Upload Qwen3-1.7B SFT Stage 1 - 10 epochs - 20250723_111953

.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-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-520/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+base_model: unsloth/Qwen3-1.7B
+tags:
+- unsloth
+- qwen3
+- mathematical-reasoning
+- sft
+- stage1
+language:
+- en
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# Qwen3-1.7B Mathematical Reasoning (SFT Stage 1)
+
+**Stage 1 SFT model** trained following "A Practical Two-Stage Recipe for Mathematical LLMs" paper.
+
+## Training Details
+
+- **Base Model**: unsloth/Qwen3-1.7B
+- **Training Method**: Supervised Fine-Tuning (Stage 1)
+- **Dataset**: RabotniKuma/Fast-Math-R1-SFT
+- **Epochs**: 10
+- **System Prompt**: "Please reason step by step, and put your final answer within \boxed{}"
+
+## Usage
+
+```python
+from unsloth import FastLanguageModel
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name="Cbgcbg/qwen3-1.7b-math-sft-stage1-20250723_111953",
+    max_seq_length=8192,
+    dtype=None,
+    load_in_4bit=True,
+)
+
+# Example
+messages = [
+    {"role": "system", "content": "Please reason step by step, and put your final answer within \boxed{}."},
+    {"role": "user", "content": "What is 2+2?"}
+]
+
+inputs = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt")
+outputs = model.generate(input_ids=inputs, max_new_tokens=256)
+```
+
+## Paper Citation
+
+Based on the methodology from:
+```
+A Practical Two-Stage Recipe for Mathematical LLMs:
+Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning
+```
+
+This is **Stage 1** - focused on maximizing accuracy. Stage 2 (GRPO) will optimize for token efficiency.

adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-1.7B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d57b6d13935a9fe934a97c0bba82fff3db769d3d8fc827aa9cdfae0096bee7e6
+size 139512976

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 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

checkpoint-500/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-1.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-1.7B
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.16.0

checkpoint-500/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-1.7B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c0d331f2a3e9b0a68adf4f5d7f72e510f2bd127177effd4381ba6a4cc14d38c
+size 139512976

checkpoint-500/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-500/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce3f6c83677a2cb7c3961529250ef25de0b837709ba4f12c753abf7aa0a1761
+size 71281012

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd424fba129a537f8bbac84700dce17d7e574412aa8c4d66a1f4309819fb17d0
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33bcfd2aeee7c5f1481faced58809a7f1b7bb9d3cb96f49d4f9ab24b68ad0f66
+size 1064

checkpoint-500/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-500/tokenizer.json

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

checkpoint-500/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": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,384 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.618357487922705,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1932367149758454,
+      "grad_norm": 9.72665023803711,
+      "learning_rate": 9.992610567545458e-06,
+      "loss": 6.4816,
+      "step": 10
+    },
+    {
+      "epoch": 0.3864734299516908,
+      "grad_norm": 5.790473937988281,
+      "learning_rate": 9.967094890324894e-06,
+      "loss": 5.3994,
+      "step": 20
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 4.916749954223633,
+      "learning_rate": 9.923454822514262e-06,
+      "loss": 4.5179,
+      "step": 30
+    },
+    {
+      "epoch": 0.7729468599033816,
+      "grad_norm": 4.569331645965576,
+      "learning_rate": 9.861849601988384e-06,
+      "loss": 3.7733,
+      "step": 40
+    },
+    {
+      "epoch": 0.966183574879227,
+      "grad_norm": 4.1129841804504395,
+      "learning_rate": 9.782504019516079e-06,
+      "loss": 3.0167,
+      "step": 50
+    },
+    {
+      "epoch": 1.1545893719806763,
+      "grad_norm": 3.721545934677124,
+      "learning_rate": 9.685707598523027e-06,
+      "loss": 2.2359,
+      "step": 60
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 2.538311004638672,
+      "learning_rate": 9.571813538652184e-06,
+      "loss": 1.5212,
+      "step": 70
+    },
+    {
+      "epoch": 1.541062801932367,
+      "grad_norm": 1.876523494720459,
+      "learning_rate": 9.441237426976596e-06,
+      "loss": 1.0284,
+      "step": 80
+    },
+    {
+      "epoch": 1.7342995169082127,
+      "grad_norm": 1.4319356679916382,
+      "learning_rate": 9.294455721567224e-06,
+      "loss": 0.7066,
+      "step": 90
+    },
+    {
+      "epoch": 1.927536231884058,
+      "grad_norm": 1.2226893901824951,
+      "learning_rate": 9.132004012949124e-06,
+      "loss": 0.5043,
+      "step": 100
+    },
+    {
+      "epoch": 2.1159420289855073,
+      "grad_norm": 1.1039533615112305,
+      "learning_rate": 8.954475069789703e-06,
+      "loss": 0.3595,
+      "step": 110
+    },
+    {
+      "epoch": 2.3091787439613527,
+      "grad_norm": 0.8911028504371643,
+      "learning_rate": 8.762516675950134e-06,
+      "loss": 0.2687,
+      "step": 120
+    },
+    {
+      "epoch": 2.502415458937198,
+      "grad_norm": 0.7713564038276672,
+      "learning_rate": 8.556829266792297e-06,
+      "loss": 0.207,
+      "step": 130
+    },
+    {
+      "epoch": 2.6956521739130435,
+      "grad_norm": 0.6270983815193176,
+      "learning_rate": 8.338163373366099e-06,
+      "loss": 0.164,
+      "step": 140
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.5450633764266968,
+      "learning_rate": 8.107316883803071e-06,
+      "loss": 0.1343,
+      "step": 150
+    },
+    {
+      "epoch": 3.077294685990338,
+      "grad_norm": 0.46505942940711975,
+      "learning_rate": 7.865132131909106e-06,
+      "loss": 0.1137,
+      "step": 160
+    },
+    {
+      "epoch": 3.2705314009661834,
+      "grad_norm": 0.4359152913093567,
+      "learning_rate": 7.612492823579744e-06,
+      "loss": 0.0973,
+      "step": 170
+    },
+    {
+      "epoch": 3.463768115942029,
+      "grad_norm": 0.3963119685649872,
+      "learning_rate": 7.350320812253196e-06,
+      "loss": 0.0875,
+      "step": 180
+    },
+    {
+      "epoch": 3.6570048309178746,
+      "grad_norm": 0.361600399017334,
+      "learning_rate": 7.079572735167119e-06,
+      "loss": 0.0769,
+      "step": 190
+    },
+    {
+      "epoch": 3.85024154589372,
+      "grad_norm": 0.3512292206287384,
+      "learning_rate": 6.8012365226930825e-06,
+      "loss": 0.0705,
+      "step": 200
+    },
+    {
+      "epoch": 4.038647342995169,
+      "grad_norm": 0.30910539627075195,
+      "learning_rate": 6.516327793485776e-06,
+      "loss": 0.0622,
+      "step": 210
+    },
+    {
+      "epoch": 4.231884057971015,
+      "grad_norm": 0.2861171364784241,
+      "learning_rate": 6.225886148600688e-06,
+      "loss": 0.0582,
+      "step": 220
+    },
+    {
+      "epoch": 4.42512077294686,
+      "grad_norm": 0.2825333774089813,
+      "learning_rate": 5.930971378102585e-06,
+      "loss": 0.0533,
+      "step": 230
+    },
+    {
+      "epoch": 4.618357487922705,
+      "grad_norm": 0.26530200242996216,
+      "learning_rate": 5.632659594006498e-06,
+      "loss": 0.0505,
+      "step": 240
+    },
+    {
+      "epoch": 4.811594202898551,
+      "grad_norm": 0.24200841784477234,
+      "learning_rate": 5.332039303661683e-06,
+      "loss": 0.0474,
+      "step": 250
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.24424873292446136,
+      "learning_rate": 5.030207437906354e-06,
+      "loss": 0.0434,
+      "step": 260
+    },
+    {
+      "epoch": 5.193236714975845,
+      "grad_norm": 0.22758834064006805,
+      "learning_rate": 4.728265348486e-06,
+      "loss": 0.0419,
+      "step": 270
+    },
+    {
+      "epoch": 5.386473429951691,
+      "grad_norm": 0.21970826387405396,
+      "learning_rate": 4.4273147893403126e-06,
+      "loss": 0.0396,
+      "step": 280
+    },
+    {
+      "epoch": 5.579710144927536,
+      "grad_norm": 0.19575871527194977,
+      "learning_rate": 4.1284538964225364e-06,
+      "loss": 0.037,
+      "step": 290
+    },
+    {
+      "epoch": 5.7729468599033815,
+      "grad_norm": 0.20970377326011658,
+      "learning_rate": 3.832773180720475e-06,
+      "loss": 0.0365,
+      "step": 300
+    },
+    {
+      "epoch": 5.966183574879227,
+      "grad_norm": 0.21905659139156342,
+      "learning_rate": 3.541351549100141e-06,
+      "loss": 0.0348,
+      "step": 310
+    },
+    {
+      "epoch": 6.154589371980676,
+      "grad_norm": 0.20344959199428558,
+      "learning_rate": 3.255252367491625e-06,
+      "loss": 0.0338,
+      "step": 320
+    },
+    {
+      "epoch": 6.3478260869565215,
+      "grad_norm": 0.18785010278224945,
+      "learning_rate": 2.9755195807821236e-06,
+      "loss": 0.0323,
+      "step": 330
+    },
+    {
+      "epoch": 6.541062801932367,
+      "grad_norm": 0.17721547186374664,
+      "learning_rate": 2.7031739035742575e-06,
+      "loss": 0.0313,
+      "step": 340
+    },
+    {
+      "epoch": 6.734299516908212,
+      "grad_norm": 0.18272855877876282,
+      "learning_rate": 2.43920909570919e-06,
+      "loss": 0.0314,
+      "step": 350
+    },
+    {
+      "epoch": 6.927536231884058,
+      "grad_norm": 0.17872507870197296,
+      "learning_rate": 2.1845883361447218e-06,
+      "loss": 0.0304,
+      "step": 360
+    },
+    {
+      "epoch": 7.115942028985507,
+      "grad_norm": 0.195228710770607,
+      "learning_rate": 1.94024070841974e-06,
+      "loss": 0.03,
+      "step": 370
+    },
+    {
+      "epoch": 7.309178743961352,
+      "grad_norm": 0.1662645787000656,
+      "learning_rate": 1.707057810529138e-06,
+      "loss": 0.0292,
+      "step": 380
+    },
+    {
+      "epoch": 7.5024154589371985,
+      "grad_norm": 0.17219869792461395,
+      "learning_rate": 1.485890501579414e-06,
+      "loss": 0.0284,
+      "step": 390
+    },
+    {
+      "epoch": 7.695652173913043,
+      "grad_norm": 0.17452393472194672,
+      "learning_rate": 1.2775457970960765e-06,
+      "loss": 0.028,
+      "step": 400
+    },
+    {
+      "epoch": 7.888888888888889,
+      "grad_norm": 0.16770771145820618,
+      "learning_rate": 1.0827839243115046e-06,
+      "loss": 0.0274,
+      "step": 410
+    },
+    {
+      "epoch": 8.077294685990339,
+      "grad_norm": 0.15907828509807587,
+      "learning_rate": 9.023155481782175e-07,
+      "loss": 0.0276,
+      "step": 420
+    },
+    {
+      "epoch": 8.270531400966183,
+      "grad_norm": 0.16959203779697418,
+      "learning_rate": 7.367991782295392e-07,
+      "loss": 0.0273,
+      "step": 430
+    },
+    {
+      "epoch": 8.46376811594203,
+      "grad_norm": 0.1602700799703598,
+      "learning_rate": 5.868387657497171e-07,
+      "loss": 0.0263,
+      "step": 440
+    },
+    {
+      "epoch": 8.657004830917874,
+      "grad_norm": 0.16489073634147644,
+      "learning_rate": 4.52981500021189e-07,
+      "loss": 0.0273,
+      "step": 450
+    },
+    {
+      "epoch": 8.85024154589372,
+      "grad_norm": 0.15676875412464142,
+      "learning_rate": 3.357158116902287e-07,
+      "loss": 0.0267,
+      "step": 460
+    },
+    {
+      "epoch": 9.03864734299517,
+      "grad_norm": 0.16544950008392334,
+      "learning_rate": 2.3546959053648565e-07,
+      "loss": 0.027,
+      "step": 470
+    },
+    {
+      "epoch": 9.231884057971014,
+      "grad_norm": 0.15167686343193054,
+      "learning_rate": 1.5260862414958554e-07,
+      "loss": 0.0262,
+      "step": 480
+    },
+    {
+      "epoch": 9.42512077294686,
+      "grad_norm": 0.158621147274971,
+      "learning_rate": 8.743526320988016e-08,
+      "loss": 0.0267,
+      "step": 490
+    },
+    {
+      "epoch": 9.618357487922705,
+      "grad_norm": 0.16042795777320862,
+      "learning_rate": 4.018731824360744e-08,
+      "loss": 0.0269,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 520,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2582315444076544e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace98255dd4db8e9bcd801eb871efd3f93c7f9f84267be6c4b9074fb866434c1
+size 5432

checkpoint-520/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen3-1.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-1.7B
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.16.0

checkpoint-520/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-1.7B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-520/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d57b6d13935a9fe934a97c0bba82fff3db769d3d8fc827aa9cdfae0096bee7e6
+size 139512976

checkpoint-520/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-520/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

checkpoint-520/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4fb4a1b5ea63c6121b6f2f1baee0ffbfe654fee510a2c2f21622f20aa332232
+size 71281012

checkpoint-520/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb36355c1377023f503b3269f5e0086ed366f52f9567544a1c17ccb466860e84
+size 14244

checkpoint-520/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d3de843e6c3602621efb94355e07b9949260442db1b420777671d02b21f6d3
+size 1064

checkpoint-520/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-520/tokenizer.json

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

checkpoint-520/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": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-520/trainer_state.json

@@ -0,0 +1,398 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 520,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1932367149758454,
+      "grad_norm": 9.72665023803711,
+      "learning_rate": 9.992610567545458e-06,
+      "loss": 6.4816,
+      "step": 10
+    },
+    {
+      "epoch": 0.3864734299516908,
+      "grad_norm": 5.790473937988281,
+      "learning_rate": 9.967094890324894e-06,
+      "loss": 5.3994,
+      "step": 20
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 4.916749954223633,
+      "learning_rate": 9.923454822514262e-06,
+      "loss": 4.5179,
+      "step": 30
+    },
+    {
+      "epoch": 0.7729468599033816,
+      "grad_norm": 4.569331645965576,
+      "learning_rate": 9.861849601988384e-06,
+      "loss": 3.7733,
+      "step": 40
+    },
+    {
+      "epoch": 0.966183574879227,
+      "grad_norm": 4.1129841804504395,
+      "learning_rate": 9.782504019516079e-06,
+      "loss": 3.0167,
+      "step": 50
+    },
+    {
+      "epoch": 1.1545893719806763,
+      "grad_norm": 3.721545934677124,
+      "learning_rate": 9.685707598523027e-06,
+      "loss": 2.2359,
+      "step": 60
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 2.538311004638672,
+      "learning_rate": 9.571813538652184e-06,
+      "loss": 1.5212,
+      "step": 70
+    },
+    {
+      "epoch": 1.541062801932367,
+      "grad_norm": 1.876523494720459,
+      "learning_rate": 9.441237426976596e-06,
+      "loss": 1.0284,
+      "step": 80
+    },
+    {
+      "epoch": 1.7342995169082127,
+      "grad_norm": 1.4319356679916382,
+      "learning_rate": 9.294455721567224e-06,
+      "loss": 0.7066,
+      "step": 90
+    },
+    {
+      "epoch": 1.927536231884058,
+      "grad_norm": 1.2226893901824951,
+      "learning_rate": 9.132004012949124e-06,
+      "loss": 0.5043,
+      "step": 100
+    },
+    {
+      "epoch": 2.1159420289855073,
+      "grad_norm": 1.1039533615112305,
+      "learning_rate": 8.954475069789703e-06,
+      "loss": 0.3595,
+      "step": 110
+    },
+    {
+      "epoch": 2.3091787439613527,
+      "grad_norm": 0.8911028504371643,
+      "learning_rate": 8.762516675950134e-06,
+      "loss": 0.2687,
+      "step": 120
+    },
+    {
+      "epoch": 2.502415458937198,
+      "grad_norm": 0.7713564038276672,
+      "learning_rate": 8.556829266792297e-06,
+      "loss": 0.207,
+      "step": 130
+    },
+    {
+      "epoch": 2.6956521739130435,
+      "grad_norm": 0.6270983815193176,
+      "learning_rate": 8.338163373366099e-06,
+      "loss": 0.164,
+      "step": 140
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.5450633764266968,
+      "learning_rate": 8.107316883803071e-06,
+      "loss": 0.1343,
+      "step": 150
+    },
+    {
+      "epoch": 3.077294685990338,
+      "grad_norm": 0.46505942940711975,
+      "learning_rate": 7.865132131909106e-06,
+      "loss": 0.1137,
+      "step": 160
+    },
+    {
+      "epoch": 3.2705314009661834,
+      "grad_norm": 0.4359152913093567,
+      "learning_rate": 7.612492823579744e-06,
+      "loss": 0.0973,
+      "step": 170
+    },
+    {
+      "epoch": 3.463768115942029,
+      "grad_norm": 0.3963119685649872,
+      "learning_rate": 7.350320812253196e-06,
+      "loss": 0.0875,
+      "step": 180
+    },
+    {
+      "epoch": 3.6570048309178746,
+      "grad_norm": 0.361600399017334,
+      "learning_rate": 7.079572735167119e-06,
+      "loss": 0.0769,
+      "step": 190
+    },
+    {
+      "epoch": 3.85024154589372,
+      "grad_norm": 0.3512292206287384,
+      "learning_rate": 6.8012365226930825e-06,
+      "loss": 0.0705,
+      "step": 200
+    },
+    {
+      "epoch": 4.038647342995169,
+      "grad_norm": 0.30910539627075195,
+      "learning_rate": 6.516327793485776e-06,
+      "loss": 0.0622,
+      "step": 210
+    },
+    {
+      "epoch": 4.231884057971015,
+      "grad_norm": 0.2861171364784241,
+      "learning_rate": 6.225886148600688e-06,
+      "loss": 0.0582,
+      "step": 220
+    },
+    {
+      "epoch": 4.42512077294686,
+      "grad_norm": 0.2825333774089813,
+      "learning_rate": 5.930971378102585e-06,
+      "loss": 0.0533,
+      "step": 230
+    },
+    {
+      "epoch": 4.618357487922705,
+      "grad_norm": 0.26530200242996216,
+      "learning_rate": 5.632659594006498e-06,
+      "loss": 0.0505,
+      "step": 240
+    },
+    {
+      "epoch": 4.811594202898551,
+      "grad_norm": 0.24200841784477234,
+      "learning_rate": 5.332039303661683e-06,
+      "loss": 0.0474,
+      "step": 250
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.24424873292446136,
+      "learning_rate": 5.030207437906354e-06,
+      "loss": 0.0434,
+      "step": 260
+    },
+    {
+      "epoch": 5.193236714975845,
+      "grad_norm": 0.22758834064006805,
+      "learning_rate": 4.728265348486e-06,
+      "loss": 0.0419,
+      "step": 270
+    },
+    {
+      "epoch": 5.386473429951691,
+      "grad_norm": 0.21970826387405396,
+      "learning_rate": 4.4273147893403126e-06,
+      "loss": 0.0396,
+      "step": 280
+    },
+    {
+      "epoch": 5.579710144927536,
+      "grad_norm": 0.19575871527194977,
+      "learning_rate": 4.1284538964225364e-06,
+      "loss": 0.037,
+      "step": 290
+    },
+    {
+      "epoch": 5.7729468599033815,
+      "grad_norm": 0.20970377326011658,
+      "learning_rate": 3.832773180720475e-06,
+      "loss": 0.0365,
+      "step": 300
+    },
+    {
+      "epoch": 5.966183574879227,
+      "grad_norm": 0.21905659139156342,
+      "learning_rate": 3.541351549100141e-06,
+      "loss": 0.0348,
+      "step": 310
+    },
+    {
+      "epoch": 6.154589371980676,
+      "grad_norm": 0.20344959199428558,
+      "learning_rate": 3.255252367491625e-06,
+      "loss": 0.0338,
+      "step": 320
+    },
+    {
+      "epoch": 6.3478260869565215,
+      "grad_norm": 0.18785010278224945,
+      "learning_rate": 2.9755195807821236e-06,
+      "loss": 0.0323,
+      "step": 330
+    },
+    {
+      "epoch": 6.541062801932367,
+      "grad_norm": 0.17721547186374664,
+      "learning_rate": 2.7031739035742575e-06,
+      "loss": 0.0313,
+      "step": 340
+    },
+    {
+      "epoch": 6.734299516908212,
+      "grad_norm": 0.18272855877876282,
+      "learning_rate": 2.43920909570919e-06,
+      "loss": 0.0314,
+      "step": 350
+    },
+    {
+      "epoch": 6.927536231884058,
+      "grad_norm": 0.17872507870197296,
+      "learning_rate": 2.1845883361447218e-06,
+      "loss": 0.0304,
+      "step": 360
+    },
+    {
+      "epoch": 7.115942028985507,
+      "grad_norm": 0.195228710770607,
+      "learning_rate": 1.94024070841974e-06,
+      "loss": 0.03,
+      "step": 370
+    },
+    {
+      "epoch": 7.309178743961352,
+      "grad_norm": 0.1662645787000656,
+      "learning_rate": 1.707057810529138e-06,
+      "loss": 0.0292,
+      "step": 380
+    },
+    {
+      "epoch": 7.5024154589371985,
+      "grad_norm": 0.17219869792461395,
+      "learning_rate": 1.485890501579414e-06,
+      "loss": 0.0284,
+      "step": 390
+    },
+    {
+      "epoch": 7.695652173913043,
+      "grad_norm": 0.17452393472194672,
+      "learning_rate": 1.2775457970960765e-06,
+      "loss": 0.028,
+      "step": 400
+    },
+    {
+      "epoch": 7.888888888888889,
+      "grad_norm": 0.16770771145820618,
+      "learning_rate": 1.0827839243115046e-06,
+      "loss": 0.0274,
+      "step": 410
+    },
+    {
+      "epoch": 8.077294685990339,
+      "grad_norm": 0.15907828509807587,
+      "learning_rate": 9.023155481782175e-07,
+      "loss": 0.0276,
+      "step": 420
+    },
+    {
+      "epoch": 8.270531400966183,
+      "grad_norm": 0.16959203779697418,
+      "learning_rate": 7.367991782295392e-07,
+      "loss": 0.0273,
+      "step": 430
+    },
+    {
+      "epoch": 8.46376811594203,
+      "grad_norm": 0.1602700799703598,
+      "learning_rate": 5.868387657497171e-07,
+      "loss": 0.0263,
+      "step": 440
+    },
+    {
+      "epoch": 8.657004830917874,
+      "grad_norm": 0.16489073634147644,
+      "learning_rate": 4.52981500021189e-07,
+      "loss": 0.0273,
+      "step": 450
+    },
+    {
+      "epoch": 8.85024154589372,
+      "grad_norm": 0.15676875412464142,
+      "learning_rate": 3.357158116902287e-07,
+      "loss": 0.0267,
+      "step": 460
+    },
+    {
+      "epoch": 9.03864734299517,
+      "grad_norm": 0.16544950008392334,
+      "learning_rate": 2.3546959053648565e-07,
+      "loss": 0.027,
+      "step": 470
+    },
+    {
+      "epoch": 9.231884057971014,
+      "grad_norm": 0.15167686343193054,
+      "learning_rate": 1.5260862414958554e-07,
+      "loss": 0.0262,
+      "step": 480
+    },
+    {
+      "epoch": 9.42512077294686,
+      "grad_norm": 0.158621147274971,
+      "learning_rate": 8.743526320988016e-08,
+      "loss": 0.0267,
+      "step": 490
+    },
+    {
+      "epoch": 9.618357487922705,
+      "grad_norm": 0.16042795777320862,
+      "learning_rate": 4.018731824360744e-08,
+      "loss": 0.0269,
+      "step": 500
+    },
+    {
+      "epoch": 9.81159420289855,
+      "grad_norm": 0.1612517535686493,
+      "learning_rate": 1.1037191878068843e-08,
+      "loss": 0.0265,
+      "step": 510
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.19540855288505554,
+      "learning_rate": 9.124976313834577e-11,
+      "loss": 0.0262,
+      "step": 520
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 520,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.347606713827328e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-520/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace98255dd4db8e9bcd801eb871efd3f93c7f9f84267be6c4b9074fb866434c1
+size 5432

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": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}