
+      "step": 1060
+    },
+    {
+      "epoch": 2.1316708229426435,
+      "grad_norm": 0.09783507883548737,
+      "learning_rate": 4.7084559033160135e-05,
+      "loss": 0.1149,
+      "step": 1070
+    },
+    {
+      "epoch": 2.1516209476309225,
+      "grad_norm": 0.09118674695491791,
+      "learning_rate": 4.5131634828865845e-05,
+      "loss": 0.1127,
+      "step": 1080
+    },
+    {
+      "epoch": 2.1516209476309225,
+      "eval_loss": 0.10765193402767181,
+      "eval_runtime": 49.1258,
+      "eval_samples_per_second": 4.295,
+      "eval_steps_per_second": 2.158,
+      "step": 1080
+    },
+    {
+      "epoch": 2.171571072319202,
+      "grad_norm": 0.08113594353199005,
+      "learning_rate": 4.320820394848794e-05,
+      "loss": 0.1151,
+      "step": 1090
+    },
+    {
+      "epoch": 2.1915211970074813,
+      "grad_norm": 0.08070435374975204,
+      "learning_rate": 4.1315300291429174e-05,
+      "loss": 0.1093,
+      "step": 1100
+    },
+    {
+      "epoch": 2.2114713216957607,
+      "grad_norm": 0.07660377770662308,
+      "learning_rate": 3.9453941347832146e-05,
+      "loss": 0.1113,
+      "step": 1110
+    },
+    {
+      "epoch": 2.2114713216957607,
+      "eval_loss": 0.10742755234241486,
+      "eval_runtime": 48.9958,
+      "eval_samples_per_second": 4.306,
+      "eval_steps_per_second": 2.163,
+      "step": 1110
+    },
+    {
+      "epoch": 2.23142144638404,
+      "grad_norm": 0.08561329543590546,
+      "learning_rate": 3.762512765164895e-05,
+      "loss": 0.1096,
+      "step": 1120
+    },
+    {
+      "epoch": 2.251371571072319,
+      "grad_norm": 0.07384736835956573,
+      "learning_rate": 3.5829842242825374e-05,
+      "loss": 0.1071,
+      "step": 1130
+    },
+    {
+      "epoch": 2.2713216957605984,
+      "grad_norm": 0.089817114174366,
+      "learning_rate": 3.406905013888875e-05,
+      "loss": 0.1128,
+      "step": 1140
+    },
+    {
+      "epoch": 2.2713216957605984,
+      "eval_loss": 0.10679538547992706,
+      "eval_runtime": 49.1277,
+      "eval_samples_per_second": 4.295,
+      "eval_steps_per_second": 2.158,
+      "step": 1140
+    },
+    {
+      "epoch": 2.291271820448878,
+      "grad_norm": 0.0809311643242836,
+      "learning_rate": 3.234369781622315e-05,
+      "loss": 0.1055,
+      "step": 1150
+    },
+    {
+      "epoch": 2.311221945137157,
+      "grad_norm": 0.11156892031431198,
+      "learning_rate": 3.065471270131132e-05,
+      "loss": 0.1118,
+      "step": 1160
+    },
+    {
+      "epoch": 2.3311720698254366,
+      "grad_norm": 0.07891872525215149,
+      "learning_rate": 2.9003002672216106e-05,
+      "loss": 0.1146,
+      "step": 1170
+    },
+    {
+      "epoch": 2.3311720698254366,
+      "eval_loss": 0.1066785454750061,
+      "eval_runtime": 49.1277,
+      "eval_samples_per_second": 4.295,
+      "eval_steps_per_second": 2.158,
+      "step": 1170
+    },
+    {
+      "epoch": 2.3511221945137155,
+      "grad_norm": 0.08137693256139755,
+      "learning_rate": 2.738945557056999e-05,
+      "loss": 0.1068,
+      "step": 1180
+    },
+    {
+      "epoch": 2.371072319201995,
+      "grad_norm": 0.08419659733772278,
+      "learning_rate": 2.5814938724334624e-05,
+      "loss": 0.1039,
+      "step": 1190
+    },
+    {
+      "epoch": 2.3910224438902743,
+      "grad_norm": 0.08609955757856369,
+      "learning_rate": 2.4280298481587104e-05,
+      "loss": 0.1138,
+      "step": 1200
+    },
+    {
+      "epoch": 2.3910224438902743,
+      "eval_loss": 0.10642586648464203,
+      "eval_runtime": 49.084,
+      "eval_samples_per_second": 4.299,
+      "eval_steps_per_second": 2.16,
+      "step": 1200
+    },
+    {
+      "epoch": 2.4109725685785537,
+      "grad_norm": 0.10461217164993286,
+      "learning_rate": 2.2786359755583632e-05,
+      "loss": 0.1181,
+      "step": 1210
+    },
+    {
+      "epoch": 2.430922693266833,
+      "grad_norm": 0.09914015233516693,
+      "learning_rate": 2.133392558134483e-05,
+      "loss": 0.1077,
+      "step": 1220
+    },
+    {
+      "epoch": 2.450872817955112,
+      "grad_norm": 0.09925994277000427,
+      "learning_rate": 1.992377668400136e-05,
+      "loss": 0.1092,
+      "step": 1230
+    },
+    {
+      "epoch": 2.450872817955112,
+      "eval_loss": 0.10633692890405655,
+      "eval_runtime": 49.0203,
+      "eval_samples_per_second": 4.304,
+      "eval_steps_per_second": 2.162,
+      "step": 1230
+    },
+    {
+      "epoch": 2.4708229426433914,
+      "grad_norm": 0.07879967987537384,
+      "learning_rate": 1.855667105913176e-05,
+      "loss": 0.105,
+      "step": 1240
+    },
+    {
+      "epoch": 2.490773067331671,
+      "grad_norm": 0.08635237067937851,
+      "learning_rate": 1.7233343565317928e-05,
+      "loss": 0.1083,
+      "step": 1250
+    },
+    {
+      "epoch": 2.51072319201995,
+      "grad_norm": 0.07894821465015411,
+      "learning_rate": 1.5954505529137587e-05,
+      "loss": 0.1025,
+      "step": 1260
+    },
+    {
+      "epoch": 2.51072319201995,
+      "eval_loss": 0.10649015009403229,
+      "eval_runtime": 49.129,
+      "eval_samples_per_second": 4.295,
+      "eval_steps_per_second": 2.158,
+      "step": 1260
+    },
+    {
+      "epoch": 2.5306733167082296,
+      "grad_norm": 0.08609526604413986,
+      "learning_rate": 1.472084436280582e-05,
+      "loss": 0.1103,
+      "step": 1270
+    },
+    {
+      "epoch": 2.5506234413965085,
+      "grad_norm": 0.12177404761314392,
+      "learning_rate": 1.3533023194671057e-05,
+      "loss": 0.1124,
+      "step": 1280
+    },
+    {
+      "epoch": 2.570573566084788,
+      "grad_norm": 0.09495075047016144,
+      "learning_rate": 1.2391680512764802e-05,
+      "loss": 0.1099,
+      "step": 1290
+    },
+    {
+      "epoch": 2.570573566084788,
+      "eval_loss": 0.10633713006973267,
+      "eval_runtime": 49.2486,
+      "eval_samples_per_second": 4.284,
+      "eval_steps_per_second": 2.152,
+      "step": 1290
+    },
+    {
+      "epoch": 2.5905236907730673,
+      "grad_norm": 0.08574570715427399,
+      "learning_rate": 1.129742982159574e-05,
+      "loss": 0.1173,
+      "step": 1300
+    },
+    {
+      "epoch": 2.6104738154613467,
+      "grad_norm": 0.08771918714046478,
+      "learning_rate": 1.0250859312373462e-05,
+      "loss": 0.1102,
+      "step": 1310
+    },
+    {
+      "epoch": 2.630423940149626,
+      "grad_norm": 0.07304377853870392,
+      "learning_rate": 9.252531546838872e-06,
+      "loss": 0.1046,
+      "step": 1320
+    },
+    {
+      "epoch": 2.630423940149626,
+      "eval_loss": 0.10615119338035583,
+      "eval_runtime": 48.6835,
+      "eval_samples_per_second": 4.334,
+      "eval_steps_per_second": 2.177,
+      "step": 1320
+    },
+    {
+      "epoch": 2.650374064837905,
+      "grad_norm": 0.09657382220029831,
+      "learning_rate": 8.30298315487098e-06,
+      "loss": 0.1147,
+      "step": 1330
+    },
+    {
+      "epoch": 2.6703241895261844,
+      "grad_norm": 0.09089631587266922,
+      "learning_rate": 7.402724546032957e-06,
+      "loss": 0.1102,
+      "step": 1340
+    },
+    {
+      "epoch": 2.690274314214464,
+      "grad_norm": 0.09991210699081421,
+      "learning_rate": 6.552239635212298e-06,
+      "loss": 0.1202,
+      "step": 1350
+    },
+    {
+      "epoch": 2.690274314214464,
+      "eval_loss": 0.10618466883897781,
+      "eval_runtime": 48.5373,
+      "eval_samples_per_second": 4.347,
+      "eval_steps_per_second": 2.184,
+      "step": 1350
+    },
+    {
+      "epoch": 2.7102244389027432,
+      "grad_norm": 0.13392846286296844,
+      "learning_rate": 5.751985582502672e-06,
+      "loss": 0.1176,
+      "step": 1360
+    },
+    {
+      "epoch": 2.7301745635910226,
+      "grad_norm": 0.10461334884166718,
+      "learning_rate": 5.002392547467194e-06,
+      "loss": 0.1116,
+      "step": 1370
+    },
+    {
+      "epoch": 2.7501246882793016,
+      "grad_norm": 0.0903896763920784,
+      "learning_rate": 4.303863457915358e-06,
+      "loss": 0.1048,
+      "step": 1380
+    },
+    {
+      "epoch": 2.7501246882793016,
+      "eval_loss": 0.10620897263288498,
+      "eval_runtime": 48.5684,
+      "eval_samples_per_second": 4.344,
+      "eval_steps_per_second": 2.182,
+      "step": 1380
+    },
+    {
+      "epoch": 2.770074812967581,
+      "grad_norm": 0.09017899632453918,
+      "learning_rate": 3.6567737933176916e-06,
+      "loss": 0.1028,
+      "step": 1390
+    },
+    {
+      "epoch": 2.7900249376558603,
+      "grad_norm": 0.08241838961839676,
+      "learning_rate": 3.0614713829747456e-06,
+      "loss": 0.1051,
+      "step": 1400
+    },
+    {
+      "epoch": 2.8099750623441397,
+      "grad_norm": 0.12076063454151154,
+      "learning_rate": 2.5182762190488873e-06,
+      "loss": 0.1124,
+      "step": 1410
+    },
+    {
+      "epoch": 2.8099750623441397,
+      "eval_loss": 0.10615089535713196,
+      "eval_runtime": 48.4144,
+      "eval_samples_per_second": 4.358,
+      "eval_steps_per_second": 2.189,
+      "step": 1410
+    },
+    {
+      "epoch": 2.829925187032419,
+      "grad_norm": 0.053800225257873535,
+      "learning_rate": 2.0274802845593133e-06,
+      "loss": 0.1149,
+      "step": 1420
+    },
+    {
+      "epoch": 2.849875311720698,
+      "grad_norm": 0.08684830367565155,
+      "learning_rate": 1.5893473964326832e-06,
+      "loss": 0.1039,
+      "step": 1430
+    },
+    {
+      "epoch": 2.8698254364089775,
+      "grad_norm": 0.10123500972986221,
+      "learning_rate": 1.2041130636940678e-06,
+      "loss": 0.1127,
+      "step": 1440
+    },
+    {
+      "epoch": 2.8698254364089775,
+      "eval_loss": 0.10614271461963654,
+      "eval_runtime": 48.6688,
+      "eval_samples_per_second": 4.335,
+      "eval_steps_per_second": 2.178,
+      "step": 1440
+    },
+    {
+      "epoch": 2.889775561097257,
+      "grad_norm": 0.09655766934156418,
+      "learning_rate": 8.71984360874023e-07,
+      "loss": 0.1105,
+      "step": 1450
+    },
+    {
+      "epoch": 2.9097256857855363,
+      "grad_norm": 0.08582356572151184,
+      "learning_rate": 5.931398167000391e-07,
+      "loss": 0.1038,
+      "step": 1460
+    },
+    {
+      "epoch": 2.9296758104738156,
+      "grad_norm": 0.11041458696126938,
+      "learning_rate": 3.677293181322594e-07,
+      "loss": 0.1046,
+      "step": 1470
+    },
+    {
+      "epoch": 2.9296758104738156,
+      "eval_loss": 0.10609422624111176,
+      "eval_runtime": 48.6034,
+      "eval_samples_per_second": 4.341,
+      "eval_steps_per_second": 2.181,
+      "step": 1470
+    },
+    {
+      "epoch": 2.9496259351620946,
+      "grad_norm": 0.08140657842159271,
+      "learning_rate": 1.9587402979491797e-07,
+      "loss": 0.1058,
+      "step": 1480
+    },
+    {
+      "epoch": 2.969576059850374,
+      "grad_norm": 0.08797825127840042,
+      "learning_rate": 7.766632884689262e-08,
+      "loss": 0.1144,
+      "step": 1490
+    },
+    {
+      "epoch": 2.9895261845386534,
+      "grad_norm": 0.1317855268716812,
+      "learning_rate": 1.316975532625886e-08,
+      "loss": 0.1069,
+      "step": 1500
+    },
+    {
+      "epoch": 2.9895261845386534,
+      "eval_loss": 0.10605818033218384,
+      "eval_runtime": 48.5753,
+      "eval_samples_per_second": 4.344,
+      "eval_steps_per_second": 2.182,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1506,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6345734237933363e+17,
+  "train_batch_size": 2,
+  "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:c6b731b0ee946922e88f44dfe39a304ed9c9f83d5608887d14bdf636bc4aea59
+size 5777

checkpoint-1506/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen3-4B-Instruct-2507
+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 0.13.2

checkpoint-1506/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "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": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1506/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0c064570a762cc303647cc94c60408cc6ab6fd213dc61a3c574df9efd5fea9
+size 528550256

checkpoint-1506/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-1506/chat_template.jinja

@@ -0,0 +1,86 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1506/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f5636b17b606e5b1aa7aaf2fe6e772116e80452f6f84cbf62086831d15c5695
+size 1057397963

checkpoint-1506/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aa9ba6f2dfc92a964250f44b423fc475d3213d62a9b60120603ece4ce5b1acb
+size 14645

checkpoint-1506/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a3a30da14cfa700e8254c762995a4b64825bad6d3d28a769f4ea60fe122362
+size 1465

checkpoint-1506/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1506/tokenizer.json

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

checkpoint-1506/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1506/trainer_state.json

@@ -0,0 +1,1484 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 30,
+  "global_step": 1506,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0199501246882793,
+      "grad_norm": 9.905351638793945,
+      "learning_rate": 1.1920529801324503e-05,
+      "loss": 2.4681,
+      "step": 10
+    },
+    {
+      "epoch": 0.0399002493765586,
+      "grad_norm": 1.0738855600357056,
+      "learning_rate": 2.5165562913907287e-05,
+      "loss": 1.192,
+      "step": 20
+    },
+    {
+      "epoch": 0.059850374064837904,
+      "grad_norm": 0.9622387290000916,
+      "learning_rate": 3.841059602649007e-05,
+      "loss": 0.651,
+      "step": 30
+    },
+    {
+      "epoch": 0.059850374064837904,
+      "eval_loss": 0.5571362376213074,
+      "eval_runtime": 48.7371,
+      "eval_samples_per_second": 4.329,
+      "eval_steps_per_second": 2.175,
+      "step": 30
+    },
+    {
+      "epoch": 0.0798004987531172,
+      "grad_norm": 0.6049273610115051,
+      "learning_rate": 5.165562913907285e-05,
+      "loss": 0.5074,
+      "step": 40
+    },
+    {
+      "epoch": 0.09975062344139651,
+      "grad_norm": 0.6833104491233826,
+      "learning_rate": 6.490066225165563e-05,
+      "loss": 0.3756,
+      "step": 50
+    },
+    {
+      "epoch": 0.11970074812967581,
+      "grad_norm": 0.5208126902580261,
+      "learning_rate": 7.814569536423842e-05,
+      "loss": 0.3065,
+      "step": 60
+    },
+    {
+      "epoch": 0.11970074812967581,
+      "eval_loss": 0.25738316774368286,
+      "eval_runtime": 48.1494,
+      "eval_samples_per_second": 4.382,
+      "eval_steps_per_second": 2.201,
+      "step": 60
+    },
+    {
+      "epoch": 0.1396508728179551,
+      "grad_norm": 0.5192306041717529,
+      "learning_rate": 9.13907284768212e-05,
+      "loss": 0.2578,
+      "step": 70
+    },
+    {
+      "epoch": 0.1596009975062344,
+      "grad_norm": 0.5098096132278442,
+      "learning_rate": 0.00010463576158940399,
+      "loss": 0.2096,
+      "step": 80
+    },
+    {
+      "epoch": 0.17955112219451372,
+      "grad_norm": 0.5306766629219055,
+      "learning_rate": 0.00011788079470198677,
+      "loss": 0.1899,
+      "step": 90
+    },
+    {
+      "epoch": 0.17955112219451372,
+      "eval_loss": 0.1828010529279709,
+      "eval_runtime": 48.0843,
+      "eval_samples_per_second": 4.388,
+      "eval_steps_per_second": 2.204,
+      "step": 90
+    },
+    {
+      "epoch": 0.19950124688279303,
+      "grad_norm": 0.3457268178462982,
+      "learning_rate": 0.00013112582781456955,
+      "loss": 0.1848,
+      "step": 100
+    },
+    {
+      "epoch": 0.2194513715710723,
+      "grad_norm": 0.47407814860343933,
+      "learning_rate": 0.00014437086092715232,
+      "loss": 0.1736,
+      "step": 110
+    },
+    {
+      "epoch": 0.23940149625935161,
+      "grad_norm": 0.3515409827232361,
+      "learning_rate": 0.00015761589403973512,
+      "loss": 0.1676,
+      "step": 120
+    },
+    {
+      "epoch": 0.23940149625935161,
+      "eval_loss": 0.1554146409034729,
+      "eval_runtime": 48.3317,
+      "eval_samples_per_second": 4.366,
+      "eval_steps_per_second": 2.193,
+      "step": 120
+    },
+    {
+      "epoch": 0.2593516209476309,
+      "grad_norm": 0.4131653904914856,
+      "learning_rate": 0.0001708609271523179,
+      "loss": 0.1643,
+      "step": 130
+    },
+    {
+      "epoch": 0.2793017456359102,
+      "grad_norm": 0.7977883219718933,
+      "learning_rate": 0.0001841059602649007,
+      "loss": 0.1543,
+      "step": 140
+    },
+    {
+      "epoch": 0.29925187032418954,
+      "grad_norm": 0.32713833451271057,
+      "learning_rate": 0.00019735099337748346,
+      "loss": 0.1569,
+      "step": 150
+    },
+    {
+      "epoch": 0.29925187032418954,
+      "eval_loss": 0.14544202387332916,
+      "eval_runtime": 48.2076,
+      "eval_samples_per_second": 4.377,
+      "eval_steps_per_second": 2.199,
+      "step": 150
+    },
+    {
+      "epoch": 0.3192019950124688,
+      "grad_norm": 0.3618054986000061,
+      "learning_rate": 0.00019998279880250371,
+      "loss": 0.1661,
+      "step": 160
+    },
+    {
+      "epoch": 0.33915211970074816,
+      "grad_norm": 0.5105156302452087,
+      "learning_rate": 0.0001999129290795728,
+      "loss": 0.1542,
+      "step": 170
+    },
+    {
+      "epoch": 0.35910224438902744,
+      "grad_norm": 0.3221360445022583,
+      "learning_rate": 0.00019978935328445287,
+      "loss": 0.1437,
+      "step": 180
+    },
+    {
+      "epoch": 0.35910224438902744,
+      "eval_loss": 0.1328973025083542,
+      "eval_runtime": 48.1577,
+      "eval_samples_per_second": 4.381,
+      "eval_steps_per_second": 2.201,
+      "step": 180
+    },
+    {
+      "epoch": 0.3790523690773067,
+      "grad_norm": 0.39137646555900574,
+      "learning_rate": 0.000199612137842687,
+      "loss": 0.1511,
+      "step": 190
+    },
+    {
+      "epoch": 0.39900249376558605,
+      "grad_norm": 0.29165342450141907,
+      "learning_rate": 0.00019938137801267064,
+      "loss": 0.1456,
+      "step": 200
+    },
+    {
+      "epoch": 0.41895261845386533,
+      "grad_norm": 0.2816756069660187,
+      "learning_rate": 0.0001990971978344475,
+      "loss": 0.1271,
+      "step": 210
+    },
+    {
+      "epoch": 0.41895261845386533,
+      "eval_loss": 0.13140253722667694,
+      "eval_runtime": 47.9806,
+      "eval_samples_per_second": 4.398,
+      "eval_steps_per_second": 2.209,
+      "step": 210
+    },
+    {
+      "epoch": 0.4389027431421446,
+      "grad_norm": 0.6542349457740784,
+      "learning_rate": 0.00019875975006303435,
+      "loss": 0.1409,
+      "step": 220
+    },
+    {
+      "epoch": 0.45885286783042395,
+      "grad_norm": 0.2651802599430084,
+      "learning_rate": 0.00019836921608631114,
+      "loss": 0.1474,
+      "step": 230
+    },
+    {
+      "epoch": 0.47880299251870323,
+      "grad_norm": 0.2070140242576599,
+      "learning_rate": 0.00019792580582751935,
+      "loss": 0.1369,
+      "step": 240
+    },
+    {
+      "epoch": 0.47880299251870323,
+      "eval_loss": 0.12214324623346329,
+      "eval_runtime": 48.2216,
+      "eval_samples_per_second": 4.376,
+      "eval_steps_per_second": 2.198,
+      "step": 240
+    },
+    {
+      "epoch": 0.49875311720698257,
+      "grad_norm": 0.16217675805091858,
+      "learning_rate": 0.00019742975763242248,
+      "loss": 0.1342,
+      "step": 250
+    },
+    {
+      "epoch": 0.5187032418952618,
+      "grad_norm": 0.17511174082756042,
+      "learning_rate": 0.00019688133814118843,
+      "loss": 0.1233,
+      "step": 260
+    },
+    {
+      "epoch": 0.5386533665835411,
+      "grad_norm": 0.16075153648853302,
+      "learning_rate": 0.0001962808421450624,
+      "loss": 0.1333,
+      "step": 270
+    },
+    {
+      "epoch": 0.5386533665835411,
+      "eval_loss": 0.11943639069795609,
+      "eval_runtime": 48.0763,
+      "eval_samples_per_second": 4.389,
+      "eval_steps_per_second": 2.205,
+      "step": 270
+    },
+    {
+      "epoch": 0.5586034912718204,
+      "grad_norm": 0.1652883142232895,
+      "learning_rate": 0.00019562859242790853,
+      "loss": 0.1308,
+      "step": 280
+    },
+    {
+      "epoch": 0.5785536159600998,
+      "grad_norm": 0.2698552906513214,
+      "learning_rate": 0.00019492493959270398,
+      "loss": 0.1378,
+      "step": 290
+    },
+    {
+      "epoch": 0.5985037406483791,
+      "grad_norm": 0.11757837980985641,
+      "learning_rate": 0.00019417026187307985,
+      "loss": 0.1186,
+      "step": 300
+    },
+    {
+      "epoch": 0.5985037406483791,
+      "eval_loss": 0.11812838912010193,
+      "eval_runtime": 48.1525,
+      "eval_samples_per_second": 4.382,
+      "eval_steps_per_second": 2.201,
+      "step": 300
+    },
+    {
+      "epoch": 0.6184538653366584,
+      "grad_norm": 0.1514044553041458,
+      "learning_rate": 0.00019336496493000985,
+      "loss": 0.1329,
+      "step": 310
+    },
+    {
+      "epoch": 0.6384039900249376,
+      "grad_norm": 0.1278185248374939,
+      "learning_rate": 0.00019250948163375563,
+      "loss": 0.1311,
+      "step": 320
+    },
+    {
+      "epoch": 0.6583541147132169,
+      "grad_norm": 0.14280234277248383,
+      "learning_rate": 0.00019160427183118674,
+      "loss": 0.1281,
+      "step": 330
+    },
+    {
+      "epoch": 0.6583541147132169,
+      "eval_loss": 0.11799625307321548,
+      "eval_runtime": 48.1223,
+      "eval_samples_per_second": 4.385,
+      "eval_steps_per_second": 2.203,
+      "step": 330
+    },
+    {
+      "epoch": 0.6783042394014963,
+      "grad_norm": 0.141315296292305,
+      "learning_rate": 0.0001906498220985997,
+      "loss": 0.1131,
+      "step": 340
+    },
+    {
+      "epoch": 0.6982543640897756,
+      "grad_norm": 0.11978308856487274,
+      "learning_rate": 0.0001896466454801692,
+      "loss": 0.1294,
+      "step": 350
+    },
+    {
+      "epoch": 0.7182044887780549,
+      "grad_norm": 0.2772483825683594,
+      "learning_rate": 0.00018859528121217204,
+      "loss": 0.1297,
+      "step": 360
+    },
+    {
+      "epoch": 0.7182044887780549,
+      "eval_loss": 0.11690443754196167,
+      "eval_runtime": 48.1421,
+      "eval_samples_per_second": 4.383,
+      "eval_steps_per_second": 2.202,
+      "step": 360
+    },
+    {
+      "epoch": 0.7381546134663342,
+      "grad_norm": 0.13961242139339447,
+      "learning_rate": 0.00018749629443313233,
+      "loss": 0.1249,
+      "step": 370
+    },
+    {
+      "epoch": 0.7581047381546134,
+      "grad_norm": 0.17335286736488342,
+      "learning_rate": 0.0001863502758800431,
+      "loss": 0.1255,
+      "step": 380
+    },
+    {
+      "epoch": 0.7780548628428927,
+      "grad_norm": 0.15879972279071808,
+      "learning_rate": 0.00018515784157082822,
+      "loss": 0.1175,
+      "step": 390
+    },
+    {
+      "epoch": 0.7780548628428927,
+      "eval_loss": 0.11526743322610855,
+      "eval_runtime": 48.2061,
+      "eval_samples_per_second": 4.377,
+      "eval_steps_per_second": 2.199,
+      "step": 390
+    },
+    {
+      "epoch": 0.7980049875311721,
+      "grad_norm": 0.11807694286108017,
+      "learning_rate": 0.00018391963247321513,
+      "loss": 0.1178,
+      "step": 400
+    },
+    {
+      "epoch": 0.8179551122194514,
+      "grad_norm": 0.11275653541088104,
+      "learning_rate": 0.00018263631416019617,
+      "loss": 0.1195,
+      "step": 410
+    },
+    {
+      "epoch": 0.8379052369077307,
+      "grad_norm": 0.12657803297042847,
+      "learning_rate": 0.000181308576452264,
+      "loss": 0.1182,
+      "step": 420
+    },
+    {
+      "epoch": 0.8379052369077307,
+      "eval_loss": 0.11410157382488251,
+      "eval_runtime": 48.3064,
+      "eval_samples_per_second": 4.368,
+      "eval_steps_per_second": 2.194,
+      "step": 420
+    },
+    {
+      "epoch": 0.85785536159601,
+      "grad_norm": 0.15267746150493622,
+      "learning_rate": 0.00017993713304661322,
+      "loss": 0.1216,
+      "step": 430
+    },
+    {
+      "epoch": 0.8778054862842892,
+      "grad_norm": 0.11593750864267349,
+      "learning_rate": 0.00017852272113350767,
+      "loss": 0.1329,
+      "step": 440
+    },
+    {
+      "epoch": 0.8977556109725686,
+      "grad_norm": 0.12276951223611832,
+      "learning_rate": 0.0001770661010000194,
+      "loss": 0.1189,
+      "step": 450
+    },
+    {
+      "epoch": 0.8977556109725686,
+      "eval_loss": 0.11431698501110077,
+      "eval_runtime": 48.1715,
+      "eval_samples_per_second": 4.38,
+      "eval_steps_per_second": 2.2,
+      "step": 450
+    },
+    {
+      "epoch": 0.9177057356608479,
+      "grad_norm": 0.11874907463788986,
+      "learning_rate": 0.00017556805562135255,
+      "loss": 0.1313,
+      "step": 460
+    },
+    {
+      "epoch": 0.9376558603491272,
+      "grad_norm": 0.22391599416732788,
+      "learning_rate": 0.00017402939023997157,
+      "loss": 0.1127,
+      "step": 470
+    },
+    {
+      "epoch": 0.9576059850374065,
+      "grad_norm": 0.09968144446611404,
+      "learning_rate": 0.00017245093193276047,
+      "loss": 0.118,
+      "step": 480
+    },
+    {
+      "epoch": 0.9576059850374065,
+      "eval_loss": 0.11578261852264404,
+      "eval_runtime": 48.1681,
+      "eval_samples_per_second": 4.38,
+      "eval_steps_per_second": 2.201,
+      "step": 480
+    },
+    {
+      "epoch": 0.9775561097256857,
+      "grad_norm": 0.09711634367704391,
+      "learning_rate": 0.00017083352916644494,
+      "loss": 0.1184,
+      "step": 490
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "grad_norm": 0.0991770550608635,
+      "learning_rate": 0.0001691780513415173,
+      "loss": 0.1215,
+      "step": 500
+    },
+    {
+      "epoch": 1.0159600997506235,
+      "grad_norm": 0.09751348197460175,
+      "learning_rate": 0.00016748538832490857,
+      "loss": 0.1206,
+      "step": 510
+    },
+    {
+      "epoch": 1.0159600997506235,
+      "eval_loss": 0.1116185411810875,
+      "eval_runtime": 48.1046,
+      "eval_samples_per_second": 4.386,
+      "eval_steps_per_second": 2.204,
+      "step": 510
+    },
+    {
+      "epoch": 1.0359102244389027,
+      "grad_norm": 0.10556904226541519,
+      "learning_rate": 0.0001657564499716595,
+      "loss": 0.1135,
+      "step": 520
+    },
+    {
+      "epoch": 1.055860349127182,
+      "grad_norm": 0.15284962952136993,
+      "learning_rate": 0.00016399216563584736,
+      "loss": 0.1218,
+      "step": 530
+    },
+    {
+      "epoch": 1.0758104738154612,
+      "grad_norm": 0.09085577726364136,
+      "learning_rate": 0.00016219348367103132,
+      "loss": 0.1171,
+      "step": 540
+    },
+    {
+      "epoch": 1.0758104738154612,
+      "eval_loss": 0.11126323789358139,
+      "eval_runtime": 48.6749,
+      "eval_samples_per_second": 4.335,
+      "eval_steps_per_second": 2.178,
+      "step": 540
+    },
+    {
+      "epoch": 1.0957605985037406,
+      "grad_norm": 0.12901732325553894,
+      "learning_rate": 0.00016036137092048525,
+      "loss": 0.1188,
+      "step": 550
+    },
+    {
+      "epoch": 1.11571072319202,
+      "grad_norm": 0.09154735505580902,
+      "learning_rate": 0.0001584968121974915,
+      "loss": 0.1232,
+      "step": 560
+    },
+    {
+      "epoch": 1.1356608478802992,
+      "grad_norm": 0.10134833306074142,
+      "learning_rate": 0.00015660080975597553,
+      "loss": 0.1205,
+      "step": 570
+    },
+    {
+      "epoch": 1.1356608478802992,
+      "eval_loss": 0.11302559077739716,
+      "eval_runtime": 48.709,
+      "eval_samples_per_second": 4.332,
+      "eval_steps_per_second": 2.176,
+      "step": 570
+    },
+    {
+      "epoch": 1.1556109725685786,
+      "grad_norm": 0.14130111038684845,
+      "learning_rate": 0.00015467438275176568,
+      "loss": 0.1214,
+      "step": 580
+    },
+    {
+      "epoch": 1.1755610972568578,
+      "grad_norm": 0.1193675845861435,
+      "learning_rate": 0.0001527185666947675,
+      "loss": 0.1173,
+      "step": 590
+    },
+    {
+      "epoch": 1.1955112219451371,
+      "grad_norm": 0.06070871651172638,
+      "learning_rate": 0.00015073441289234745,
+      "loss": 0.1189,
+      "step": 600
+    },
+    {
+      "epoch": 1.1955112219451371,
+      "eval_loss": 0.11231612414121628,
+      "eval_runtime": 48.6333,
+      "eval_samples_per_second": 4.339,
+      "eval_steps_per_second": 2.18,
+      "step": 600
+    },
+    {
+      "epoch": 1.2154613466334165,
+      "grad_norm": 0.08564524352550507,
+      "learning_rate": 0.00014872298788422497,
+      "loss": 0.1194,
+      "step": 610
+    },
+    {
+      "epoch": 1.2354114713216957,
+      "grad_norm": 0.1110881119966507,
+      "learning_rate": 0.00014668537286917664,
+      "loss": 0.117,
+      "step": 620
+    },
+    {
+      "epoch": 1.255361596009975,
+      "grad_norm": 0.10232548415660858,
+      "learning_rate": 0.00014462266312386085,
+      "loss": 0.1235,
+      "step": 630
+    },
+    {
+      "epoch": 1.255361596009975,
+      "eval_loss": 0.11166342347860336,
+      "eval_runtime": 48.6028,
+      "eval_samples_per_second": 4.341,
+      "eval_steps_per_second": 2.181,
+      "step": 630
+    },
+    {
+      "epoch": 1.2753117206982543,
+      "grad_norm": 0.08676601946353912,
+      "learning_rate": 0.00014253596741407507,
+      "loss": 0.1281,
+      "step": 640
+    },
+    {
+      "epoch": 1.2952618453865337,
+      "grad_norm": 0.09077729284763336,
+      "learning_rate": 0.0001404264073987623,
+      "loss": 0.1242,
+      "step": 650
+    },
+    {
+      "epoch": 1.315211970074813,
+      "grad_norm": 0.3734651505947113,
+      "learning_rate": 0.00013829511702708727,
+      "loss": 0.1137,
+      "step": 660
+    },
+    {
+      "epoch": 1.315211970074813,
+      "eval_loss": 0.11021307855844498,
+      "eval_runtime": 48.6287,
+      "eval_samples_per_second": 4.339,
+      "eval_steps_per_second": 2.18,
+      "step": 660
+    },
+    {
+      "epoch": 1.3351620947630922,
+      "grad_norm": 0.09780021756887436,
+      "learning_rate": 0.00013614324192890592,
+      "loss": 0.1219,
+      "step": 670
+    },
+    {
+      "epoch": 1.3551122194513716,
+      "grad_norm": 0.09793366491794586,
+      "learning_rate": 0.00013397193879895671,
+      "loss": 0.1046,
+      "step": 680
+    },
+    {
+      "epoch": 1.3750623441396508,
+      "grad_norm": 0.11061827093362808,
+      "learning_rate": 0.00013178237477510374,
+      "loss": 0.1174,
+      "step": 690
+    },
+    {
+      "epoch": 1.3750623441396508,
+      "eval_loss": 0.1095186397433281,
+      "eval_runtime": 48.691,
+      "eval_samples_per_second": 4.333,
+      "eval_steps_per_second": 2.177,
+      "step": 690
+    },
+    {
+      "epoch": 1.3950124688279302,
+      "grad_norm": 0.11096978187561035,
+      "learning_rate": 0.0001295757268109666,
+      "loss": 0.1071,
+      "step": 700
+    },
+    {
+      "epoch": 1.4149625935162096,
+      "grad_norm": 0.10013638436794281,
+      "learning_rate": 0.0001273531810432741,
+      "loss": 0.1262,
+      "step": 710
+    },
+    {
+      "epoch": 1.4349127182044887,
+      "grad_norm": 0.12431971728801727,
+      "learning_rate": 0.00012511593215428141,
+      "loss": 0.1098,
+      "step": 720
+    },
+    {
+      "epoch": 1.4349127182044887,
+      "eval_loss": 0.10981423407793045,
+      "eval_runtime": 48.7018,
+      "eval_samples_per_second": 4.332,
+      "eval_steps_per_second": 2.177,
+      "step": 720
+    },
+    {
+      "epoch": 1.4548628428927681,
+      "grad_norm": 0.13086780905723572,
+      "learning_rate": 0.0001228651827295943,
+      "loss": 0.1142,
+      "step": 730
+    },
+    {
+      "epoch": 1.4748129675810473,
+      "grad_norm": 0.08466003090143204,
+      "learning_rate": 0.00012060214261174465,
+      "loss": 0.1144,
+      "step": 740
+    },
+    {
+      "epoch": 1.4947630922693267,
+      "grad_norm": 0.11653965711593628,
+      "learning_rate": 0.00011832802824986523,
+      "loss": 0.1183,
+      "step": 750
+    },
+    {
+      "epoch": 1.4947630922693267,
+      "eval_loss": 0.10894475877285004,
+      "eval_runtime": 48.6934,
+      "eval_samples_per_second": 4.333,
+      "eval_steps_per_second": 2.177,
+      "step": 750
+    },
+    {
+      "epoch": 1.514713216957606,
+      "grad_norm": 0.11816778779029846,
+      "learning_rate": 0.00011604406204581346,
+      "loss": 0.13,
+      "step": 760
+    },
+    {
+      "epoch": 1.5346633416458852,
+      "grad_norm": 0.09233927726745605,
+      "learning_rate": 0.00011375147169709519,
+      "loss": 0.109,
+      "step": 770
+    },
+    {
+      "epoch": 1.5546134663341646,
+      "grad_norm": 0.08808460831642151,
+      "learning_rate": 0.00011145148953694195,
+      "loss": 0.1145,
+      "step": 780
+    },
+    {
+      "epoch": 1.5546134663341646,
+      "eval_loss": 0.10957030206918716,
+      "eval_runtime": 48.6129,
+      "eval_samples_per_second": 4.34,
+      "eval_steps_per_second": 2.18,
+      "step": 780
+    },
+    {
+      "epoch": 1.5745635910224438,
+      "grad_norm": 0.0909830778837204,
+      "learning_rate": 0.00010914535187189654,
+      "loss": 0.1115,
+      "step": 790
+    },
+    {
+      "epoch": 1.5945137157107232,
+      "grad_norm": 0.08932233601808548,
+      "learning_rate": 0.00010683429831726252,
+      "loss": 0.1191,
+      "step": 800
+    },
+    {
+      "epoch": 1.6144638403990026,
+      "grad_norm": 0.08355925977230072,
+      "learning_rate": 0.0001045195711307756,
+      "loss": 0.1127,
+      "step": 810
+    },
+    {
+      "epoch": 1.6144638403990026,
+      "eval_loss": 0.10913572460412979,
+      "eval_runtime": 48.4393,
+      "eval_samples_per_second": 4.356,
+      "eval_steps_per_second": 2.188,
+      "step": 810
+    },
+    {
+      "epoch": 1.6344139650872818,
+      "grad_norm": 0.06819329410791397,
+      "learning_rate": 0.00010220241454485406,
+      "loss": 0.1098,
+      "step": 820
+    },
+    {
+      "epoch": 1.654364089775561,
+      "grad_norm": 0.6049116849899292,
+      "learning_rate": 9.988407409778838e-05,
+      "loss": 0.1141,
+      "step": 830
+    },
+    {
+      "epoch": 1.6743142144638403,
+      "grad_norm": 0.07323434203863144,
+      "learning_rate": 9.756579596422839e-05,
+      "loss": 0.1049,
+      "step": 840
+    },
+    {
+      "epoch": 1.6743142144638403,
+      "eval_loss": 0.10999356210231781,
+      "eval_runtime": 48.6539,
+      "eval_samples_per_second": 4.337,
+      "eval_steps_per_second": 2.179,
+      "step": 840
+    },
+    {
+      "epoch": 1.6942643391521197,
+      "grad_norm": 0.10413742810487747,
+      "learning_rate": 9.524882628532858e-05,
+      "loss": 0.1158,
+      "step": 850
+    },
+    {
+      "epoch": 1.714214463840399,
+      "grad_norm": 0.08523685485124588,
+      "learning_rate": 9.293441049891148e-05,
+      "loss": 0.115,
+      "step": 860
+    },
+    {
+      "epoch": 1.7341645885286783,
+      "grad_norm": 0.12683580815792084,
+      "learning_rate": 9.062379267000898e-05,
+      "loss": 0.1185,
+      "step": 870
+    },
+    {
+      "epoch": 1.7341645885286783,
+      "eval_loss": 0.10940343141555786,
+      "eval_runtime": 48.6011,
+      "eval_samples_per_second": 4.341,
+      "eval_steps_per_second": 2.181,
+      "step": 870
+    },
+    {
+      "epoch": 1.7541147132169574,
+      "grad_norm": 0.10133107006549835,
+      "learning_rate": 8.831821482214159e-05,
+      "loss": 0.1194,
+      "step": 880
+    },
+    {
+      "epoch": 1.7740648379052368,
+      "grad_norm": 0.08002304285764694,
+      "learning_rate": 8.601891626969514e-05,
+      "loss": 0.1178,
+      "step": 890
+    },
+    {
+      "epoch": 1.7940149625935162,
+      "grad_norm": 0.0782008096575737,
+      "learning_rate": 8.372713295175352e-05,
+      "loss": 0.1162,
+      "step": 900
+    },
+    {
+      "epoch": 1.7940149625935162,
+      "eval_loss": 0.10899555683135986,
+      "eval_runtime": 48.522,
+      "eval_samples_per_second": 4.349,
+      "eval_steps_per_second": 2.185,
+      "step": 900
+    },
+    {
+      "epoch": 1.8139650872817956,
+      "grad_norm": 0.08133247494697571,
+      "learning_rate": 8.14440967677461e-05,
+      "loss": 0.1234,
+      "step": 910
+    },
+    {
+      "epoch": 1.8339152119700748,
+      "grad_norm": 0.08592060953378677,
+      "learning_rate": 7.917103491526617e-05,
+      "loss": 0.1073,
+      "step": 920
+    },
+    {
+      "epoch": 1.853865336658354,
+      "grad_norm": 0.07544530183076859,
+      "learning_rate": 7.690916923041708e-05,
+      "loss": 0.1072,
+      "step": 930
+    },
+    {
+      "epoch": 1.853865336658354,
+      "eval_loss": 0.10886865854263306,
+      "eval_runtime": 48.4695,
+      "eval_samples_per_second": 4.353,
+      "eval_steps_per_second": 2.187,
+      "step": 930
+    },
+    {
+      "epoch": 1.8738154613466333,
+      "grad_norm": 0.10101612657308578,
+      "learning_rate": 7.465971553104014e-05,
+      "loss": 0.1109,
+      "step": 940
+    },
+    {
+      "epoch": 1.8937655860349127,
+      "grad_norm": 0.07430823147296906,
+      "learning_rate": 7.242388296317757e-05,
+      "loss": 0.108,
+      "step": 950
+    },
+    {
+      "epoch": 1.9137157107231921,
+      "grad_norm": 0.0772905945777893,
+      "learning_rate": 7.020287335112179e-05,
+      "loss": 0.1087,
+      "step": 960
+    },
+    {
+      "epoch": 1.9137157107231921,
+      "eval_loss": 0.10754832625389099,
+      "eval_runtime": 48.5946,
+      "eval_samples_per_second": 4.342,
+      "eval_steps_per_second": 2.181,
+      "step": 960
+    },
+    {
+      "epoch": 1.9336658354114713,
+      "grad_norm": 0.08496296405792236,
+      "learning_rate": 6.799788055140025e-05,
+      "loss": 0.1203,
+      "step": 970
+    },
+    {
+      "epoch": 1.9536159600997505,
+      "grad_norm": 0.07446739822626114,
+      "learning_rate": 6.58100898110432e-05,
+      "loss": 0.1158,
+      "step": 980
+    },
+    {
+      "epoch": 1.9735660847880299,
+      "grad_norm": 0.08105003088712692,
+      "learning_rate": 6.364067713047943e-05,
+      "loss": 0.1184,
+      "step": 990
+    },
+    {
+      "epoch": 1.9735660847880299,
+      "eval_loss": 0.1074095070362091,
+      "eval_runtime": 48.6824,
+      "eval_samples_per_second": 4.334,
+      "eval_steps_per_second": 2.177,
+      "step": 990
+    },
+    {
+      "epoch": 1.9935162094763093,
+      "grad_norm": 0.08692453801631927,
+      "learning_rate": 6.149080863140208e-05,
+      "loss": 0.1145,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0119700748129676,
+      "grad_norm": 0.0745435431599617,
+      "learning_rate": 5.9361639929944867e-05,
+      "loss": 0.1081,
+      "step": 1010
+    },
+    {
+      "epoch": 2.031920199501247,
+      "grad_norm": 0.08805131912231445,
+      "learning_rate": 5.7254315515505105e-05,
+      "loss": 0.1092,
+      "step": 1020
+    },
+    {
+      "epoch": 2.031920199501247,
+      "eval_loss": 0.10798249393701553,
+      "eval_runtime": 48.9954,
+      "eval_samples_per_second": 4.307,
+      "eval_steps_per_second": 2.163,
+      "step": 1020
+    },
+    {
+      "epoch": 2.051870324189526,
+      "grad_norm": 0.08542945981025696,
+      "learning_rate": 5.5169968135547655e-05,
+      "loss": 0.1185,
+      "step": 1030
+    },
+    {
+      "epoch": 2.0718204488778054,
+      "grad_norm": 0.08667082339525223,
+      "learning_rate": 5.310971818672077e-05,
+      "loss": 0.1107,
+      "step": 1040
+    },
+    {
+      "epoch": 2.0917705735660848,
+      "grad_norm": 0.0777161717414856,
+      "learning_rate": 5.1074673112610584e-05,
+      "loss": 0.1082,
+      "step": 1050
+    },
+    {
+      "epoch": 2.0917705735660848,
+      "eval_loss": 0.10762733221054077,
+      "eval_runtime": 49.1196,
+      "eval_samples_per_second": 4.296,
+      "eval_steps_per_second": 2.158,
+      "step": 1050
+    },
+    {
+      "epoch": 2.111720698254364,
+      "grad_norm": 0.06888756155967712,
+      "learning_rate": 4.906592680845829e-05,
+      "loss": 0.1075,
+      "step": 1060
+    },
+    {
+      "epoch": 2.1316708229426435,
+      "grad_norm": 0.09783507883548737,
+      "learning_rate": 4.7084559033160135e-05,
+      "loss": 0.1149,
+      "step": 1070
+    },
+    {
+      "epoch": 2.1516209476309225,
+      "grad_norm": 0.09118674695491791,
+      "learning_rate": 4.5131634828865845e-05,
+      "loss": 0.1127,
+      "step": 1080
+    },
+    {
+      "epoch": 2.1516209476309225,
+      "eval_loss": 0.10765193402767181,
+      "eval_runtime": 49.1258,
+      "eval_samples_per_second": 4.295,
+      "eval_steps_per_second": 2.158,
+      "step": 1080
+    },
+    {
+      "epoch": 2.171571072319202,
+      "grad_norm": 0.08113594353199005,
+      "learning_rate": 4.320820394848794e-05,
+      "loss": 0.1151,
+      "step": 1090
+    },
+    {
+      "epoch": 2.1915211970074813,
+      "grad_norm": 0.08070435374975204,
+      "learning_rate": 4.1315300291429174e-05,
+      "loss": 0.1093,
+      "step": 1100
+    },
+    {
+      "epoch": 2.2114713216957607,
+      "grad_norm": 0.07660377770662308,
+      "learning_rate": 3.9453941347832146e-05,
+      "loss": 0.1113,
+      "step": 1110
+    },
+    {
+      "epoch": 2.2114713216957607,
+      "eval_loss": 0.10742755234241486,
+      "eval_runtime": 48.9958,
+      "eval_samples_per_second": 4.306,
+      "eval_steps_per_second": 2.163,
+      "step": 1110
+    },
+    {
+      "epoch": 2.23142144638404,
+      "grad_norm": 0.08561329543590546,
+      "learning_rate": 3.762512765164895e-05,
+      "loss": 0.1096,
+      "step": 1120
+    },
+    {
+      "epoch": 2.251371571072319,
+      "grad_norm": 0.07384736835956573,
+      "learning_rate": 3.5829842242825374e-05,
+      "loss": 0.1071,
+      "step": 1130
+    },
+    {
+      "epoch": 2.2713216957605984,
+      "grad_norm": 0.089817114174366,
+      "learning_rate": 3.406905013888875e-05,
+      "loss": 0.1128,
+      "step": 1140
+    },
+    {
+      "epoch": 2.2713216957605984,
+      "eval_loss": 0.10679538547992706,
+      "eval_runtime": 49.1277,
+      "eval_samples_per_second": 4.295,
+      "eval_steps_per_second": 2.158,
+      "step": 1140
+    },
+    {
+      "epoch": 2.291271820448878,
+      "grad_norm": 0.0809311643242836,
+      "learning_rate": 3.234369781622315e-05,
+      "loss": 0.1055,
+      "step": 1150
+    },
+    {
+      "epoch": 2.311221945137157,
+      "grad_norm": 0.11156892031431198,
+      "learning_rate": 3.065471270131132e-05,
+      "loss": 0.1118,
+      "step": 1160
+    },
+    {
+      "epoch": 2.3311720698254366,
+      "grad_norm": 0.07891872525215149,
+      "learning_rate": 2.9003002672216106e-05,
+      "loss": 0.1146,
+      "step": 1170
+    },
+    {
+      "epoch": 2.3311720698254366,
+      "eval_loss": 0.1066785454750061,
+      "eval_runtime": 49.1277,
+      "eval_samples_per_second": 4.295,
+      "eval_steps_per_second": 2.158,
+      "step": 1170
+    },
+    {
+      "epoch": 2.3511221945137155,
+      "grad_norm": 0.08137693256139755,
+      "learning_rate": 2.738945557056999e-05,
+      "loss": 0.1068,
+      "step": 1180
+    },
+    {
+      "epoch": 2.371072319201995,
+      "grad_norm": 0.08419659733772278,
+      "learning_rate": 2.5814938724334624e-05,
+      "loss": 0.1039,
+      "step": 1190
+    },
+    {
+      "epoch": 2.3910224438902743,
+      "grad_norm": 0.08609955757856369,
+      "learning_rate": 2.4280298481587104e-05,
+      "loss": 0.1138,
+      "step": 1200
+    },
+    {
+      "epoch": 2.3910224438902743,
+      "eval_loss": 0.10642586648464203,
+      "eval_runtime": 49.084,
+      "eval_samples_per_second": 4.299,
+      "eval_steps_per_second": 2.16,
+      "step": 1200
+    },
+    {
+      "epoch": 2.4109725685785537,
+      "grad_norm": 0.10461217164993286,
+      "learning_rate": 2.2786359755583632e-05,
+      "loss": 0.1181,
+      "step": 1210
+    },
+    {
+      "epoch": 2.430922693266833,
+      "grad_norm": 0.09914015233516693,
+      "learning_rate": 2.133392558134483e-05,
+      "loss": 0.1077,
+      "step": 1220
+    },
+    {
+      "epoch": 2.450872817955112,
+      "grad_norm": 0.09925994277000427,
+      "learning_rate": 1.992377668400136e-05,
+      "loss": 0.1092,
+      "step": 1230
+    },
+    {
+      "epoch": 2.450872817955112,
+      "eval_loss": 0.10633692890405655,
+      "eval_runtime": 49.0203,
+      "eval_samples_per_second": 4.304,
+      "eval_steps_per_second": 2.162,
+      "step": 1230
+    },
+    {
+      "epoch": 2.4708229426433914,
+      "grad_norm": 0.07879967987537384,
+      "learning_rate": 1.855667105913176e-05,
+      "loss": 0.105,
+      "step": 1240
+    },
+    {
+      "epoch": 2.490773067331671,
+      "grad_norm": 0.08635237067937851,
+      "learning_rate": 1.7233343565317928e-05,
+      "loss": 0.1083,
+      "step": 1250
+    },
+    {
+      "epoch": 2.51072319201995,
+      "grad_norm": 0.07894821465015411,
+      "learning_rate": 1.5954505529137587e-05,
+      "loss": 0.1025,
+      "step": 1260
+    },
+    {
+      "epoch": 2.51072319201995,
+      "eval_loss": 0.10649015009403229,
+      "eval_runtime": 49.129,
+      "eval_samples_per_second": 4.295,
+      "eval_steps_per_second": 2.158,
+      "step": 1260
+    },
+    {
+      "epoch": 2.5306733167082296,
+      "grad_norm": 0.08609526604413986,
+      "learning_rate": 1.472084436280582e-05,
+      "loss": 0.1103,
+      "step": 1270
+    },
+    {
+      "epoch": 2.5506234413965085,
+      "grad_norm": 0.12177404761314392,
+      "learning_rate": 1.3533023194671057e-05,
+      "loss": 0.1124,
+      "step": 1280
+    },
+    {
+      "epoch": 2.570573566084788,
+      "grad_norm": 0.09495075047016144,
+      "learning_rate": 1.2391680512764802e-05,
+      "loss": 0.1099,
+      "step": 1290
+    },
+    {
+      "epoch": 2.570573566084788,
+      "eval_loss": 0.10633713006973267,
+      "eval_runtime": 49.2486,
+      "eval_samples_per_second": 4.284,
+      "eval_steps_per_second": 2.152,
+      "step": 1290
+    },
+    {
+      "epoch": 2.5905236907730673,
+      "grad_norm": 0.08574570715427399,
+      "learning_rate": 1.129742982159574e-05,
+      "loss": 0.1173,
+      "step": 1300
+    },
+    {
+      "epoch": 2.6104738154613467,
+      "grad_norm": 0.08771918714046478,
+      "learning_rate": 1.0250859312373462e-05,
+      "loss": 0.1102,
+      "step": 1310
+    },
+    {
+      "epoch": 2.630423940149626,
+      "grad_norm": 0.07304377853870392,
+      "learning_rate": 9.252531546838872e-06,
+      "loss": 0.1046,
+      "step": 1320
+    },
+    {
+      "epoch": 2.630423940149626,
+      "eval_loss": 0.10615119338035583,
+      "eval_runtime": 48.6835,
+      "eval_samples_per_second": 4.334,
+      "eval_steps_per_second": 2.177,
+      "step": 1320
+    },
+    {
+      "epoch": 2.650374064837905,
+      "grad_norm": 0.09657382220029831,
+      "learning_rate": 8.30298315487098e-06,
+      "loss": 0.1147,
+      "step": 1330
+    },
+    {
+      "epoch": 2.6703241895261844,
+      "grad_norm": 0.09089631587266922,
+      "learning_rate": 7.402724546032957e-06,
+      "loss": 0.1102,
+      "step": 1340
+    },
+    {
+      "epoch": 2.690274314214464,
+      "grad_norm": 0.09991210699081421,
+      "learning_rate": 6.552239635212298e-06,
+      "loss": 0.1202,
+      "step": 1350
+    },
+    {
+      "epoch": 2.690274314214464,
+      "eval_loss": 0.10618466883897781,
+      "eval_runtime": 48.5373,
+      "eval_samples_per_second": 4.347,
+      "eval_steps_per_second": 2.184,
+      "step": 1350
+    },
+    {
+      "epoch": 2.7102244389027432,
+      "grad_norm": 0.13392846286296844,
+      "learning_rate": 5.751985582502672e-06,
+      "loss": 0.1176,
+      "step": 1360
+    },
+    {
+      "epoch": 2.7301745635910226,
+      "grad_norm": 0.10461334884166718,
+      "learning_rate": 5.002392547467194e-06,
+      "loss": 0.1116,
+      "step": 1370
+    },
+    {
+      "epoch": 2.7501246882793016,
+      "grad_norm": 0.0903896763920784,
+      "learning_rate": 4.303863457915358e-06,
+      "loss": 0.1048,
+      "step": 1380
+    },
+    {
+      "epoch": 2.7501246882793016,
+      "eval_loss": 0.10620897263288498,
+      "eval_runtime": 48.5684,
+      "eval_samples_per_second": 4.344,
+      "eval_steps_per_second": 2.182,
+      "step": 1380
+    },
+    {
+      "epoch": 2.770074812967581,
+      "grad_norm": 0.09017899632453918,
+      "learning_rate": 3.6567737933176916e-06,
+      "loss": 0.1028,
+      "step": 1390
+    },
+    {
+      "epoch": 2.7900249376558603,
+      "grad_norm": 0.08241838961839676,
+      "learning_rate": 3.0614713829747456e-06,
+      "loss": 0.1051,
+      "step": 1400
+    },
+    {
+      "epoch": 2.8099750623441397,
+      "grad_norm": 0.12076063454151154,
+      "learning_rate": 2.5182762190488873e-06,
+      "loss": 0.1124,
+      "step": 1410
+    },
+    {
+      "epoch": 2.8099750623441397,
+      "eval_loss": 0.10615089535713196,
+      "eval_runtime": 48.4144,
+      "eval_samples_per_second": 4.358,
+      "eval_steps_per_second": 2.189,
+      "step": 1410
+    },
+    {
+      "epoch": 2.829925187032419,
+      "grad_norm": 0.053800225257873535,
+      "learning_rate": 2.0274802845593133e-06,
+      "loss": 0.1149,
+      "step": 1420
+    },
+    {
+      "epoch": 2.849875311720698,
+      "grad_norm": 0.08684830367565155,
+      "learning_rate": 1.5893473964326832e-06,
+      "loss": 0.1039,
+      "step": 1430
+    },
+    {
+      "epoch": 2.8698254364089775,
+      "grad_norm": 0.10123500972986221,
+      "learning_rate": 1.2041130636940678e-06,
+      "loss": 0.1127,
+      "step": 1440
+    },
+    {
+      "epoch": 2.8698254364089775,
+      "eval_loss": 0.10614271461963654,
+      "eval_runtime": 48.6688,
+      "eval_samples_per_second": 4.335,
+      "eval_steps_per_second": 2.178,
+      "step": 1440
+    },
+    {
+      "epoch": 2.889775561097257,
+      "grad_norm": 0.09655766934156418,
+      "learning_rate": 8.71984360874023e-07,
+      "loss": 0.1105,
+      "step": 1450
+    },
+    {
+      "epoch": 2.9097256857855363,
+      "grad_norm": 0.08582356572151184,
+      "learning_rate": 5.931398167000391e-07,
+      "loss": 0.1038,
+      "step": 1460
+    },
+    {
+      "epoch": 2.9296758104738156,
+      "grad_norm": 0.11041458696126938,
+      "learning_rate": 3.677293181322594e-07,
+      "loss": 0.1046,
+      "step": 1470
+    },
+    {
+      "epoch": 2.9296758104738156,
+      "eval_loss": 0.10609422624111176,
+      "eval_runtime": 48.6034,
+      "eval_samples_per_second": 4.341,
+      "eval_steps_per_second": 2.181,
+      "step": 1470
+    },
+    {
+      "epoch": 2.9496259351620946,
+      "grad_norm": 0.08140657842159271,
+      "learning_rate": 1.9587402979491797e-07,
+      "loss": 0.1058,
+      "step": 1480
+    },
+    {
+      "epoch": 2.969576059850374,
+      "grad_norm": 0.08797825127840042,
+      "learning_rate": 7.766632884689262e-08,
+      "loss": 0.1144,
+      "step": 1490
+    },
+    {
+      "epoch": 2.9895261845386534,
+      "grad_norm": 0.1317855268716812,
+      "learning_rate": 1.316975532625886e-08,
+      "loss": 0.1069,
+      "step": 1500
+    },
+    {
+      "epoch": 2.9895261845386534,
+      "eval_loss": 0.10605818033218384,
+      "eval_runtime": 48.5753,
+      "eval_samples_per_second": 4.344,
+      "eval_steps_per_second": 2.182,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1506,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6429055635399885e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1506/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b731b0ee946922e88f44dfe39a304ed9c9f83d5608887d14bdf636bc4aea59
+size 5777

config.json

@@ -0,0 +1,82 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151654,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.2",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.12.7",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 262144,
+  "pad_token_id": 151654,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.56.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24eaa820700acfb9607a017abb6f080857a2b494bc6ac38f7504154764bedc61
+size 3545956199

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}