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

.gitattributes

@@ -33,3 +33,5 @@ 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-1493/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+datasets:
+- u-10bei/sft_alfworld_trajectory_dataset_v5
+language:
+- en
+license: apache-2.0
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- lora
+- agent
+- tool-use
+- alfworld
+- dbbench
+---
+
+# ＜【課題】ここは自分で記入して下さい＞
+
+This repository provides a **LoRA adapter** fine-tuned from
+**Qwen/Qwen2.5-7B-Instruct** 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/Qwen2.5-7B-Instruct
+- Method: LoRA (full precision base)
+- Max sequence length: 2048
+- Epochs: 1
+- Learning rate: 2e-06
+- LoRA: r=64, alpha=128
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+base = "Qwen/Qwen2.5-7B-Instruct"
+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
+
+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": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "o_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 sha256:93f55e64997cf8b8ab7e1179692af5a653ed1cbdcfef809cc4e318d058be0dbe
+size 645975704

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.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-1493/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+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-1493/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1493/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93f55e64997cf8b8ab7e1179692af5a653ed1cbdcfef809cc4e318d058be0dbe
+size 645975704

checkpoint-1493/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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-1493/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.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-1493/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:333502a1f62ec40f420b43bdc6a5d0f696d4978d55df2b8c8df2cb380370c9ee
+size 1292182139

checkpoint-1493/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1ae74d04cd880a1c2921db0c6aabc530aaab9f30cca8e03577294c3a55afc4
+size 14645

checkpoint-1493/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdc5aae9bfd6e47fbfcdb362ea9df2baf48f10d26f2aa20e440a73d315588168
+size 1465

checkpoint-1493/special_tokens_map.json

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

checkpoint-1493/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-1493/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1493/trainer_state.json

@@ -0,0 +1,1309 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 1493,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0066990453860324905,
+      "grad_norm": 4.1086554527282715,
+      "learning_rate": 1.2e-07,
+      "loss": 1.2942,
+      "step": 10
+    },
+    {
+      "epoch": 0.013398090772064981,
+      "grad_norm": 5.194592475891113,
+      "learning_rate": 2.533333333333333e-07,
+      "loss": 1.2763,
+      "step": 20
+    },
+    {
+      "epoch": 0.02009713615809747,
+      "grad_norm": 4.679239273071289,
+      "learning_rate": 3.8666666666666664e-07,
+      "loss": 1.2829,
+      "step": 30
+    },
+    {
+      "epoch": 0.026796181544129962,
+      "grad_norm": 3.8410086631774902,
+      "learning_rate": 5.2e-07,
+      "loss": 1.283,
+      "step": 40
+    },
+    {
+      "epoch": 0.03349522693016245,
+      "grad_norm": 4.020298957824707,
+      "learning_rate": 6.533333333333333e-07,
+      "loss": 1.2604,
+      "step": 50
+    },
+    {
+      "epoch": 0.03349522693016245,
+      "eval_loss": 1.2969393730163574,
+      "eval_runtime": 209.3255,
+      "eval_samples_per_second": 3.0,
+      "eval_steps_per_second": 1.5,
+      "step": 50
+    },
+    {
+      "epoch": 0.04019427231619494,
+      "grad_norm": 5.327147960662842,
+      "learning_rate": 7.866666666666666e-07,
+      "loss": 1.271,
+      "step": 60
+    },
+    {
+      "epoch": 0.04689331770222743,
+      "grad_norm": 4.076837539672852,
+      "learning_rate": 9.2e-07,
+      "loss": 1.1554,
+      "step": 70
+    },
+    {
+      "epoch": 0.053592363088259924,
+      "grad_norm": 3.4663000106811523,
+      "learning_rate": 1.0533333333333331e-06,
+      "loss": 1.0665,
+      "step": 80
+    },
+    {
+      "epoch": 0.060291408474292416,
+      "grad_norm": 2.5894055366516113,
+      "learning_rate": 1.1866666666666668e-06,
+      "loss": 0.929,
+      "step": 90
+    },
+    {
+      "epoch": 0.0669904538603249,
+      "grad_norm": 1.9452061653137207,
+      "learning_rate": 1.32e-06,
+      "loss": 0.8991,
+      "step": 100
+    },
+    {
+      "epoch": 0.0669904538603249,
+      "eval_loss": 0.8443965315818787,
+      "eval_runtime": 208.8493,
+      "eval_samples_per_second": 3.007,
+      "eval_steps_per_second": 1.503,
+      "step": 100
+    },
+    {
+      "epoch": 0.0736894992463574,
+      "grad_norm": 1.504184603691101,
+      "learning_rate": 1.4533333333333333e-06,
+      "loss": 0.7564,
+      "step": 110
+    },
+    {
+      "epoch": 0.08038854463238988,
+      "grad_norm": 1.2230907678604126,
+      "learning_rate": 1.5866666666666666e-06,
+      "loss": 0.7699,
+      "step": 120
+    },
+    {
+      "epoch": 0.08708759001842238,
+      "grad_norm": 0.9594787955284119,
+      "learning_rate": 1.7199999999999998e-06,
+      "loss": 0.6664,
+      "step": 130
+    },
+    {
+      "epoch": 0.09378663540445487,
+      "grad_norm": 0.7925115823745728,
+      "learning_rate": 1.853333333333333e-06,
+      "loss": 0.6537,
+      "step": 140
+    },
+    {
+      "epoch": 0.10048568079048735,
+      "grad_norm": 0.8098723888397217,
+      "learning_rate": 1.9866666666666666e-06,
+      "loss": 0.6235,
+      "step": 150
+    },
+    {
+      "epoch": 0.10048568079048735,
+      "eval_loss": 0.6279202103614807,
+      "eval_runtime": 205.2416,
+      "eval_samples_per_second": 3.06,
+      "eval_steps_per_second": 1.53,
+      "step": 150
+    },
+    {
+      "epoch": 0.10718472617651985,
+      "grad_norm": 0.6131410002708435,
+      "learning_rate": 1.999778391353092e-06,
+      "loss": 0.5812,
+      "step": 160
+    },
+    {
+      "epoch": 0.11388377156255233,
+      "grad_norm": 0.8551118969917297,
+      "learning_rate": 1.9990124628709946e-06,
+      "loss": 0.5784,
+      "step": 170
+    },
+    {
+      "epoch": 0.12058281694858483,
+      "grad_norm": 0.8900917172431946,
+      "learning_rate": 1.997699897643206e-06,
+      "loss": 0.5592,
+      "step": 180
+    },
+    {
+      "epoch": 0.12728186233461733,
+      "grad_norm": 0.7699607610702515,
+      "learning_rate": 1.9958414138753656e-06,
+      "loss": 0.5486,
+      "step": 190
+    },
+    {
+      "epoch": 0.1339809077206498,
+      "grad_norm": 0.7753857970237732,
+      "learning_rate": 1.9934380284872376e-06,
+      "loss": 0.5142,
+      "step": 200
+    },
+    {
+      "epoch": 0.1339809077206498,
+      "eval_loss": 0.5324934124946594,
+      "eval_runtime": 202.3339,
+      "eval_samples_per_second": 3.104,
+      "eval_steps_per_second": 1.552,
+      "step": 200
+    },
+    {
+      "epoch": 0.1406799531066823,
+      "grad_norm": 0.9436492323875427,
+      "learning_rate": 1.9904910565562783e-06,
+      "loss": 0.5267,
+      "step": 210
+    },
+    {
+      "epoch": 0.1473789984927148,
+      "grad_norm": 0.9100019931793213,
+      "learning_rate": 1.987002110598052e-06,
+      "loss": 0.4898,
+      "step": 220
+    },
+    {
+      "epoch": 0.15407804387874727,
+      "grad_norm": 0.909028947353363,
+      "learning_rate": 1.982973099683902e-06,
+      "loss": 0.4972,
+      "step": 230
+    },
+    {
+      "epoch": 0.16077708926477977,
+      "grad_norm": 0.8425203561782837,
+      "learning_rate": 1.9784062283963493e-06,
+      "loss": 0.4771,
+      "step": 240
+    },
+    {
+      "epoch": 0.16747613465081226,
+      "grad_norm": 0.9417065382003784,
+      "learning_rate": 1.973303995622798e-06,
+      "loss": 0.4686,
+      "step": 250
+    },
+    {
+      "epoch": 0.16747613465081226,
+      "eval_loss": 0.46108540892601013,
+      "eval_runtime": 202.4625,
+      "eval_samples_per_second": 3.102,
+      "eval_steps_per_second": 1.551,
+      "step": 250
+    },
+    {
+      "epoch": 0.17417518003684476,
+      "grad_norm": 1.0608958005905151,
+      "learning_rate": 1.967669193188197e-06,
+      "loss": 0.4465,
+      "step": 260
+    },
+    {
+      "epoch": 0.18087422542287723,
+      "grad_norm": 0.8219178318977356,
+      "learning_rate": 1.9615049043274204e-06,
+      "loss": 0.4379,
+      "step": 270
+    },
+    {
+      "epoch": 0.18757327080890973,
+      "grad_norm": 1.178179144859314,
+      "learning_rate": 1.954814501998192e-06,
+      "loss": 0.4275,
+      "step": 280
+    },
+    {
+      "epoch": 0.19427231619494223,
+      "grad_norm": 1.1529687643051147,
+      "learning_rate": 1.9476016470354796e-06,
+      "loss": 0.3927,
+      "step": 290
+    },
+    {
+      "epoch": 0.2009713615809747,
+      "grad_norm": 1.0554969310760498,
+      "learning_rate": 1.9398702861483674e-06,
+      "loss": 0.4022,
+      "step": 300
+    },
+    {
+      "epoch": 0.2009713615809747,
+      "eval_loss": 0.4019053876399994,
+      "eval_runtime": 206.4042,
+      "eval_samples_per_second": 3.043,
+      "eval_steps_per_second": 1.521,
+      "step": 300
+    },
+    {
+      "epoch": 0.2076704069670072,
+      "grad_norm": 1.1419163942337036,
+      "learning_rate": 1.9316246497605126e-06,
+      "loss": 0.3692,
+      "step": 310
+    },
+    {
+      "epoch": 0.2143694523530397,
+      "grad_norm": 1.0754777193069458,
+      "learning_rate": 1.922869249695348e-06,
+      "loss": 0.3751,
+      "step": 320
+    },
+    {
+      "epoch": 0.2210684977390722,
+      "grad_norm": 0.9499768614768982,
+      "learning_rate": 1.9136088767073214e-06,
+      "loss": 0.3613,
+      "step": 330
+    },
+    {
+      "epoch": 0.22776754312510467,
+      "grad_norm": 1.374733805656433,
+      "learning_rate": 1.9038485978605e-06,
+      "loss": 0.3438,
+      "step": 340
+    },
+    {
+      "epoch": 0.23446658851113716,
+      "grad_norm": 1.114905595779419,
+      "learning_rate": 1.8935937537559922e-06,
+      "loss": 0.3611,
+      "step": 350
+    },
+    {
+      "epoch": 0.23446658851113716,
+      "eval_loss": 0.3528285026550293,
+      "eval_runtime": 202.6686,
+      "eval_samples_per_second": 3.099,
+      "eval_steps_per_second": 1.549,
+      "step": 350
+    },
+    {
+      "epoch": 0.24116563389716966,
+      "grad_norm": 1.2642089128494263,
+      "learning_rate": 1.8828499556096906e-06,
+      "loss": 0.3464,
+      "step": 360
+    },
+    {
+      "epoch": 0.24786467928320213,
+      "grad_norm": 1.3557504415512085,
+      "learning_rate": 1.8716230821819447e-06,
+      "loss": 0.3404,
+      "step": 370
+    },
+    {
+      "epoch": 0.25456372466923466,
+      "grad_norm": 1.1253280639648438,
+      "learning_rate": 1.8599192765608362e-06,
+      "loss": 0.3278,
+      "step": 380
+    },
+    {
+      "epoch": 0.2612627700552671,
+      "grad_norm": 1.256253957748413,
+      "learning_rate": 1.8477449428008242e-06,
+      "loss": 0.32,
+      "step": 390
+    },
+    {
+      "epoch": 0.2679618154412996,
+      "grad_norm": 1.3315330743789673,
+      "learning_rate": 1.835106742418591e-06,
+      "loss": 0.3326,
+      "step": 400
+    },
+    {
+      "epoch": 0.2679618154412996,
+      "eval_loss": 0.3122718334197998,
+      "eval_runtime": 209.3144,
+      "eval_samples_per_second": 3.0,
+      "eval_steps_per_second": 1.5,
+      "step": 400
+    },
+    {
+      "epoch": 0.2746608608273321,
+      "grad_norm": 1.7147033214569092,
+      "learning_rate": 1.822011590748014e-06,
+      "loss": 0.3029,
+      "step": 410
+    },
+    {
+      "epoch": 0.2813599062133646,
+      "grad_norm": 1.5132501125335693,
+      "learning_rate": 1.8084666531562528e-06,
+      "loss": 0.3196,
+      "step": 420
+    },
+    {
+      "epoch": 0.2880589515993971,
+      "grad_norm": 1.2777931690216064,
+      "learning_rate": 1.7944793411230248e-06,
+      "loss": 0.2857,
+      "step": 430
+    },
+    {
+      "epoch": 0.2947579969854296,
+      "grad_norm": 1.2335401773452759,
+      "learning_rate": 1.780057308185212e-06,
+      "loss": 0.2925,
+      "step": 440
+    },
+    {
+      "epoch": 0.3014570423714621,
+      "grad_norm": 1.2779353857040405,
+      "learning_rate": 1.7652084457490233e-06,
+      "loss": 0.2674,
+      "step": 450
+    },
+    {
+      "epoch": 0.3014570423714621,
+      "eval_loss": 0.2787730097770691,
+      "eval_runtime": 209.6027,
+      "eval_samples_per_second": 2.996,
+      "eval_steps_per_second": 1.498,
+      "step": 450
+    },
+    {
+      "epoch": 0.30815608775749453,
+      "grad_norm": 1.4865727424621582,
+      "learning_rate": 1.7499408787719945e-06,
+      "loss": 0.2831,
+      "step": 460
+    },
+    {
+      "epoch": 0.31485513314352703,
+      "grad_norm": 1.3024545907974243,
+      "learning_rate": 1.7342629613172001e-06,
+      "loss": 0.2685,
+      "step": 470
+    },
+    {
+      "epoch": 0.32155417852955953,
+      "grad_norm": 1.9648115634918213,
+      "learning_rate": 1.718183271982101e-06,
+      "loss": 0.2689,
+      "step": 480
+    },
+    {
+      "epoch": 0.32825322391559203,
+      "grad_norm": 1.6339739561080933,
+      "learning_rate": 1.7017106092045305e-06,
+      "loss": 0.2572,
+      "step": 490
+    },
+    {
+      "epoch": 0.33495226930162453,
+      "grad_norm": 1.4009311199188232,
+      "learning_rate": 1.6848539864483925e-06,
+      "loss": 0.233,
+      "step": 500
+    },
+    {
+      "epoch": 0.33495226930162453,
+      "eval_loss": 0.2506704032421112,
+      "eval_runtime": 209.375,
+      "eval_samples_per_second": 2.999,
+      "eval_steps_per_second": 1.5,
+      "step": 500
+    },
+    {
+      "epoch": 0.341651314687657,
+      "grad_norm": 1.3794124126434326,
+      "learning_rate": 1.6676226272717e-06,
+      "loss": 0.228,
+      "step": 510
+    },
+    {
+      "epoch": 0.3483503600736895,
+      "grad_norm": 1.3594862222671509,
+      "learning_rate": 1.6500259602796545e-06,
+      "loss": 0.2538,
+      "step": 520
+    },
+    {
+      "epoch": 0.35504940545972197,
+      "grad_norm": 1.6545219421386719,
+      "learning_rate": 1.6320736139655304e-06,
+      "loss": 0.2197,
+      "step": 530
+    },
+    {
+      "epoch": 0.36174845084575447,
+      "grad_norm": 1.4704442024230957,
+      "learning_rate": 1.6137754114421834e-06,
+      "loss": 0.2366,
+      "step": 540
+    },
+    {
+      "epoch": 0.36844749623178696,
+      "grad_norm": 1.5769726037979126,
+      "learning_rate": 1.5951413650670666e-06,
+      "loss": 0.2368,
+      "step": 550
+    },
+    {
+      "epoch": 0.36844749623178696,
+      "eval_loss": 0.228424072265625,
+      "eval_runtime": 210.22,
+      "eval_samples_per_second": 2.987,
+      "eval_steps_per_second": 1.494,
+      "step": 550
+    },
+    {
+      "epoch": 0.37514654161781946,
+      "grad_norm": 1.3758552074432373,
+      "learning_rate": 1.5761816709637014e-06,
+      "loss": 0.2158,
+      "step": 560
+    },
+    {
+      "epoch": 0.38184558700385196,
+      "grad_norm": 1.3098106384277344,
+      "learning_rate": 1.5569067034425876e-06,
+      "loss": 0.2311,
+      "step": 570
+    },
+    {
+      "epoch": 0.38854463238988446,
+      "grad_norm": 1.5566669702529907,
+      "learning_rate": 1.5373270093246217e-06,
+      "loss": 0.2202,
+      "step": 580
+    },
+    {
+      "epoch": 0.39524367777591696,
+      "grad_norm": 1.5586082935333252,
+      "learning_rate": 1.5174533021701165e-06,
+      "loss": 0.2099,
+      "step": 590
+    },
+    {
+      "epoch": 0.4019427231619494,
+      "grad_norm": 1.7853736877441406,
+      "learning_rate": 1.497296456416587e-06,
+      "loss": 0.2153,
+      "step": 600
+    },
+    {
+      "epoch": 0.4019427231619494,
+      "eval_loss": 0.2123781442642212,
+      "eval_runtime": 209.9919,
+      "eval_samples_per_second": 2.991,
+      "eval_steps_per_second": 1.495,
+      "step": 600
+    },
+    {
+      "epoch": 0.4086417685479819,
+      "grad_norm": 1.4956289529800415,
+      "learning_rate": 1.476867501428506e-06,
+      "loss": 0.2003,
+      "step": 610
+    },
+    {
+      "epoch": 0.4153408139340144,
+      "grad_norm": 2.1181328296661377,
+      "learning_rate": 1.4561776154622891e-06,
+      "loss": 0.2062,
+      "step": 620
+    },
+    {
+      "epoch": 0.4220398593200469,
+      "grad_norm": 1.7311185598373413,
+      "learning_rate": 1.435238119549809e-06,
+      "loss": 0.2059,
+      "step": 630
+    },
+    {
+      "epoch": 0.4287389047060794,
+      "grad_norm": 1.7530423402786255,
+      "learning_rate": 1.4140604713037856e-06,
+      "loss": 0.2255,
+      "step": 640
+    },
+    {
+      "epoch": 0.4354379500921119,
+      "grad_norm": 1.5334357023239136,
+      "learning_rate": 1.392656258648443e-06,
+      "loss": 0.1917,
+      "step": 650
+    },
+    {
+      "epoch": 0.4354379500921119,
+      "eval_loss": 0.2000122219324112,
+      "eval_runtime": 210.4187,
+      "eval_samples_per_second": 2.985,
+      "eval_steps_per_second": 1.492,
+      "step": 650
+    },
+    {
+      "epoch": 0.4421369954781444,
+      "grad_norm": 1.7240939140319824,
+      "learning_rate": 1.3710371934788629e-06,
+      "loss": 0.2241,
+      "step": 660
+    },
+    {
+      "epoch": 0.44883604086417683,
+      "grad_norm": 1.3888474702835083,
+      "learning_rate": 1.3492151052525022e-06,
+      "loss": 0.2014,
+      "step": 670
+    },
+    {
+      "epoch": 0.45553508625020933,
+      "grad_norm": 1.712149977684021,
+      "learning_rate": 1.3272019345163873e-06,
+      "loss": 0.2102,
+      "step": 680
+    },
+    {
+      "epoch": 0.46223413163624183,
+      "grad_norm": 1.8144246339797974,
+      "learning_rate": 1.3050097263735173e-06,
+      "loss": 0.1958,
+      "step": 690
+    },
+    {
+      "epoch": 0.46893317702227433,
+      "grad_norm": 1.395092248916626,
+      "learning_rate": 1.2826506238920629e-06,
+      "loss": 0.1914,
+      "step": 700
+    },
+    {
+      "epoch": 0.46893317702227433,
+      "eval_loss": 0.18932001292705536,
+      "eval_runtime": 210.0115,
+      "eval_samples_per_second": 2.99,
+      "eval_steps_per_second": 1.495,
+      "step": 700
+    },
+    {
+      "epoch": 0.4756322224083068,
+      "grad_norm": 1.2977328300476074,
+      "learning_rate": 1.2601368614609538e-06,
+      "loss": 0.1791,
+      "step": 710
+    },
+    {
+      "epoch": 0.4823312677943393,
+      "grad_norm": 1.5144984722137451,
+      "learning_rate": 1.2374807580955037e-06,
+      "loss": 0.1954,
+      "step": 720
+    },
+    {
+      "epoch": 0.4890303131803718,
+      "grad_norm": 1.26352858543396,
+      "learning_rate": 1.2146947106967264e-06,
+      "loss": 0.1887,
+      "step": 730
+    },
+    {
+      "epoch": 0.49572935856640427,
+      "grad_norm": 1.966431736946106,
+      "learning_rate": 1.1917911872680354e-06,
+      "loss": 0.1828,
+      "step": 740
+    },
+    {
+      "epoch": 0.5024284039524368,
+      "grad_norm": 1.801213264465332,
+      "learning_rate": 1.168782720093038e-06,
+      "loss": 0.1822,
+      "step": 750
+    },
+    {
+      "epoch": 0.5024284039524368,
+      "eval_loss": 0.18144512176513672,
+      "eval_runtime": 209.9966,
+      "eval_samples_per_second": 2.991,
+      "eval_steps_per_second": 1.495,
+      "step": 750
+    },
+    {
+      "epoch": 0.5091274493384693,
+      "grad_norm": 1.3575425148010254,
+      "learning_rate": 1.1456818988781564e-06,
+      "loss": 0.1781,
+      "step": 760
+    },
+    {
+      "epoch": 0.5158264947245017,
+      "grad_norm": 1.884732961654663,
+      "learning_rate": 1.1225013638638296e-06,
+      "loss": 0.1856,
+      "step": 770
+    },
+    {
+      "epoch": 0.5225255401105342,
+      "grad_norm": 1.4941363334655762,
+      "learning_rate": 1.0992537989080618e-06,
+      "loss": 0.1588,
+      "step": 780
+    },
+    {
+      "epoch": 0.5292245854965667,
+      "grad_norm": 1.5482722520828247,
+      "learning_rate": 1.075951924546106e-06,
+      "loss": 0.1758,
+      "step": 790
+    },
+    {
+      "epoch": 0.5359236308825992,
+      "grad_norm": 1.2940350770950317,
+      "learning_rate": 1.0526084910300797e-06,
+      "loss": 0.1856,
+      "step": 800
+    },
+    {
+      "epoch": 0.5359236308825992,
+      "eval_loss": 0.1753692328929901,
+      "eval_runtime": 210.1082,
+      "eval_samples_per_second": 2.989,
+      "eval_steps_per_second": 1.494,
+      "step": 800
+    },
+    {
+      "epoch": 0.5426226762686317,
+      "grad_norm": 1.7873057126998901,
+      "learning_rate": 1.0292362713523174e-06,
+      "loss": 0.1718,
+      "step": 810
+    },
+    {
+      "epoch": 0.5493217216546642,
+      "grad_norm": 1.7354981899261475,
+      "learning_rate": 1.0058480542562825e-06,
+      "loss": 0.1935,
+      "step": 820
+    },
+    {
+      "epoch": 0.5560207670406967,
+      "grad_norm": 1.8902477025985718,
+      "learning_rate": 9.824566372388593e-07,
+      "loss": 0.1648,
+      "step": 830
+    },
+    {
+      "epoch": 0.5627198124267292,
+      "grad_norm": 1.3803671598434448,
+      "learning_rate": 9.590748195478557e-07,
+      "loss": 0.1722,
+      "step": 840
+    },
+    {
+      "epoch": 0.5694188578127617,
+      "grad_norm": 1.9309909343719482,
+      "learning_rate": 9.357153951785475e-07,
+      "loss": 0.1815,
+      "step": 850
+    },
+    {
+      "epoch": 0.5694188578127617,
+      "eval_loss": 0.16952912509441376,
+      "eval_runtime": 208.9831,
+      "eval_samples_per_second": 3.005,
+      "eval_steps_per_second": 1.503,
+      "step": 850
+    },
+    {
+      "epoch": 0.5761179031987942,
+      "grad_norm": 2.0065739154815674,
+      "learning_rate": 9.123911458730987e-07,
+      "loss": 0.1816,
+      "step": 860
+    },
+    {
+      "epoch": 0.5828169485848267,
+      "grad_norm": 1.3279434442520142,
+      "learning_rate": 8.891148341266828e-07,
+      "loss": 0.1597,
+      "step": 870
+    },
+    {
+      "epoch": 0.5895159939708592,
+      "grad_norm": 1.592751145362854,
+      "learning_rate": 8.658991962041394e-07,
+      "loss": 0.1662,
+      "step": 880
+    },
+    {
+      "epoch": 0.5962150393568917,
+      "grad_norm": 1.47665274143219,
+      "learning_rate": 8.4275693517098e-07,
+      "loss": 0.1791,
+      "step": 890
+    },
+    {
+      "epoch": 0.6029140847429242,
+      "grad_norm": 1.8228442668914795,
+      "learning_rate": 8.197007139425631e-07,
+      "loss": 0.1499,
+      "step": 900
+    },
+    {
+      "epoch": 0.6029140847429242,
+      "eval_loss": 0.16557829082012177,
+      "eval_runtime": 207.0195,
+      "eval_samples_per_second": 3.034,
+      "eval_steps_per_second": 1.517,
+      "step": 900
+    },
+    {
+      "epoch": 0.6096131301289566,
+      "grad_norm": 1.7560912370681763,
+      "learning_rate": 7.967431483552356e-07,
+      "loss": 0.19,
+      "step": 910
+    },
+    {
+      "epoch": 0.6163121755149891,
+      "grad_norm": 1.7260010242462158,
+      "learning_rate": 7.73896800263237e-07,
+      "loss": 0.168,
+      "step": 920
+    },
+    {
+      "epoch": 0.6230112209010216,
+      "grad_norm": 1.6843092441558838,
+      "learning_rate": 7.511741706651385e-07,
+      "loss": 0.1897,
+      "step": 930
+    },
+    {
+      "epoch": 0.6297102662870541,
+      "grad_norm": 1.423301100730896,
+      "learning_rate": 7.285876928635863e-07,
+      "loss": 0.162,
+      "step": 940
+    },
+    {
+      "epoch": 0.6364093116730866,
+      "grad_norm": 1.5540543794631958,
+      "learning_rate": 7.061497256620792e-07,
+      "loss": 0.1733,
+      "step": 950
+    },
+    {
+      "epoch": 0.6364093116730866,
+      "eval_loss": 0.16183187067508698,
+      "eval_runtime": 206.8579,
+      "eval_samples_per_second": 3.036,
+      "eval_steps_per_second": 1.518,
+      "step": 950
+    },
+    {
+      "epoch": 0.6431083570591191,
+      "grad_norm": 1.6898900270462036,
+      "learning_rate": 6.838725466025165e-07,
+      "loss": 0.1765,
+      "step": 960
+    },
+    {
+      "epoch": 0.6498074024451516,
+      "grad_norm": 1.6521717309951782,
+      "learning_rate": 6.617683452472083e-07,
+      "loss": 0.1642,
+      "step": 970
+    },
+    {
+      "epoch": 0.6565064478311841,
+      "grad_norm": 1.9242119789123535,
+      "learning_rate": 6.398492165090246e-07,
+      "loss": 0.1761,
+      "step": 980
+    },
+    {
+      "epoch": 0.6632054932172166,
+      "grad_norm": 1.9432291984558105,
+      "learning_rate": 6.181271540333379e-07,
+      "loss": 0.1696,
+      "step": 990
+    },
+    {
+      "epoch": 0.6699045386032491,
+      "grad_norm": 1.2695698738098145,
+      "learning_rate": 5.966140436353728e-07,
+      "loss": 0.1779,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6699045386032491,
+      "eval_loss": 0.15969812870025635,
+      "eval_runtime": 206.9864,
+      "eval_samples_per_second": 3.034,
+      "eval_steps_per_second": 1.517,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6766035839892816,
+      "grad_norm": 1.7133862972259521,
+      "learning_rate": 5.753216567965625e-07,
+      "loss": 0.1636,
+      "step": 1010
+    },
+    {
+      "epoch": 0.683302629375314,
+      "grad_norm": 1.5325969457626343,
+      "learning_rate": 5.542616442234618e-07,
+      "loss": 0.1655,
+      "step": 1020
+    },
+    {
+      "epoch": 0.6900016747613466,
+      "grad_norm": 1.3512976169586182,
+      "learning_rate": 5.334455294727477e-07,
+      "loss": 0.1612,
+      "step": 1030
+    },
+    {
+      "epoch": 0.696700720147379,
+      "grad_norm": 1.694158911705017,
+      "learning_rate": 5.128847026457931e-07,
+      "loss": 0.1631,
+      "step": 1040
+    },
+    {
+      "epoch": 0.7033997655334114,
+      "grad_norm": 1.8738293647766113,
+      "learning_rate": 4.925904141562662e-07,
+      "loss": 0.1578,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7033997655334114,
+      "eval_loss": 0.15765480697155,
+      "eval_runtime": 206.2605,
+      "eval_samples_per_second": 3.045,
+      "eval_steps_per_second": 1.522,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7100988109194439,
+      "grad_norm": 1.7786355018615723,
+      "learning_rate": 4.72573768574156e-07,
+      "loss": 0.1526,
+      "step": 1060
+    },
+    {
+      "epoch": 0.7167978563054764,
+      "grad_norm": 1.5581673383712769,
+      "learning_rate": 4.528457185496134e-07,
+      "loss": 0.158,
+      "step": 1070
+    },
+    {
+      "epoch": 0.7234969016915089,
+      "grad_norm": 1.292310118675232,
+      "learning_rate": 4.334170588199061e-07,
+      "loss": 0.1488,
+      "step": 1080
+    },
+    {
+      "epoch": 0.7301959470775414,
+      "grad_norm": 1.2164219617843628,
+      "learning_rate": 4.1429842030278774e-07,
+      "loss": 0.1682,
+      "step": 1090
+    },
+    {
+      "epoch": 0.7368949924635739,
+      "grad_norm": 1.3037480115890503,
+      "learning_rate": 3.955002642795031e-07,
+      "loss": 0.1667,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7368949924635739,
+      "eval_loss": 0.15579576790332794,
+      "eval_runtime": 210.0947,
+      "eval_samples_per_second": 2.989,
+      "eval_steps_per_second": 1.495,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7435940378496064,
+      "grad_norm": 1.4214398860931396,
+      "learning_rate": 3.770328766706139e-07,
+      "loss": 0.1642,
+      "step": 1110
+    },
+    {
+      "epoch": 0.7502930832356389,
+      "grad_norm": 1.7904776334762573,
+      "learning_rate": 3.5890636240778015e-07,
+      "loss": 0.1632,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7569921286216714,
+      "grad_norm": 1.4325569868087769,
+      "learning_rate": 3.411306399045697e-07,
+      "loss": 0.1501,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7636911740077039,
+      "grad_norm": 1.7353627681732178,
+      "learning_rate": 3.2371543562933357e-07,
+      "loss": 0.1589,
+      "step": 1140
+    },
+    {
+      "epoch": 0.7703902193937364,
+      "grad_norm": 1.7524937391281128,
+      "learning_rate": 3.066702787831017e-07,
+      "loss": 0.1571,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7703902193937364,
+      "eval_loss": 0.15445640683174133,
+      "eval_runtime": 210.1488,
+      "eval_samples_per_second": 2.988,
+      "eval_steps_per_second": 1.494,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7770892647797689,
+      "grad_norm": 1.4093834161758423,
+      "learning_rate": 2.900044960854244e-07,
+      "loss": 0.1581,
+      "step": 1160
+    },
+    {
+      "epoch": 0.7837883101658014,
+      "grad_norm": 1.8619221448898315,
+      "learning_rate": 2.737272066710036e-07,
+      "loss": 0.1677,
+      "step": 1170
+    },
+    {
+      "epoch": 0.7904873555518339,
+      "grad_norm": 1.5498839616775513,
+      "learning_rate": 2.578473170999127e-07,
+      "loss": 0.1523,
+      "step": 1180
+    },
+    {
+      "epoch": 0.7971864009378663,
+      "grad_norm": 1.6244864463806152,
+      "learning_rate": 2.423735164841294e-07,
+      "loss": 0.1786,
+      "step": 1190
+    },
+    {
+      "epoch": 0.8038854463238988,
+      "grad_norm": 1.524354100227356,
+      "learning_rate": 2.2731427173305307e-07,
+      "loss": 0.1589,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8038854463238988,
+      "eval_loss": 0.1536036878824234,
+      "eval_runtime": 210.0623,
+      "eval_samples_per_second": 2.99,
+      "eval_steps_per_second": 1.495,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8105844917099313,
+      "grad_norm": 1.598970890045166,
+      "learning_rate": 2.1267782292060576e-07,
+      "loss": 0.1602,
+      "step": 1210
+    },
+    {
+      "epoch": 0.8172835370959638,
+      "grad_norm": 2.381743907928467,
+      "learning_rate": 1.984721787764534e-07,
+      "loss": 0.1645,
+      "step": 1220
+    },
+    {
+      "epoch": 0.8239825824819963,
+      "grad_norm": 1.6264909505844116,
+      "learning_rate": 1.847051123038098e-07,
+      "loss": 0.1554,
+      "step": 1230
+    },
+    {
+      "epoch": 0.8306816278680288,
+      "grad_norm": 1.6028659343719482,
+      "learning_rate": 1.7138415652622994e-07,
+      "loss": 0.1627,
+      "step": 1240
+    },
+    {
+      "epoch": 0.8373806732540613,
+      "grad_norm": 1.627546787261963,
+      "learning_rate": 1.5851660036571113e-07,
+      "loss": 0.1671,
+      "step": 1250
+    },
+    {
+      "epoch": 0.8373806732540613,
+      "eval_loss": 0.1531084179878235,
+      "eval_runtime": 210.0584,
+      "eval_samples_per_second": 2.99,
+      "eval_steps_per_second": 1.495,
+      "step": 1250
+    },
+    {
+      "epoch": 0.8440797186400938,
+      "grad_norm": 1.817571759223938,
+      "learning_rate": 1.4610948465436068e-07,
+      "loss": 0.1623,
+      "step": 1260
+    },
+    {
+      "epoch": 0.8507787640261263,
+      "grad_norm": 1.5762296915054321,
+      "learning_rate": 1.3416959828181518e-07,
+      "loss": 0.1628,
+      "step": 1270
+    },
+    {
+      "epoch": 0.8574778094121588,
+      "grad_norm": 1.2046678066253662,
+      "learning_rate": 1.2270347448051455e-07,
+      "loss": 0.1573,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8641768547981913,
+      "grad_norm": 2.2138359546661377,
+      "learning_rate": 1.1171738725086832e-07,
+      "loss": 0.1672,
+      "step": 1290
+    },
+    {
+      "epoch": 0.8708759001842238,
+      "grad_norm": 1.2620127201080322,
+      "learning_rate": 1.0121734792826353e-07,
+      "loss": 0.1457,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8708759001842238,
+      "eval_loss": 0.15241335332393646,
+      "eval_runtime": 210.1227,
+      "eval_samples_per_second": 2.989,
+      "eval_steps_per_second": 1.494,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8775749455702563,
+      "grad_norm": 1.4510090351104736,
+      "learning_rate": 9.120910189380293e-08,
+      "loss": 0.1704,
+      "step": 1310
+    },
+    {
+      "epoch": 0.8842739909562888,
+      "grad_norm": 1.9066110849380493,
+      "learning_rate": 8.169812543056154e-08,
+      "loss": 0.1668,
+      "step": 1320
+    },
+    {
+      "epoch": 0.8909730363423212,
+      "grad_norm": 1.3622069358825684,
+      "learning_rate": 7.268962272709101e-08,
+      "loss": 0.1468,
+      "step": 1330
+    },
+    {
+      "epoch": 0.8976720817283537,
+      "grad_norm": 1.8316006660461426,
+      "learning_rate": 6.418852302980649e-08,
+      "loss": 0.1603,
+      "step": 1340
+    },
+    {
+      "epoch": 0.9043711271143862,
+      "grad_norm": 1.3818883895874023,
+      "learning_rate": 5.619947794581614e-08,
+      "loss": 0.1557,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9043711271143862,
+      "eval_loss": 0.15219451487064362,
+      "eval_runtime": 210.3926,
+      "eval_samples_per_second": 2.985,
+      "eval_steps_per_second": 1.492,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9110701725004187,
+      "grad_norm": 1.553291916847229,
+      "learning_rate": 4.8726858897667814e-08,
+      "loss": 0.1449,
+      "step": 1360
+    },
+    {
+      "epoch": 0.9177692178864512,
+      "grad_norm": 1.3580824136734009,
+      "learning_rate": 4.1774754731407235e-08,
+      "loss": 0.1536,
+      "step": 1370
+    },
+    {
+      "epoch": 0.9244682632724837,
+      "grad_norm": 1.717352032661438,
+      "learning_rate": 3.534696947925453e-08,
+      "loss": 0.1577,
+      "step": 1380
+    },
+    {
+      "epoch": 0.9311673086585162,
+      "grad_norm": 1.5122058391571045,
+      "learning_rate": 2.9447020278125067e-08,
+      "loss": 0.1471,
+      "step": 1390
+    },
+    {
+      "epoch": 0.9378663540445487,
+      "grad_norm": 1.3521865606307983,
+      "learning_rate": 2.407813544513315e-08,
+      "loss": 0.1657,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9378663540445487,
+      "eval_loss": 0.15204142034053802,
+      "eval_runtime": 210.0733,
+      "eval_samples_per_second": 2.989,
+      "eval_steps_per_second": 1.495,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9445653994305812,
+      "grad_norm": 1.4450511932373047,
+      "learning_rate": 1.924325271112992e-08,
+      "loss": 0.1526,
+      "step": 1410
+    },
+    {
+      "epoch": 0.9512644448166137,
+      "grad_norm": 1.2123303413391113,
+      "learning_rate": 1.494501761324529e-08,
+      "loss": 0.1525,
+      "step": 1420
+    },
+    {
+      "epoch": 0.9579634902026462,
+      "grad_norm": 1.5129427909851074,
+      "learning_rate": 1.11857820473098e-08,
+      "loss": 0.1572,
+      "step": 1430
+    },
+    {
+      "epoch": 0.9646625355886786,
+      "grad_norm": 1.4353489875793457,
+      "learning_rate": 7.967602980951226e-09,
+      "loss": 0.1573,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9713615809747111,
+      "grad_norm": 1.2168687582015991,
+      "learning_rate": 5.29224132806938e-09,
+      "loss": 0.1507,
+      "step": 1450
+    },
+    {
+      "epoch": 0.9713615809747111,
+      "eval_loss": 0.15192590653896332,
+      "eval_runtime": 210.4778,
+      "eval_samples_per_second": 2.984,
+      "eval_steps_per_second": 1.492,
+      "step": 1450
+    },
+    {
+      "epoch": 0.9780606263607436,
+      "grad_norm": 1.9652212858200073,
+      "learning_rate": 3.1611609853041676e-09,
+      "loss": 0.1583,
+      "step": 1460
+    },
+    {
+      "epoch": 0.984759671746776,
+      "grad_norm": 1.7049267292022705,
+      "learning_rate": 1.5755280310244534e-09,
+      "loss": 0.1576,
+      "step": 1470
+    },
+    {
+      "epoch": 0.9914587171328085,
+      "grad_norm": 1.3600727319717407,
+      "learning_rate": 5.362100872773334e-10,
+      "loss": 0.1512,
+      "step": 1480
+    },
+    {
+      "epoch": 0.998157762518841,
+      "grad_norm": 1.3379324674606323,
+      "learning_rate": 4.3775845044780045e-11,
+      "loss": 0.1571,
+      "step": 1490
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1493,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.3882191414872576e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1493/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5a224113d6f020e0ac71ad6b4f514558f0c128781c5e955c17ed55195391d17
+size 5777

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}