Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-VL-3B-Instruct-AWQ
+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 0.12.0

adapter_config.json

@@ -0,0 +1,279 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct-AWQ",
+  "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": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.layers.1.mlp.up_proj",
+    "model.layers.18.mlp.gate_proj",
+    "model.layers.8.mlp.gate_proj",
+    "model.layers.27.mlp.up_proj",
+    "model.layers.12.mlp.down_proj",
+    "model.layers.9.mlp.up_proj",
+    "model.layers.17.self_attn.o_proj",
+    "model.layers.20.self_attn.q_proj",
+    "model.layers.24.self_attn.o_proj",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.13.self_attn.o_proj",
+    "model.layers.27.self_attn.q_proj",
+    "model.layers.11.mlp.gate_proj",
+    "model.layers.30.mlp.gate_proj",
+    "model.layers.30.self_attn.k_proj",
+    "model.layers.24.mlp.down_proj",
+    "model.layers.13.mlp.up_proj",
+    "model.layers.24.mlp.up_proj",
+    "model.layers.35.self_attn.q_proj",
+    "model.layers.26.self_attn.q_proj",
+    "model.layers.32.self_attn.o_proj",
+    "model.layers.9.mlp.gate_proj",
+    "model.layers.33.mlp.gate_proj",
+    "model.layers.0.mlp.down_proj",
+    "model.layers.24.self_attn.v_proj",
+    "model.layers.2.self_attn.o_proj",
+    "model.layers.1.mlp.gate_proj",
+    "model.layers.3.mlp.up_proj",
+    "model.layers.14.mlp.up_proj",
+    "model.layers.7.mlp.up_proj",
+    "model.layers.15.self_attn.q_proj",
+    "model.layers.18.self_attn.v_proj",
+    "model.layers.19.mlp.gate_proj",
+    "model.layers.35.mlp.down_proj",
+    "model.layers.8.mlp.down_proj",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.10.mlp.down_proj",
+    "model.layers.34.self_attn.v_proj",
+    "model.layers.20.self_attn.v_proj",
+    "model.layers.34.self_attn.q_proj",
+    "model.layers.21.mlp.gate_proj",
+    "model.layers.15.mlp.up_proj",
+    "model.layers.28.mlp.down_proj",
+    "model.layers.9.mlp.down_proj",
+    "model.layers.14.self_attn.v_proj",
+    "model.layers.6.self_attn.o_proj",
+    "model.layers.7.self_attn.k_proj",
+    "model.layers.32.mlp.gate_proj",
+    "model.layers.33.self_attn.q_proj",
+    "model.layers.14.self_attn.o_proj",
+    "model.layers.4.mlp.gate_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.10.mlp.up_proj",
+    "model.layers.13.mlp.gate_proj",
+    "model.layers.23.mlp.up_proj",
+    "model.layers.28.self_attn.k_proj",
+    "model.layers.35.mlp.up_proj",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.5.self_attn.o_proj",
+    "model.layers.28.mlp.up_proj",
+    "model.layers.26.mlp.gate_proj",
+    "model.layers.19.mlp.up_proj",
+    "model.layers.18.self_attn.k_proj",
+    "model.layers.30.mlp.down_proj",
+    "model.layers.21.self_attn.v_proj",
+    "model.layers.17.mlp.up_proj",
+    "model.layers.28.self_attn.v_proj",
+    "model.layers.3.mlp.gate_proj",
+    "model.layers.19.self_attn.o_proj",
+    "model.layers.6.mlp.down_proj",
+    "model.layers.20.self_attn.k_proj",
+    "model.layers.17.self_attn.q_proj",
+    "model.layers.25.mlp.down_proj",
+    "model.layers.28.self_attn.q_proj",
+    "model.layers.0.self_attn.v_proj",
+    "model.layers.29.self_attn.k_proj",
+    "model.layers.13.self_attn.q_proj",
+    "model.layers.29.self_attn.q_proj",
+    "model.layers.32.self_attn.k_proj",
+    "model.layers.34.mlp.down_proj",
+    "model.layers.35.self_attn.k_proj",
+    "model.layers.5.mlp.gate_proj",
+    "model.layers.3.self_attn.o_proj",
+    "model.layers.34.self_attn.o_proj",
+    "model.layers.1.self_attn.o_proj",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.34.self_attn.k_proj",
+    "model.layers.23.self_attn.o_proj",
+    "model.layers.4.mlp.down_proj",
+    "model.layers.17.self_attn.k_proj",
+    "model.layers.2.self_attn.q_proj",
+    "model.layers.25.mlp.gate_proj",
+    "model.layers.30.self_attn.o_proj",
+    "model.layers.21.mlp.down_proj",
+    "model.layers.6.mlp.up_proj",
+    "model.layers.19.self_attn.v_proj",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.23.self_attn.v_proj",
+    "model.layers.31.self_attn.q_proj",
+    "model.layers.1.self_attn.k_proj",
+    "model.layers.26.self_attn.v_proj",
+    "model.layers.3.mlp.down_proj",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.33.self_attn.k_proj",
+    "model.layers.33.mlp.up_proj",
+    "model.layers.2.mlp.down_proj",
+    "model.layers.15.self_attn.k_proj",
+    "model.layers.10.self_attn.k_proj",
+    "model.layers.0.self_attn.q_proj",
+    "model.layers.12.self_attn.o_proj",
+    "model.layers.7.self_attn.o_proj",
+    "model.layers.16.mlp.down_proj",
+    "model.layers.5.mlp.up_proj",
+    "model.layers.16.self_attn.q_proj",
+    "model.layers.21.self_attn.o_proj",
+    "model.layers.11.mlp.up_proj",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.11.self_attn.k_proj",
+    "model.layers.35.self_attn.v_proj",
+    "model.layers.3.self_attn.k_proj",
+    "model.layers.27.self_attn.k_proj",
+    "model.layers.34.mlp.gate_proj",
+    "model.layers.25.self_attn.k_proj",
+    "model.layers.25.mlp.up_proj",
+    "model.layers.26.mlp.down_proj",
+    "model.layers.34.mlp.up_proj",
+    "model.layers.13.self_attn.k_proj",
+    "model.layers.27.self_attn.o_proj",
+    "model.layers.21.self_attn.q_proj",
+    "model.layers.29.mlp.gate_proj",
+    "model.layers.8.self_attn.o_proj",
+    "model.layers.10.self_attn.o_proj",
+    "model.layers.26.self_attn.k_proj",
+    "model.layers.24.mlp.gate_proj",
+    "model.layers.32.self_attn.q_proj",
+    "model.layers.5.self_attn.k_proj",
+    "model.layers.5.mlp.down_proj",
+    "model.layers.23.mlp.gate_proj",
+    "model.layers.1.self_attn.v_proj",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.6.mlp.gate_proj",
+    "model.layers.4.self_attn.o_proj",
+    "model.layers.21.self_attn.k_proj",
+    "model.layers.17.mlp.down_proj",
+    "model.layers.22.self_attn.v_proj",
+    "model.layers.2.self_attn.k_proj",
+    "model.layers.2.mlp.gate_proj",
+    "model.layers.29.self_attn.v_proj",
+    "model.layers.29.mlp.down_proj",
+    "model.layers.0.self_attn.k_proj",
+    "model.layers.17.mlp.gate_proj",
+    "model.layers.0.self_attn.o_proj",
+    "model.layers.21.mlp.up_proj",
+    "model.layers.1.self_attn.q_proj",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.22.self_attn.q_proj",
+    "model.layers.12.mlp.gate_proj",
+    "model.layers.31.self_attn.o_proj",
+    "model.layers.35.self_attn.o_proj",
+    "model.layers.9.self_attn.o_proj",
+    "model.layers.26.self_attn.o_proj",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.22.mlp.gate_proj",
+    "model.layers.19.self_attn.k_proj",
+    "model.layers.22.self_attn.k_proj",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.33.mlp.down_proj",
+    "model.layers.11.self_attn.o_proj",
+    "model.layers.23.mlp.down_proj",
+    "model.layers.31.self_attn.v_proj",
+    "model.layers.31.mlp.gate_proj",
+    "model.layers.7.mlp.gate_proj",
+    "model.layers.27.mlp.gate_proj",
+    "model.layers.13.self_attn.v_proj",
+    "model.layers.29.self_attn.o_proj",
+    "model.layers.17.self_attn.v_proj",
+    "model.layers.10.mlp.gate_proj",
+    "model.layers.29.mlp.up_proj",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.27.self_attn.v_proj",
+    "model.layers.8.mlp.up_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.6.self_attn.k_proj",
+    "model.layers.12.self_attn.k_proj",
+    "model.layers.15.mlp.down_proj",
+    "model.layers.25.self_attn.v_proj",
+    "model.layers.16.mlp.gate_proj",
+    "model.layers.9.self_attn.k_proj",
+    "model.layers.7.mlp.down_proj",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.14.mlp.gate_proj",
+    "model.layers.24.self_attn.q_proj",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.24.self_attn.k_proj",
+    "model.layers.18.self_attn.o_proj",
+    "model.layers.28.self_attn.o_proj",
+    "model.layers.31.mlp.down_proj",
+    "model.layers.25.self_attn.q_proj",
+    "model.layers.12.mlp.up_proj",
+    "model.layers.32.mlp.up_proj",
+    "model.layers.28.mlp.gate_proj",
+    "model.layers.30.self_attn.v_proj",
+    "model.layers.27.mlp.down_proj",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.13.mlp.down_proj",
+    "model.layers.16.mlp.up_proj",
+    "model.layers.20.self_attn.o_proj",
+    "model.layers.22.mlp.up_proj",
+    "model.layers.23.self_attn.k_proj",
+    "model.layers.0.mlp.gate_proj",
+    "model.layers.22.mlp.down_proj",
+    "model.layers.25.self_attn.o_proj",
+    "model.layers.2.self_attn.v_proj",
+    "model.layers.15.self_attn.o_proj",
+    "model.layers.33.self_attn.v_proj",
+    "model.layers.26.mlp.up_proj",
+    "model.layers.19.mlp.down_proj",
+    "model.layers.31.mlp.up_proj",
+    "model.layers.14.self_attn.k_proj",
+    "model.layers.3.self_attn.v_proj",
+    "model.layers.15.mlp.gate_proj",
+    "model.layers.20.mlp.up_proj",
+    "model.layers.18.self_attn.q_proj",
+    "model.layers.35.mlp.gate_proj",
+    "model.layers.4.mlp.up_proj",
+    "model.layers.16.self_attn.k_proj",
+    "model.layers.22.self_attn.o_proj",
+    "model.layers.32.self_attn.v_proj",
+    "model.layers.2.mlp.up_proj",
+    "model.layers.4.self_attn.k_proj",
+    "model.layers.18.mlp.up_proj",
+    "model.layers.20.mlp.gate_proj",
+    "model.layers.20.mlp.down_proj",
+    "model.layers.12.self_attn.v_proj",
+    "model.layers.30.mlp.up_proj",
+    "model.layers.18.mlp.down_proj",
+    "model.layers.31.self_attn.k_proj",
+    "model.layers.0.mlp.up_proj",
+    "model.layers.3.self_attn.q_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.11.mlp.down_proj",
+    "model.layers.16.self_attn.o_proj",
+    "model.layers.32.mlp.down_proj",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.30.self_attn.q_proj",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.1.mlp.down_proj",
+    "model.layers.16.self_attn.v_proj",
+    "model.layers.33.self_attn.o_proj",
+    "model.layers.14.mlp.down_proj",
+    "model.layers.8.self_attn.k_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 sha256:488d180c0e8b6824ea8afd1aedb699229230161ef2800beccf05d85f5299b6dd
+size 59933632

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.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

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 sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

tokenizer_config.json

@@ -0,0 +1,213 @@
+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_max_length": 60000,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1062 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 147,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006843455945252352,
+      "grad_norm": 0.636521577835083,
+      "learning_rate": 1.3698630136986302e-06,
+      "loss": 1.1329,
+      "step": 1
+    },
+    {
+      "epoch": 0.013686911890504704,
+      "grad_norm": 0.6118377447128296,
+      "learning_rate": 2.7397260273972604e-06,
+      "loss": 1.1221,
+      "step": 2
+    },
+    {
+      "epoch": 0.020530367835757058,
+      "grad_norm": 0.6123018264770508,
+      "learning_rate": 4.10958904109589e-06,
+      "loss": 1.0956,
+      "step": 3
+    },
+    {
+      "epoch": 0.02737382378100941,
+      "grad_norm": 0.6341288685798645,
+      "learning_rate": 5.479452054794521e-06,
+      "loss": 1.0895,
+      "step": 4
+    },
+    {
+      "epoch": 0.03421727972626176,
+      "grad_norm": 0.6400193572044373,
+      "learning_rate": 6.849315068493151e-06,
+      "loss": 1.1281,
+      "step": 5
+    },
+    {
+      "epoch": 0.041060735671514116,
+      "grad_norm": 0.6368623375892639,
+      "learning_rate": 8.21917808219178e-06,
+      "loss": 1.0861,
+      "step": 6
+    },
+    {
+      "epoch": 0.04790419161676647,
+      "grad_norm": 0.6226847171783447,
+      "learning_rate": 9.589041095890411e-06,
+      "loss": 1.0808,
+      "step": 7
+    },
+    {
+      "epoch": 0.05474764756201882,
+      "grad_norm": 0.6211888194084167,
+      "learning_rate": 1.0958904109589042e-05,
+      "loss": 1.1314,
+      "step": 8
+    },
+    {
+      "epoch": 0.06159110350727117,
+      "grad_norm": 0.6583495736122131,
+      "learning_rate": 1.2328767123287671e-05,
+      "loss": 1.1426,
+      "step": 9
+    },
+    {
+      "epoch": 0.06843455945252352,
+      "grad_norm": 0.6530178785324097,
+      "learning_rate": 1.3698630136986302e-05,
+      "loss": 1.1281,
+      "step": 10
+    },
+    {
+      "epoch": 0.07527801539777587,
+      "grad_norm": 0.6536809206008911,
+      "learning_rate": 1.5068493150684931e-05,
+      "loss": 1.1049,
+      "step": 11
+    },
+    {
+      "epoch": 0.08212147134302823,
+      "grad_norm": 0.617668628692627,
+      "learning_rate": 1.643835616438356e-05,
+      "loss": 1.0988,
+      "step": 12
+    },
+    {
+      "epoch": 0.08896492728828058,
+      "grad_norm": 0.6528647541999817,
+      "learning_rate": 1.780821917808219e-05,
+      "loss": 1.1277,
+      "step": 13
+    },
+    {
+      "epoch": 0.09580838323353294,
+      "grad_norm": 0.6655603647232056,
+      "learning_rate": 1.9178082191780822e-05,
+      "loss": 1.1288,
+      "step": 14
+    },
+    {
+      "epoch": 0.10265183917878529,
+      "grad_norm": 0.6599170565605164,
+      "learning_rate": 2.0547945205479453e-05,
+      "loss": 1.0877,
+      "step": 15
+    },
+    {
+      "epoch": 0.10949529512403763,
+      "grad_norm": 0.6430280804634094,
+      "learning_rate": 2.1917808219178083e-05,
+      "loss": 1.0996,
+      "step": 16
+    },
+    {
+      "epoch": 0.11633875106929,
+      "grad_norm": 0.6132543087005615,
+      "learning_rate": 2.328767123287671e-05,
+      "loss": 1.0562,
+      "step": 17
+    },
+    {
+      "epoch": 0.12318220701454234,
+      "grad_norm": 0.6341537237167358,
+      "learning_rate": 2.4657534246575342e-05,
+      "loss": 1.0608,
+      "step": 18
+    },
+    {
+      "epoch": 0.1300256629597947,
+      "grad_norm": 0.6119030117988586,
+      "learning_rate": 2.6027397260273973e-05,
+      "loss": 1.1043,
+      "step": 19
+    },
+    {
+      "epoch": 0.13686911890504705,
+      "grad_norm": 0.6095110177993774,
+      "learning_rate": 2.7397260273972603e-05,
+      "loss": 1.0031,
+      "step": 20
+    },
+    {
+      "epoch": 0.1437125748502994,
+      "grad_norm": 0.6125332117080688,
+      "learning_rate": 2.8767123287671234e-05,
+      "loss": 1.0211,
+      "step": 21
+    },
+    {
+      "epoch": 0.15055603079555174,
+      "grad_norm": 0.5320484638214111,
+      "learning_rate": 3.0136986301369862e-05,
+      "loss": 1.0035,
+      "step": 22
+    },
+    {
+      "epoch": 0.15739948674080412,
+      "grad_norm": 0.5538317561149597,
+      "learning_rate": 3.1506849315068496e-05,
+      "loss": 1.0123,
+      "step": 23
+    },
+    {
+      "epoch": 0.16424294268605646,
+      "grad_norm": 0.49668481945991516,
+      "learning_rate": 3.287671232876712e-05,
+      "loss": 1.0105,
+      "step": 24
+    },
+    {
+      "epoch": 0.1710863986313088,
+      "grad_norm": 0.4756055474281311,
+      "learning_rate": 3.424657534246575e-05,
+      "loss": 0.97,
+      "step": 25
+    },
+    {
+      "epoch": 0.17792985457656116,
+      "grad_norm": 0.45267367362976074,
+      "learning_rate": 3.561643835616438e-05,
+      "loss": 0.9567,
+      "step": 26
+    },
+    {
+      "epoch": 0.1847733105218135,
+      "grad_norm": 0.41849184036254883,
+      "learning_rate": 3.698630136986301e-05,
+      "loss": 0.9829,
+      "step": 27
+    },
+    {
+      "epoch": 0.19161676646706588,
+      "grad_norm": 0.4102514982223511,
+      "learning_rate": 3.8356164383561644e-05,
+      "loss": 0.9688,
+      "step": 28
+    },
+    {
+      "epoch": 0.19846022241231823,
+      "grad_norm": 0.388466477394104,
+      "learning_rate": 3.9726027397260274e-05,
+      "loss": 0.9291,
+      "step": 29
+    },
+    {
+      "epoch": 0.20530367835757057,
+      "grad_norm": 0.37776416540145874,
+      "learning_rate": 4.1095890410958905e-05,
+      "loss": 0.9405,
+      "step": 30
+    },
+    {
+      "epoch": 0.21214713430282292,
+      "grad_norm": 0.3908478021621704,
+      "learning_rate": 4.2465753424657536e-05,
+      "loss": 0.9224,
+      "step": 31
+    },
+    {
+      "epoch": 0.21899059024807527,
+      "grad_norm": 0.37186965346336365,
+      "learning_rate": 4.383561643835617e-05,
+      "loss": 0.9149,
+      "step": 32
+    },
+    {
+      "epoch": 0.22583404619332764,
+      "grad_norm": 0.3980225920677185,
+      "learning_rate": 4.520547945205479e-05,
+      "loss": 0.9399,
+      "step": 33
+    },
+    {
+      "epoch": 0.23267750213858,
+      "grad_norm": 0.43066874146461487,
+      "learning_rate": 4.657534246575342e-05,
+      "loss": 0.9326,
+      "step": 34
+    },
+    {
+      "epoch": 0.23952095808383234,
+      "grad_norm": 0.4322938024997711,
+      "learning_rate": 4.794520547945205e-05,
+      "loss": 0.9361,
+      "step": 35
+    },
+    {
+      "epoch": 0.24636441402908468,
+      "grad_norm": 0.40527796745300293,
+      "learning_rate": 4.9315068493150684e-05,
+      "loss": 0.8739,
+      "step": 36
+    },
+    {
+      "epoch": 0.25320786997433703,
+      "grad_norm": 0.4267694354057312,
+      "learning_rate": 5.068493150684932e-05,
+      "loss": 0.8942,
+      "step": 37
+    },
+    {
+      "epoch": 0.2600513259195894,
+      "grad_norm": 0.3659462034702301,
+      "learning_rate": 5.2054794520547945e-05,
+      "loss": 0.8692,
+      "step": 38
+    },
+    {
+      "epoch": 0.2668947818648417,
+      "grad_norm": 0.3301553726196289,
+      "learning_rate": 5.342465753424658e-05,
+      "loss": 0.9074,
+      "step": 39
+    },
+    {
+      "epoch": 0.2737382378100941,
+      "grad_norm": 0.28800147771835327,
+      "learning_rate": 5.479452054794521e-05,
+      "loss": 0.8746,
+      "step": 40
+    },
+    {
+      "epoch": 0.2805816937553465,
+      "grad_norm": 0.29222574830055237,
+      "learning_rate": 5.616438356164384e-05,
+      "loss": 0.8465,
+      "step": 41
+    },
+    {
+      "epoch": 0.2874251497005988,
+      "grad_norm": 0.3136586844921112,
+      "learning_rate": 5.753424657534247e-05,
+      "loss": 0.8279,
+      "step": 42
+    },
+    {
+      "epoch": 0.29426860564585117,
+      "grad_norm": 0.30682700872421265,
+      "learning_rate": 5.89041095890411e-05,
+      "loss": 0.8283,
+      "step": 43
+    },
+    {
+      "epoch": 0.3011120615911035,
+      "grad_norm": 0.31840255856513977,
+      "learning_rate": 6.0273972602739724e-05,
+      "loss": 0.8239,
+      "step": 44
+    },
+    {
+      "epoch": 0.30795551753635586,
+      "grad_norm": 0.335709810256958,
+      "learning_rate": 6.164383561643835e-05,
+      "loss": 0.7844,
+      "step": 45
+    },
+    {
+      "epoch": 0.31479897348160824,
+      "grad_norm": 0.35194239020347595,
+      "learning_rate": 6.301369863013699e-05,
+      "loss": 0.7742,
+      "step": 46
+    },
+    {
+      "epoch": 0.32164242942686055,
+      "grad_norm": 0.31687647104263306,
+      "learning_rate": 6.438356164383562e-05,
+      "loss": 0.8081,
+      "step": 47
+    },
+    {
+      "epoch": 0.32848588537211293,
+      "grad_norm": 0.3712421655654907,
+      "learning_rate": 6.575342465753424e-05,
+      "loss": 0.8125,
+      "step": 48
+    },
+    {
+      "epoch": 0.33532934131736525,
+      "grad_norm": 0.3325323462486267,
+      "learning_rate": 6.712328767123288e-05,
+      "loss": 0.8222,
+      "step": 49
+    },
+    {
+      "epoch": 0.3421727972626176,
+      "grad_norm": 0.363585889339447,
+      "learning_rate": 6.84931506849315e-05,
+      "loss": 0.7796,
+      "step": 50
+    },
+    {
+      "epoch": 0.34901625320787,
+      "grad_norm": 0.2978096604347229,
+      "learning_rate": 6.986301369863014e-05,
+      "loss": 0.7721,
+      "step": 51
+    },
+    {
+      "epoch": 0.3558597091531223,
+      "grad_norm": 0.3298179507255554,
+      "learning_rate": 7.123287671232876e-05,
+      "loss": 0.8432,
+      "step": 52
+    },
+    {
+      "epoch": 0.3627031650983747,
+      "grad_norm": 0.3100487291812897,
+      "learning_rate": 7.26027397260274e-05,
+      "loss": 0.8087,
+      "step": 53
+    },
+    {
+      "epoch": 0.369546621043627,
+      "grad_norm": 0.2862851917743683,
+      "learning_rate": 7.397260273972603e-05,
+      "loss": 0.7897,
+      "step": 54
+    },
+    {
+      "epoch": 0.3763900769888794,
+      "grad_norm": 0.2820994257926941,
+      "learning_rate": 7.534246575342466e-05,
+      "loss": 0.7961,
+      "step": 55
+    },
+    {
+      "epoch": 0.38323353293413176,
+      "grad_norm": 0.2562536299228668,
+      "learning_rate": 7.671232876712329e-05,
+      "loss": 0.7868,
+      "step": 56
+    },
+    {
+      "epoch": 0.3900769888793841,
+      "grad_norm": 0.27137479186058044,
+      "learning_rate": 7.808219178082192e-05,
+      "loss": 0.7652,
+      "step": 57
+    },
+    {
+      "epoch": 0.39692044482463645,
+      "grad_norm": 0.23977969586849213,
+      "learning_rate": 7.945205479452055e-05,
+      "loss": 0.7396,
+      "step": 58
+    },
+    {
+      "epoch": 0.4037639007698888,
+      "grad_norm": 0.2629208564758301,
+      "learning_rate": 8.082191780821919e-05,
+      "loss": 0.7764,
+      "step": 59
+    },
+    {
+      "epoch": 0.41060735671514115,
+      "grad_norm": 0.25315892696380615,
+      "learning_rate": 8.219178082191781e-05,
+      "loss": 0.7837,
+      "step": 60
+    },
+    {
+      "epoch": 0.4174508126603935,
+      "grad_norm": 0.2620966136455536,
+      "learning_rate": 8.356164383561645e-05,
+      "loss": 0.7686,
+      "step": 61
+    },
+    {
+      "epoch": 0.42429426860564584,
+      "grad_norm": 0.27335497736930847,
+      "learning_rate": 8.493150684931507e-05,
+      "loss": 0.7577,
+      "step": 62
+    },
+    {
+      "epoch": 0.4311377245508982,
+      "grad_norm": 0.26212769746780396,
+      "learning_rate": 8.630136986301371e-05,
+      "loss": 0.7834,
+      "step": 63
+    },
+    {
+      "epoch": 0.43798118049615054,
+      "grad_norm": 0.2612573802471161,
+      "learning_rate": 8.767123287671233e-05,
+      "loss": 0.7433,
+      "step": 64
+    },
+    {
+      "epoch": 0.4448246364414029,
+      "grad_norm": 0.2643480598926544,
+      "learning_rate": 8.904109589041096e-05,
+      "loss": 0.7472,
+      "step": 65
+    },
+    {
+      "epoch": 0.4516680923866553,
+      "grad_norm": 0.2663419246673584,
+      "learning_rate": 9.041095890410958e-05,
+      "loss": 0.7438,
+      "step": 66
+    },
+    {
+      "epoch": 0.4585115483319076,
+      "grad_norm": 0.2881511151790619,
+      "learning_rate": 9.178082191780822e-05,
+      "loss": 0.7486,
+      "step": 67
+    },
+    {
+      "epoch": 0.46535500427716,
+      "grad_norm": 0.2844236195087433,
+      "learning_rate": 9.315068493150684e-05,
+      "loss": 0.749,
+      "step": 68
+    },
+    {
+      "epoch": 0.4721984602224123,
+      "grad_norm": 0.2508685886859894,
+      "learning_rate": 9.452054794520548e-05,
+      "loss": 0.7505,
+      "step": 69
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "grad_norm": 0.2729940116405487,
+      "learning_rate": 9.58904109589041e-05,
+      "loss": 0.7503,
+      "step": 70
+    },
+    {
+      "epoch": 0.48588537211291705,
+      "grad_norm": 0.27925217151641846,
+      "learning_rate": 9.726027397260274e-05,
+      "loss": 0.7145,
+      "step": 71
+    },
+    {
+      "epoch": 0.49272882805816937,
+      "grad_norm": 0.2549479603767395,
+      "learning_rate": 9.863013698630137e-05,
+      "loss": 0.7324,
+      "step": 72
+    },
+    {
+      "epoch": 0.49957228400342174,
+      "grad_norm": 0.2751714587211609,
+      "learning_rate": 0.0001,
+      "loss": 0.737,
+      "step": 73
+    },
+    {
+      "epoch": 0.5064157399486741,
+      "grad_norm": 0.2604736387729645,
+      "learning_rate": 9.999942837898412e-05,
+      "loss": 0.6876,
+      "step": 74
+    },
+    {
+      "epoch": 0.5132591958939264,
+      "grad_norm": 0.26937931776046753,
+      "learning_rate": 9.999771352900648e-05,
+      "loss": 0.739,
+      "step": 75
+    },
+    {
+      "epoch": 0.5201026518391788,
+      "grad_norm": 0.27722448110580444,
+      "learning_rate": 9.999485548927685e-05,
+      "loss": 0.7586,
+      "step": 76
+    },
+    {
+      "epoch": 0.5269461077844312,
+      "grad_norm": 0.2813119888305664,
+      "learning_rate": 9.999085432514387e-05,
+      "loss": 0.7489,
+      "step": 77
+    },
+    {
+      "epoch": 0.5337895637296834,
+      "grad_norm": 0.2670259177684784,
+      "learning_rate": 9.998571012809351e-05,
+      "loss": 0.7449,
+      "step": 78
+    },
+    {
+      "epoch": 0.5406330196749358,
+      "grad_norm": 0.26460105180740356,
+      "learning_rate": 9.997942301574701e-05,
+      "loss": 0.7246,
+      "step": 79
+    },
+    {
+      "epoch": 0.5474764756201882,
+      "grad_norm": 0.28915923833847046,
+      "learning_rate": 9.997199313185821e-05,
+      "loss": 0.6571,
+      "step": 80
+    },
+    {
+      "epoch": 0.5543199315654406,
+      "grad_norm": 0.28808340430259705,
+      "learning_rate": 9.996342064631019e-05,
+      "loss": 0.708,
+      "step": 81
+    },
+    {
+      "epoch": 0.561163387510693,
+      "grad_norm": 0.27782848477363586,
+      "learning_rate": 9.995370575511151e-05,
+      "loss": 0.706,
+      "step": 82
+    },
+    {
+      "epoch": 0.5680068434559452,
+      "grad_norm": 0.3175579011440277,
+      "learning_rate": 9.994284868039156e-05,
+      "loss": 0.7523,
+      "step": 83
+    },
+    {
+      "epoch": 0.5748502994011976,
+      "grad_norm": 0.30353713035583496,
+      "learning_rate": 9.993084967039567e-05,
+      "loss": 0.7526,
+      "step": 84
+    },
+    {
+      "epoch": 0.58169375534645,
+      "grad_norm": 0.29647502303123474,
+      "learning_rate": 9.991770899947926e-05,
+      "loss": 0.7076,
+      "step": 85
+    },
+    {
+      "epoch": 0.5885372112917023,
+      "grad_norm": 0.32934725284576416,
+      "learning_rate": 9.990342696810168e-05,
+      "loss": 0.7126,
+      "step": 86
+    },
+    {
+      "epoch": 0.5953806672369547,
+      "grad_norm": 0.2991587817668915,
+      "learning_rate": 9.988800390281931e-05,
+      "loss": 0.7159,
+      "step": 87
+    },
+    {
+      "epoch": 0.602224123182207,
+      "grad_norm": 0.31571540236473083,
+      "learning_rate": 9.987144015627809e-05,
+      "loss": 0.7373,
+      "step": 88
+    },
+    {
+      "epoch": 0.6090675791274593,
+      "grad_norm": 0.3044937252998352,
+      "learning_rate": 9.985373610720542e-05,
+      "loss": 0.6924,
+      "step": 89
+    },
+    {
+      "epoch": 0.6159110350727117,
+      "grad_norm": 0.3055077791213989,
+      "learning_rate": 9.983489216040158e-05,
+      "loss": 0.752,
+      "step": 90
+    },
+    {
+      "epoch": 0.6227544910179641,
+      "grad_norm": 0.2858261168003082,
+      "learning_rate": 9.981490874673039e-05,
+      "loss": 0.6882,
+      "step": 91
+    },
+    {
+      "epoch": 0.6295979469632165,
+      "grad_norm": 0.30504581332206726,
+      "learning_rate": 9.979378632310945e-05,
+      "loss": 0.715,
+      "step": 92
+    },
+    {
+      "epoch": 0.6364414029084687,
+      "grad_norm": 0.37040433287620544,
+      "learning_rate": 9.977152537249958e-05,
+      "loss": 0.7085,
+      "step": 93
+    },
+    {
+      "epoch": 0.6432848588537211,
+      "grad_norm": 0.2956722378730774,
+      "learning_rate": 9.974812640389388e-05,
+      "loss": 0.7037,
+      "step": 94
+    },
+    {
+      "epoch": 0.6501283147989735,
+      "grad_norm": 0.3040579855442047,
+      "learning_rate": 9.972358995230604e-05,
+      "loss": 0.6937,
+      "step": 95
+    },
+    {
+      "epoch": 0.6569717707442259,
+      "grad_norm": 0.3133929967880249,
+      "learning_rate": 9.969791657875811e-05,
+      "loss": 0.7143,
+      "step": 96
+    },
+    {
+      "epoch": 0.6638152266894782,
+      "grad_norm": 0.2941054701805115,
+      "learning_rate": 9.96711068702677e-05,
+      "loss": 0.7168,
+      "step": 97
+    },
+    {
+      "epoch": 0.6706586826347305,
+      "grad_norm": 0.2904185950756073,
+      "learning_rate": 9.96431614398345e-05,
+      "loss": 0.6964,
+      "step": 98
+    },
+    {
+      "epoch": 0.6775021385799829,
+      "grad_norm": 0.2977200746536255,
+      "learning_rate": 9.961408092642633e-05,
+      "loss": 0.7085,
+      "step": 99
+    },
+    {
+      "epoch": 0.6843455945252352,
+      "grad_norm": 0.2830125093460083,
+      "learning_rate": 9.95838659949645e-05,
+      "loss": 0.6769,
+      "step": 100
+    },
+    {
+      "epoch": 0.6911890504704876,
+      "grad_norm": 0.29378968477249146,
+      "learning_rate": 9.955251733630861e-05,
+      "loss": 0.6764,
+      "step": 101
+    },
+    {
+      "epoch": 0.69803250641574,
+      "grad_norm": 0.35132017731666565,
+      "learning_rate": 9.952003566724074e-05,
+      "loss": 0.6965,
+      "step": 102
+    },
+    {
+      "epoch": 0.7048759623609923,
+      "grad_norm": 0.3158476650714874,
+      "learning_rate": 9.948642173044905e-05,
+      "loss": 0.6941,
+      "step": 103
+    },
+    {
+      "epoch": 0.7117194183062446,
+      "grad_norm": 0.2933897376060486,
+      "learning_rate": 9.945167629451089e-05,
+      "loss": 0.7003,
+      "step": 104
+    },
+    {
+      "epoch": 0.718562874251497,
+      "grad_norm": 0.3008817434310913,
+      "learning_rate": 9.941580015387508e-05,
+      "loss": 0.6724,
+      "step": 105
+    },
+    {
+      "epoch": 0.7254063301967494,
+      "grad_norm": 0.29962071776390076,
+      "learning_rate": 9.93787941288439e-05,
+      "loss": 0.6877,
+      "step": 106
+    },
+    {
+      "epoch": 0.7322497861420018,
+      "grad_norm": 0.3388601243495941,
+      "learning_rate": 9.934065906555416e-05,
+      "loss": 0.6897,
+      "step": 107
+    },
+    {
+      "epoch": 0.739093242087254,
+      "grad_norm": 0.32225191593170166,
+      "learning_rate": 9.930139583595805e-05,
+      "loss": 0.6868,
+      "step": 108
+    },
+    {
+      "epoch": 0.7459366980325064,
+      "grad_norm": 0.3365332782268524,
+      "learning_rate": 9.926100533780303e-05,
+      "loss": 0.7156,
+      "step": 109
+    },
+    {
+      "epoch": 0.7527801539777588,
+      "grad_norm": 0.3135209381580353,
+      "learning_rate": 9.921948849461142e-05,
+      "loss": 0.702,
+      "step": 110
+    },
+    {
+      "epoch": 0.7596236099230111,
+      "grad_norm": 0.31001490354537964,
+      "learning_rate": 9.917684625565923e-05,
+      "loss": 0.6543,
+      "step": 111
+    },
+    {
+      "epoch": 0.7664670658682635,
+      "grad_norm": 0.31618010997772217,
+      "learning_rate": 9.913307959595444e-05,
+      "loss": 0.6705,
+      "step": 112
+    },
+    {
+      "epoch": 0.7733105218135158,
+      "grad_norm": 0.28696200251579285,
+      "learning_rate": 9.908818951621474e-05,
+      "loss": 0.7028,
+      "step": 113
+    },
+    {
+      "epoch": 0.7801539777587682,
+      "grad_norm": 0.35822418332099915,
+      "learning_rate": 9.904217704284469e-05,
+      "loss": 0.7049,
+      "step": 114
+    },
+    {
+      "epoch": 0.7869974337040205,
+      "grad_norm": 0.2970781624317169,
+      "learning_rate": 9.89950432279121e-05,
+      "loss": 0.667,
+      "step": 115
+    },
+    {
+      "epoch": 0.7938408896492729,
+      "grad_norm": 0.29399991035461426,
+      "learning_rate": 9.89467891491242e-05,
+      "loss": 0.6859,
+      "step": 116
+    },
+    {
+      "epoch": 0.8006843455945253,
+      "grad_norm": 0.2999393045902252,
+      "learning_rate": 9.889741590980279e-05,
+      "loss": 0.6549,
+      "step": 117
+    },
+    {
+      "epoch": 0.8075278015397775,
+      "grad_norm": 0.29656848311424255,
+      "learning_rate": 9.88469246388591e-05,
+      "loss": 0.6783,
+      "step": 118
+    },
+    {
+      "epoch": 0.8143712574850299,
+      "grad_norm": 0.31677696108818054,
+      "learning_rate": 9.879531649076799e-05,
+      "loss": 0.6479,
+      "step": 119
+    },
+    {
+      "epoch": 0.8212147134302823,
+      "grad_norm": 0.3267195522785187,
+      "learning_rate": 9.874259264554158e-05,
+      "loss": 0.6527,
+      "step": 120
+    },
+    {
+      "epoch": 0.8280581693755347,
+      "grad_norm": 0.3279348313808441,
+      "learning_rate": 9.868875430870216e-05,
+      "loss": 0.6612,
+      "step": 121
+    },
+    {
+      "epoch": 0.834901625320787,
+      "grad_norm": 0.34102728962898254,
+      "learning_rate": 9.863380271125473e-05,
+      "loss": 0.6996,
+      "step": 122
+    },
+    {
+      "epoch": 0.8417450812660393,
+      "grad_norm": 0.37898045778274536,
+      "learning_rate": 9.85777391096588e-05,
+      "loss": 0.7019,
+      "step": 123
+    },
+    {
+      "epoch": 0.8485885372112917,
+      "grad_norm": 0.30976685881614685,
+      "learning_rate": 9.85205647857997e-05,
+      "loss": 0.6918,
+      "step": 124
+    },
+    {
+      "epoch": 0.8554319931565441,
+      "grad_norm": 0.32494568824768066,
+      "learning_rate": 9.846228104695923e-05,
+      "loss": 0.7099,
+      "step": 125
+    },
+    {
+      "epoch": 0.8622754491017964,
+      "grad_norm": 0.3217870593070984,
+      "learning_rate": 9.840288922578578e-05,
+      "loss": 0.7257,
+      "step": 126
+    },
+    {
+      "epoch": 0.8691189050470488,
+      "grad_norm": 0.3261460065841675,
+      "learning_rate": 9.834239068026387e-05,
+      "loss": 0.6898,
+      "step": 127
+    },
+    {
+      "epoch": 0.8759623609923011,
+      "grad_norm": 0.3442898094654083,
+      "learning_rate": 9.828078679368313e-05,
+      "loss": 0.6742,
+      "step": 128
+    },
+    {
+      "epoch": 0.8828058169375534,
+      "grad_norm": 0.3025893270969391,
+      "learning_rate": 9.82180789746066e-05,
+      "loss": 0.6592,
+      "step": 129
+    },
+    {
+      "epoch": 0.8896492728828058,
+      "grad_norm": 0.3118937015533447,
+      "learning_rate": 9.815426865683857e-05,
+      "loss": 0.7023,
+      "step": 130
+    },
+    {
+      "epoch": 0.8964927288280582,
+      "grad_norm": 0.32637274265289307,
+      "learning_rate": 9.808935729939175e-05,
+      "loss": 0.6555,
+      "step": 131
+    },
+    {
+      "epoch": 0.9033361847733106,
+      "grad_norm": 0.6886576414108276,
+      "learning_rate": 9.802334638645403e-05,
+      "loss": 0.64,
+      "step": 132
+    },
+    {
+      "epoch": 0.9101796407185628,
+      "grad_norm": 0.3311843276023865,
+      "learning_rate": 9.79562374273544e-05,
+      "loss": 0.6643,
+      "step": 133
+    },
+    {
+      "epoch": 0.9170230966638152,
+      "grad_norm": 0.35473594069480896,
+      "learning_rate": 9.788803195652851e-05,
+      "loss": 0.6591,
+      "step": 134
+    },
+    {
+      "epoch": 0.9238665526090676,
+      "grad_norm": 0.3117069602012634,
+      "learning_rate": 9.78187315334836e-05,
+      "loss": 0.631,
+      "step": 135
+    },
+    {
+      "epoch": 0.93071000855432,
+      "grad_norm": 0.3736455738544464,
+      "learning_rate": 9.774833774276278e-05,
+      "loss": 0.6897,
+      "step": 136
+    },
+    {
+      "epoch": 0.9375534644995723,
+      "grad_norm": 0.33595332503318787,
+      "learning_rate": 9.767685219390883e-05,
+      "loss": 0.7136,
+      "step": 137
+    },
+    {
+      "epoch": 0.9443969204448246,
+      "grad_norm": 0.349388986825943,
+      "learning_rate": 9.76042765214275e-05,
+      "loss": 0.6487,
+      "step": 138
+    },
+    {
+      "epoch": 0.951240376390077,
+      "grad_norm": 0.33862006664276123,
+      "learning_rate": 9.753061238474991e-05,
+      "loss": 0.6937,
+      "step": 139
+    },
+    {
+      "epoch": 0.9580838323353293,
+      "grad_norm": 0.3326554596424103,
+      "learning_rate": 9.745586146819484e-05,
+      "loss": 0.6584,
+      "step": 140
+    },
+    {
+      "epoch": 0.9649272882805817,
+      "grad_norm": 0.3634846806526184,
+      "learning_rate": 9.738002548093008e-05,
+      "loss": 0.6712,
+      "step": 141
+    },
+    {
+      "epoch": 0.9717707442258341,
+      "grad_norm": 0.3282196521759033,
+      "learning_rate": 9.730310615693338e-05,
+      "loss": 0.6258,
+      "step": 142
+    },
+    {
+      "epoch": 0.9786142001710864,
+      "grad_norm": 0.31521832942962646,
+      "learning_rate": 9.722510525495286e-05,
+      "loss": 0.6688,
+      "step": 143
+    },
+    {
+      "epoch": 0.9854576561163387,
+      "grad_norm": 0.33898505568504333,
+      "learning_rate": 9.714602455846666e-05,
+      "loss": 0.6672,
+      "step": 144
+    },
+    {
+      "epoch": 0.9923011120615911,
+      "grad_norm": 0.3225289285182953,
+      "learning_rate": 9.706586587564237e-05,
+      "loss": 0.6525,
+      "step": 145
+    },
+    {
+      "epoch": 0.9991445680068435,
+      "grad_norm": 0.3071536123752594,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 0.6478,
+      "step": 146
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.11246766895055771,
+      "learning_rate": 9.690232190684747e-05,
+      "loss": 0.0797,
+      "step": 147
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0526453703573504e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}