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-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1234/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+datasets:
+- u-10bei/sft_alfworld_trajectory_dataset_v5
+- 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: 4096
+- 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_v4
+
+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": [
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "up_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 sha256:15a79747a8e339fa6eb80dd15a1b90fb8cd3bebdcbc354434a8efe9ec1445b23
+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-1200/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-1200/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": [
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b39da285000e79d434ed1697958abe3ad0d3fa20e156a29eee397369ca8d3b
+size 528550256

checkpoint-1200/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-1200/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-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ce8edaf0ee628f44e8a81b1455f21e848bc9b43917c1319de5e70b9e19df2f
+size 1057397963

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49dc7dc6e62a334c060dba5a2f382dbfe4bcc20fc4c40c4527af5595a496cae9
+size 14645

checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6d949af11124459170d8f615d47f6836e3ebe3663df9853e0b395fbb7ece29
+size 1465

checkpoint-1200/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-1200/tokenizer.json

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

checkpoint-1200/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-1200/trainer_state.json

@@ -0,0 +1,1194 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9458527682011764,
+  "eval_steps": 30,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01622388967755019,
+      "grad_norm": 8.625337600708008,
+      "learning_rate": 1.4516129032258066e-05,
+      "loss": 2.6755,
+      "step": 10
+    },
+    {
+      "epoch": 0.03244777935510038,
+      "grad_norm": 0.859293520450592,
+      "learning_rate": 3.0645161290322585e-05,
+      "loss": 1.0056,
+      "step": 20
+    },
+    {
+      "epoch": 0.04867166903265058,
+      "grad_norm": 0.7715856432914734,
+      "learning_rate": 4.67741935483871e-05,
+      "loss": 0.6365,
+      "step": 30
+    },
+    {
+      "epoch": 0.04867166903265058,
+      "eval_loss": 0.5236709713935852,
+      "eval_runtime": 55.0101,
+      "eval_samples_per_second": 4.726,
+      "eval_steps_per_second": 4.726,
+      "step": 30
+    },
+    {
+      "epoch": 0.06489555871020077,
+      "grad_norm": 0.5313697457313538,
+      "learning_rate": 6.290322580645161e-05,
+      "loss": 0.4295,
+      "step": 40
+    },
+    {
+      "epoch": 0.08111944838775097,
+      "grad_norm": 1.1634626388549805,
+      "learning_rate": 7.903225806451613e-05,
+      "loss": 0.3387,
+      "step": 50
+    },
+    {
+      "epoch": 0.09734333806530115,
+      "grad_norm": 0.7073950171470642,
+      "learning_rate": 9.516129032258065e-05,
+      "loss": 0.2797,
+      "step": 60
+    },
+    {
+      "epoch": 0.09734333806530115,
+      "eval_loss": 0.2691636085510254,
+      "eval_runtime": 54.4477,
+      "eval_samples_per_second": 4.775,
+      "eval_steps_per_second": 4.775,
+      "step": 60
+    },
+    {
+      "epoch": 0.11356722774285134,
+      "grad_norm": 0.5980345606803894,
+      "learning_rate": 0.00011129032258064515,
+      "loss": 0.2525,
+      "step": 70
+    },
+    {
+      "epoch": 0.12979111742040153,
+      "grad_norm": 0.5646739602088928,
+      "learning_rate": 0.0001274193548387097,
+      "loss": 0.2208,
+      "step": 80
+    },
+    {
+      "epoch": 0.14601500709795173,
+      "grad_norm": 0.33468499779701233,
+      "learning_rate": 0.00014354838709677422,
+      "loss": 0.2018,
+      "step": 90
+    },
+    {
+      "epoch": 0.14601500709795173,
+      "eval_loss": 0.1886902004480362,
+      "eval_runtime": 54.4734,
+      "eval_samples_per_second": 4.773,
+      "eval_steps_per_second": 4.773,
+      "step": 90
+    },
+    {
+      "epoch": 0.16223889677550193,
+      "grad_norm": 0.3952212929725647,
+      "learning_rate": 0.00015967741935483872,
+      "loss": 0.1841,
+      "step": 100
+    },
+    {
+      "epoch": 0.1784627864530521,
+      "grad_norm": 0.34694239497184753,
+      "learning_rate": 0.00017580645161290325,
+      "loss": 0.1731,
+      "step": 110
+    },
+    {
+      "epoch": 0.1946866761306023,
+      "grad_norm": 0.3307943046092987,
+      "learning_rate": 0.00019193548387096775,
+      "loss": 0.1736,
+      "step": 120
+    },
+    {
+      "epoch": 0.1946866761306023,
+      "eval_loss": 0.1661035567522049,
+      "eval_runtime": 54.4184,
+      "eval_samples_per_second": 4.778,
+      "eval_steps_per_second": 4.778,
+      "step": 120
+    },
+    {
+      "epoch": 0.2109105658081525,
+      "grad_norm": 0.2933768928050995,
+      "learning_rate": 0.0001999899871766749,
+      "loss": 0.1616,
+      "step": 130
+    },
+    {
+      "epoch": 0.22713445548570269,
+      "grad_norm": 0.3262489438056946,
+      "learning_rate": 0.00019990989662046818,
+      "loss": 0.1619,
+      "step": 140
+    },
+    {
+      "epoch": 0.2433583451632529,
+      "grad_norm": 0.18724548816680908,
+      "learning_rate": 0.00019974977965945,
+      "loss": 0.1482,
+      "step": 150
+    },
+    {
+      "epoch": 0.2433583451632529,
+      "eval_loss": 0.14517094194889069,
+      "eval_runtime": 54.4554,
+      "eval_samples_per_second": 4.775,
+      "eval_steps_per_second": 4.775,
+      "step": 150
+    },
+    {
+      "epoch": 0.25958223484080306,
+      "grad_norm": 0.39443448185920715,
+      "learning_rate": 0.0001995097645450266,
+      "loss": 0.1571,
+      "step": 160
+    },
+    {
+      "epoch": 0.2758061245183533,
+      "grad_norm": 0.3215681314468384,
+      "learning_rate": 0.00019919004352588767,
+      "loss": 0.1518,
+      "step": 170
+    },
+    {
+      "epoch": 0.29203001419590346,
+      "grad_norm": 0.1917540580034256,
+      "learning_rate": 0.0001987908726940178,
+      "loss": 0.1477,
+      "step": 180
+    },
+    {
+      "epoch": 0.29203001419590346,
+      "eval_loss": 0.1380539983510971,
+      "eval_runtime": 54.5257,
+      "eval_samples_per_second": 4.768,
+      "eval_steps_per_second": 4.768,
+      "step": 180
+    },
+    {
+      "epoch": 0.30825390387345364,
+      "grad_norm": 0.27752983570098877,
+      "learning_rate": 0.00019831257177957044,
+      "loss": 0.1352,
+      "step": 190
+    },
+    {
+      "epoch": 0.32447779355100387,
+      "grad_norm": 0.3052772879600525,
+      "learning_rate": 0.00019775552389476864,
+      "loss": 0.1425,
+      "step": 200
+    },
+    {
+      "epoch": 0.34070168322855404,
+      "grad_norm": 0.17911162972450256,
+      "learning_rate": 0.00019712017522703764,
+      "loss": 0.1411,
+      "step": 210
+    },
+    {
+      "epoch": 0.34070168322855404,
+      "eval_loss": 0.13320107758045197,
+      "eval_runtime": 54.1867,
+      "eval_samples_per_second": 4.798,
+      "eval_steps_per_second": 4.798,
+      "step": 210
+    },
+    {
+      "epoch": 0.3569255729061042,
+      "grad_norm": 0.15296442806720734,
+      "learning_rate": 0.0001964070346816151,
+      "loss": 0.1378,
+      "step": 220
+    },
+    {
+      "epoch": 0.37314946258365445,
+      "grad_norm": 0.17346209287643433,
+      "learning_rate": 0.00019561667347392508,
+      "loss": 0.136,
+      "step": 230
+    },
+    {
+      "epoch": 0.3893733522612046,
+      "grad_norm": 0.16340570151805878,
+      "learning_rate": 0.00019474972467204297,
+      "loss": 0.1395,
+      "step": 240
+    },
+    {
+      "epoch": 0.3893733522612046,
+      "eval_loss": 0.13255620002746582,
+      "eval_runtime": 54.3562,
+      "eval_samples_per_second": 4.783,
+      "eval_steps_per_second": 4.783,
+      "step": 240
+    },
+    {
+      "epoch": 0.4055972419387548,
+      "grad_norm": 0.2969210147857666,
+      "learning_rate": 0.0001938068826896166,
+      "loss": 0.1368,
+      "step": 250
+    },
+    {
+      "epoch": 0.421821131616305,
+      "grad_norm": 0.20236295461654663,
+      "learning_rate": 0.00019278890272965096,
+      "loss": 0.1273,
+      "step": 260
+    },
+    {
+      "epoch": 0.4380450212938552,
+      "grad_norm": 0.2891747057437897,
+      "learning_rate": 0.00019169660017960137,
+      "loss": 0.129,
+      "step": 270
+    },
+    {
+      "epoch": 0.4380450212938552,
+      "eval_loss": 0.12807676196098328,
+      "eval_runtime": 54.3522,
+      "eval_samples_per_second": 4.784,
+      "eval_steps_per_second": 4.784,
+      "step": 270
+    },
+    {
+      "epoch": 0.45426891097140537,
+      "grad_norm": 0.20254789292812347,
+      "learning_rate": 0.0001905308499582597,
+      "loss": 0.141,
+      "step": 280
+    },
+    {
+      "epoch": 0.4704928006489556,
+      "grad_norm": 0.1715897023677826,
+      "learning_rate": 0.00018929258581495685,
+      "loss": 0.1329,
+      "step": 290
+    },
+    {
+      "epoch": 0.4867166903265058,
+      "grad_norm": 0.3499029278755188,
+      "learning_rate": 0.00018798279958164295,
+      "loss": 0.1355,
+      "step": 300
+    },
+    {
+      "epoch": 0.4867166903265058,
+      "eval_loss": 0.12350723892450333,
+      "eval_runtime": 54.5668,
+      "eval_samples_per_second": 4.765,
+      "eval_steps_per_second": 4.765,
+      "step": 300
+    },
+    {
+      "epoch": 0.502940580004056,
+      "grad_norm": 0.15775884687900543,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.126,
+      "step": 310
+    },
+    {
+      "epoch": 0.5191644696816061,
+      "grad_norm": 0.19402213394641876,
+      "learning_rate": 0.00018515291377333112,
+      "loss": 0.1332,
+      "step": 320
+    },
+    {
+      "epoch": 0.5353883593591564,
+      "grad_norm": 0.13237500190734863,
+      "learning_rate": 0.0001836350808965776,
+      "loss": 0.1441,
+      "step": 330
+    },
+    {
+      "epoch": 0.5353883593591564,
+      "eval_loss": 0.12080405652523041,
+      "eval_runtime": 54.7379,
+      "eval_samples_per_second": 4.75,
+      "eval_steps_per_second": 4.75,
+      "step": 330
+    },
+    {
+      "epoch": 0.5516122490367066,
+      "grad_norm": 0.29119789600372314,
+      "learning_rate": 0.00018205025751070875,
+      "loss": 0.1245,
+      "step": 340
+    },
+    {
+      "epoch": 0.5678361387142568,
+      "grad_norm": 0.15898150205612183,
+      "learning_rate": 0.00018039971303669407,
+      "loss": 0.121,
+      "step": 350
+    },
+    {
+      "epoch": 0.5840600283918069,
+      "grad_norm": 0.13710354268550873,
+      "learning_rate": 0.000178684769537159,
+      "loss": 0.1346,
+      "step": 360
+    },
+    {
+      "epoch": 0.5840600283918069,
+      "eval_loss": 0.12007435411214828,
+      "eval_runtime": 54.7789,
+      "eval_samples_per_second": 4.746,
+      "eval_steps_per_second": 4.746,
+      "step": 360
+    },
+    {
+      "epoch": 0.6002839180693571,
+      "grad_norm": 0.12323573976755142,
+      "learning_rate": 0.0001769068006574317,
+      "loss": 0.1311,
+      "step": 370
+    },
+    {
+      "epoch": 0.6165078077469073,
+      "grad_norm": 0.14197634160518646,
+      "learning_rate": 0.00017506723052527242,
+      "loss": 0.122,
+      "step": 380
+    },
+    {
+      "epoch": 0.6327316974244576,
+      "grad_norm": 0.13415870070457458,
+      "learning_rate": 0.00017316753261016783,
+      "loss": 0.1242,
+      "step": 390
+    },
+    {
+      "epoch": 0.6327316974244576,
+      "eval_loss": 0.11815402656793594,
+      "eval_runtime": 54.9041,
+      "eval_samples_per_second": 4.736,
+      "eval_steps_per_second": 4.736,
+      "step": 390
+    },
+    {
+      "epoch": 0.6489555871020077,
+      "grad_norm": 0.14391979575157166,
+      "learning_rate": 0.00017120922854310257,
+      "loss": 0.1235,
+      "step": 400
+    },
+    {
+      "epoch": 0.6651794767795579,
+      "grad_norm": 0.12567928433418274,
+      "learning_rate": 0.00016919388689775464,
+      "loss": 0.1292,
+      "step": 410
+    },
+    {
+      "epoch": 0.6814033664571081,
+      "grad_norm": 0.24638038873672485,
+      "learning_rate": 0.0001671231219340903,
+      "loss": 0.124,
+      "step": 420
+    },
+    {
+      "epoch": 0.6814033664571081,
+      "eval_loss": 0.11765418201684952,
+      "eval_runtime": 54.8324,
+      "eval_samples_per_second": 4.742,
+      "eval_steps_per_second": 4.742,
+      "step": 420
+    },
+    {
+      "epoch": 0.6976272561346583,
+      "grad_norm": 0.11872219294309616,
+      "learning_rate": 0.00016499859230536466,
+      "loss": 0.1284,
+      "step": 430
+    },
+    {
+      "epoch": 0.7138511458122084,
+      "grad_norm": 0.14060816168785095,
+      "learning_rate": 0.00016282199972956425,
+      "loss": 0.1228,
+      "step": 440
+    },
+    {
+      "epoch": 0.7300750354897587,
+      "grad_norm": 0.1108463779091835,
+      "learning_rate": 0.00016059508762635482,
+      "loss": 0.1315,
+      "step": 450
+    },
+    {
+      "epoch": 0.7300750354897587,
+      "eval_loss": 0.11692557483911514,
+      "eval_runtime": 55.1996,
+      "eval_samples_per_second": 4.71,
+      "eval_steps_per_second": 4.71,
+      "step": 450
+    },
+    {
+      "epoch": 0.7462989251673089,
+      "grad_norm": 0.13592351973056793,
+      "learning_rate": 0.00015831963972062733,
+      "loss": 0.1235,
+      "step": 460
+    },
+    {
+      "epoch": 0.7625228148448591,
+      "grad_norm": 0.12181869149208069,
+      "learning_rate": 0.00015599747861375955,
+      "loss": 0.12,
+      "step": 470
+    },
+    {
+      "epoch": 0.7787467045224092,
+      "grad_norm": 0.37740716338157654,
+      "learning_rate": 0.00015363046432373824,
+      "loss": 0.119,
+      "step": 480
+    },
+    {
+      "epoch": 0.7787467045224092,
+      "eval_loss": 0.11858060956001282,
+      "eval_runtime": 55.2002,
+      "eval_samples_per_second": 4.71,
+      "eval_steps_per_second": 4.71,
+      "step": 480
+    },
+    {
+      "epoch": 0.7949705941999594,
+      "grad_norm": 0.3189144432544708,
+      "learning_rate": 0.00015122049279531143,
+      "loss": 0.1322,
+      "step": 490
+    },
+    {
+      "epoch": 0.8111944838775096,
+      "grad_norm": 0.15118102729320526,
+      "learning_rate": 0.00014876949438136347,
+      "loss": 0.1211,
+      "step": 500
+    },
+    {
+      "epoch": 0.8274183735550599,
+      "grad_norm": 0.09746048599481583,
+      "learning_rate": 0.0001462794322967299,
+      "loss": 0.124,
+      "step": 510
+    },
+    {
+      "epoch": 0.8274183735550599,
+      "eval_loss": 0.11739031225442886,
+      "eval_runtime": 54.9138,
+      "eval_samples_per_second": 4.735,
+      "eval_steps_per_second": 4.735,
+      "step": 510
+    },
+    {
+      "epoch": 0.84364226323261,
+      "grad_norm": 0.11682560294866562,
+      "learning_rate": 0.00014375230104569044,
+      "loss": 0.1219,
+      "step": 520
+    },
+    {
+      "epoch": 0.8598661529101602,
+      "grad_norm": 0.10706628113985062,
+      "learning_rate": 0.0001411901248243993,
+      "loss": 0.1198,
+      "step": 530
+    },
+    {
+      "epoch": 0.8760900425877104,
+      "grad_norm": 0.26870429515838623,
+      "learning_rate": 0.0001385949558995329,
+      "loss": 0.1253,
+      "step": 540
+    },
+    {
+      "epoch": 0.8760900425877104,
+      "eval_loss": 0.11531012505292892,
+      "eval_runtime": 54.9326,
+      "eval_samples_per_second": 4.733,
+      "eval_steps_per_second": 4.733,
+      "step": 540
+    },
+    {
+      "epoch": 0.8923139322652606,
+      "grad_norm": 0.09110305458307266,
+      "learning_rate": 0.0001359688729644536,
+      "loss": 0.1129,
+      "step": 550
+    },
+    {
+      "epoch": 0.9085378219428107,
+      "grad_norm": 0.11204719543457031,
+      "learning_rate": 0.00013331397947420576,
+      "loss": 0.129,
+      "step": 560
+    },
+    {
+      "epoch": 0.924761711620361,
+      "grad_norm": 0.15059269964694977,
+      "learning_rate": 0.00013063240196067836,
+      "loss": 0.1272,
+      "step": 570
+    },
+    {
+      "epoch": 0.924761711620361,
+      "eval_loss": 0.11525142192840576,
+      "eval_runtime": 55.1098,
+      "eval_samples_per_second": 4.718,
+      "eval_steps_per_second": 4.718,
+      "step": 570
+    },
+    {
+      "epoch": 0.9409856012979112,
+      "grad_norm": 0.11085380613803864,
+      "learning_rate": 0.00012792628832928302,
+      "loss": 0.1243,
+      "step": 580
+    },
+    {
+      "epoch": 0.9572094909754614,
+      "grad_norm": 0.10796050727367401,
+      "learning_rate": 0.00012519780613851254,
+      "loss": 0.1197,
+      "step": 590
+    },
+    {
+      "epoch": 0.9734333806530115,
+      "grad_norm": 0.08801472187042236,
+      "learning_rate": 0.00012244914086375724,
+      "loss": 0.1261,
+      "step": 600
+    },
+    {
+      "epoch": 0.9734333806530115,
+      "eval_loss": 0.11538033187389374,
+      "eval_runtime": 54.7547,
+      "eval_samples_per_second": 4.748,
+      "eval_steps_per_second": 4.748,
+      "step": 600
+    },
+    {
+      "epoch": 0.9896572703305617,
+      "grad_norm": 0.08395121991634369,
+      "learning_rate": 0.00011968249414677055,
+      "loss": 0.1215,
+      "step": 610
+    },
+    {
+      "epoch": 1.0048671669032652,
+      "grad_norm": 0.10106801986694336,
+      "learning_rate": 0.00011690008203218493,
+      "loss": 0.1206,
+      "step": 620
+    },
+    {
+      "epoch": 1.0210910565808153,
+      "grad_norm": 0.08509080857038498,
+      "learning_rate": 0.00011410413319249194,
+      "loss": 0.1125,
+      "step": 630
+    },
+    {
+      "epoch": 1.0210910565808153,
+      "eval_loss": 0.11403891444206238,
+      "eval_runtime": 54.6547,
+      "eval_samples_per_second": 4.757,
+      "eval_steps_per_second": 4.757,
+      "step": 630
+    },
+    {
+      "epoch": 1.0373149462583655,
+      "grad_norm": 0.09074535965919495,
+      "learning_rate": 0.00011129688714290729,
+      "loss": 0.1167,
+      "step": 640
+    },
+    {
+      "epoch": 1.0535388359359157,
+      "grad_norm": 0.10673358291387558,
+      "learning_rate": 0.00010848059244755093,
+      "loss": 0.1082,
+      "step": 650
+    },
+    {
+      "epoch": 1.0697627256134659,
+      "grad_norm": 0.11839364469051361,
+      "learning_rate": 0.00010565750491837925,
+      "loss": 0.1192,
+      "step": 660
+    },
+    {
+      "epoch": 1.0697627256134659,
+      "eval_loss": 0.11325760185718536,
+      "eval_runtime": 54.7532,
+      "eval_samples_per_second": 4.749,
+      "eval_steps_per_second": 4.749,
+      "step": 660
+    },
+    {
+      "epoch": 1.085986615291016,
+      "grad_norm": 0.08097315579652786,
+      "learning_rate": 0.00010282988580831183,
+      "loss": 0.1188,
+      "step": 670
+    },
+    {
+      "epoch": 1.1022105049685662,
+      "grad_norm": 0.10252730548381805,
+      "learning_rate": 0.0001,
+      "loss": 0.1217,
+      "step": 680
+    },
+    {
+      "epoch": 1.1184343946461164,
+      "grad_norm": 0.1087854653596878,
+      "learning_rate": 9.71701141916882e-05,
+      "loss": 0.1185,
+      "step": 690
+    },
+    {
+      "epoch": 1.1184343946461164,
+      "eval_loss": 0.11274029314517975,
+      "eval_runtime": 54.6489,
+      "eval_samples_per_second": 4.758,
+      "eval_steps_per_second": 4.758,
+      "step": 690
+    },
+    {
+      "epoch": 1.1346582843236666,
+      "grad_norm": 0.09857626259326935,
+      "learning_rate": 9.434249508162076e-05,
+      "loss": 0.1225,
+      "step": 700
+    },
+    {
+      "epoch": 1.1508821740012167,
+      "grad_norm": 0.09853193908929825,
+      "learning_rate": 9.151940755244912e-05,
+      "loss": 0.1185,
+      "step": 710
+    },
+    {
+      "epoch": 1.167106063678767,
+      "grad_norm": 0.0954899936914444,
+      "learning_rate": 8.870311285709274e-05,
+      "loss": 0.1336,
+      "step": 720
+    },
+    {
+      "epoch": 1.167106063678767,
+      "eval_loss": 0.11281841993331909,
+      "eval_runtime": 54.5506,
+      "eval_samples_per_second": 4.766,
+      "eval_steps_per_second": 4.766,
+      "step": 720
+    },
+    {
+      "epoch": 1.183329953356317,
+      "grad_norm": 0.0967244803905487,
+      "learning_rate": 8.58958668075081e-05,
+      "loss": 0.118,
+      "step": 730
+    },
+    {
+      "epoch": 1.1995538430338675,
+      "grad_norm": 0.09406362473964691,
+      "learning_rate": 8.309991796781511e-05,
+      "loss": 0.1218,
+      "step": 740
+    },
+    {
+      "epoch": 1.2157777327114176,
+      "grad_norm": 0.0989699587225914,
+      "learning_rate": 8.031750585322947e-05,
+      "loss": 0.1178,
+      "step": 750
+    },
+    {
+      "epoch": 1.2157777327114176,
+      "eval_loss": 0.11203999817371368,
+      "eval_runtime": 54.636,
+      "eval_samples_per_second": 4.759,
+      "eval_steps_per_second": 4.759,
+      "step": 750
+    },
+    {
+      "epoch": 1.2320016223889678,
+      "grad_norm": 0.10200025886297226,
+      "learning_rate": 7.755085913624274e-05,
+      "loss": 0.1126,
+      "step": 760
+    },
+    {
+      "epoch": 1.248225512066518,
+      "grad_norm": 0.09863891452550888,
+      "learning_rate": 7.48021938614875e-05,
+      "loss": 0.1253,
+      "step": 770
+    },
+    {
+      "epoch": 1.2644494017440682,
+      "grad_norm": 0.07942435145378113,
+      "learning_rate": 7.2073711670717e-05,
+      "loss": 0.1188,
+      "step": 780
+    },
+    {
+      "epoch": 1.2644494017440682,
+      "eval_loss": 0.11259657144546509,
+      "eval_runtime": 54.5511,
+      "eval_samples_per_second": 4.766,
+      "eval_steps_per_second": 4.766,
+      "step": 780
+    },
+    {
+      "epoch": 1.2806732914216183,
+      "grad_norm": 0.13004329800605774,
+      "learning_rate": 6.936759803932167e-05,
+      "loss": 0.1158,
+      "step": 790
+    },
+    {
+      "epoch": 1.2968971810991685,
+      "grad_norm": 0.08646363765001297,
+      "learning_rate": 6.668602052579424e-05,
+      "loss": 0.1173,
+      "step": 800
+    },
+    {
+      "epoch": 1.3131210707767187,
+      "grad_norm": 0.08868124336004257,
+      "learning_rate": 6.403112703554643e-05,
+      "loss": 0.1065,
+      "step": 810
+    },
+    {
+      "epoch": 1.3131210707767187,
+      "eval_loss": 0.1115630567073822,
+      "eval_runtime": 55.0171,
+      "eval_samples_per_second": 4.726,
+      "eval_steps_per_second": 4.726,
+      "step": 810
+    },
+    {
+      "epoch": 1.3293449604542689,
+      "grad_norm": 0.08065708726644516,
+      "learning_rate": 6.140504410046712e-05,
+      "loss": 0.1243,
+      "step": 820
+    },
+    {
+      "epoch": 1.345568850131819,
+      "grad_norm": 0.08410122245550156,
+      "learning_rate": 5.880987517560075e-05,
+      "loss": 0.114,
+      "step": 830
+    },
+    {
+      "epoch": 1.3617927398093692,
+      "grad_norm": 0.0926986113190651,
+      "learning_rate": 5.624769895430961e-05,
+      "loss": 0.1178,
+      "step": 840
+    },
+    {
+      "epoch": 1.3617927398093692,
+      "eval_loss": 0.11092434078454971,
+      "eval_runtime": 55.2141,
+      "eval_samples_per_second": 4.709,
+      "eval_steps_per_second": 4.709,
+      "step": 840
+    },
+    {
+      "epoch": 1.3780166294869196,
+      "grad_norm": 0.07351404428482056,
+      "learning_rate": 5.372056770327013e-05,
+      "loss": 0.1108,
+      "step": 850
+    },
+    {
+      "epoch": 1.3942405191644696,
+      "grad_norm": 0.08835868537425995,
+      "learning_rate": 5.123050561863657e-05,
+      "loss": 0.1127,
+      "step": 860
+    },
+    {
+      "epoch": 1.41046440884202,
+      "grad_norm": 0.08012858778238297,
+      "learning_rate": 4.877950720468859e-05,
+      "loss": 0.1118,
+      "step": 870
+    },
+    {
+      "epoch": 1.41046440884202,
+      "eval_loss": 0.11060689389705658,
+      "eval_runtime": 55.1249,
+      "eval_samples_per_second": 4.717,
+      "eval_steps_per_second": 4.717,
+      "step": 870
+    },
+    {
+      "epoch": 1.4266882985195701,
+      "grad_norm": 0.09063031524419785,
+      "learning_rate": 4.636953567626177e-05,
+      "loss": 0.1195,
+      "step": 880
+    },
+    {
+      "epoch": 1.4429121881971203,
+      "grad_norm": 0.07680074125528336,
+      "learning_rate": 4.4002521386240466e-05,
+      "loss": 0.1133,
+      "step": 890
+    },
+    {
+      "epoch": 1.4591360778746705,
+      "grad_norm": 0.09211437404155731,
+      "learning_rate": 4.168036027937267e-05,
+      "loss": 0.113,
+      "step": 900
+    },
+    {
+      "epoch": 1.4591360778746705,
+      "eval_loss": 0.1109917163848877,
+      "eval_runtime": 54.6876,
+      "eval_samples_per_second": 4.754,
+      "eval_steps_per_second": 4.754,
+      "step": 900
+    },
+    {
+      "epoch": 1.4753599675522207,
+      "grad_norm": 0.08036933839321136,
+      "learning_rate": 3.9404912373645185e-05,
+      "loss": 0.1183,
+      "step": 910
+    },
+    {
+      "epoch": 1.4915838572297708,
+      "grad_norm": 0.07682196795940399,
+      "learning_rate": 3.717800027043576e-05,
+      "loss": 0.1198,
+      "step": 920
+    },
+    {
+      "epoch": 1.507807746907321,
+      "grad_norm": 0.08601044863462448,
+      "learning_rate": 3.500140769463533e-05,
+      "loss": 0.1209,
+      "step": 930
+    },
+    {
+      "epoch": 1.507807746907321,
+      "eval_loss": 0.1104922965168953,
+      "eval_runtime": 54.6525,
+      "eval_samples_per_second": 4.757,
+      "eval_steps_per_second": 4.757,
+      "step": 930
+    },
+    {
+      "epoch": 1.5240316365848712,
+      "grad_norm": 0.08242760598659515,
+      "learning_rate": 3.287687806590971e-05,
+      "loss": 0.1127,
+      "step": 940
+    },
+    {
+      "epoch": 1.5402555262624213,
+      "grad_norm": 0.08664223551750183,
+      "learning_rate": 3.080611310224539e-05,
+      "loss": 0.1193,
+      "step": 950
+    },
+    {
+      "epoch": 1.5564794159399717,
+      "grad_norm": 0.08529651165008545,
+      "learning_rate": 2.879077145689746e-05,
+      "loss": 0.1126,
+      "step": 960
+    },
+    {
+      "epoch": 1.5564794159399717,
+      "eval_loss": 0.10984186083078384,
+      "eval_runtime": 54.6191,
+      "eval_samples_per_second": 4.76,
+      "eval_steps_per_second": 4.76,
+      "step": 960
+    },
+    {
+      "epoch": 1.5727033056175217,
+      "grad_norm": 0.07219547033309937,
+      "learning_rate": 2.6832467389832173e-05,
+      "loss": 0.1182,
+      "step": 970
+    },
+    {
+      "epoch": 1.588927195295072,
+      "grad_norm": 0.10246000438928604,
+      "learning_rate": 2.493276947472756e-05,
+      "loss": 0.1109,
+      "step": 980
+    },
+    {
+      "epoch": 1.605151084972622,
+      "grad_norm": 0.08859504014253616,
+      "learning_rate": 2.3093199342568318e-05,
+      "loss": 0.1137,
+      "step": 990
+    },
+    {
+      "epoch": 1.605151084972622,
+      "eval_loss": 0.10924239456653595,
+      "eval_runtime": 54.6323,
+      "eval_samples_per_second": 4.759,
+      "eval_steps_per_second": 4.759,
+      "step": 990
+    },
+    {
+      "epoch": 1.6213749746501724,
+      "grad_norm": 0.08224408328533173,
+      "learning_rate": 2.1315230462840985e-05,
+      "loss": 0.1168,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6375988643277226,
+      "grad_norm": 0.09429515153169632,
+      "learning_rate": 1.9600286963305957e-05,
+      "loss": 0.114,
+      "step": 1010
+    },
+    {
+      "epoch": 1.6538227540052728,
+      "grad_norm": 0.08045922219753265,
+      "learning_rate": 1.7949742489291255e-05,
+      "loss": 0.111,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6538227540052728,
+      "eval_loss": 0.10893593728542328,
+      "eval_runtime": 54.7365,
+      "eval_samples_per_second": 4.75,
+      "eval_steps_per_second": 4.75,
+      "step": 1020
+    },
+    {
+      "epoch": 1.670046643682823,
+      "grad_norm": 0.0847032219171524,
+      "learning_rate": 1.6364919103422393e-05,
+      "loss": 0.1142,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6862705333603731,
+      "grad_norm": 0.08252795040607452,
+      "learning_rate": 1.4847086226668872e-05,
+      "loss": 0.1126,
+      "step": 1040
+    },
+    {
+      "epoch": 1.7024944230379233,
+      "grad_norm": 0.0862165316939354,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.1186,
+      "step": 1050
+    },
+    {
+      "epoch": 1.7024944230379233,
+      "eval_loss": 0.1090201735496521,
+      "eval_runtime": 54.7713,
+      "eval_samples_per_second": 4.747,
+      "eval_steps_per_second": 4.747,
+      "step": 1050
+    },
+    {
+      "epoch": 1.7187183127154735,
+      "grad_norm": 0.09021241962909698,
+      "learning_rate": 1.2017200418357078e-05,
+      "loss": 0.1178,
+      "step": 1060
+    },
+    {
+      "epoch": 1.7349422023930239,
+      "grad_norm": 0.07867942750453949,
+      "learning_rate": 1.0707414185043163e-05,
+      "loss": 0.1041,
+      "step": 1070
+    },
+    {
+      "epoch": 1.7511660920705738,
+      "grad_norm": 0.10106240212917328,
+      "learning_rate": 9.469150041740338e-06,
+      "loss": 0.1111,
+      "step": 1080
+    },
+    {
+      "epoch": 1.7511660920705738,
+      "eval_loss": 0.10924577713012695,
+      "eval_runtime": 54.6761,
+      "eval_samples_per_second": 4.755,
+      "eval_steps_per_second": 4.755,
+      "step": 1080
+    },
+    {
+      "epoch": 1.7673899817481242,
+      "grad_norm": 0.1259811371564865,
+      "learning_rate": 8.303399820398672e-06,
+      "loss": 0.1118,
+      "step": 1090
+    },
+    {
+      "epoch": 1.7836138714256742,
+      "grad_norm": 0.07995796203613281,
+      "learning_rate": 7.211097270349066e-06,
+      "loss": 0.1005,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7998377611032246,
+      "grad_norm": 0.0811864510178566,
+      "learning_rate": 6.1931173103834115e-06,
+      "loss": 0.115,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7998377611032246,
+      "eval_loss": 0.10901561379432678,
+      "eval_runtime": 54.5743,
+      "eval_samples_per_second": 4.764,
+      "eval_steps_per_second": 4.764,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8160616507807745,
+      "grad_norm": 0.10539617389440536,
+      "learning_rate": 5.250275327957032e-06,
+      "loss": 0.1129,
+      "step": 1120
+    },
+    {
+      "epoch": 1.832285540458325,
+      "grad_norm": 0.15508656203746796,
+      "learning_rate": 4.383326526074916e-06,
+      "loss": 0.1258,
+      "step": 1130
+    },
+    {
+      "epoch": 1.848509430135875,
+      "grad_norm": 0.08507981151342392,
+      "learning_rate": 3.592965318384944e-06,
+      "loss": 0.1123,
+      "step": 1140
+    },
+    {
+      "epoch": 1.848509430135875,
+      "eval_loss": 0.1087607592344284,
+      "eval_runtime": 54.908,
+      "eval_samples_per_second": 4.735,
+      "eval_steps_per_second": 4.735,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8647333198134253,
+      "grad_norm": 0.08362692594528198,
+      "learning_rate": 2.8798247729623806e-06,
+      "loss": 0.1164,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8809572094909754,
+      "grad_norm": 0.08825893700122833,
+      "learning_rate": 2.2444761052313856e-06,
+      "loss": 0.1223,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8971810991685256,
+      "grad_norm": 0.07475200295448303,
+      "learning_rate": 1.6874282204295766e-06,
+      "loss": 0.1101,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8971810991685256,
+      "eval_loss": 0.108616404235363,
+      "eval_runtime": 55.1832,
+      "eval_samples_per_second": 4.712,
+      "eval_steps_per_second": 4.712,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9134049888460758,
+      "grad_norm": 0.07395757734775543,
+      "learning_rate": 1.209127305982205e-06,
+      "loss": 0.1217,
+      "step": 1180
+    },
+    {
+      "epoch": 1.929628878523626,
+      "grad_norm": 0.1036606878042221,
+      "learning_rate": 8.099564741123166e-07,
+      "loss": 0.1167,
+      "step": 1190
+    },
+    {
+      "epoch": 1.9458527682011764,
+      "grad_norm": 0.07940636575222015,
+      "learning_rate": 4.902354549733978e-07,
+      "loss": 0.1111,
+      "step": 1200
+    },
+    {
+      "epoch": 1.9458527682011764,
+      "eval_loss": 0.10869967937469482,
+      "eval_runtime": 54.8601,
+      "eval_samples_per_second": 4.739,
+      "eval_steps_per_second": 4.739,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1234,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.675362213715753e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:655eb02b0fc57181f2ec10794d297d90572f277d219938ab929b99cc63bae9d3
+size 5777

checkpoint-1234/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-1234/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": [
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1234/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a79747a8e339fa6eb80dd15a1b90fb8cd3bebdcbc354434a8efe9ec1445b23
+size 528550256

checkpoint-1234/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-1234/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-1234/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c1950696eb03b18de9ca14c900464cc48336a645cef79b9ad1a4514286ae782
+size 1057397963

checkpoint-1234/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c6125e7f8b1d602d445684db96028dd4bebf6136a4ba2ad7a2511744f2e8d2
+size 14645

checkpoint-1234/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf0609e30028e090577bdfc35ea416e5919760eaf4c70564e6be8994ee67cff2
+size 1465

checkpoint-1234/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-1234/tokenizer.json

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

checkpoint-1234/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-1234/trainer_state.json

@@ -0,0 +1,1223 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 30,
+  "global_step": 1234,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01622388967755019,
+      "grad_norm": 8.625337600708008,
+      "learning_rate": 1.4516129032258066e-05,
+      "loss": 2.6755,
+      "step": 10
+    },
+    {
+      "epoch": 0.03244777935510038,
+      "grad_norm": 0.859293520450592,
+      "learning_rate": 3.0645161290322585e-05,
+      "loss": 1.0056,
+      "step": 20
+    },
+    {
+      "epoch": 0.04867166903265058,
+      "grad_norm": 0.7715856432914734,
+      "learning_rate": 4.67741935483871e-05,
+      "loss": 0.6365,
+      "step": 30
+    },
+    {
+      "epoch": 0.04867166903265058,
+      "eval_loss": 0.5236709713935852,
+      "eval_runtime": 55.0101,
+      "eval_samples_per_second": 4.726,
+      "eval_steps_per_second": 4.726,
+      "step": 30
+    },
+    {
+      "epoch": 0.06489555871020077,
+      "grad_norm": 0.5313697457313538,
+      "learning_rate": 6.290322580645161e-05,
+      "loss": 0.4295,
+      "step": 40
+    },
+    {
+      "epoch": 0.08111944838775097,
+      "grad_norm": 1.1634626388549805,
+      "learning_rate": 7.903225806451613e-05,
+      "loss": 0.3387,
+      "step": 50
+    },
+    {
+      "epoch": 0.09734333806530115,
+      "grad_norm": 0.7073950171470642,
+      "learning_rate": 9.516129032258065e-05,
+      "loss": 0.2797,
+      "step": 60
+    },
+    {
+      "epoch": 0.09734333806530115,
+      "eval_loss": 0.2691636085510254,
+      "eval_runtime": 54.4477,
+      "eval_samples_per_second": 4.775,
+      "eval_steps_per_second": 4.775,
+      "step": 60
+    },
+    {
+      "epoch": 0.11356722774285134,
+      "grad_norm": 0.5980345606803894,
+      "learning_rate": 0.00011129032258064515,
+      "loss": 0.2525,
+      "step": 70
+    },
+    {
+      "epoch": 0.12979111742040153,
+      "grad_norm": 0.5646739602088928,
+      "learning_rate": 0.0001274193548387097,
+      "loss": 0.2208,
+      "step": 80
+    },
+    {
+      "epoch": 0.14601500709795173,
+      "grad_norm": 0.33468499779701233,
+      "learning_rate": 0.00014354838709677422,
+      "loss": 0.2018,
+      "step": 90
+    },
+    {
+      "epoch": 0.14601500709795173,
+      "eval_loss": 0.1886902004480362,
+      "eval_runtime": 54.4734,
+      "eval_samples_per_second": 4.773,
+      "eval_steps_per_second": 4.773,
+      "step": 90
+    },
+    {
+      "epoch": 0.16223889677550193,
+      "grad_norm": 0.3952212929725647,
+      "learning_rate": 0.00015967741935483872,
+      "loss": 0.1841,
+      "step": 100
+    },
+    {
+      "epoch": 0.1784627864530521,
+      "grad_norm": 0.34694239497184753,
+      "learning_rate": 0.00017580645161290325,
+      "loss": 0.1731,
+      "step": 110
+    },
+    {
+      "epoch": 0.1946866761306023,
+      "grad_norm": 0.3307943046092987,
+      "learning_rate": 0.00019193548387096775,
+      "loss": 0.1736,
+      "step": 120
+    },
+    {
+      "epoch": 0.1946866761306023,
+      "eval_loss": 0.1661035567522049,
+      "eval_runtime": 54.4184,
+      "eval_samples_per_second": 4.778,
+      "eval_steps_per_second": 4.778,
+      "step": 120
+    },
+    {
+      "epoch": 0.2109105658081525,
+      "grad_norm": 0.2933768928050995,
+      "learning_rate": 0.0001999899871766749,
+      "loss": 0.1616,
+      "step": 130
+    },
+    {
+      "epoch": 0.22713445548570269,
+      "grad_norm": 0.3262489438056946,
+      "learning_rate": 0.00019990989662046818,
+      "loss": 0.1619,
+      "step": 140
+    },
+    {
+      "epoch": 0.2433583451632529,
+      "grad_norm": 0.18724548816680908,
+      "learning_rate": 0.00019974977965945,
+      "loss": 0.1482,
+      "step": 150
+    },
+    {
+      "epoch": 0.2433583451632529,
+      "eval_loss": 0.14517094194889069,
+      "eval_runtime": 54.4554,
+      "eval_samples_per_second": 4.775,
+      "eval_steps_per_second": 4.775,
+      "step": 150
+    },
+    {
+      "epoch": 0.25958223484080306,
+      "grad_norm": 0.39443448185920715,
+      "learning_rate": 0.0001995097645450266,
+      "loss": 0.1571,
+      "step": 160
+    },
+    {
+      "epoch": 0.2758061245183533,
+      "grad_norm": 0.3215681314468384,
+      "learning_rate": 0.00019919004352588767,
+      "loss": 0.1518,
+      "step": 170
+    },
+    {
+      "epoch": 0.29203001419590346,
+      "grad_norm": 0.1917540580034256,
+      "learning_rate": 0.0001987908726940178,
+      "loss": 0.1477,
+      "step": 180
+    },
+    {
+      "epoch": 0.29203001419590346,
+      "eval_loss": 0.1380539983510971,
+      "eval_runtime": 54.5257,
+      "eval_samples_per_second": 4.768,
+      "eval_steps_per_second": 4.768,
+      "step": 180
+    },
+    {
+      "epoch": 0.30825390387345364,
+      "grad_norm": 0.27752983570098877,
+      "learning_rate": 0.00019831257177957044,
+      "loss": 0.1352,
+      "step": 190
+    },
+    {
+      "epoch": 0.32447779355100387,
+      "grad_norm": 0.3052772879600525,
+      "learning_rate": 0.00019775552389476864,
+      "loss": 0.1425,
+      "step": 200
+    },
+    {
+      "epoch": 0.34070168322855404,
+      "grad_norm": 0.17911162972450256,
+      "learning_rate": 0.00019712017522703764,
+      "loss": 0.1411,
+      "step": 210
+    },
+    {
+      "epoch": 0.34070168322855404,
+      "eval_loss": 0.13320107758045197,
+      "eval_runtime": 54.1867,
+      "eval_samples_per_second": 4.798,
+      "eval_steps_per_second": 4.798,
+      "step": 210
+    },
+    {
+      "epoch": 0.3569255729061042,
+      "grad_norm": 0.15296442806720734,
+      "learning_rate": 0.0001964070346816151,
+      "loss": 0.1378,
+      "step": 220
+    },
+    {
+      "epoch": 0.37314946258365445,
+      "grad_norm": 0.17346209287643433,
+      "learning_rate": 0.00019561667347392508,
+      "loss": 0.136,
+      "step": 230
+    },
+    {
+      "epoch": 0.3893733522612046,
+      "grad_norm": 0.16340570151805878,
+      "learning_rate": 0.00019474972467204297,
+      "loss": 0.1395,
+      "step": 240
+    },
+    {
+      "epoch": 0.3893733522612046,
+      "eval_loss": 0.13255620002746582,
+      "eval_runtime": 54.3562,
+      "eval_samples_per_second": 4.783,
+      "eval_steps_per_second": 4.783,
+      "step": 240
+    },
+    {
+      "epoch": 0.4055972419387548,
+      "grad_norm": 0.2969210147857666,
+      "learning_rate": 0.0001938068826896166,
+      "loss": 0.1368,
+      "step": 250
+    },
+    {
+      "epoch": 0.421821131616305,
+      "grad_norm": 0.20236295461654663,
+      "learning_rate": 0.00019278890272965096,
+      "loss": 0.1273,
+      "step": 260
+    },
+    {
+      "epoch": 0.4380450212938552,
+      "grad_norm": 0.2891747057437897,
+      "learning_rate": 0.00019169660017960137,
+      "loss": 0.129,
+      "step": 270
+    },
+    {
+      "epoch": 0.4380450212938552,
+      "eval_loss": 0.12807676196098328,
+      "eval_runtime": 54.3522,
+      "eval_samples_per_second": 4.784,
+      "eval_steps_per_second": 4.784,
+      "step": 270
+    },
+    {
+      "epoch": 0.45426891097140537,
+      "grad_norm": 0.20254789292812347,
+      "learning_rate": 0.0001905308499582597,
+      "loss": 0.141,
+      "step": 280
+    },
+    {
+      "epoch": 0.4704928006489556,
+      "grad_norm": 0.1715897023677826,
+      "learning_rate": 0.00018929258581495685,
+      "loss": 0.1329,
+      "step": 290
+    },
+    {
+      "epoch": 0.4867166903265058,
+      "grad_norm": 0.3499029278755188,
+      "learning_rate": 0.00018798279958164295,
+      "loss": 0.1355,
+      "step": 300
+    },
+    {
+      "epoch": 0.4867166903265058,
+      "eval_loss": 0.12350723892450333,
+      "eval_runtime": 54.5668,
+      "eval_samples_per_second": 4.765,
+      "eval_steps_per_second": 4.765,
+      "step": 300
+    },
+    {
+      "epoch": 0.502940580004056,
+      "grad_norm": 0.15775884687900543,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.126,
+      "step": 310
+    },
+    {
+      "epoch": 0.5191644696816061,
+      "grad_norm": 0.19402213394641876,
+      "learning_rate": 0.00018515291377333112,
+      "loss": 0.1332,
+      "step": 320
+    },
+    {
+      "epoch": 0.5353883593591564,
+      "grad_norm": 0.13237500190734863,
+      "learning_rate": 0.0001836350808965776,
+      "loss": 0.1441,
+      "step": 330
+    },
+    {
+      "epoch": 0.5353883593591564,
+      "eval_loss": 0.12080405652523041,
+      "eval_runtime": 54.7379,
+      "eval_samples_per_second": 4.75,
+      "eval_steps_per_second": 4.75,
+      "step": 330
+    },
+    {
+      "epoch": 0.5516122490367066,
+      "grad_norm": 0.29119789600372314,
+      "learning_rate": 0.00018205025751070875,
+      "loss": 0.1245,
+      "step": 340
+    },
+    {
+      "epoch": 0.5678361387142568,
+      "grad_norm": 0.15898150205612183,
+      "learning_rate": 0.00018039971303669407,
+      "loss": 0.121,
+      "step": 350
+    },
+    {
+      "epoch": 0.5840600283918069,
+      "grad_norm": 0.13710354268550873,
+      "learning_rate": 0.000178684769537159,
+      "loss": 0.1346,
+      "step": 360
+    },
+    {
+      "epoch": 0.5840600283918069,
+      "eval_loss": 0.12007435411214828,
+      "eval_runtime": 54.7789,
+      "eval_samples_per_second": 4.746,
+      "eval_steps_per_second": 4.746,
+      "step": 360
+    },
+    {
+      "epoch": 0.6002839180693571,
+      "grad_norm": 0.12323573976755142,
+      "learning_rate": 0.0001769068006574317,
+      "loss": 0.1311,
+      "step": 370
+    },
+    {
+      "epoch": 0.6165078077469073,
+      "grad_norm": 0.14197634160518646,
+      "learning_rate": 0.00017506723052527242,
+      "loss": 0.122,
+      "step": 380
+    },
+    {
+      "epoch": 0.6327316974244576,
+      "grad_norm": 0.13415870070457458,
+      "learning_rate": 0.00017316753261016783,
+      "loss": 0.1242,
+      "step": 390
+    },
+    {
+      "epoch": 0.6327316974244576,
+      "eval_loss": 0.11815402656793594,
+      "eval_runtime": 54.9041,
+      "eval_samples_per_second": 4.736,
+      "eval_steps_per_second": 4.736,
+      "step": 390
+    },
+    {
+      "epoch": 0.6489555871020077,
+      "grad_norm": 0.14391979575157166,
+      "learning_rate": 0.00017120922854310257,
+      "loss": 0.1235,
+      "step": 400
+    },
+    {
+      "epoch": 0.6651794767795579,
+      "grad_norm": 0.12567928433418274,
+      "learning_rate": 0.00016919388689775464,
+      "loss": 0.1292,
+      "step": 410
+    },
+    {
+      "epoch": 0.6814033664571081,
+      "grad_norm": 0.24638038873672485,
+      "learning_rate": 0.0001671231219340903,
+      "loss": 0.124,
+      "step": 420
+    },
+    {
+      "epoch": 0.6814033664571081,
+      "eval_loss": 0.11765418201684952,
+      "eval_runtime": 54.8324,
+      "eval_samples_per_second": 4.742,
+      "eval_steps_per_second": 4.742,
+      "step": 420
+    },
+    {
+      "epoch": 0.6976272561346583,
+      "grad_norm": 0.11872219294309616,
+      "learning_rate": 0.00016499859230536466,
+      "loss": 0.1284,
+      "step": 430
+    },
+    {
+      "epoch": 0.7138511458122084,
+      "grad_norm": 0.14060816168785095,
+      "learning_rate": 0.00016282199972956425,
+      "loss": 0.1228,
+      "step": 440
+    },
+    {
+      "epoch": 0.7300750354897587,
+      "grad_norm": 0.1108463779091835,
+      "learning_rate": 0.00016059508762635482,
+      "loss": 0.1315,
+      "step": 450
+    },
+    {
+      "epoch": 0.7300750354897587,
+      "eval_loss": 0.11692557483911514,
+      "eval_runtime": 55.1996,
+      "eval_samples_per_second": 4.71,
+      "eval_steps_per_second": 4.71,
+      "step": 450
+    },
+    {
+      "epoch": 0.7462989251673089,
+      "grad_norm": 0.13592351973056793,
+      "learning_rate": 0.00015831963972062733,
+      "loss": 0.1235,
+      "step": 460
+    },
+    {
+      "epoch": 0.7625228148448591,
+      "grad_norm": 0.12181869149208069,
+      "learning_rate": 0.00015599747861375955,
+      "loss": 0.12,
+      "step": 470
+    },
+    {
+      "epoch": 0.7787467045224092,
+      "grad_norm": 0.37740716338157654,
+      "learning_rate": 0.00015363046432373824,
+      "loss": 0.119,
+      "step": 480
+    },
+    {
+      "epoch": 0.7787467045224092,
+      "eval_loss": 0.11858060956001282,
+      "eval_runtime": 55.2002,
+      "eval_samples_per_second": 4.71,
+      "eval_steps_per_second": 4.71,
+      "step": 480
+    },
+    {
+      "epoch": 0.7949705941999594,
+      "grad_norm": 0.3189144432544708,
+      "learning_rate": 0.00015122049279531143,
+      "loss": 0.1322,
+      "step": 490
+    },
+    {
+      "epoch": 0.8111944838775096,
+      "grad_norm": 0.15118102729320526,
+      "learning_rate": 0.00014876949438136347,
+      "loss": 0.1211,
+      "step": 500
+    },
+    {
+      "epoch": 0.8274183735550599,
+      "grad_norm": 0.09746048599481583,
+      "learning_rate": 0.0001462794322967299,
+      "loss": 0.124,
+      "step": 510
+    },
+    {
+      "epoch": 0.8274183735550599,
+      "eval_loss": 0.11739031225442886,
+      "eval_runtime": 54.9138,
+      "eval_samples_per_second": 4.735,
+      "eval_steps_per_second": 4.735,
+      "step": 510
+    },
+    {
+      "epoch": 0.84364226323261,
+      "grad_norm": 0.11682560294866562,
+      "learning_rate": 0.00014375230104569044,
+      "loss": 0.1219,
+      "step": 520
+    },
+    {
+      "epoch": 0.8598661529101602,
+      "grad_norm": 0.10706628113985062,
+      "learning_rate": 0.0001411901248243993,
+      "loss": 0.1198,
+      "step": 530
+    },
+    {
+      "epoch": 0.8760900425877104,
+      "grad_norm": 0.26870429515838623,
+      "learning_rate": 0.0001385949558995329,
+      "loss": 0.1253,
+      "step": 540
+    },
+    {
+      "epoch": 0.8760900425877104,
+      "eval_loss": 0.11531012505292892,
+      "eval_runtime": 54.9326,
+      "eval_samples_per_second": 4.733,
+      "eval_steps_per_second": 4.733,
+      "step": 540
+    },
+    {
+      "epoch": 0.8923139322652606,
+      "grad_norm": 0.09110305458307266,
+      "learning_rate": 0.0001359688729644536,
+      "loss": 0.1129,
+      "step": 550
+    },
+    {
+      "epoch": 0.9085378219428107,
+      "grad_norm": 0.11204719543457031,
+      "learning_rate": 0.00013331397947420576,
+      "loss": 0.129,
+      "step": 560
+    },
+    {
+      "epoch": 0.924761711620361,
+      "grad_norm": 0.15059269964694977,
+      "learning_rate": 0.00013063240196067836,
+      "loss": 0.1272,
+      "step": 570
+    },
+    {
+      "epoch": 0.924761711620361,
+      "eval_loss": 0.11525142192840576,
+      "eval_runtime": 55.1098,
+      "eval_samples_per_second": 4.718,
+      "eval_steps_per_second": 4.718,
+      "step": 570
+    },
+    {
+      "epoch": 0.9409856012979112,
+      "grad_norm": 0.11085380613803864,
+      "learning_rate": 0.00012792628832928302,
+      "loss": 0.1243,
+      "step": 580
+    },
+    {
+      "epoch": 0.9572094909754614,
+      "grad_norm": 0.10796050727367401,
+      "learning_rate": 0.00012519780613851254,
+      "loss": 0.1197,
+      "step": 590
+    },
+    {
+      "epoch": 0.9734333806530115,
+      "grad_norm": 0.08801472187042236,
+      "learning_rate": 0.00012244914086375724,
+      "loss": 0.1261,
+      "step": 600
+    },
+    {
+      "epoch": 0.9734333806530115,
+      "eval_loss": 0.11538033187389374,
+      "eval_runtime": 54.7547,
+      "eval_samples_per_second": 4.748,
+      "eval_steps_per_second": 4.748,
+      "step": 600
+    },
+    {
+      "epoch": 0.9896572703305617,
+      "grad_norm": 0.08395121991634369,
+      "learning_rate": 0.00011968249414677055,
+      "loss": 0.1215,
+      "step": 610
+    },
+    {
+      "epoch": 1.0048671669032652,
+      "grad_norm": 0.10106801986694336,
+      "learning_rate": 0.00011690008203218493,
+      "loss": 0.1206,
+      "step": 620
+    },
+    {
+      "epoch": 1.0210910565808153,
+      "grad_norm": 0.08509080857038498,
+      "learning_rate": 0.00011410413319249194,
+      "loss": 0.1125,
+      "step": 630
+    },
+    {
+      "epoch": 1.0210910565808153,
+      "eval_loss": 0.11403891444206238,
+      "eval_runtime": 54.6547,
+      "eval_samples_per_second": 4.757,
+      "eval_steps_per_second": 4.757,
+      "step": 630
+    },
+    {
+      "epoch": 1.0373149462583655,
+      "grad_norm": 0.09074535965919495,
+      "learning_rate": 0.00011129688714290729,
+      "loss": 0.1167,
+      "step": 640
+    },
+    {
+      "epoch": 1.0535388359359157,
+      "grad_norm": 0.10673358291387558,
+      "learning_rate": 0.00010848059244755093,
+      "loss": 0.1082,
+      "step": 650
+    },
+    {
+      "epoch": 1.0697627256134659,
+      "grad_norm": 0.11839364469051361,
+      "learning_rate": 0.00010565750491837925,
+      "loss": 0.1192,
+      "step": 660
+    },
+    {
+      "epoch": 1.0697627256134659,
+      "eval_loss": 0.11325760185718536,
+      "eval_runtime": 54.7532,
+      "eval_samples_per_second": 4.749,
+      "eval_steps_per_second": 4.749,
+      "step": 660
+    },
+    {
+      "epoch": 1.085986615291016,
+      "grad_norm": 0.08097315579652786,
+      "learning_rate": 0.00010282988580831183,
+      "loss": 0.1188,
+      "step": 670
+    },
+    {
+      "epoch": 1.1022105049685662,
+      "grad_norm": 0.10252730548381805,
+      "learning_rate": 0.0001,
+      "loss": 0.1217,
+      "step": 680
+    },
+    {
+      "epoch": 1.1184343946461164,
+      "grad_norm": 0.1087854653596878,
+      "learning_rate": 9.71701141916882e-05,
+      "loss": 0.1185,
+      "step": 690
+    },
+    {
+      "epoch": 1.1184343946461164,
+      "eval_loss": 0.11274029314517975,
+      "eval_runtime": 54.6489,
+      "eval_samples_per_second": 4.758,
+      "eval_steps_per_second": 4.758,
+      "step": 690
+    },
+    {
+      "epoch": 1.1346582843236666,
+      "grad_norm": 0.09857626259326935,
+      "learning_rate": 9.434249508162076e-05,
+      "loss": 0.1225,
+      "step": 700
+    },
+    {
+      "epoch": 1.1508821740012167,
+      "grad_norm": 0.09853193908929825,
+      "learning_rate": 9.151940755244912e-05,
+      "loss": 0.1185,
+      "step": 710
+    },
+    {
+      "epoch": 1.167106063678767,
+      "grad_norm": 0.0954899936914444,
+      "learning_rate": 8.870311285709274e-05,
+      "loss": 0.1336,
+      "step": 720
+    },
+    {
+      "epoch": 1.167106063678767,
+      "eval_loss": 0.11281841993331909,
+      "eval_runtime": 54.5506,
+      "eval_samples_per_second": 4.766,
+      "eval_steps_per_second": 4.766,
+      "step": 720
+    },
+    {
+      "epoch": 1.183329953356317,
+      "grad_norm": 0.0967244803905487,
+      "learning_rate": 8.58958668075081e-05,
+      "loss": 0.118,
+      "step": 730
+    },
+    {
+      "epoch": 1.1995538430338675,
+      "grad_norm": 0.09406362473964691,
+      "learning_rate": 8.309991796781511e-05,
+      "loss": 0.1218,
+      "step": 740
+    },
+    {
+      "epoch": 1.2157777327114176,
+      "grad_norm": 0.0989699587225914,
+      "learning_rate": 8.031750585322947e-05,
+      "loss": 0.1178,
+      "step": 750
+    },
+    {
+      "epoch": 1.2157777327114176,
+      "eval_loss": 0.11203999817371368,
+      "eval_runtime": 54.636,
+      "eval_samples_per_second": 4.759,
+      "eval_steps_per_second": 4.759,
+      "step": 750
+    },
+    {
+      "epoch": 1.2320016223889678,
+      "grad_norm": 0.10200025886297226,
+      "learning_rate": 7.755085913624274e-05,
+      "loss": 0.1126,
+      "step": 760
+    },
+    {
+      "epoch": 1.248225512066518,
+      "grad_norm": 0.09863891452550888,
+      "learning_rate": 7.48021938614875e-05,
+      "loss": 0.1253,
+      "step": 770
+    },
+    {
+      "epoch": 1.2644494017440682,
+      "grad_norm": 0.07942435145378113,
+      "learning_rate": 7.2073711670717e-05,
+      "loss": 0.1188,
+      "step": 780
+    },
+    {
+      "epoch": 1.2644494017440682,
+      "eval_loss": 0.11259657144546509,
+      "eval_runtime": 54.5511,
+      "eval_samples_per_second": 4.766,
+      "eval_steps_per_second": 4.766,
+      "step": 780
+    },
+    {
+      "epoch": 1.2806732914216183,
+      "grad_norm": 0.13004329800605774,
+      "learning_rate": 6.936759803932167e-05,
+      "loss": 0.1158,
+      "step": 790
+    },
+    {
+      "epoch": 1.2968971810991685,
+      "grad_norm": 0.08646363765001297,
+      "learning_rate": 6.668602052579424e-05,
+      "loss": 0.1173,
+      "step": 800
+    },
+    {
+      "epoch": 1.3131210707767187,
+      "grad_norm": 0.08868124336004257,
+      "learning_rate": 6.403112703554643e-05,
+      "loss": 0.1065,
+      "step": 810
+    },
+    {
+      "epoch": 1.3131210707767187,
+      "eval_loss": 0.1115630567073822,
+      "eval_runtime": 55.0171,
+      "eval_samples_per_second": 4.726,
+      "eval_steps_per_second": 4.726,
+      "step": 810
+    },
+    {
+      "epoch": 1.3293449604542689,
+      "grad_norm": 0.08065708726644516,
+      "learning_rate": 6.140504410046712e-05,
+      "loss": 0.1243,
+      "step": 820
+    },
+    {
+      "epoch": 1.345568850131819,
+      "grad_norm": 0.08410122245550156,
+      "learning_rate": 5.880987517560075e-05,
+      "loss": 0.114,
+      "step": 830
+    },
+    {
+      "epoch": 1.3617927398093692,
+      "grad_norm": 0.0926986113190651,
+      "learning_rate": 5.624769895430961e-05,
+      "loss": 0.1178,
+      "step": 840
+    },
+    {
+      "epoch": 1.3617927398093692,
+      "eval_loss": 0.11092434078454971,
+      "eval_runtime": 55.2141,
+      "eval_samples_per_second": 4.709,
+      "eval_steps_per_second": 4.709,
+      "step": 840
+    },
+    {
+      "epoch": 1.3780166294869196,
+      "grad_norm": 0.07351404428482056,
+      "learning_rate": 5.372056770327013e-05,
+      "loss": 0.1108,
+      "step": 850
+    },
+    {
+      "epoch": 1.3942405191644696,
+      "grad_norm": 0.08835868537425995,
+      "learning_rate": 5.123050561863657e-05,
+      "loss": 0.1127,
+      "step": 860
+    },
+    {
+      "epoch": 1.41046440884202,
+      "grad_norm": 0.08012858778238297,
+      "learning_rate": 4.877950720468859e-05,
+      "loss": 0.1118,
+      "step": 870
+    },
+    {
+      "epoch": 1.41046440884202,
+      "eval_loss": 0.11060689389705658,
+      "eval_runtime": 55.1249,
+      "eval_samples_per_second": 4.717,
+      "eval_steps_per_second": 4.717,
+      "step": 870
+    },
+    {
+      "epoch": 1.4266882985195701,
+      "grad_norm": 0.09063031524419785,
+      "learning_rate": 4.636953567626177e-05,
+      "loss": 0.1195,
+      "step": 880
+    },
+    {
+      "epoch": 1.4429121881971203,
+      "grad_norm": 0.07680074125528336,
+      "learning_rate": 4.4002521386240466e-05,
+      "loss": 0.1133,
+      "step": 890
+    },
+    {
+      "epoch": 1.4591360778746705,
+      "grad_norm": 0.09211437404155731,
+      "learning_rate": 4.168036027937267e-05,
+      "loss": 0.113,
+      "step": 900
+    },
+    {
+      "epoch": 1.4591360778746705,
+      "eval_loss": 0.1109917163848877,
+      "eval_runtime": 54.6876,
+      "eval_samples_per_second": 4.754,
+      "eval_steps_per_second": 4.754,
+      "step": 900
+    },
+    {
+      "epoch": 1.4753599675522207,
+      "grad_norm": 0.08036933839321136,
+      "learning_rate": 3.9404912373645185e-05,
+      "loss": 0.1183,
+      "step": 910
+    },
+    {
+      "epoch": 1.4915838572297708,
+      "grad_norm": 0.07682196795940399,
+      "learning_rate": 3.717800027043576e-05,
+      "loss": 0.1198,
+      "step": 920
+    },
+    {
+      "epoch": 1.507807746907321,
+      "grad_norm": 0.08601044863462448,
+      "learning_rate": 3.500140769463533e-05,
+      "loss": 0.1209,
+      "step": 930
+    },
+    {
+      "epoch": 1.507807746907321,
+      "eval_loss": 0.1104922965168953,
+      "eval_runtime": 54.6525,
+      "eval_samples_per_second": 4.757,
+      "eval_steps_per_second": 4.757,
+      "step": 930
+    },
+    {
+      "epoch": 1.5240316365848712,
+      "grad_norm": 0.08242760598659515,
+      "learning_rate": 3.287687806590971e-05,
+      "loss": 0.1127,
+      "step": 940
+    },
+    {
+      "epoch": 1.5402555262624213,
+      "grad_norm": 0.08664223551750183,
+      "learning_rate": 3.080611310224539e-05,
+      "loss": 0.1193,
+      "step": 950
+    },
+    {
+      "epoch": 1.5564794159399717,
+      "grad_norm": 0.08529651165008545,
+      "learning_rate": 2.879077145689746e-05,
+      "loss": 0.1126,
+      "step": 960
+    },
+    {
+      "epoch": 1.5564794159399717,
+      "eval_loss": 0.10984186083078384,
+      "eval_runtime": 54.6191,
+      "eval_samples_per_second": 4.76,
+      "eval_steps_per_second": 4.76,
+      "step": 960
+    },
+    {
+      "epoch": 1.5727033056175217,
+      "grad_norm": 0.07219547033309937,
+      "learning_rate": 2.6832467389832173e-05,
+      "loss": 0.1182,
+      "step": 970
+    },
+    {
+      "epoch": 1.588927195295072,
+      "grad_norm": 0.10246000438928604,
+      "learning_rate": 2.493276947472756e-05,
+      "loss": 0.1109,
+      "step": 980
+    },
+    {
+      "epoch": 1.605151084972622,
+      "grad_norm": 0.08859504014253616,
+      "learning_rate": 2.3093199342568318e-05,
+      "loss": 0.1137,
+      "step": 990
+    },
+    {
+      "epoch": 1.605151084972622,
+      "eval_loss": 0.10924239456653595,
+      "eval_runtime": 54.6323,
+      "eval_samples_per_second": 4.759,
+      "eval_steps_per_second": 4.759,
+      "step": 990
+    },
+    {
+      "epoch": 1.6213749746501724,
+      "grad_norm": 0.08224408328533173,
+      "learning_rate": 2.1315230462840985e-05,
+      "loss": 0.1168,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6375988643277226,
+      "grad_norm": 0.09429515153169632,
+      "learning_rate": 1.9600286963305957e-05,
+      "loss": 0.114,
+      "step": 1010
+    },
+    {
+      "epoch": 1.6538227540052728,
+      "grad_norm": 0.08045922219753265,
+      "learning_rate": 1.7949742489291255e-05,
+      "loss": 0.111,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6538227540052728,
+      "eval_loss": 0.10893593728542328,
+      "eval_runtime": 54.7365,
+      "eval_samples_per_second": 4.75,
+      "eval_steps_per_second": 4.75,
+      "step": 1020
+    },
+    {
+      "epoch": 1.670046643682823,
+      "grad_norm": 0.0847032219171524,
+      "learning_rate": 1.6364919103422393e-05,
+      "loss": 0.1142,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6862705333603731,
+      "grad_norm": 0.08252795040607452,
+      "learning_rate": 1.4847086226668872e-05,
+      "loss": 0.1126,
+      "step": 1040
+    },
+    {
+      "epoch": 1.7024944230379233,
+      "grad_norm": 0.0862165316939354,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.1186,
+      "step": 1050
+    },
+    {
+      "epoch": 1.7024944230379233,
+      "eval_loss": 0.1090201735496521,
+      "eval_runtime": 54.7713,
+      "eval_samples_per_second": 4.747,
+      "eval_steps_per_second": 4.747,
+      "step": 1050
+    },
+    {
+      "epoch": 1.7187183127154735,
+      "grad_norm": 0.09021241962909698,
+      "learning_rate": 1.2017200418357078e-05,
+      "loss": 0.1178,
+      "step": 1060
+    },
+    {
+      "epoch": 1.7349422023930239,
+      "grad_norm": 0.07867942750453949,
+      "learning_rate": 1.0707414185043163e-05,
+      "loss": 0.1041,
+      "step": 1070
+    },
+    {
+      "epoch": 1.7511660920705738,
+      "grad_norm": 0.10106240212917328,
+      "learning_rate": 9.469150041740338e-06,
+      "loss": 0.1111,
+      "step": 1080
+    },
+    {
+      "epoch": 1.7511660920705738,
+      "eval_loss": 0.10924577713012695,
+      "eval_runtime": 54.6761,
+      "eval_samples_per_second": 4.755,
+      "eval_steps_per_second": 4.755,
+      "step": 1080
+    },
+    {
+      "epoch": 1.7673899817481242,
+      "grad_norm": 0.1259811371564865,
+      "learning_rate": 8.303399820398672e-06,
+      "loss": 0.1118,
+      "step": 1090
+    },
+    {
+      "epoch": 1.7836138714256742,
+      "grad_norm": 0.07995796203613281,
+      "learning_rate": 7.211097270349066e-06,
+      "loss": 0.1005,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7998377611032246,
+      "grad_norm": 0.0811864510178566,
+      "learning_rate": 6.1931173103834115e-06,
+      "loss": 0.115,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7998377611032246,
+      "eval_loss": 0.10901561379432678,
+      "eval_runtime": 54.5743,
+      "eval_samples_per_second": 4.764,
+      "eval_steps_per_second": 4.764,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8160616507807745,
+      "grad_norm": 0.10539617389440536,
+      "learning_rate": 5.250275327957032e-06,
+      "loss": 0.1129,
+      "step": 1120
+    },
+    {
+      "epoch": 1.832285540458325,
+      "grad_norm": 0.15508656203746796,
+      "learning_rate": 4.383326526074916e-06,
+      "loss": 0.1258,
+      "step": 1130
+    },
+    {
+      "epoch": 1.848509430135875,
+      "grad_norm": 0.08507981151342392,
+      "learning_rate": 3.592965318384944e-06,
+      "loss": 0.1123,
+      "step": 1140
+    },
+    {
+      "epoch": 1.848509430135875,
+      "eval_loss": 0.1087607592344284,
+      "eval_runtime": 54.908,
+      "eval_samples_per_second": 4.735,
+      "eval_steps_per_second": 4.735,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8647333198134253,
+      "grad_norm": 0.08362692594528198,
+      "learning_rate": 2.8798247729623806e-06,
+      "loss": 0.1164,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8809572094909754,
+      "grad_norm": 0.08825893700122833,
+      "learning_rate": 2.2444761052313856e-06,
+      "loss": 0.1223,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8971810991685256,
+      "grad_norm": 0.07475200295448303,
+      "learning_rate": 1.6874282204295766e-06,
+      "loss": 0.1101,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8971810991685256,
+      "eval_loss": 0.108616404235363,
+      "eval_runtime": 55.1832,
+      "eval_samples_per_second": 4.712,
+      "eval_steps_per_second": 4.712,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9134049888460758,
+      "grad_norm": 0.07395757734775543,
+      "learning_rate": 1.209127305982205e-06,
+      "loss": 0.1217,
+      "step": 1180
+    },
+    {
+      "epoch": 1.929628878523626,
+      "grad_norm": 0.1036606878042221,
+      "learning_rate": 8.099564741123166e-07,
+      "loss": 0.1167,
+      "step": 1190
+    },
+    {
+      "epoch": 1.9458527682011764,
+      "grad_norm": 0.07940636575222015,
+      "learning_rate": 4.902354549733978e-07,
+      "loss": 0.1111,
+      "step": 1200
+    },
+    {
+      "epoch": 1.9458527682011764,
+      "eval_loss": 0.10869967937469482,
+      "eval_runtime": 54.8601,
+      "eval_samples_per_second": 4.739,
+      "eval_steps_per_second": 4.739,
+      "step": 1200
+    },
+    {
+      "epoch": 1.9620766578787263,
+      "grad_norm": 0.08885055780410767,
+      "learning_rate": 2.5022034055003364e-07,
+      "loss": 0.1167,
+      "step": 1210
+    },
+    {
+      "epoch": 1.9783005475562767,
+      "grad_norm": 0.0910600945353508,
+      "learning_rate": 9.010337953185843e-08,
+      "loss": 0.1076,
+      "step": 1220
+    },
+    {
+      "epoch": 1.9945244372338267,
+      "grad_norm": 0.07792419195175171,
+      "learning_rate": 1.0012823325111776e-08,
+      "loss": 0.12,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9945244372338267,
+      "eval_loss": 0.10875582695007324,
+      "eval_runtime": 54.7624,
+      "eval_samples_per_second": 4.748,
+      "eval_steps_per_second": 4.748,
+      "step": 1230
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1234,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 1.722645378352681e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1234/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:655eb02b0fc57181f2ec10794d297d90572f277d219938ab929b99cc63bae9d3
+size 5777

config.json

@@ -0,0 +1,70 @@
+{
+  "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,
+  "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-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa474a72e8b3490c80568150900c88a979d9a64aff35f90ce5941579ed8e81f
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ea44f8671e0c2fd0a1134518ddb0e1322d682fa5e398086ecd0cf2d5bd45907
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_parameters": 4022468096,
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

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
+}