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-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-948/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": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b65d3f4fa7f58f2ecadc8c72b0385f61bf0044a3acc3d8bc00fd3fbe6911bb
+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-900/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-900/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": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-900/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65c880cc976454bf24559354f62fa96b090f59bce5c89118e5df640813ec04f9
+size 528550256

checkpoint-900/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-900/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-900/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fddee05f058e072ba90f50b1d7047388aa1d4b766ea5928dbd9154a85617d2c
+size 1057397963

checkpoint-900/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a803f235a0922ce15d83a820a8f5bcc833b2575d925648bc54789550427a5be1
+size 14645

checkpoint-900/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29d6e1d9b0052c01b6461c61c43944643dc5b7f2a1fba0dba35f3c534ed6491b
+size 1465

checkpoint-900/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-900/tokenizer.json

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

checkpoint-900/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-900/trainer_state.json

@@ -0,0 +1,904 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8989712476919018,
+  "eval_steps": 30,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.021102611448166712,
+      "grad_norm": 5.49099588394165,
+      "learning_rate": 1.8947368421052634e-05,
+      "loss": 2.4799,
+      "step": 10
+    },
+    {
+      "epoch": 0.042205222896333425,
+      "grad_norm": 0.7057839035987854,
+      "learning_rate": 4e-05,
+      "loss": 0.9017,
+      "step": 20
+    },
+    {
+      "epoch": 0.06330783434450013,
+      "grad_norm": 0.7793235778808594,
+      "learning_rate": 6.105263157894737e-05,
+      "loss": 0.5561,
+      "step": 30
+    },
+    {
+      "epoch": 0.06330783434450013,
+      "eval_loss": 0.49612972140312195,
+      "eval_runtime": 44.7367,
+      "eval_samples_per_second": 4.471,
+      "eval_steps_per_second": 4.471,
+      "step": 30
+    },
+    {
+      "epoch": 0.08441044579266685,
+      "grad_norm": 0.6479541063308716,
+      "learning_rate": 8.210526315789474e-05,
+      "loss": 0.4088,
+      "step": 40
+    },
+    {
+      "epoch": 0.10551305724083355,
+      "grad_norm": 0.6190423965454102,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 0.3332,
+      "step": 50
+    },
+    {
+      "epoch": 0.12661566868900026,
+      "grad_norm": 0.48822861909866333,
+      "learning_rate": 0.00012421052631578949,
+      "loss": 0.2752,
+      "step": 60
+    },
+    {
+      "epoch": 0.12661566868900026,
+      "eval_loss": 0.25475138425827026,
+      "eval_runtime": 44.1798,
+      "eval_samples_per_second": 4.527,
+      "eval_steps_per_second": 4.527,
+      "step": 60
+    },
+    {
+      "epoch": 0.14771828013716698,
+      "grad_norm": 0.3956296443939209,
+      "learning_rate": 0.00014526315789473686,
+      "loss": 0.2283,
+      "step": 70
+    },
+    {
+      "epoch": 0.1688208915853337,
+      "grad_norm": 0.6851626038551331,
+      "learning_rate": 0.00016631578947368423,
+      "loss": 0.2017,
+      "step": 80
+    },
+    {
+      "epoch": 0.1899235030335004,
+      "grad_norm": 2.741124153137207,
+      "learning_rate": 0.0001873684210526316,
+      "loss": 0.1877,
+      "step": 90
+    },
+    {
+      "epoch": 0.1899235030335004,
+      "eval_loss": 0.19585472345352173,
+      "eval_runtime": 44.05,
+      "eval_samples_per_second": 4.54,
+      "eval_steps_per_second": 4.54,
+      "step": 90
+    },
+    {
+      "epoch": 0.2110261144816671,
+      "grad_norm": 0.4686296880245209,
+      "learning_rate": 0.00019998914864890175,
+      "loss": 0.1862,
+      "step": 100
+    },
+    {
+      "epoch": 0.23212872592983383,
+      "grad_norm": 0.5210604071617126,
+      "learning_rate": 0.0001998670979935533,
+      "loss": 0.1754,
+      "step": 110
+    },
+    {
+      "epoch": 0.2532313373780005,
+      "grad_norm": 0.2621477246284485,
+      "learning_rate": 0.00019960959858204754,
+      "loss": 0.1767,
+      "step": 120
+    },
+    {
+      "epoch": 0.2532313373780005,
+      "eval_loss": 0.16388529539108276,
+      "eval_runtime": 44.3724,
+      "eval_samples_per_second": 4.507,
+      "eval_steps_per_second": 4.507,
+      "step": 120
+    },
+    {
+      "epoch": 0.27433394882616724,
+      "grad_norm": 0.3740817904472351,
+      "learning_rate": 0.00019921699965828662,
+      "loss": 0.1666,
+      "step": 130
+    },
+    {
+      "epoch": 0.29543656027433396,
+      "grad_norm": 0.5232918858528137,
+      "learning_rate": 0.00019868983370030348,
+      "loss": 0.1624,
+      "step": 140
+    },
+    {
+      "epoch": 0.3165391717225007,
+      "grad_norm": 0.2019444853067398,
+      "learning_rate": 0.00019802881569806706,
+      "loss": 0.1647,
+      "step": 150
+    },
+    {
+      "epoch": 0.3165391717225007,
+      "eval_loss": 0.15114803612232208,
+      "eval_runtime": 44.2313,
+      "eval_samples_per_second": 4.522,
+      "eval_steps_per_second": 4.522,
+      "step": 150
+    },
+    {
+      "epoch": 0.3376417831706674,
+      "grad_norm": 0.23078428208827972,
+      "learning_rate": 0.00019723484218374865,
+      "loss": 0.142,
+      "step": 160
+    },
+    {
+      "epoch": 0.35874439461883406,
+      "grad_norm": 0.15399664640426636,
+      "learning_rate": 0.00019630899001576405,
+      "loss": 0.1472,
+      "step": 170
+    },
+    {
+      "epoch": 0.3798470060670008,
+      "grad_norm": 0.21795395016670227,
+      "learning_rate": 0.0001952525149182412,
+      "loss": 0.1511,
+      "step": 180
+    },
+    {
+      "epoch": 0.3798470060670008,
+      "eval_loss": 0.14088743925094604,
+      "eval_runtime": 44.23,
+      "eval_samples_per_second": 4.522,
+      "eval_steps_per_second": 4.522,
+      "step": 180
+    },
+    {
+      "epoch": 0.4009496175151675,
+      "grad_norm": 0.2159528136253357,
+      "learning_rate": 0.00019406684977789395,
+      "loss": 0.1426,
+      "step": 190
+    },
+    {
+      "epoch": 0.4220522289633342,
+      "grad_norm": 0.154087632894516,
+      "learning_rate": 0.00019275360270061217,
+      "loss": 0.1469,
+      "step": 200
+    },
+    {
+      "epoch": 0.44315484041150094,
+      "grad_norm": 0.1741837114095688,
+      "learning_rate": 0.0001913145548304034,
+      "loss": 0.139,
+      "step": 210
+    },
+    {
+      "epoch": 0.44315484041150094,
+      "eval_loss": 0.13762199878692627,
+      "eval_runtime": 44.3745,
+      "eval_samples_per_second": 4.507,
+      "eval_steps_per_second": 4.507,
+      "step": 210
+    },
+    {
+      "epoch": 0.46425745185966766,
+      "grad_norm": 0.14827653765678406,
+      "learning_rate": 0.00018975165793364503,
+      "loss": 0.1391,
+      "step": 220
+    },
+    {
+      "epoch": 0.4853600633078343,
+      "grad_norm": 0.152383491396904,
+      "learning_rate": 0.00018806703175192283,
+      "loss": 0.1418,
+      "step": 230
+    },
+    {
+      "epoch": 0.506462674756001,
+      "grad_norm": 0.2013552486896515,
+      "learning_rate": 0.0001862629611270464,
+      "loss": 0.1442,
+      "step": 240
+    },
+    {
+      "epoch": 0.506462674756001,
+      "eval_loss": 0.136888787150383,
+      "eval_runtime": 44.4633,
+      "eval_samples_per_second": 4.498,
+      "eval_steps_per_second": 4.498,
+      "step": 240
+    },
+    {
+      "epoch": 0.5275652862041678,
+      "grad_norm": 0.16066157817840576,
+      "learning_rate": 0.00018434189290214106,
+      "loss": 0.1424,
+      "step": 250
+    },
+    {
+      "epoch": 0.5486678976523345,
+      "grad_norm": 0.1520007848739624,
+      "learning_rate": 0.00018230643260301838,
+      "loss": 0.1608,
+      "step": 260
+    },
+    {
+      "epoch": 0.5697705091005012,
+      "grad_norm": 0.1666969507932663,
+      "learning_rate": 0.00018015934090432757,
+      "loss": 0.1342,
+      "step": 270
+    },
+    {
+      "epoch": 0.5697705091005012,
+      "eval_loss": 0.13377884030342102,
+      "eval_runtime": 44.2414,
+      "eval_samples_per_second": 4.521,
+      "eval_steps_per_second": 4.521,
+      "step": 270
+    },
+    {
+      "epoch": 0.5908731205486679,
+      "grad_norm": 0.1368287354707718,
+      "learning_rate": 0.00017790352988527984,
+      "loss": 0.1367,
+      "step": 280
+    },
+    {
+      "epoch": 0.6119757319968346,
+      "grad_norm": 0.13659009337425232,
+      "learning_rate": 0.000175542059080024,
+      "loss": 0.14,
+      "step": 290
+    },
+    {
+      "epoch": 0.6330783434450014,
+      "grad_norm": 0.19124054908752441,
+      "learning_rate": 0.00017307813132803066,
+      "loss": 0.1403,
+      "step": 300
+    },
+    {
+      "epoch": 0.6330783434450014,
+      "eval_loss": 0.13211439549922943,
+      "eval_runtime": 44.7668,
+      "eval_samples_per_second": 4.468,
+      "eval_steps_per_second": 4.468,
+      "step": 300
+    },
+    {
+      "epoch": 0.6541809548931681,
+      "grad_norm": 0.14924179017543793,
+      "learning_rate": 0.0001705150884301129,
+      "loss": 0.1317,
+      "step": 310
+    },
+    {
+      "epoch": 0.6752835663413348,
+      "grad_norm": 0.1274843066930771,
+      "learning_rate": 0.00016785640661597467,
+      "loss": 0.1477,
+      "step": 320
+    },
+    {
+      "epoch": 0.6963861777895014,
+      "grad_norm": 0.15062034130096436,
+      "learning_rate": 0.00016510569182943524,
+      "loss": 0.1367,
+      "step": 330
+    },
+    {
+      "epoch": 0.6963861777895014,
+      "eval_loss": 0.13036254048347473,
+      "eval_runtime": 44.6273,
+      "eval_samples_per_second": 4.482,
+      "eval_steps_per_second": 4.482,
+      "step": 330
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "grad_norm": 0.13609440624713898,
+      "learning_rate": 0.00016226667483772275,
+      "loss": 0.1294,
+      "step": 340
+    },
+    {
+      "epoch": 0.7385914006858348,
+      "grad_norm": 0.12146595865488052,
+      "learning_rate": 0.00015934320617147214,
+      "loss": 0.1356,
+      "step": 350
+    },
+    {
+      "epoch": 0.7596940121340016,
+      "grad_norm": 0.33670490980148315,
+      "learning_rate": 0.0001563392509022882,
+      "loss": 0.1348,
+      "step": 360
+    },
+    {
+      "epoch": 0.7596940121340016,
+      "eval_loss": 0.1280602663755417,
+      "eval_runtime": 44.5897,
+      "eval_samples_per_second": 4.485,
+      "eval_steps_per_second": 4.485,
+      "step": 360
+    },
+    {
+      "epoch": 0.7807966235821683,
+      "grad_norm": 0.11047045141458511,
+      "learning_rate": 0.00015325888326495833,
+      "loss": 0.1306,
+      "step": 370
+    },
+    {
+      "epoch": 0.801899235030335,
+      "grad_norm": 0.24782629311084747,
+      "learning_rate": 0.0001501062811316082,
+      "loss": 0.1421,
+      "step": 380
+    },
+    {
+      "epoch": 0.8230018464785017,
+      "grad_norm": 0.15822850167751312,
+      "learning_rate": 0.0001468857203452953,
+      "loss": 0.1345,
+      "step": 390
+    },
+    {
+      "epoch": 0.8230018464785017,
+      "eval_loss": 0.12854796648025513,
+      "eval_runtime": 44.5908,
+      "eval_samples_per_second": 4.485,
+      "eval_steps_per_second": 4.485,
+      "step": 390
+    },
+    {
+      "epoch": 0.8441044579266684,
+      "grad_norm": 0.17262572050094604,
+      "learning_rate": 0.00014360156892072518,
+      "loss": 0.138,
+      "step": 400
+    },
+    {
+      "epoch": 0.8652070693748352,
+      "grad_norm": 0.16533038020133972,
+      "learning_rate": 0.00014025828111995635,
+      "loss": 0.13,
+      "step": 410
+    },
+    {
+      "epoch": 0.8863096808230019,
+      "grad_norm": 0.10585814714431763,
+      "learning_rate": 0.00013686039141112886,
+      "loss": 0.1267,
+      "step": 420
+    },
+    {
+      "epoch": 0.8863096808230019,
+      "eval_loss": 0.12870755791664124,
+      "eval_runtime": 44.5358,
+      "eval_samples_per_second": 4.491,
+      "eval_steps_per_second": 4.491,
+      "step": 420
+    },
+    {
+      "epoch": 0.9074122922711686,
+      "grad_norm": 0.12024762481451035,
+      "learning_rate": 0.00013341250831840998,
+      "loss": 0.1394,
+      "step": 430
+    },
+    {
+      "epoch": 0.9285149037193353,
+      "grad_norm": 0.11544947326183319,
+      "learning_rate": 0.0001299193081714986,
+      "loss": 0.1409,
+      "step": 440
+    },
+    {
+      "epoch": 0.9496175151675019,
+      "grad_norm": 0.2589576840400696,
+      "learning_rate": 0.0001263855287631654,
+      "loss": 0.1352,
+      "step": 450
+    },
+    {
+      "epoch": 0.9496175151675019,
+      "eval_loss": 0.12487487494945526,
+      "eval_runtime": 44.5323,
+      "eval_samples_per_second": 4.491,
+      "eval_steps_per_second": 4.491,
+      "step": 450
+    },
+    {
+      "epoch": 0.9707201266156686,
+      "grad_norm": 0.13384610414505005,
+      "learning_rate": 0.00012281596292343163,
+      "loss": 0.1231,
+      "step": 460
+    },
+    {
+      "epoch": 0.9918227380638354,
+      "grad_norm": 0.10393290221691132,
+      "learning_rate": 0.00011921545201910099,
+      "loss": 0.1347,
+      "step": 470
+    },
+    {
+      "epoch": 1.0126615668689,
+      "grad_norm": 0.11627262830734253,
+      "learning_rate": 0.00011558887938746194,
+      "loss": 0.1305,
+      "step": 480
+    },
+    {
+      "epoch": 1.0126615668689,
+      "eval_loss": 0.12428628653287888,
+      "eval_runtime": 44.5885,
+      "eval_samples_per_second": 4.485,
+      "eval_steps_per_second": 4.485,
+      "step": 480
+    },
+    {
+      "epoch": 1.0337641783170668,
+      "grad_norm": 0.13240262866020203,
+      "learning_rate": 0.00011194116371306573,
+      "loss": 0.1308,
+      "step": 490
+    },
+    {
+      "epoch": 1.0548667897652335,
+      "grad_norm": 0.15070736408233643,
+      "learning_rate": 0.00010827725235656294,
+      "loss": 0.13,
+      "step": 500
+    },
+    {
+      "epoch": 1.0759694012134002,
+      "grad_norm": 0.1023663654923439,
+      "learning_rate": 0.00010460211464464757,
+      "loss": 0.1291,
+      "step": 510
+    },
+    {
+      "epoch": 1.0759694012134002,
+      "eval_loss": 0.12311653047800064,
+      "eval_runtime": 44.4742,
+      "eval_samples_per_second": 4.497,
+      "eval_steps_per_second": 4.497,
+      "step": 510
+    },
+    {
+      "epoch": 1.097072012661567,
+      "grad_norm": 0.11538528650999069,
+      "learning_rate": 0.00010092073513020834,
+      "loss": 0.1314,
+      "step": 520
+    },
+    {
+      "epoch": 1.1181746241097337,
+      "grad_norm": 0.09773898124694824,
+      "learning_rate": 9.723810683182883e-05,
+      "loss": 0.1238,
+      "step": 530
+    },
+    {
+      "epoch": 1.1392772355579002,
+      "grad_norm": 0.1469469964504242,
+      "learning_rate": 9.355922446180593e-05,
+      "loss": 0.1302,
+      "step": 540
+    },
+    {
+      "epoch": 1.1392772355579002,
+      "eval_loss": 0.12340555340051651,
+      "eval_runtime": 44.7791,
+      "eval_samples_per_second": 4.466,
+      "eval_steps_per_second": 4.466,
+      "step": 540
+    },
+    {
+      "epoch": 1.160379847006067,
+      "grad_norm": 0.08568503707647324,
+      "learning_rate": 8.988907765187104e-05,
+      "loss": 0.1291,
+      "step": 550
+    },
+    {
+      "epoch": 1.1814824584542336,
+      "grad_norm": 0.11329666525125504,
+      "learning_rate": 8.623264418580185e-05,
+      "loss": 0.1243,
+      "step": 560
+    },
+    {
+      "epoch": 1.2025850699024003,
+      "grad_norm": 0.20136046409606934,
+      "learning_rate": 8.259488324810359e-05,
+      "loss": 0.1236,
+      "step": 570
+    },
+    {
+      "epoch": 1.2025850699024003,
+      "eval_loss": 0.12261851131916046,
+      "eval_runtime": 44.5714,
+      "eval_samples_per_second": 4.487,
+      "eval_steps_per_second": 4.487,
+      "step": 570
+    },
+    {
+      "epoch": 1.223687681350567,
+      "grad_norm": 0.09609243273735046,
+      "learning_rate": 7.89807286979162e-05,
+      "loss": 0.125,
+      "step": 580
+    },
+    {
+      "epoch": 1.2447902927987338,
+      "grad_norm": 0.15356111526489258,
+      "learning_rate": 7.539508237726986e-05,
+      "loss": 0.1268,
+      "step": 590
+    },
+    {
+      "epoch": 1.2658929042469005,
+      "grad_norm": 0.09328490495681763,
+      "learning_rate": 7.184280746276537e-05,
+      "loss": 0.1239,
+      "step": 600
+    },
+    {
+      "epoch": 1.2658929042469005,
+      "eval_loss": 0.1222267746925354,
+      "eval_runtime": 44.5091,
+      "eval_samples_per_second": 4.493,
+      "eval_steps_per_second": 4.493,
+      "step": 600
+    },
+    {
+      "epoch": 1.2869955156950672,
+      "grad_norm": 0.10134255886077881,
+      "learning_rate": 6.832872186969583e-05,
+      "loss": 0.122,
+      "step": 610
+    },
+    {
+      "epoch": 1.308098127143234,
+      "grad_norm": 0.08854757249355316,
+      "learning_rate": 6.485759171755574e-05,
+      "loss": 0.1271,
+      "step": 620
+    },
+    {
+      "epoch": 1.3292007385914006,
+      "grad_norm": 0.12832631170749664,
+      "learning_rate": 6.143412486580051e-05,
+      "loss": 0.1243,
+      "step": 630
+    },
+    {
+      "epoch": 1.3292007385914006,
+      "eval_loss": 0.1208844780921936,
+      "eval_runtime": 44.7617,
+      "eval_samples_per_second": 4.468,
+      "eval_steps_per_second": 4.468,
+      "step": 630
+    },
+    {
+      "epoch": 1.3503033500395674,
+      "grad_norm": 0.10490237921476364,
+      "learning_rate": 5.8062964528623096e-05,
+      "loss": 0.1233,
+      "step": 640
+    },
+    {
+      "epoch": 1.371405961487734,
+      "grad_norm": 0.09632379561662674,
+      "learning_rate": 5.474868297740874e-05,
+      "loss": 0.1246,
+      "step": 650
+    },
+    {
+      "epoch": 1.3925085729359008,
+      "grad_norm": 0.09513814002275467,
+      "learning_rate": 5.149577533940836e-05,
+      "loss": 0.125,
+      "step": 660
+    },
+    {
+      "epoch": 1.3925085729359008,
+      "eval_loss": 0.12093473225831985,
+      "eval_runtime": 44.6914,
+      "eval_samples_per_second": 4.475,
+      "eval_steps_per_second": 4.475,
+      "step": 660
+    },
+    {
+      "epoch": 1.4136111843840675,
+      "grad_norm": 0.08354990929365158,
+      "learning_rate": 4.8308653501042166e-05,
+      "loss": 0.1247,
+      "step": 670
+    },
+    {
+      "epoch": 1.4347137958322342,
+      "grad_norm": 0.07765179127454758,
+      "learning_rate": 4.519164012410171e-05,
+      "loss": 0.1225,
+      "step": 680
+    },
+    {
+      "epoch": 1.455816407280401,
+      "grad_norm": 0.09267658740282059,
+      "learning_rate": 4.214896278296646e-05,
+      "loss": 0.1269,
+      "step": 690
+    },
+    {
+      "epoch": 1.455816407280401,
+      "eval_loss": 0.12080849707126617,
+      "eval_runtime": 44.6277,
+      "eval_samples_per_second": 4.482,
+      "eval_steps_per_second": 4.482,
+      "step": 690
+    },
+    {
+      "epoch": 1.4769190187285677,
+      "grad_norm": 0.10476211458444595,
+      "learning_rate": 3.9184748230786584e-05,
+      "loss": 0.1207,
+      "step": 700
+    },
+    {
+      "epoch": 1.4980216301767344,
+      "grad_norm": 0.09438898414373398,
+      "learning_rate": 3.6303016802408594e-05,
+      "loss": 0.1243,
+      "step": 710
+    },
+    {
+      "epoch": 1.5191242416249011,
+      "grad_norm": 0.09003426134586334,
+      "learning_rate": 3.3507676961634796e-05,
+      "loss": 0.1225,
+      "step": 720
+    },
+    {
+      "epoch": 1.5191242416249011,
+      "eval_loss": 0.11986906081438065,
+      "eval_runtime": 44.9813,
+      "eval_samples_per_second": 4.446,
+      "eval_steps_per_second": 4.446,
+      "step": 720
+    },
+    {
+      "epoch": 1.5402268530730678,
+      "grad_norm": 0.09385745972394943,
+      "learning_rate": 3.080252000021264e-05,
+      "loss": 0.1262,
+      "step": 730
+    },
+    {
+      "epoch": 1.5613294645212346,
+      "grad_norm": 0.09874516725540161,
+      "learning_rate": 2.8191214895743424e-05,
+      "loss": 0.1195,
+      "step": 740
+    },
+    {
+      "epoch": 1.5824320759694013,
+      "grad_norm": 0.08888901770114899,
+      "learning_rate": 2.5677303335484025e-05,
+      "loss": 0.1176,
+      "step": 750
+    },
+    {
+      "epoch": 1.5824320759694013,
+      "eval_loss": 0.11973254382610321,
+      "eval_runtime": 44.7792,
+      "eval_samples_per_second": 4.466,
+      "eval_steps_per_second": 4.466,
+      "step": 750
+    },
+    {
+      "epoch": 1.603534687417568,
+      "grad_norm": 0.08025766164064407,
+      "learning_rate": 2.3264194912791605e-05,
+      "loss": 0.1294,
+      "step": 760
+    },
+    {
+      "epoch": 1.6246372988657347,
+      "grad_norm": 0.1188935935497284,
+      "learning_rate": 2.0955162502726135e-05,
+      "loss": 0.1186,
+      "step": 770
+    },
+    {
+      "epoch": 1.6457399103139014,
+      "grad_norm": 0.0846625491976738,
+      "learning_rate": 1.8753337823082084e-05,
+      "loss": 0.1227,
+      "step": 780
+    },
+    {
+      "epoch": 1.6457399103139014,
+      "eval_loss": 0.11954256147146225,
+      "eval_runtime": 44.8428,
+      "eval_samples_per_second": 4.46,
+      "eval_steps_per_second": 4.46,
+      "step": 780
+    },
+    {
+      "epoch": 1.6668425217620682,
+      "grad_norm": 0.09665997326374054,
+      "learning_rate": 1.666170718687069e-05,
+      "loss": 0.121,
+      "step": 790
+    },
+    {
+      "epoch": 1.6879451332102349,
+      "grad_norm": 0.10237396508455276,
+      "learning_rate": 1.4683107452013223e-05,
+      "loss": 0.122,
+      "step": 800
+    },
+    {
+      "epoch": 1.7090477446584016,
+      "grad_norm": 0.09061301499605179,
+      "learning_rate": 1.2820222173738628e-05,
+      "loss": 0.1133,
+      "step": 810
+    },
+    {
+      "epoch": 1.7090477446584016,
+      "eval_loss": 0.11932696402072906,
+      "eval_runtime": 44.6177,
+      "eval_samples_per_second": 4.483,
+      "eval_steps_per_second": 4.483,
+      "step": 810
+    },
+    {
+      "epoch": 1.7301503561065683,
+      "grad_norm": 0.09903734177350998,
+      "learning_rate": 1.1075577964904104e-05,
+      "loss": 0.1259,
+      "step": 820
+    },
+    {
+      "epoch": 1.751252967554735,
+      "grad_norm": 0.0887165367603302,
+      "learning_rate": 9.451541069175273e-06,
+      "loss": 0.116,
+      "step": 830
+    },
+    {
+      "epoch": 1.7723555790029017,
+      "grad_norm": 0.09350364655256271,
+      "learning_rate": 7.950314151713056e-06,
+      "loss": 0.1241,
+      "step": 840
+    },
+    {
+      "epoch": 1.7723555790029017,
+      "eval_loss": 0.11908172816038132,
+      "eval_runtime": 44.7048,
+      "eval_samples_per_second": 4.474,
+      "eval_steps_per_second": 4.474,
+      "step": 840
+    },
+    {
+      "epoch": 1.7934581904510685,
+      "grad_norm": 0.10343047231435776,
+      "learning_rate": 6.57393331172097e-06,
+      "loss": 0.1183,
+      "step": 850
+    },
+    {
+      "epoch": 1.8145608018992352,
+      "grad_norm": 0.08541911840438843,
+      "learning_rate": 5.324265320903843e-06,
+      "loss": 0.1258,
+      "step": 860
+    },
+    {
+      "epoch": 1.835663413347402,
+      "grad_norm": 0.10567805916070938,
+      "learning_rate": 4.203005091583801e-06,
+      "loss": 0.1204,
+      "step": 870
+    },
+    {
+      "epoch": 1.835663413347402,
+      "eval_loss": 0.11883310228586197,
+      "eval_runtime": 44.6887,
+      "eval_samples_per_second": 4.475,
+      "eval_steps_per_second": 4.475,
+      "step": 870
+    },
+    {
+      "epoch": 1.8567660247955684,
+      "grad_norm": 0.10206745564937592,
+      "learning_rate": 3.2116733779075094e-06,
+      "loss": 0.1273,
+      "step": 880
+    },
+    {
+      "epoch": 1.8778686362437351,
+      "grad_norm": 0.09496993571519852,
+      "learning_rate": 2.351614713262418e-06,
+      "loss": 0.1239,
+      "step": 890
+    },
+    {
+      "epoch": 1.8989712476919018,
+      "grad_norm": 0.13183720409870148,
+      "learning_rate": 1.623995586699334e-06,
+      "loss": 0.122,
+      "step": 900
+    },
+    {
+      "epoch": 1.8989712476919018,
+      "eval_loss": 0.11881602555513382,
+      "eval_runtime": 44.6717,
+      "eval_samples_per_second": 4.477,
+      "eval_steps_per_second": 4.477,
+      "step": 900
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 948,
+  "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": 1.348133794370519e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-900/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:205b533064fa1dc8ee63d524ef9e21004b40a49ecb894334eb028f111208dbcf
+size 5777

checkpoint-948/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-948/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": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-948/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b65d3f4fa7f58f2ecadc8c72b0385f61bf0044a3acc3d8bc00fd3fbe6911bb
+size 528550256

checkpoint-948/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-948/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-948/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c36813422ab2f244c048cb736ae70e83b0b3e210ac7bdfbca57c9dd65277ca82
+size 1057397963

checkpoint-948/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a008ac8d1b8700bb8a053c5b1f2aab21006aa2bb73a45f46e806c8e49b9b7b5
+size 14645

checkpoint-948/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93137690dead97a15b2b04636ec8ecdb8cfc8d961842c452fe04dae7d474c6a2
+size 1465

checkpoint-948/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-948/tokenizer.json

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

checkpoint-948/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-948/trainer_state.json

@@ -0,0 +1,940 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 30,
+  "global_step": 948,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.021102611448166712,
+      "grad_norm": 5.49099588394165,
+      "learning_rate": 1.8947368421052634e-05,
+      "loss": 2.4799,
+      "step": 10
+    },
+    {
+      "epoch": 0.042205222896333425,
+      "grad_norm": 0.7057839035987854,
+      "learning_rate": 4e-05,
+      "loss": 0.9017,
+      "step": 20
+    },
+    {
+      "epoch": 0.06330783434450013,
+      "grad_norm": 0.7793235778808594,
+      "learning_rate": 6.105263157894737e-05,
+      "loss": 0.5561,
+      "step": 30
+    },
+    {
+      "epoch": 0.06330783434450013,
+      "eval_loss": 0.49612972140312195,
+      "eval_runtime": 44.7367,
+      "eval_samples_per_second": 4.471,
+      "eval_steps_per_second": 4.471,
+      "step": 30
+    },
+    {
+      "epoch": 0.08441044579266685,
+      "grad_norm": 0.6479541063308716,
+      "learning_rate": 8.210526315789474e-05,
+      "loss": 0.4088,
+      "step": 40
+    },
+    {
+      "epoch": 0.10551305724083355,
+      "grad_norm": 0.6190423965454102,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 0.3332,
+      "step": 50
+    },
+    {
+      "epoch": 0.12661566868900026,
+      "grad_norm": 0.48822861909866333,
+      "learning_rate": 0.00012421052631578949,
+      "loss": 0.2752,
+      "step": 60
+    },
+    {
+      "epoch": 0.12661566868900026,
+      "eval_loss": 0.25475138425827026,
+      "eval_runtime": 44.1798,
+      "eval_samples_per_second": 4.527,
+      "eval_steps_per_second": 4.527,
+      "step": 60
+    },
+    {
+      "epoch": 0.14771828013716698,
+      "grad_norm": 0.3956296443939209,
+      "learning_rate": 0.00014526315789473686,
+      "loss": 0.2283,
+      "step": 70
+    },
+    {
+      "epoch": 0.1688208915853337,
+      "grad_norm": 0.6851626038551331,
+      "learning_rate": 0.00016631578947368423,
+      "loss": 0.2017,
+      "step": 80
+    },
+    {
+      "epoch": 0.1899235030335004,
+      "grad_norm": 2.741124153137207,
+      "learning_rate": 0.0001873684210526316,
+      "loss": 0.1877,
+      "step": 90
+    },
+    {
+      "epoch": 0.1899235030335004,
+      "eval_loss": 0.19585472345352173,
+      "eval_runtime": 44.05,
+      "eval_samples_per_second": 4.54,
+      "eval_steps_per_second": 4.54,
+      "step": 90
+    },
+    {
+      "epoch": 0.2110261144816671,
+      "grad_norm": 0.4686296880245209,
+      "learning_rate": 0.00019998914864890175,
+      "loss": 0.1862,
+      "step": 100
+    },
+    {
+      "epoch": 0.23212872592983383,
+      "grad_norm": 0.5210604071617126,
+      "learning_rate": 0.0001998670979935533,
+      "loss": 0.1754,
+      "step": 110
+    },
+    {
+      "epoch": 0.2532313373780005,
+      "grad_norm": 0.2621477246284485,
+      "learning_rate": 0.00019960959858204754,
+      "loss": 0.1767,
+      "step": 120
+    },
+    {
+      "epoch": 0.2532313373780005,
+      "eval_loss": 0.16388529539108276,
+      "eval_runtime": 44.3724,
+      "eval_samples_per_second": 4.507,
+      "eval_steps_per_second": 4.507,
+      "step": 120
+    },
+    {
+      "epoch": 0.27433394882616724,
+      "grad_norm": 0.3740817904472351,
+      "learning_rate": 0.00019921699965828662,
+      "loss": 0.1666,
+      "step": 130
+    },
+    {
+      "epoch": 0.29543656027433396,
+      "grad_norm": 0.5232918858528137,
+      "learning_rate": 0.00019868983370030348,
+      "loss": 0.1624,
+      "step": 140
+    },
+    {
+      "epoch": 0.3165391717225007,
+      "grad_norm": 0.2019444853067398,
+      "learning_rate": 0.00019802881569806706,
+      "loss": 0.1647,
+      "step": 150
+    },
+    {
+      "epoch": 0.3165391717225007,
+      "eval_loss": 0.15114803612232208,
+      "eval_runtime": 44.2313,
+      "eval_samples_per_second": 4.522,
+      "eval_steps_per_second": 4.522,
+      "step": 150
+    },
+    {
+      "epoch": 0.3376417831706674,
+      "grad_norm": 0.23078428208827972,
+      "learning_rate": 0.00019723484218374865,
+      "loss": 0.142,
+      "step": 160
+    },
+    {
+      "epoch": 0.35874439461883406,
+      "grad_norm": 0.15399664640426636,
+      "learning_rate": 0.00019630899001576405,
+      "loss": 0.1472,
+      "step": 170
+    },
+    {
+      "epoch": 0.3798470060670008,
+      "grad_norm": 0.21795395016670227,
+      "learning_rate": 0.0001952525149182412,
+      "loss": 0.1511,
+      "step": 180
+    },
+    {
+      "epoch": 0.3798470060670008,
+      "eval_loss": 0.14088743925094604,
+      "eval_runtime": 44.23,
+      "eval_samples_per_second": 4.522,
+      "eval_steps_per_second": 4.522,
+      "step": 180
+    },
+    {
+      "epoch": 0.4009496175151675,
+      "grad_norm": 0.2159528136253357,
+      "learning_rate": 0.00019406684977789395,
+      "loss": 0.1426,
+      "step": 190
+    },
+    {
+      "epoch": 0.4220522289633342,
+      "grad_norm": 0.154087632894516,
+      "learning_rate": 0.00019275360270061217,
+      "loss": 0.1469,
+      "step": 200
+    },
+    {
+      "epoch": 0.44315484041150094,
+      "grad_norm": 0.1741837114095688,
+      "learning_rate": 0.0001913145548304034,
+      "loss": 0.139,
+      "step": 210
+    },
+    {
+      "epoch": 0.44315484041150094,
+      "eval_loss": 0.13762199878692627,
+      "eval_runtime": 44.3745,
+      "eval_samples_per_second": 4.507,
+      "eval_steps_per_second": 4.507,
+      "step": 210
+    },
+    {
+      "epoch": 0.46425745185966766,
+      "grad_norm": 0.14827653765678406,
+      "learning_rate": 0.00018975165793364503,
+      "loss": 0.1391,
+      "step": 220
+    },
+    {
+      "epoch": 0.4853600633078343,
+      "grad_norm": 0.152383491396904,
+      "learning_rate": 0.00018806703175192283,
+      "loss": 0.1418,
+      "step": 230
+    },
+    {
+      "epoch": 0.506462674756001,
+      "grad_norm": 0.2013552486896515,
+      "learning_rate": 0.0001862629611270464,
+      "loss": 0.1442,
+      "step": 240
+    },
+    {
+      "epoch": 0.506462674756001,
+      "eval_loss": 0.136888787150383,
+      "eval_runtime": 44.4633,
+      "eval_samples_per_second": 4.498,
+      "eval_steps_per_second": 4.498,
+      "step": 240
+    },
+    {
+      "epoch": 0.5275652862041678,
+      "grad_norm": 0.16066157817840576,
+      "learning_rate": 0.00018434189290214106,
+      "loss": 0.1424,
+      "step": 250
+    },
+    {
+      "epoch": 0.5486678976523345,
+      "grad_norm": 0.1520007848739624,
+      "learning_rate": 0.00018230643260301838,
+      "loss": 0.1608,
+      "step": 260
+    },
+    {
+      "epoch": 0.5697705091005012,
+      "grad_norm": 0.1666969507932663,
+      "learning_rate": 0.00018015934090432757,
+      "loss": 0.1342,
+      "step": 270
+    },
+    {
+      "epoch": 0.5697705091005012,
+      "eval_loss": 0.13377884030342102,
+      "eval_runtime": 44.2414,
+      "eval_samples_per_second": 4.521,
+      "eval_steps_per_second": 4.521,
+      "step": 270
+    },
+    {
+      "epoch": 0.5908731205486679,
+      "grad_norm": 0.1368287354707718,
+      "learning_rate": 0.00017790352988527984,
+      "loss": 0.1367,
+      "step": 280
+    },
+    {
+      "epoch": 0.6119757319968346,
+      "grad_norm": 0.13659009337425232,
+      "learning_rate": 0.000175542059080024,
+      "loss": 0.14,
+      "step": 290
+    },
+    {
+      "epoch": 0.6330783434450014,
+      "grad_norm": 0.19124054908752441,
+      "learning_rate": 0.00017307813132803066,
+      "loss": 0.1403,
+      "step": 300
+    },
+    {
+      "epoch": 0.6330783434450014,
+      "eval_loss": 0.13211439549922943,
+      "eval_runtime": 44.7668,
+      "eval_samples_per_second": 4.468,
+      "eval_steps_per_second": 4.468,
+      "step": 300
+    },
+    {
+      "epoch": 0.6541809548931681,
+      "grad_norm": 0.14924179017543793,
+      "learning_rate": 0.0001705150884301129,
+      "loss": 0.1317,
+      "step": 310
+    },
+    {
+      "epoch": 0.6752835663413348,
+      "grad_norm": 0.1274843066930771,
+      "learning_rate": 0.00016785640661597467,
+      "loss": 0.1477,
+      "step": 320
+    },
+    {
+      "epoch": 0.6963861777895014,
+      "grad_norm": 0.15062034130096436,
+      "learning_rate": 0.00016510569182943524,
+      "loss": 0.1367,
+      "step": 330
+    },
+    {
+      "epoch": 0.6963861777895014,
+      "eval_loss": 0.13036254048347473,
+      "eval_runtime": 44.6273,
+      "eval_samples_per_second": 4.482,
+      "eval_steps_per_second": 4.482,
+      "step": 330
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "grad_norm": 0.13609440624713898,
+      "learning_rate": 0.00016226667483772275,
+      "loss": 0.1294,
+      "step": 340
+    },
+    {
+      "epoch": 0.7385914006858348,
+      "grad_norm": 0.12146595865488052,
+      "learning_rate": 0.00015934320617147214,
+      "loss": 0.1356,
+      "step": 350
+    },
+    {
+      "epoch": 0.7596940121340016,
+      "grad_norm": 0.33670490980148315,
+      "learning_rate": 0.0001563392509022882,
+      "loss": 0.1348,
+      "step": 360
+    },
+    {
+      "epoch": 0.7596940121340016,
+      "eval_loss": 0.1280602663755417,
+      "eval_runtime": 44.5897,
+      "eval_samples_per_second": 4.485,
+      "eval_steps_per_second": 4.485,
+      "step": 360
+    },
+    {
+      "epoch": 0.7807966235821683,
+      "grad_norm": 0.11047045141458511,
+      "learning_rate": 0.00015325888326495833,
+      "loss": 0.1306,
+      "step": 370
+    },
+    {
+      "epoch": 0.801899235030335,
+      "grad_norm": 0.24782629311084747,
+      "learning_rate": 0.0001501062811316082,
+      "loss": 0.1421,
+      "step": 380
+    },
+    {
+      "epoch": 0.8230018464785017,
+      "grad_norm": 0.15822850167751312,
+      "learning_rate": 0.0001468857203452953,
+      "loss": 0.1345,
+      "step": 390
+    },
+    {
+      "epoch": 0.8230018464785017,
+      "eval_loss": 0.12854796648025513,
+      "eval_runtime": 44.5908,
+      "eval_samples_per_second": 4.485,
+      "eval_steps_per_second": 4.485,
+      "step": 390
+    },
+    {
+      "epoch": 0.8441044579266684,
+      "grad_norm": 0.17262572050094604,
+      "learning_rate": 0.00014360156892072518,
+      "loss": 0.138,
+      "step": 400
+    },
+    {
+      "epoch": 0.8652070693748352,
+      "grad_norm": 0.16533038020133972,
+      "learning_rate": 0.00014025828111995635,
+      "loss": 0.13,
+      "step": 410
+    },
+    {
+      "epoch": 0.8863096808230019,
+      "grad_norm": 0.10585814714431763,
+      "learning_rate": 0.00013686039141112886,
+      "loss": 0.1267,
+      "step": 420
+    },
+    {
+      "epoch": 0.8863096808230019,
+      "eval_loss": 0.12870755791664124,
+      "eval_runtime": 44.5358,
+      "eval_samples_per_second": 4.491,
+      "eval_steps_per_second": 4.491,
+      "step": 420
+    },
+    {
+      "epoch": 0.9074122922711686,
+      "grad_norm": 0.12024762481451035,
+      "learning_rate": 0.00013341250831840998,
+      "loss": 0.1394,
+      "step": 430
+    },
+    {
+      "epoch": 0.9285149037193353,
+      "grad_norm": 0.11544947326183319,
+      "learning_rate": 0.0001299193081714986,
+      "loss": 0.1409,
+      "step": 440
+    },
+    {
+      "epoch": 0.9496175151675019,
+      "grad_norm": 0.2589576840400696,
+      "learning_rate": 0.0001263855287631654,
+      "loss": 0.1352,
+      "step": 450
+    },
+    {
+      "epoch": 0.9496175151675019,
+      "eval_loss": 0.12487487494945526,
+      "eval_runtime": 44.5323,
+      "eval_samples_per_second": 4.491,
+      "eval_steps_per_second": 4.491,
+      "step": 450
+    },
+    {
+      "epoch": 0.9707201266156686,
+      "grad_norm": 0.13384610414505005,
+      "learning_rate": 0.00012281596292343163,
+      "loss": 0.1231,
+      "step": 460
+    },
+    {
+      "epoch": 0.9918227380638354,
+      "grad_norm": 0.10393290221691132,
+      "learning_rate": 0.00011921545201910099,
+      "loss": 0.1347,
+      "step": 470
+    },
+    {
+      "epoch": 1.0126615668689,
+      "grad_norm": 0.11627262830734253,
+      "learning_rate": 0.00011558887938746194,
+      "loss": 0.1305,
+      "step": 480
+    },
+    {
+      "epoch": 1.0126615668689,
+      "eval_loss": 0.12428628653287888,
+      "eval_runtime": 44.5885,
+      "eval_samples_per_second": 4.485,
+      "eval_steps_per_second": 4.485,
+      "step": 480
+    },
+    {
+      "epoch": 1.0337641783170668,
+      "grad_norm": 0.13240262866020203,
+      "learning_rate": 0.00011194116371306573,
+      "loss": 0.1308,
+      "step": 490
+    },
+    {
+      "epoch": 1.0548667897652335,
+      "grad_norm": 0.15070736408233643,
+      "learning_rate": 0.00010827725235656294,
+      "loss": 0.13,
+      "step": 500
+    },
+    {
+      "epoch": 1.0759694012134002,
+      "grad_norm": 0.1023663654923439,
+      "learning_rate": 0.00010460211464464757,
+      "loss": 0.1291,
+      "step": 510
+    },
+    {
+      "epoch": 1.0759694012134002,
+      "eval_loss": 0.12311653047800064,
+      "eval_runtime": 44.4742,
+      "eval_samples_per_second": 4.497,
+      "eval_steps_per_second": 4.497,
+      "step": 510
+    },
+    {
+      "epoch": 1.097072012661567,
+      "grad_norm": 0.11538528650999069,
+      "learning_rate": 0.00010092073513020834,
+      "loss": 0.1314,
+      "step": 520
+    },
+    {
+      "epoch": 1.1181746241097337,
+      "grad_norm": 0.09773898124694824,
+      "learning_rate": 9.723810683182883e-05,
+      "loss": 0.1238,
+      "step": 530
+    },
+    {
+      "epoch": 1.1392772355579002,
+      "grad_norm": 0.1469469964504242,
+      "learning_rate": 9.355922446180593e-05,
+      "loss": 0.1302,
+      "step": 540
+    },
+    {
+      "epoch": 1.1392772355579002,
+      "eval_loss": 0.12340555340051651,
+      "eval_runtime": 44.7791,
+      "eval_samples_per_second": 4.466,
+      "eval_steps_per_second": 4.466,
+      "step": 540
+    },
+    {
+      "epoch": 1.160379847006067,
+      "grad_norm": 0.08568503707647324,
+      "learning_rate": 8.988907765187104e-05,
+      "loss": 0.1291,
+      "step": 550
+    },
+    {
+      "epoch": 1.1814824584542336,
+      "grad_norm": 0.11329666525125504,
+      "learning_rate": 8.623264418580185e-05,
+      "loss": 0.1243,
+      "step": 560
+    },
+    {
+      "epoch": 1.2025850699024003,
+      "grad_norm": 0.20136046409606934,
+      "learning_rate": 8.259488324810359e-05,
+      "loss": 0.1236,
+      "step": 570
+    },
+    {
+      "epoch": 1.2025850699024003,
+      "eval_loss": 0.12261851131916046,
+      "eval_runtime": 44.5714,
+      "eval_samples_per_second": 4.487,
+      "eval_steps_per_second": 4.487,
+      "step": 570
+    },
+    {
+      "epoch": 1.223687681350567,
+      "grad_norm": 0.09609243273735046,
+      "learning_rate": 7.89807286979162e-05,
+      "loss": 0.125,
+      "step": 580
+    },
+    {
+      "epoch": 1.2447902927987338,
+      "grad_norm": 0.15356111526489258,
+      "learning_rate": 7.539508237726986e-05,
+      "loss": 0.1268,
+      "step": 590
+    },
+    {
+      "epoch": 1.2658929042469005,
+      "grad_norm": 0.09328490495681763,
+      "learning_rate": 7.184280746276537e-05,
+      "loss": 0.1239,
+      "step": 600
+    },
+    {
+      "epoch": 1.2658929042469005,
+      "eval_loss": 0.1222267746925354,
+      "eval_runtime": 44.5091,
+      "eval_samples_per_second": 4.493,
+      "eval_steps_per_second": 4.493,
+      "step": 600
+    },
+    {
+      "epoch": 1.2869955156950672,
+      "grad_norm": 0.10134255886077881,
+      "learning_rate": 6.832872186969583e-05,
+      "loss": 0.122,
+      "step": 610
+    },
+    {
+      "epoch": 1.308098127143234,
+      "grad_norm": 0.08854757249355316,
+      "learning_rate": 6.485759171755574e-05,
+      "loss": 0.1271,
+      "step": 620
+    },
+    {
+      "epoch": 1.3292007385914006,
+      "grad_norm": 0.12832631170749664,
+      "learning_rate": 6.143412486580051e-05,
+      "loss": 0.1243,
+      "step": 630
+    },
+    {
+      "epoch": 1.3292007385914006,
+      "eval_loss": 0.1208844780921936,
+      "eval_runtime": 44.7617,
+      "eval_samples_per_second": 4.468,
+      "eval_steps_per_second": 4.468,
+      "step": 630
+    },
+    {
+      "epoch": 1.3503033500395674,
+      "grad_norm": 0.10490237921476364,
+      "learning_rate": 5.8062964528623096e-05,
+      "loss": 0.1233,
+      "step": 640
+    },
+    {
+      "epoch": 1.371405961487734,
+      "grad_norm": 0.09632379561662674,
+      "learning_rate": 5.474868297740874e-05,
+      "loss": 0.1246,
+      "step": 650
+    },
+    {
+      "epoch": 1.3925085729359008,
+      "grad_norm": 0.09513814002275467,
+      "learning_rate": 5.149577533940836e-05,
+      "loss": 0.125,
+      "step": 660
+    },
+    {
+      "epoch": 1.3925085729359008,
+      "eval_loss": 0.12093473225831985,
+      "eval_runtime": 44.6914,
+      "eval_samples_per_second": 4.475,
+      "eval_steps_per_second": 4.475,
+      "step": 660
+    },
+    {
+      "epoch": 1.4136111843840675,
+      "grad_norm": 0.08354990929365158,
+      "learning_rate": 4.8308653501042166e-05,
+      "loss": 0.1247,
+      "step": 670
+    },
+    {
+      "epoch": 1.4347137958322342,
+      "grad_norm": 0.07765179127454758,
+      "learning_rate": 4.519164012410171e-05,
+      "loss": 0.1225,
+      "step": 680
+    },
+    {
+      "epoch": 1.455816407280401,
+      "grad_norm": 0.09267658740282059,
+      "learning_rate": 4.214896278296646e-05,
+      "loss": 0.1269,
+      "step": 690
+    },
+    {
+      "epoch": 1.455816407280401,
+      "eval_loss": 0.12080849707126617,
+      "eval_runtime": 44.6277,
+      "eval_samples_per_second": 4.482,
+      "eval_steps_per_second": 4.482,
+      "step": 690
+    },
+    {
+      "epoch": 1.4769190187285677,
+      "grad_norm": 0.10476211458444595,
+      "learning_rate": 3.9184748230786584e-05,
+      "loss": 0.1207,
+      "step": 700
+    },
+    {
+      "epoch": 1.4980216301767344,
+      "grad_norm": 0.09438898414373398,
+      "learning_rate": 3.6303016802408594e-05,
+      "loss": 0.1243,
+      "step": 710
+    },
+    {
+      "epoch": 1.5191242416249011,
+      "grad_norm": 0.09003426134586334,
+      "learning_rate": 3.3507676961634796e-05,
+      "loss": 0.1225,
+      "step": 720
+    },
+    {
+      "epoch": 1.5191242416249011,
+      "eval_loss": 0.11986906081438065,
+      "eval_runtime": 44.9813,
+      "eval_samples_per_second": 4.446,
+      "eval_steps_per_second": 4.446,
+      "step": 720
+    },
+    {
+      "epoch": 1.5402268530730678,
+      "grad_norm": 0.09385745972394943,
+      "learning_rate": 3.080252000021264e-05,
+      "loss": 0.1262,
+      "step": 730
+    },
+    {
+      "epoch": 1.5613294645212346,
+      "grad_norm": 0.09874516725540161,
+      "learning_rate": 2.8191214895743424e-05,
+      "loss": 0.1195,
+      "step": 740
+    },
+    {
+      "epoch": 1.5824320759694013,
+      "grad_norm": 0.08888901770114899,
+      "learning_rate": 2.5677303335484025e-05,
+      "loss": 0.1176,
+      "step": 750
+    },
+    {
+      "epoch": 1.5824320759694013,
+      "eval_loss": 0.11973254382610321,
+      "eval_runtime": 44.7792,
+      "eval_samples_per_second": 4.466,
+      "eval_steps_per_second": 4.466,
+      "step": 750
+    },
+    {
+      "epoch": 1.603534687417568,
+      "grad_norm": 0.08025766164064407,
+      "learning_rate": 2.3264194912791605e-05,
+      "loss": 0.1294,
+      "step": 760
+    },
+    {
+      "epoch": 1.6246372988657347,
+      "grad_norm": 0.1188935935497284,
+      "learning_rate": 2.0955162502726135e-05,
+      "loss": 0.1186,
+      "step": 770
+    },
+    {
+      "epoch": 1.6457399103139014,
+      "grad_norm": 0.0846625491976738,
+      "learning_rate": 1.8753337823082084e-05,
+      "loss": 0.1227,
+      "step": 780
+    },
+    {
+      "epoch": 1.6457399103139014,
+      "eval_loss": 0.11954256147146225,
+      "eval_runtime": 44.8428,
+      "eval_samples_per_second": 4.46,
+      "eval_steps_per_second": 4.46,
+      "step": 780
+    },
+    {
+      "epoch": 1.6668425217620682,
+      "grad_norm": 0.09665997326374054,
+      "learning_rate": 1.666170718687069e-05,
+      "loss": 0.121,
+      "step": 790
+    },
+    {
+      "epoch": 1.6879451332102349,
+      "grad_norm": 0.10237396508455276,
+      "learning_rate": 1.4683107452013223e-05,
+      "loss": 0.122,
+      "step": 800
+    },
+    {
+      "epoch": 1.7090477446584016,
+      "grad_norm": 0.09061301499605179,
+      "learning_rate": 1.2820222173738628e-05,
+      "loss": 0.1133,
+      "step": 810
+    },
+    {
+      "epoch": 1.7090477446584016,
+      "eval_loss": 0.11932696402072906,
+      "eval_runtime": 44.6177,
+      "eval_samples_per_second": 4.483,
+      "eval_steps_per_second": 4.483,
+      "step": 810
+    },
+    {
+      "epoch": 1.7301503561065683,
+      "grad_norm": 0.09903734177350998,
+      "learning_rate": 1.1075577964904104e-05,
+      "loss": 0.1259,
+      "step": 820
+    },
+    {
+      "epoch": 1.751252967554735,
+      "grad_norm": 0.0887165367603302,
+      "learning_rate": 9.451541069175273e-06,
+      "loss": 0.116,
+      "step": 830
+    },
+    {
+      "epoch": 1.7723555790029017,
+      "grad_norm": 0.09350364655256271,
+      "learning_rate": 7.950314151713056e-06,
+      "loss": 0.1241,
+      "step": 840
+    },
+    {
+      "epoch": 1.7723555790029017,
+      "eval_loss": 0.11908172816038132,
+      "eval_runtime": 44.7048,
+      "eval_samples_per_second": 4.474,
+      "eval_steps_per_second": 4.474,
+      "step": 840
+    },
+    {
+      "epoch": 1.7934581904510685,
+      "grad_norm": 0.10343047231435776,
+      "learning_rate": 6.57393331172097e-06,
+      "loss": 0.1183,
+      "step": 850
+    },
+    {
+      "epoch": 1.8145608018992352,
+      "grad_norm": 0.08541911840438843,
+      "learning_rate": 5.324265320903843e-06,
+      "loss": 0.1258,
+      "step": 860
+    },
+    {
+      "epoch": 1.835663413347402,
+      "grad_norm": 0.10567805916070938,
+      "learning_rate": 4.203005091583801e-06,
+      "loss": 0.1204,
+      "step": 870
+    },
+    {
+      "epoch": 1.835663413347402,
+      "eval_loss": 0.11883310228586197,
+      "eval_runtime": 44.6887,
+      "eval_samples_per_second": 4.475,
+      "eval_steps_per_second": 4.475,
+      "step": 870
+    },
+    {
+      "epoch": 1.8567660247955684,
+      "grad_norm": 0.10206745564937592,
+      "learning_rate": 3.2116733779075094e-06,
+      "loss": 0.1273,
+      "step": 880
+    },
+    {
+      "epoch": 1.8778686362437351,
+      "grad_norm": 0.09496993571519852,
+      "learning_rate": 2.351614713262418e-06,
+      "loss": 0.1239,
+      "step": 890
+    },
+    {
+      "epoch": 1.8989712476919018,
+      "grad_norm": 0.13183720409870148,
+      "learning_rate": 1.623995586699334e-06,
+      "loss": 0.122,
+      "step": 900
+    },
+    {
+      "epoch": 1.8989712476919018,
+      "eval_loss": 0.11881602555513382,
+      "eval_runtime": 44.6717,
+      "eval_samples_per_second": 4.477,
+      "eval_steps_per_second": 4.477,
+      "step": 900
+    },
+    {
+      "epoch": 1.9200738591400686,
+      "grad_norm": 0.09778941422700882,
+      "learning_rate": 1.029802860834983e-06,
+      "loss": 0.1264,
+      "step": 910
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 0.10276590287685394,
+      "learning_rate": 5.698424333799413e-07,
+      "loss": 0.1205,
+      "step": 920
+    },
+    {
+      "epoch": 1.962279082036402,
+      "grad_norm": 0.08584799617528915,
+      "learning_rate": 2.4473814410759245e-07,
+      "loss": 0.1253,
+      "step": 930
+    },
+    {
+      "epoch": 1.962279082036402,
+      "eval_loss": 0.11866004765033722,
+      "eval_runtime": 44.6565,
+      "eval_samples_per_second": 4.479,
+      "eval_steps_per_second": 4.479,
+      "step": 930
+    },
+    {
+      "epoch": 1.9833816934845687,
+      "grad_norm": 0.08022117614746094,
+      "learning_rate": 5.4930928746410596e-08,
+      "loss": 0.1215,
+      "step": 940
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 948,
+  "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": 1.42087045072171e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-948/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:205b533064fa1dc8ee63d524ef9e21004b40a49ecb894334eb028f111208dbcf
+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:fc44a435f63a7e25e7ff88ece8209cf70201d69bf0137caecf72f6255457f379
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af3551cc21c28586d646e0dc4dfbd7779855c615ff847f4416e5fb65b73f7f1d
+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
+}