Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +159 -0
- added_tokens.json +28 -0
- args.json +353 -0
- chat_template.jinja +61 -0
- config.json +68 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +406 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -0
- trainer_state.json +1394 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- finance
|
| 7 |
+
- earnings-call
|
| 8 |
+
- evasion-detection
|
| 9 |
+
- qwen3
|
| 10 |
+
- text-classification
|
| 11 |
+
base_model: Qwen/Qwen3-4B-Instruct-2507
|
| 12 |
+
datasets:
|
| 13 |
+
- earnings-call-qa
|
| 14 |
+
metrics:
|
| 15 |
+
- accuracy
|
| 16 |
+
- f1
|
| 17 |
+
model-index:
|
| 18 |
+
- name: Qwen3-4B-Evasion
|
| 19 |
+
results:
|
| 20 |
+
- task:
|
| 21 |
+
type: text-classification
|
| 22 |
+
name: Evasion Classification
|
| 23 |
+
metrics:
|
| 24 |
+
- type: accuracy
|
| 25 |
+
value: 0.7508
|
| 26 |
+
name: Accuracy
|
| 27 |
+
- type: f1
|
| 28 |
+
value: 0.7475
|
| 29 |
+
name: Weighted F1
|
| 30 |
+
library_name: transformers
|
| 31 |
+
pipeline_tag: text-classification
|
| 32 |
+
---
|
| 33 |
+
|
| 34 |
+
# Qwen3-4B-Evasion
|
| 35 |
+
|
| 36 |
+
A fine-tuned model for detecting evasion levels in earnings call Q&A responses.
|
| 37 |
+
|
| 38 |
+
## Model Description
|
| 39 |
+
|
| 40 |
+
**Qwen3-4B-Evasion** is a specialized model fine-tuned from [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) for analyzing executive responses during earnings call Q&A sessions. The model classifies responses into three evasion categories based on the Rasiah taxonomy.
|
| 41 |
+
|
| 42 |
+
## Intended Use
|
| 43 |
+
|
| 44 |
+
### Primary Use Case
|
| 45 |
+
- Analyze transparency and directness of executive responses in earnings calls
|
| 46 |
+
- Financial discourse analysis
|
| 47 |
+
- Corporate communication research
|
| 48 |
+
|
| 49 |
+
### Classification Categories
|
| 50 |
+
|
| 51 |
+
- **direct**: Clear, on-topic resolution to the question
|
| 52 |
+
- **intermediate**: Partially responsive, incomplete, or softened answer
|
| 53 |
+
- **fully_evasive**: Does not provide requested information
|
| 54 |
+
|
| 55 |
+
## Training Details
|
| 56 |
+
|
| 57 |
+
### Training Data
|
| 58 |
+
- **Dataset**: 27,097 earnings call Q&A pairs
|
| 59 |
+
- **Source**: Annotated by DeepSeek-V3.2 and Qwen3-Max models
|
| 60 |
+
- **Label Distribution**:
|
| 61 |
+
- intermediate: 45.4%
|
| 62 |
+
- direct: 29.8%
|
| 63 |
+
- fully_evasive: 24.9%
|
| 64 |
+
|
| 65 |
+
### Training Configuration
|
| 66 |
+
- **Base Model**: Qwen/Qwen3-4B-Instruct-2507
|
| 67 |
+
- **Training Type**: Full parameter fine-tuning
|
| 68 |
+
- **Hardware**: 2x NVIDIA B200 GPUs
|
| 69 |
+
- **Epochs**: 2
|
| 70 |
+
- **Batch Size**: 32 (effective)
|
| 71 |
+
- **Learning Rate**: 2e-5
|
| 72 |
+
- **Framework**: MS-SWIFT
|
| 73 |
+
|
| 74 |
+
## Performance
|
| 75 |
+
|
| 76 |
+
Evaluated on 297 human-annotated benchmark samples:
|
| 77 |
+
|
| 78 |
+
| Metric | Score |
|
| 79 |
+
|--------|-------|
|
| 80 |
+
| **Overall Accuracy** | 75.08% |
|
| 81 |
+
| **Weighted F1** | 74.75% |
|
| 82 |
+
| **Weighted Precision** | 77.56% |
|
| 83 |
+
| **Weighted Recall** | 75.08% |
|
| 84 |
+
|
| 85 |
+
### Per-Class Performance
|
| 86 |
+
|
| 87 |
+
| Class | Precision | Recall | F1-Score | Support |
|
| 88 |
+
|-------|-----------|--------|----------|---------|
|
| 89 |
+
| direct | 86.67% | 54.74% | 67.10% | 95 |
|
| 90 |
+
| intermediate | 63.12% | 80.91% | 70.92% | 110 |
|
| 91 |
+
| fully_evasive | 85.42% | 89.13% | 87.23% | 92 |
|
| 92 |
+
|
| 93 |
+
## Usage
|
| 94 |
+
|
| 95 |
+
```python
|
| 96 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 97 |
+
|
| 98 |
+
model_name = "FutureMa/Qwen3-4B-Evasion"
|
| 99 |
+
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
|
| 100 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 101 |
+
|
| 102 |
+
# Prepare input
|
| 103 |
+
question = "What are your revenue projections for next quarter?"
|
| 104 |
+
answer = "We don't provide specific guidance on that."
|
| 105 |
+
|
| 106 |
+
prompt = f"""You are a financial discourse analyst. Classify the evasion level of this executive response.
|
| 107 |
+
|
| 108 |
+
Question: {question}
|
| 109 |
+
Answer: {answer}
|
| 110 |
+
|
| 111 |
+
Return JSON: {{"rasiah":"direct|intermediate|fully_evasive","confidence":0.00}}"""
|
| 112 |
+
|
| 113 |
+
messages = [{"role": "user", "content": prompt}]
|
| 114 |
+
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 115 |
+
inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
| 116 |
+
|
| 117 |
+
outputs = model.generate(**inputs, max_new_tokens=128, temperature=1)
|
| 118 |
+
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
| 119 |
+
print(response)
|
| 120 |
+
```
|
| 121 |
+
|
| 122 |
+
## Limitations
|
| 123 |
+
|
| 124 |
+
- **Direct Class Recall**: Lower recall (54.74%) for direct responses - model tends to be conservative
|
| 125 |
+
- **Domain Specific**: Optimized for earnings call context, may not generalize to other domains
|
| 126 |
+
- **English Only**: Trained exclusively on English text
|
| 127 |
+
- **Confidence Calibration**: Model confidence scores may require further calibration
|
| 128 |
+
|
| 129 |
+
## Bias and Ethical Considerations
|
| 130 |
+
|
| 131 |
+
- Training data derived from corporate earnings calls may reflect existing biases in financial communication
|
| 132 |
+
- Model should not be used as sole determinant for investment decisions
|
| 133 |
+
- Human oversight recommended for critical applications
|
| 134 |
+
|
| 135 |
+
## Citation
|
| 136 |
+
|
| 137 |
+
```bibtex
|
| 138 |
+
@misc{qwen3-4b-evasion,
|
| 139 |
+
author = {Shijian Ma},
|
| 140 |
+
title = {Qwen3-4B-Evasion: Earnings Call Evasion Detection Model},
|
| 141 |
+
year = {2025},
|
| 142 |
+
publisher = {HuggingFace},
|
| 143 |
+
howpublished = {\url{https://huggingface.co/FutureMa/Qwen3-4B-Evasion}}
|
| 144 |
+
}
|
| 145 |
+
```
|
| 146 |
+
|
| 147 |
+
## License
|
| 148 |
+
|
| 149 |
+
Apache 2.0
|
| 150 |
+
|
| 151 |
+
## Acknowledgments
|
| 152 |
+
|
| 153 |
+
- Base model: [Qwen Team](https://huggingface.co/Qwen)
|
| 154 |
+
- Training framework: [MS-SWIFT](https://github.com/modelscope/ms-swift)
|
| 155 |
+
- Evasion taxonomy: Rasiah et al.
|
| 156 |
+
|
| 157 |
+
## Contact
|
| 158 |
+
|
| 159 |
+
For questions or issues, please open an issue on the model repository.
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
args.json
ADDED
|
@@ -0,0 +1,353 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v1-20251231-073918",
|
| 3 |
+
"overwrite_output_dir": false,
|
| 4 |
+
"do_train": false,
|
| 5 |
+
"do_eval": false,
|
| 6 |
+
"do_predict": false,
|
| 7 |
+
"eval_strategy": "no",
|
| 8 |
+
"prediction_loss_only": false,
|
| 9 |
+
"per_device_train_batch_size": 8,
|
| 10 |
+
"per_device_eval_batch_size": 1,
|
| 11 |
+
"per_gpu_train_batch_size": null,
|
| 12 |
+
"per_gpu_eval_batch_size": null,
|
| 13 |
+
"gradient_accumulation_steps": 2,
|
| 14 |
+
"eval_accumulation_steps": null,
|
| 15 |
+
"eval_delay": 0,
|
| 16 |
+
"torch_empty_cache_steps": null,
|
| 17 |
+
"learning_rate": 2e-05,
|
| 18 |
+
"weight_decay": 0.1,
|
| 19 |
+
"adam_beta1": 0.9,
|
| 20 |
+
"adam_beta2": 0.95,
|
| 21 |
+
"adam_epsilon": 1e-08,
|
| 22 |
+
"max_grad_norm": 1.0,
|
| 23 |
+
"num_train_epochs": 2.0,
|
| 24 |
+
"max_steps": -1,
|
| 25 |
+
"lr_scheduler_type": "cosine",
|
| 26 |
+
"lr_scheduler_kwargs": null,
|
| 27 |
+
"warmup_ratio": 0.03,
|
| 28 |
+
"warmup_steps": 0,
|
| 29 |
+
"log_level": "passive",
|
| 30 |
+
"log_level_replica": "warning",
|
| 31 |
+
"log_on_each_node": true,
|
| 32 |
+
"logging_dir": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v1-20251231-073918/runs",
|
| 33 |
+
"logging_strategy": "steps",
|
| 34 |
+
"logging_first_step": true,
|
| 35 |
+
"logging_steps": 10,
|
| 36 |
+
"logging_nan_inf_filter": true,
|
| 37 |
+
"save_strategy": "steps",
|
| 38 |
+
"save_steps": 500.0,
|
| 39 |
+
"save_total_limit": 3,
|
| 40 |
+
"save_safetensors": true,
|
| 41 |
+
"save_on_each_node": false,
|
| 42 |
+
"save_only_model": false,
|
| 43 |
+
"restore_callback_states_from_checkpoint": false,
|
| 44 |
+
"no_cuda": false,
|
| 45 |
+
"use_cpu": false,
|
| 46 |
+
"use_mps_device": false,
|
| 47 |
+
"seed": 42,
|
| 48 |
+
"data_seed": 42,
|
| 49 |
+
"jit_mode_eval": false,
|
| 50 |
+
"bf16": true,
|
| 51 |
+
"fp16": false,
|
| 52 |
+
"fp16_opt_level": "O1",
|
| 53 |
+
"half_precision_backend": "auto",
|
| 54 |
+
"bf16_full_eval": false,
|
| 55 |
+
"fp16_full_eval": false,
|
| 56 |
+
"tf32": null,
|
| 57 |
+
"local_rank": 0,
|
| 58 |
+
"ddp_backend": null,
|
| 59 |
+
"tpu_num_cores": null,
|
| 60 |
+
"tpu_metrics_debug": false,
|
| 61 |
+
"debug": null,
|
| 62 |
+
"dataloader_drop_last": false,
|
| 63 |
+
"eval_steps": 500.0,
|
| 64 |
+
"dataloader_num_workers": 8,
|
| 65 |
+
"dataloader_prefetch_factor": null,
|
| 66 |
+
"past_index": -1,
|
| 67 |
+
"run_name": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v1-20251231-073918",
|
| 68 |
+
"disable_tqdm": null,
|
| 69 |
+
"remove_unused_columns": true,
|
| 70 |
+
"label_names": null,
|
| 71 |
+
"load_best_model_at_end": false,
|
| 72 |
+
"metric_for_best_model": "loss",
|
| 73 |
+
"greater_is_better": false,
|
| 74 |
+
"ignore_data_skip": false,
|
| 75 |
+
"fsdp": [],
|
| 76 |
+
"fsdp_min_num_params": 0,
|
| 77 |
+
"fsdp_config": null,
|
| 78 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 79 |
+
"accelerator_config": {
|
| 80 |
+
"dispatch_batches": false
|
| 81 |
+
},
|
| 82 |
+
"parallelism_config": null,
|
| 83 |
+
"deepspeed": null,
|
| 84 |
+
"label_smoothing_factor": 0.0,
|
| 85 |
+
"optim": "adamw_torch_fused",
|
| 86 |
+
"optim_args": null,
|
| 87 |
+
"adafactor": false,
|
| 88 |
+
"group_by_length": false,
|
| 89 |
+
"length_column_name": "length",
|
| 90 |
+
"report_to": [
|
| 91 |
+
"tensorboard"
|
| 92 |
+
],
|
| 93 |
+
"project": "huggingface",
|
| 94 |
+
"trackio_space_id": "trackio",
|
| 95 |
+
"ddp_find_unused_parameters": null,
|
| 96 |
+
"ddp_bucket_cap_mb": null,
|
| 97 |
+
"ddp_broadcast_buffers": null,
|
| 98 |
+
"dataloader_pin_memory": true,
|
| 99 |
+
"dataloader_persistent_workers": false,
|
| 100 |
+
"skip_memory_metrics": true,
|
| 101 |
+
"use_legacy_prediction_loop": false,
|
| 102 |
+
"push_to_hub": false,
|
| 103 |
+
"resume_from_checkpoint": null,
|
| 104 |
+
"hub_model_id": null,
|
| 105 |
+
"hub_strategy": "every_save",
|
| 106 |
+
"hub_token": null,
|
| 107 |
+
"hub_private_repo": null,
|
| 108 |
+
"hub_always_push": false,
|
| 109 |
+
"hub_revision": null,
|
| 110 |
+
"gradient_checkpointing": true,
|
| 111 |
+
"gradient_checkpointing_kwargs": "{\"use_reentrant\": false}",
|
| 112 |
+
"include_inputs_for_metrics": false,
|
| 113 |
+
"include_for_metrics": [],
|
| 114 |
+
"eval_do_concat_batches": true,
|
| 115 |
+
"fp16_backend": "auto",
|
| 116 |
+
"push_to_hub_model_id": null,
|
| 117 |
+
"push_to_hub_organization": null,
|
| 118 |
+
"push_to_hub_token": null,
|
| 119 |
+
"mp_parameters": "",
|
| 120 |
+
"auto_find_batch_size": false,
|
| 121 |
+
"full_determinism": false,
|
| 122 |
+
"torchdynamo": null,
|
| 123 |
+
"ray_scope": "last",
|
| 124 |
+
"ddp_timeout": 18000000,
|
| 125 |
+
"torch_compile": false,
|
| 126 |
+
"torch_compile_backend": null,
|
| 127 |
+
"torch_compile_mode": null,
|
| 128 |
+
"include_tokens_per_second": false,
|
| 129 |
+
"include_num_input_tokens_seen": false,
|
| 130 |
+
"neftune_noise_alpha": null,
|
| 131 |
+
"optim_target_modules": null,
|
| 132 |
+
"batch_eval_metrics": false,
|
| 133 |
+
"eval_on_start": false,
|
| 134 |
+
"use_liger_kernel": false,
|
| 135 |
+
"liger_kernel_config": null,
|
| 136 |
+
"eval_use_gather_object": false,
|
| 137 |
+
"average_tokens_across_devices": true,
|
| 138 |
+
"sortish_sampler": false,
|
| 139 |
+
"predict_with_generate": false,
|
| 140 |
+
"generation_max_length": null,
|
| 141 |
+
"generation_num_beams": null,
|
| 142 |
+
"generation_config": null,
|
| 143 |
+
"tuner_backend": "peft",
|
| 144 |
+
"vit_gradient_checkpointing": null,
|
| 145 |
+
"router_aux_loss_coef": 0.0,
|
| 146 |
+
"enable_dft_loss": false,
|
| 147 |
+
"enable_channel_loss": false,
|
| 148 |
+
"check_model": true,
|
| 149 |
+
"acc_strategy": "token",
|
| 150 |
+
"train_dataloader_shuffle": true,
|
| 151 |
+
"max_epochs": null,
|
| 152 |
+
"aligner_lr": null,
|
| 153 |
+
"vit_lr": null,
|
| 154 |
+
"use_logits_to_keep": null,
|
| 155 |
+
"ds3_gather_for_generation": true,
|
| 156 |
+
"resume_only_model": false,
|
| 157 |
+
"optimizer": null,
|
| 158 |
+
"loss_type": null,
|
| 159 |
+
"metric": null,
|
| 160 |
+
"eval_use_evalscope": false,
|
| 161 |
+
"eval_dataset": [],
|
| 162 |
+
"eval_dataset_args": null,
|
| 163 |
+
"eval_limit": null,
|
| 164 |
+
"eval_generation_config": null,
|
| 165 |
+
"extra_eval_args": null,
|
| 166 |
+
"use_flash_ckpt": false,
|
| 167 |
+
"use_ray": false,
|
| 168 |
+
"ray_exp_name": null,
|
| 169 |
+
"device_groups": null,
|
| 170 |
+
"model": "Qwen/Qwen3-4B-Instruct-2507",
|
| 171 |
+
"model_type": "qwen3_nothinking",
|
| 172 |
+
"model_revision": null,
|
| 173 |
+
"task_type": "causal_lm",
|
| 174 |
+
"torch_dtype": "bfloat16",
|
| 175 |
+
"attn_impl": null,
|
| 176 |
+
"new_special_tokens": [],
|
| 177 |
+
"num_labels": null,
|
| 178 |
+
"problem_type": null,
|
| 179 |
+
"rope_scaling": null,
|
| 180 |
+
"device_map": null,
|
| 181 |
+
"max_memory": {},
|
| 182 |
+
"max_model_len": null,
|
| 183 |
+
"local_repo_path": null,
|
| 184 |
+
"init_strategy": null,
|
| 185 |
+
"template": "qwen3_nothinking",
|
| 186 |
+
"system": null,
|
| 187 |
+
"max_length": 2048,
|
| 188 |
+
"truncation_strategy": "delete",
|
| 189 |
+
"max_pixels": null,
|
| 190 |
+
"agent_template": null,
|
| 191 |
+
"norm_bbox": null,
|
| 192 |
+
"use_chat_template": true,
|
| 193 |
+
"padding_side": "right",
|
| 194 |
+
"padding_free": false,
|
| 195 |
+
"loss_scale": "default",
|
| 196 |
+
"sequence_parallel_size": 1,
|
| 197 |
+
"template_backend": "swift",
|
| 198 |
+
"response_prefix": null,
|
| 199 |
+
"enable_thinking": null,
|
| 200 |
+
"add_non_thinking_prefix": true,
|
| 201 |
+
"dataset": [
|
| 202 |
+
"/home/ubuntu/ms-swift/data/evasion_qa27k_msswift.jsonl"
|
| 203 |
+
],
|
| 204 |
+
"val_dataset": [],
|
| 205 |
+
"cached_dataset": [],
|
| 206 |
+
"cached_val_dataset": [],
|
| 207 |
+
"split_dataset_ratio": 0.0,
|
| 208 |
+
"dataset_num_proc": 1,
|
| 209 |
+
"load_from_cache_file": false,
|
| 210 |
+
"dataset_shuffle": true,
|
| 211 |
+
"val_dataset_shuffle": false,
|
| 212 |
+
"streaming": false,
|
| 213 |
+
"interleave_prob": null,
|
| 214 |
+
"stopping_strategy": "first_exhausted",
|
| 215 |
+
"shuffle_buffer_size": 1000,
|
| 216 |
+
"download_mode": "reuse_dataset_if_exists",
|
| 217 |
+
"columns": {},
|
| 218 |
+
"strict": false,
|
| 219 |
+
"model_name": null,
|
| 220 |
+
"model_author": null,
|
| 221 |
+
"custom_dataset_info": [],
|
| 222 |
+
"quant_method": null,
|
| 223 |
+
"quant_bits": null,
|
| 224 |
+
"hqq_axis": null,
|
| 225 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 226 |
+
"bnb_4bit_quant_type": "nf4",
|
| 227 |
+
"bnb_4bit_use_double_quant": true,
|
| 228 |
+
"bnb_4bit_quant_storage": null,
|
| 229 |
+
"max_new_tokens": 64,
|
| 230 |
+
"temperature": 0.0,
|
| 231 |
+
"top_k": null,
|
| 232 |
+
"top_p": null,
|
| 233 |
+
"repetition_penalty": null,
|
| 234 |
+
"num_beams": 1,
|
| 235 |
+
"stream": false,
|
| 236 |
+
"stop_words": [],
|
| 237 |
+
"logprobs": false,
|
| 238 |
+
"top_logprobs": null,
|
| 239 |
+
"structured_outputs_regex": null,
|
| 240 |
+
"ckpt_dir": null,
|
| 241 |
+
"lora_modules": [],
|
| 242 |
+
"train_type": "full",
|
| 243 |
+
"adapters": [],
|
| 244 |
+
"external_plugins": [],
|
| 245 |
+
"model_kwargs": {},
|
| 246 |
+
"load_args": false,
|
| 247 |
+
"load_data_args": false,
|
| 248 |
+
"packing": false,
|
| 249 |
+
"packing_length": null,
|
| 250 |
+
"packing_num_proc": 1,
|
| 251 |
+
"lazy_tokenize": false,
|
| 252 |
+
"custom_register_path": [],
|
| 253 |
+
"use_hf": false,
|
| 254 |
+
"ignore_args_error": false,
|
| 255 |
+
"use_swift_lora": false,
|
| 256 |
+
"freeze_parameters": [],
|
| 257 |
+
"freeze_parameters_regex": null,
|
| 258 |
+
"freeze_parameters_ratio": 0.0,
|
| 259 |
+
"trainable_parameters": [],
|
| 260 |
+
"trainable_parameters_regex": null,
|
| 261 |
+
"freeze_llm": false,
|
| 262 |
+
"freeze_vit": true,
|
| 263 |
+
"freeze_aligner": true,
|
| 264 |
+
"target_modules": [
|
| 265 |
+
"all-linear"
|
| 266 |
+
],
|
| 267 |
+
"target_regex": null,
|
| 268 |
+
"target_parameters": null,
|
| 269 |
+
"modules_to_save": [],
|
| 270 |
+
"lora_rank": 8,
|
| 271 |
+
"lora_alpha": 32,
|
| 272 |
+
"lora_dropout": 0.05,
|
| 273 |
+
"lora_bias": "none",
|
| 274 |
+
"lora_dtype": null,
|
| 275 |
+
"lorap_lr_ratio": null,
|
| 276 |
+
"use_rslora": false,
|
| 277 |
+
"use_dora": false,
|
| 278 |
+
"lora_ga_batch_size": 2,
|
| 279 |
+
"lora_ga_iters": 2,
|
| 280 |
+
"lora_ga_max_length": 1024,
|
| 281 |
+
"lora_ga_direction": "ArB2r",
|
| 282 |
+
"lora_ga_scale": "stable",
|
| 283 |
+
"lora_ga_stable_gamma": 16,
|
| 284 |
+
"init_weights": true,
|
| 285 |
+
"fourier_n_frequency": 2000,
|
| 286 |
+
"fourier_scaling": 300.0,
|
| 287 |
+
"boft_block_size": 4,
|
| 288 |
+
"boft_block_num": 0,
|
| 289 |
+
"boft_n_butterfly_factor": 1,
|
| 290 |
+
"boft_dropout": 0.0,
|
| 291 |
+
"vera_rank": 256,
|
| 292 |
+
"vera_projection_prng_key": 0,
|
| 293 |
+
"vera_dropout": 0.0,
|
| 294 |
+
"vera_d_initial": 0.1,
|
| 295 |
+
"adapter_act": "gelu",
|
| 296 |
+
"adapter_length": 128,
|
| 297 |
+
"use_galore": false,
|
| 298 |
+
"galore_target_modules": null,
|
| 299 |
+
"galore_rank": 128,
|
| 300 |
+
"galore_update_proj_gap": 50,
|
| 301 |
+
"galore_scale": 1.0,
|
| 302 |
+
"galore_proj_type": "std",
|
| 303 |
+
"galore_optim_per_parameter": false,
|
| 304 |
+
"galore_with_embedding": false,
|
| 305 |
+
"galore_quantization": false,
|
| 306 |
+
"galore_proj_quant": false,
|
| 307 |
+
"galore_proj_bits": 4,
|
| 308 |
+
"galore_proj_group_size": 256,
|
| 309 |
+
"galore_cos_threshold": 0.4,
|
| 310 |
+
"galore_gamma_proj": 2,
|
| 311 |
+
"galore_queue_size": 5,
|
| 312 |
+
"adalora_target_r": 8,
|
| 313 |
+
"adalora_init_r": 12,
|
| 314 |
+
"adalora_tinit": 0,
|
| 315 |
+
"adalora_tfinal": 0,
|
| 316 |
+
"adalora_deltaT": 1,
|
| 317 |
+
"adalora_beta1": 0.85,
|
| 318 |
+
"adalora_beta2": 0.85,
|
| 319 |
+
"adalora_orth_reg_weight": 0.5,
|
| 320 |
+
"llamapro_num_new_blocks": 4,
|
| 321 |
+
"llamapro_num_groups": null,
|
| 322 |
+
"lisa_activated_layers": 0,
|
| 323 |
+
"lisa_step_interval": 20,
|
| 324 |
+
"reft_layer_key": null,
|
| 325 |
+
"reft_layers": null,
|
| 326 |
+
"reft_rank": 4,
|
| 327 |
+
"reft_intervention_type": "LoreftIntervention",
|
| 328 |
+
"reft_args": null,
|
| 329 |
+
"swanlab_token": null,
|
| 330 |
+
"swanlab_project": "ms-swift",
|
| 331 |
+
"swanlab_workspace": null,
|
| 332 |
+
"swanlab_exp_name": null,
|
| 333 |
+
"swanlab_notification_method": null,
|
| 334 |
+
"swanlab_webhook_url": null,
|
| 335 |
+
"swanlab_secret": null,
|
| 336 |
+
"swanlab_mode": "cloud",
|
| 337 |
+
"add_version": true,
|
| 338 |
+
"create_checkpoint_symlink": false,
|
| 339 |
+
"zero_hpz_partition_size": null,
|
| 340 |
+
"deepspeed_autotp_size": null,
|
| 341 |
+
"early_stop_interval": null,
|
| 342 |
+
"rank": 0,
|
| 343 |
+
"global_world_size": 2,
|
| 344 |
+
"local_world_size": 2,
|
| 345 |
+
"model_suffix": "Qwen3-4B-Instruct-2507",
|
| 346 |
+
"model_info": "ModelInfo(model_type='qwen3_nothinking', model_dir='/home/ubuntu/.cache/modelscope/hub/models/Qwen/Qwen3-4B-Instruct-2507', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
|
| 347 |
+
"model_meta": "ModelMeta(model_type='qwen3_nothinking', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-235B-A22B-Instruct-2507-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507', hf_model_id='Qwen/Qwen3-4B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_nothinking', get_function=<function get_model_tokenizer_with_flash_attn at 0x70c718bef490>, model_arch=None, architectures=['Qwen3MoeForCausalLM', 'Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])",
|
| 348 |
+
"model_dir": "/home/ubuntu/.cache/modelscope/hub/models/Qwen/Qwen3-4B-Instruct-2507",
|
| 349 |
+
"_val_dataset_exists": [],
|
| 350 |
+
"hub": "<class 'swift.hub.hub.MSHub'>",
|
| 351 |
+
"evaluation_strategy": "steps",
|
| 352 |
+
"training_args": "Seq2SeqTrainingArguments(output_dir='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v1-20251231-073918', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=8, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.03, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v1-20251231-073918/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=500, save_total_limit=3, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=500.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v1-20251231-073918', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs={'use_reentrant': False}, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)"
|
| 353 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# 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>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\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" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- for message in messages %}
|
| 18 |
+
{%- if message.content is string %}
|
| 19 |
+
{%- set content = message.content %}
|
| 20 |
+
{%- else %}
|
| 21 |
+
{%- set content = '' %}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
+
{%- elif message.role == "assistant" %}
|
| 26 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 27 |
+
{%- if message.tool_calls %}
|
| 28 |
+
{%- for tool_call in message.tool_calls %}
|
| 29 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 30 |
+
{{- '\n' }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{%- if tool_call.function %}
|
| 33 |
+
{%- set tool_call = tool_call.function %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 36 |
+
{{- tool_call.name }}
|
| 37 |
+
{{- '", "arguments": ' }}
|
| 38 |
+
{%- if tool_call.arguments is string %}
|
| 39 |
+
{{- tool_call.arguments }}
|
| 40 |
+
{%- else %}
|
| 41 |
+
{{- tool_call.arguments | tojson }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{{- '}\n</tool_call>' }}
|
| 44 |
+
{%- endfor %}
|
| 45 |
+
{%- endif %}
|
| 46 |
+
{{- '<|im_end|>\n' }}
|
| 47 |
+
{%- elif message.role == "tool" %}
|
| 48 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 49 |
+
{{- '<|im_start|>user' }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{{- '\n<tool_response>\n' }}
|
| 52 |
+
{{- content }}
|
| 53 |
+
{{- '\n</tool_response>' }}
|
| 54 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 55 |
+
{{- '<|im_end|>\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{%- endfor %}
|
| 59 |
+
{%- if add_generation_prompt %}
|
| 60 |
+
{{- '<|im_start|>assistant\n' }}
|
| 61 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2560,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 9728,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 262144,
|
| 53 |
+
"max_window_layers": 36,
|
| 54 |
+
"model_type": "qwen3",
|
| 55 |
+
"num_attention_heads": 32,
|
| 56 |
+
"num_hidden_layers": 36,
|
| 57 |
+
"num_key_value_heads": 8,
|
| 58 |
+
"pad_token_id": 151643,
|
| 59 |
+
"rms_norm_eps": 1e-06,
|
| 60 |
+
"rope_scaling": null,
|
| 61 |
+
"rope_theta": 5000000,
|
| 62 |
+
"sliding_window": null,
|
| 63 |
+
"tie_word_embeddings": true,
|
| 64 |
+
"transformers_version": "4.57.3",
|
| 65 |
+
"use_cache": false,
|
| 66 |
+
"use_sliding_window": false,
|
| 67 |
+
"vocab_size": 151936
|
| 68 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.3"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85c6ac7361f9fa1628b95f7a5462511d9a711d38adef3ab0bfc5de92ad4d0c27
|
| 3 |
+
size 4967215360
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e552b551f490e5c0fd54c7d0ef914e512c79e7e30481370c948678352673b03c
|
| 3 |
+
size 3077766632
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,406 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 4022468096,
|
| 4 |
+
"total_size": 8044936192
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 405 |
+
}
|
| 406 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39ac89e56fec4dacd012d8108324c37dc5238afe141f68f6c8dea7b7222bbe6e
|
| 3 |
+
size 16090225449
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95e5fc2074c0df31522a514f862c86cb00d71c946a7f15cc9ec0e53a69fb28a7
|
| 3 |
+
size 14917
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e7153eae67b6c9232a41bc996a2bf5b83229b8c7230d61911ac0fd40e64154e
|
| 3 |
+
size 14917
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cebc4fd0a8a189aa9b371f3e058580335b13df782675613f6af7a02d0799151b
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 1010000,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1394 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500.0,
|
| 7 |
+
"global_step": 1690,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0011841326228537595,
|
| 14 |
+
"grad_norm": 219.0,
|
| 15 |
+
"learning_rate": 3.921568627450981e-07,
|
| 16 |
+
"loss": 1.2013294696807861,
|
| 17 |
+
"step": 1,
|
| 18 |
+
"token_acc": 0.8954758190327613
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.011841326228537596,
|
| 22 |
+
"grad_norm": 50.0,
|
| 23 |
+
"learning_rate": 3.92156862745098e-06,
|
| 24 |
+
"loss": 0.8140333493550619,
|
| 25 |
+
"step": 10,
|
| 26 |
+
"token_acc": 0.9158278375564041
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.023682652457075192,
|
| 30 |
+
"grad_norm": 15.0625,
|
| 31 |
+
"learning_rate": 7.84313725490196e-06,
|
| 32 |
+
"loss": 0.25884711742401123,
|
| 33 |
+
"step": 20,
|
| 34 |
+
"token_acc": 0.9479379018347185
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.035523978685612786,
|
| 38 |
+
"grad_norm": 4.78125,
|
| 39 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 40 |
+
"loss": 0.13083882331848146,
|
| 41 |
+
"step": 30,
|
| 42 |
+
"token_acc": 0.9458783043954325
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.047365304914150384,
|
| 46 |
+
"grad_norm": 4.65625,
|
| 47 |
+
"learning_rate": 1.568627450980392e-05,
|
| 48 |
+
"loss": 0.11950666904449463,
|
| 49 |
+
"step": 40,
|
| 50 |
+
"token_acc": 0.953747256193164
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.05920663114268798,
|
| 54 |
+
"grad_norm": 3.921875,
|
| 55 |
+
"learning_rate": 1.9607843137254903e-05,
|
| 56 |
+
"loss": 0.10617152452468873,
|
| 57 |
+
"step": 50,
|
| 58 |
+
"token_acc": 0.9590588235294117
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.07104795737122557,
|
| 62 |
+
"grad_norm": 2.25,
|
| 63 |
+
"learning_rate": 1.9998512057697314e-05,
|
| 64 |
+
"loss": 0.10807085037231445,
|
| 65 |
+
"step": 60,
|
| 66 |
+
"token_acc": 0.9589895524715422
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.08288928359976318,
|
| 70 |
+
"grad_norm": 2.375,
|
| 71 |
+
"learning_rate": 1.9993369121919753e-05,
|
| 72 |
+
"loss": 0.10784111022949219,
|
| 73 |
+
"step": 70,
|
| 74 |
+
"token_acc": 0.9572008747266479
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.09473060982830077,
|
| 78 |
+
"grad_norm": 2.9375,
|
| 79 |
+
"learning_rate": 1.998455471202776e-05,
|
| 80 |
+
"loss": 0.10691288709640503,
|
| 81 |
+
"step": 80,
|
| 82 |
+
"token_acc": 0.9570600219401347
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.10657193605683836,
|
| 86 |
+
"grad_norm": 1.578125,
|
| 87 |
+
"learning_rate": 1.9972072066356417e-05,
|
| 88 |
+
"loss": 0.11526317596435547,
|
| 89 |
+
"step": 90,
|
| 90 |
+
"token_acc": 0.9496324104489285
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.11841326228537596,
|
| 94 |
+
"grad_norm": 3.09375,
|
| 95 |
+
"learning_rate": 1.995592577091769e-05,
|
| 96 |
+
"loss": 0.10205183029174805,
|
| 97 |
+
"step": 100,
|
| 98 |
+
"token_acc": 0.9572502348888193
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.13025458851391356,
|
| 102 |
+
"grad_norm": 3.1875,
|
| 103 |
+
"learning_rate": 1.9936121757715598e-05,
|
| 104 |
+
"loss": 0.10735645294189453,
|
| 105 |
+
"step": 110,
|
| 106 |
+
"token_acc": 0.9611528822055138
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.14209591474245115,
|
| 110 |
+
"grad_norm": 1.796875,
|
| 111 |
+
"learning_rate": 1.991266730256683e-05,
|
| 112 |
+
"loss": 0.10336060523986816,
|
| 113 |
+
"step": 120,
|
| 114 |
+
"token_acc": 0.9576736165543188
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.15393724097098876,
|
| 118 |
+
"grad_norm": 2.078125,
|
| 119 |
+
"learning_rate": 1.9885571022427676e-05,
|
| 120 |
+
"loss": 0.09967223405838013,
|
| 121 |
+
"step": 130,
|
| 122 |
+
"token_acc": 0.959868317918169
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.16577856719952636,
|
| 126 |
+
"grad_norm": 1.140625,
|
| 127 |
+
"learning_rate": 1.9854842872228247e-05,
|
| 128 |
+
"loss": 0.09939006567001343,
|
| 129 |
+
"step": 140,
|
| 130 |
+
"token_acc": 0.9603572547790661
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.17761989342806395,
|
| 134 |
+
"grad_norm": 1.2890625,
|
| 135 |
+
"learning_rate": 1.98204941412151e-05,
|
| 136 |
+
"loss": 0.0902411937713623,
|
| 137 |
+
"step": 150,
|
| 138 |
+
"token_acc": 0.9632122730118973
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.18946121965660154,
|
| 142 |
+
"grad_norm": 2.984375,
|
| 143 |
+
"learning_rate": 1.9782537448803707e-05,
|
| 144 |
+
"loss": 0.10655044317245484,
|
| 145 |
+
"step": 160,
|
| 146 |
+
"token_acc": 0.9559263340154258
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.20130254588513913,
|
| 150 |
+
"grad_norm": 2.65625,
|
| 151 |
+
"learning_rate": 1.9740986739942146e-05,
|
| 152 |
+
"loss": 0.10265426635742188,
|
| 153 |
+
"step": 170,
|
| 154 |
+
"token_acc": 0.9573600877880546
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.21314387211367672,
|
| 158 |
+
"grad_norm": 1.3046875,
|
| 159 |
+
"learning_rate": 1.9695857279987897e-05,
|
| 160 |
+
"loss": 0.09765652418136597,
|
| 161 |
+
"step": 180,
|
| 162 |
+
"token_acc": 0.9597620165962111
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.22498519834221434,
|
| 166 |
+
"grad_norm": 1.4140625,
|
| 167 |
+
"learning_rate": 1.9647165649099465e-05,
|
| 168 |
+
"loss": 0.09450024366378784,
|
| 169 |
+
"step": 190,
|
| 170 |
+
"token_acc": 0.963653454488485
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.23682652457075193,
|
| 174 |
+
"grad_norm": 1.3046875,
|
| 175 |
+
"learning_rate": 1.9594929736144978e-05,
|
| 176 |
+
"loss": 0.10988011360168456,
|
| 177 |
+
"step": 200,
|
| 178 |
+
"token_acc": 0.9540840231141652
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.24866785079928952,
|
| 182 |
+
"grad_norm": 1.828125,
|
| 183 |
+
"learning_rate": 1.9539168732129977e-05,
|
| 184 |
+
"loss": 0.09797856211662292,
|
| 185 |
+
"step": 210,
|
| 186 |
+
"token_acc": 0.9617614793919448
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.2605091770278271,
|
| 190 |
+
"grad_norm": 4.15625,
|
| 191 |
+
"learning_rate": 1.9479903123146835e-05,
|
| 192 |
+
"loss": 0.09065916538238525,
|
| 193 |
+
"step": 220,
|
| 194 |
+
"token_acc": 0.9650382394256282
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.27235050325636473,
|
| 198 |
+
"grad_norm": 1.9765625,
|
| 199 |
+
"learning_rate": 1.9417154682848314e-05,
|
| 200 |
+
"loss": 0.10036060810089112,
|
| 201 |
+
"step": 230,
|
| 202 |
+
"token_acc": 0.961611076148521
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.2841918294849023,
|
| 206 |
+
"grad_norm": 2.234375,
|
| 207 |
+
"learning_rate": 1.935094646444815e-05,
|
| 208 |
+
"loss": 0.09578206539154052,
|
| 209 |
+
"step": 240,
|
| 210 |
+
"token_acc": 0.9624119028974158
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.2960331557134399,
|
| 214 |
+
"grad_norm": 2.171875,
|
| 215 |
+
"learning_rate": 1.928130279225149e-05,
|
| 216 |
+
"loss": 0.09263083934783936,
|
| 217 |
+
"step": 250,
|
| 218 |
+
"token_acc": 0.963653454488485
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.30787448194197753,
|
| 222 |
+
"grad_norm": 1.6640625,
|
| 223 |
+
"learning_rate": 1.920824925271838e-05,
|
| 224 |
+
"loss": 0.09710139036178589,
|
| 225 |
+
"step": 260,
|
| 226 |
+
"token_acc": 0.9595754643358826
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3197158081705151,
|
| 230 |
+
"grad_norm": 3.40625,
|
| 231 |
+
"learning_rate": 1.9131812685063512e-05,
|
| 232 |
+
"loss": 0.10172030925750733,
|
| 233 |
+
"step": 270,
|
| 234 |
+
"token_acc": 0.957680250783699
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.3315571343990527,
|
| 238 |
+
"grad_norm": 1.9609375,
|
| 239 |
+
"learning_rate": 1.9052021171395742e-05,
|
| 240 |
+
"loss": 0.10712752342224122,
|
| 241 |
+
"step": 280,
|
| 242 |
+
"token_acc": 0.9577840552416823
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.3433984606275903,
|
| 246 |
+
"grad_norm": 1.0703125,
|
| 247 |
+
"learning_rate": 1.896890402640098e-05,
|
| 248 |
+
"loss": 0.09744402766227722,
|
| 249 |
+
"step": 290,
|
| 250 |
+
"token_acc": 0.9596054485674025
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.3552397868561279,
|
| 254 |
+
"grad_norm": 2.359375,
|
| 255 |
+
"learning_rate": 1.8882491786572226e-05,
|
| 256 |
+
"loss": 0.09446089267730713,
|
| 257 |
+
"step": 300,
|
| 258 |
+
"token_acc": 0.9636648394675019
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.36708111308466546,
|
| 262 |
+
"grad_norm": 1.828125,
|
| 263 |
+
"learning_rate": 1.8792816198990768e-05,
|
| 264 |
+
"loss": 0.09970860481262207,
|
| 265 |
+
"step": 310,
|
| 266 |
+
"token_acc": 0.9583398590446358
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.3789224393132031,
|
| 270 |
+
"grad_norm": 1.5390625,
|
| 271 |
+
"learning_rate": 1.8699910209662536e-05,
|
| 272 |
+
"loss": 0.09670261144638062,
|
| 273 |
+
"step": 320,
|
| 274 |
+
"token_acc": 0.9606150949317432
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.3907637655417407,
|
| 278 |
+
"grad_norm": 2.828125,
|
| 279 |
+
"learning_rate": 1.8603807951414093e-05,
|
| 280 |
+
"loss": 0.09714120626449585,
|
| 281 |
+
"step": 330,
|
| 282 |
+
"token_acc": 0.9602938877598874
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.40260509177027826,
|
| 286 |
+
"grad_norm": 1.890625,
|
| 287 |
+
"learning_rate": 1.850454473135249e-05,
|
| 288 |
+
"loss": 0.09373531341552735,
|
| 289 |
+
"step": 340,
|
| 290 |
+
"token_acc": 0.9619166536600593
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.4144464179988159,
|
| 294 |
+
"grad_norm": 2.25,
|
| 295 |
+
"learning_rate": 1.8402157017893795e-05,
|
| 296 |
+
"loss": 0.09355499744415283,
|
| 297 |
+
"step": 350,
|
| 298 |
+
"token_acc": 0.9667919799498746
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.42628774422735344,
|
| 302 |
+
"grad_norm": 0.8828125,
|
| 303 |
+
"learning_rate": 1.829668242736489e-05,
|
| 304 |
+
"loss": 0.08944010734558105,
|
| 305 |
+
"step": 360,
|
| 306 |
+
"token_acc": 0.9638327853452325
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.43812907045589106,
|
| 310 |
+
"grad_norm": 1.2265625,
|
| 311 |
+
"learning_rate": 1.8188159710183595e-05,
|
| 312 |
+
"loss": 0.09383893013000488,
|
| 313 |
+
"step": 370,
|
| 314 |
+
"token_acc": 0.9663642052565707
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.4499703966844287,
|
| 318 |
+
"grad_norm": 2.953125,
|
| 319 |
+
"learning_rate": 1.807662873662209e-05,
|
| 320 |
+
"loss": 0.09152829647064209,
|
| 321 |
+
"step": 380,
|
| 322 |
+
"token_acc": 0.9641403069213905
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.46181172291296624,
|
| 326 |
+
"grad_norm": 1.6953125,
|
| 327 |
+
"learning_rate": 1.796213048215896e-05,
|
| 328 |
+
"loss": 0.10058202743530273,
|
| 329 |
+
"step": 390,
|
| 330 |
+
"token_acc": 0.961363279409455
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.47365304914150386,
|
| 334 |
+
"grad_norm": 1.7421875,
|
| 335 |
+
"learning_rate": 1.7844707012425155e-05,
|
| 336 |
+
"loss": 0.0878696620464325,
|
| 337 |
+
"step": 400,
|
| 338 |
+
"token_acc": 0.9662956576265872
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.4854943753700414,
|
| 342 |
+
"grad_norm": 1.3828125,
|
| 343 |
+
"learning_rate": 1.772440146774945e-05,
|
| 344 |
+
"loss": 0.09355847835540772,
|
| 345 |
+
"step": 410,
|
| 346 |
+
"token_acc": 0.9618928627205997
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.49733570159857904,
|
| 350 |
+
"grad_norm": 1.3828125,
|
| 351 |
+
"learning_rate": 1.7601258047309096e-05,
|
| 352 |
+
"loss": 0.09457954168319702,
|
| 353 |
+
"step": 420,
|
| 354 |
+
"token_acc": 0.9631430363864492
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.5091770278271166,
|
| 358 |
+
"grad_norm": 1.0234375,
|
| 359 |
+
"learning_rate": 1.7475321992891417e-05,
|
| 360 |
+
"loss": 0.09055821895599366,
|
| 361 |
+
"step": 430,
|
| 362 |
+
"token_acc": 0.9654251139399654
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.5210183540556542,
|
| 366 |
+
"grad_norm": 1.9921875,
|
| 367 |
+
"learning_rate": 1.73466395722724e-05,
|
| 368 |
+
"loss": 0.09674708843231201,
|
| 369 |
+
"step": 440,
|
| 370 |
+
"token_acc": 0.9611041405269761
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.5328596802841918,
|
| 374 |
+
"grad_norm": 1.671875,
|
| 375 |
+
"learning_rate": 1.7215258062218323e-05,
|
| 376 |
+
"loss": 0.10127317905426025,
|
| 377 |
+
"step": 450,
|
| 378 |
+
"token_acc": 0.9612791973663584
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.5447010065127295,
|
| 382 |
+
"grad_norm": 2.28125,
|
| 383 |
+
"learning_rate": 1.708122573111669e-05,
|
| 384 |
+
"loss": 0.08792918920516968,
|
| 385 |
+
"step": 460,
|
| 386 |
+
"token_acc": 0.9650962591954922
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.5565423327412671,
|
| 390 |
+
"grad_norm": 2.171875,
|
| 391 |
+
"learning_rate": 1.6944591821242867e-05,
|
| 392 |
+
"loss": 0.09947954416275025,
|
| 393 |
+
"step": 470,
|
| 394 |
+
"token_acc": 0.9605057758351545
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.5683836589698046,
|
| 398 |
+
"grad_norm": 1.46875,
|
| 399 |
+
"learning_rate": 1.680540653066891e-05,
|
| 400 |
+
"loss": 0.0963528037071228,
|
| 401 |
+
"step": 480,
|
| 402 |
+
"token_acc": 0.9614842649131048
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.5802249851983422,
|
| 406 |
+
"grad_norm": 1.1015625,
|
| 407 |
+
"learning_rate": 1.6663720994821246e-05,
|
| 408 |
+
"loss": 0.0961789608001709,
|
| 409 |
+
"step": 490,
|
| 410 |
+
"token_acc": 0.9619599248591109
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.5920663114268798,
|
| 414 |
+
"grad_norm": 2.109375,
|
| 415 |
+
"learning_rate": 1.651958726769396e-05,
|
| 416 |
+
"loss": 0.090640389919281,
|
| 417 |
+
"step": 500,
|
| 418 |
+
"token_acc": 0.963166144200627
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.6039076376554174,
|
| 422 |
+
"grad_norm": 0.9140625,
|
| 423 |
+
"learning_rate": 1.6373058302724655e-05,
|
| 424 |
+
"loss": 0.08862148523330689,
|
| 425 |
+
"step": 510,
|
| 426 |
+
"token_acc": 0.9642521166509878
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.6157489638839551,
|
| 430 |
+
"grad_norm": 1.7421875,
|
| 431 |
+
"learning_rate": 1.6224187933339808e-05,
|
| 432 |
+
"loss": 0.08748204708099365,
|
| 433 |
+
"step": 520,
|
| 434 |
+
"token_acc": 0.9620749098887321
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.6275902901124926,
|
| 438 |
+
"grad_norm": 1.5546875,
|
| 439 |
+
"learning_rate": 1.6073030853176862e-05,
|
| 440 |
+
"loss": 0.09252775907516479,
|
| 441 |
+
"step": 530,
|
| 442 |
+
"token_acc": 0.9616528408201597
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.6394316163410302,
|
| 446 |
+
"grad_norm": 1.296875,
|
| 447 |
+
"learning_rate": 1.5919642595990275e-05,
|
| 448 |
+
"loss": 0.08904544115066529,
|
| 449 |
+
"step": 540,
|
| 450 |
+
"token_acc": 0.9668594653743943
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.6512729425695678,
|
| 454 |
+
"grad_norm": 1.8203125,
|
| 455 |
+
"learning_rate": 1.5764079515248922e-05,
|
| 456 |
+
"loss": 0.08241082429885864,
|
| 457 |
+
"step": 550,
|
| 458 |
+
"token_acc": 0.9658628249295333
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.6631142687981054,
|
| 462 |
+
"grad_norm": 1.6015625,
|
| 463 |
+
"learning_rate": 1.5606398763432318e-05,
|
| 464 |
+
"loss": 0.0839945912361145,
|
| 465 |
+
"step": 560,
|
| 466 |
+
"token_acc": 0.9672131147540983
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.6749555950266429,
|
| 470 |
+
"grad_norm": 1.5,
|
| 471 |
+
"learning_rate": 1.5446658271033336e-05,
|
| 472 |
+
"loss": 0.09018040895462036,
|
| 473 |
+
"step": 570,
|
| 474 |
+
"token_acc": 0.9658574784651527
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.6867969212551805,
|
| 478 |
+
"grad_norm": 1.40625,
|
| 479 |
+
"learning_rate": 1.528491672527504e-05,
|
| 480 |
+
"loss": 0.08107317686080932,
|
| 481 |
+
"step": 580,
|
| 482 |
+
"token_acc": 0.9681967726774244
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.6986382474837182,
|
| 486 |
+
"grad_norm": 1.453125,
|
| 487 |
+
"learning_rate": 1.512123354854955e-05,
|
| 488 |
+
"loss": 0.08852046132087707,
|
| 489 |
+
"step": 590,
|
| 490 |
+
"token_acc": 0.9663957486714598
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.7104795737122558,
|
| 494 |
+
"grad_norm": 1.1875,
|
| 495 |
+
"learning_rate": 1.4955668876586763e-05,
|
| 496 |
+
"loss": 0.07870029807090759,
|
| 497 |
+
"step": 600,
|
| 498 |
+
"token_acc": 0.9683862849952816
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.7223208999407934,
|
| 502 |
+
"grad_norm": 1.4609375,
|
| 503 |
+
"learning_rate": 1.4788283536361036e-05,
|
| 504 |
+
"loss": 0.0841621994972229,
|
| 505 |
+
"step": 610,
|
| 506 |
+
"token_acc": 0.9685781618224666
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.7341622261693309,
|
| 510 |
+
"grad_norm": 1.6171875,
|
| 511 |
+
"learning_rate": 1.4619139023743916e-05,
|
| 512 |
+
"loss": 0.08564043045043945,
|
| 513 |
+
"step": 620,
|
| 514 |
+
"token_acc": 0.9654417513682565
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.7460035523978685,
|
| 518 |
+
"grad_norm": 1.203125,
|
| 519 |
+
"learning_rate": 1.4448297480911086e-05,
|
| 520 |
+
"loss": 0.09037463665008545,
|
| 521 |
+
"step": 630,
|
| 522 |
+
"token_acc": 0.963363081258807
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.7578448786264061,
|
| 526 |
+
"grad_norm": 0.9609375,
|
| 527 |
+
"learning_rate": 1.4275821673511903e-05,
|
| 528 |
+
"loss": 0.09671027660369873,
|
| 529 |
+
"step": 640,
|
| 530 |
+
"token_acc": 0.959305055564251
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.7696862048549438,
|
| 534 |
+
"grad_norm": 1.5078125,
|
| 535 |
+
"learning_rate": 1.4101774967609854e-05,
|
| 536 |
+
"loss": 0.09160791039466858,
|
| 537 |
+
"step": 650,
|
| 538 |
+
"token_acc": 0.9654741446648961
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.7815275310834814,
|
| 542 |
+
"grad_norm": 1.421875,
|
| 543 |
+
"learning_rate": 1.392622130640243e-05,
|
| 544 |
+
"loss": 0.095394766330719,
|
| 545 |
+
"step": 660,
|
| 546 |
+
"token_acc": 0.9619956208945887
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.7933688573120189,
|
| 550 |
+
"grad_norm": 1.78125,
|
| 551 |
+
"learning_rate": 1.3749225186728991e-05,
|
| 552 |
+
"loss": 0.08577767610549927,
|
| 553 |
+
"step": 670,
|
| 554 |
+
"token_acc": 0.966750313676286
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.8052101835405565,
|
| 558 |
+
"grad_norm": 2.0625,
|
| 559 |
+
"learning_rate": 1.357085163537517e-05,
|
| 560 |
+
"loss": 0.09209753274917602,
|
| 561 |
+
"step": 680,
|
| 562 |
+
"token_acc": 0.9620608899297424
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.8170515097690941,
|
| 566 |
+
"grad_norm": 2.390625,
|
| 567 |
+
"learning_rate": 1.3391166185182651e-05,
|
| 568 |
+
"loss": 0.0821334183216095,
|
| 569 |
+
"step": 690,
|
| 570 |
+
"token_acc": 0.9690383111806099
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.8288928359976317,
|
| 574 |
+
"grad_norm": 1.2109375,
|
| 575 |
+
"learning_rate": 1.3210234850972966e-05,
|
| 576 |
+
"loss": 0.09119898080825806,
|
| 577 |
+
"step": 700,
|
| 578 |
+
"token_acc": 0.9637817497648166
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.8407341622261694,
|
| 582 |
+
"grad_norm": 1.8671875,
|
| 583 |
+
"learning_rate": 1.3028124105294255e-05,
|
| 584 |
+
"loss": 0.0862145483493805,
|
| 585 |
+
"step": 710,
|
| 586 |
+
"token_acc": 0.9672259683236631
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.8525754884547069,
|
| 590 |
+
"grad_norm": 1.34375,
|
| 591 |
+
"learning_rate": 1.2844900853999847e-05,
|
| 592 |
+
"loss": 0.08162487745285034,
|
| 593 |
+
"step": 720,
|
| 594 |
+
"token_acc": 0.9676405906377631
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.8644168146832445,
|
| 598 |
+
"grad_norm": 1.7890625,
|
| 599 |
+
"learning_rate": 1.2660632411667648e-05,
|
| 600 |
+
"loss": 0.08193669319152833,
|
| 601 |
+
"step": 730,
|
| 602 |
+
"token_acc": 0.9653278945716975
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.8762581409117821,
|
| 606 |
+
"grad_norm": 1.6015625,
|
| 607 |
+
"learning_rate": 1.2475386476869364e-05,
|
| 608 |
+
"loss": 0.09078997969627381,
|
| 609 |
+
"step": 740,
|
| 610 |
+
"token_acc": 0.9639045825486503
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.8880994671403197,
|
| 614 |
+
"grad_norm": 1.671875,
|
| 615 |
+
"learning_rate": 1.2289231107298672e-05,
|
| 616 |
+
"loss": 0.09944761395454407,
|
| 617 |
+
"step": 750,
|
| 618 |
+
"token_acc": 0.9596546310832025
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.8999407933688574,
|
| 622 |
+
"grad_norm": 1.1171875,
|
| 623 |
+
"learning_rate": 1.2102234694767401e-05,
|
| 624 |
+
"loss": 0.0917394757270813,
|
| 625 |
+
"step": 760,
|
| 626 |
+
"token_acc": 0.9615505335844319
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.9117821195973949,
|
| 630 |
+
"grad_norm": 1.609375,
|
| 631 |
+
"learning_rate": 1.1914465940079036e-05,
|
| 632 |
+
"loss": 0.08656581044197083,
|
| 633 |
+
"step": 770,
|
| 634 |
+
"token_acc": 0.9671951028096061
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.9236234458259325,
|
| 638 |
+
"grad_norm": 1.28125,
|
| 639 |
+
"learning_rate": 1.1725993827788625e-05,
|
| 640 |
+
"loss": 0.08798307180404663,
|
| 641 |
+
"step": 780,
|
| 642 |
+
"token_acc": 0.9632065132299984
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.9354647720544701,
|
| 646 |
+
"grad_norm": 1.4765625,
|
| 647 |
+
"learning_rate": 1.1536887600858487e-05,
|
| 648 |
+
"loss": 0.08726394176483154,
|
| 649 |
+
"step": 790,
|
| 650 |
+
"token_acc": 0.9665934755332497
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.9473060982830077,
|
| 654 |
+
"grad_norm": 0.89453125,
|
| 655 |
+
"learning_rate": 1.134721673521897e-05,
|
| 656 |
+
"loss": 0.0808544933795929,
|
| 657 |
+
"step": 800,
|
| 658 |
+
"token_acc": 0.9646211646837821
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.9591474245115453,
|
| 662 |
+
"grad_norm": 1.3671875,
|
| 663 |
+
"learning_rate": 1.1157050914243614e-05,
|
| 664 |
+
"loss": 0.08560880422592163,
|
| 665 |
+
"step": 810,
|
| 666 |
+
"token_acc": 0.9667189952904238
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.9709887507400828,
|
| 670 |
+
"grad_norm": 1.3359375,
|
| 671 |
+
"learning_rate": 1.0966460003148115e-05,
|
| 672 |
+
"loss": 0.0828078031539917,
|
| 673 |
+
"step": 820,
|
| 674 |
+
"token_acc": 0.9668499607227022
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.9828300769686205,
|
| 678 |
+
"grad_norm": 1.921875,
|
| 679 |
+
"learning_rate": 1.0775514023322444e-05,
|
| 680 |
+
"loss": 0.09345529675483703,
|
| 681 |
+
"step": 830,
|
| 682 |
+
"token_acc": 0.9608886107634543
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.9946714031971581,
|
| 686 |
+
"grad_norm": 1.2578125,
|
| 687 |
+
"learning_rate": 1.058428312660566e-05,
|
| 688 |
+
"loss": 0.08514059782028198,
|
| 689 |
+
"step": 840,
|
| 690 |
+
"token_acc": 0.9657169693174703
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.0059206631142688,
|
| 694 |
+
"grad_norm": 1.015625,
|
| 695 |
+
"learning_rate": 1.0392837569512715e-05,
|
| 696 |
+
"loss": 0.08234425187110901,
|
| 697 |
+
"step": 850,
|
| 698 |
+
"token_acc": 0.9645318540931249
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.0177619893428065,
|
| 702 |
+
"grad_norm": 1.8359375,
|
| 703 |
+
"learning_rate": 1.020124768742286e-05,
|
| 704 |
+
"loss": 0.07545605897903443,
|
| 705 |
+
"step": 860,
|
| 706 |
+
"token_acc": 0.9709147771696638
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.029603315571344,
|
| 710 |
+
"grad_norm": 1.1640625,
|
| 711 |
+
"learning_rate": 1.0009583868739053e-05,
|
| 712 |
+
"loss": 0.07274842262268066,
|
| 713 |
+
"step": 870,
|
| 714 |
+
"token_acc": 0.9721873035826524
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.0414446417998815,
|
| 718 |
+
"grad_norm": 1.3359375,
|
| 719 |
+
"learning_rate": 9.817916529027898e-06,
|
| 720 |
+
"loss": 0.07491129636764526,
|
| 721 |
+
"step": 880,
|
| 722 |
+
"token_acc": 0.9713480507280413
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 1.0532859680284192,
|
| 726 |
+
"grad_norm": 1.15625,
|
| 727 |
+
"learning_rate": 9.626316085149588e-06,
|
| 728 |
+
"loss": 0.07744649052619934,
|
| 729 |
+
"step": 890,
|
| 730 |
+
"token_acc": 0.9709102283390679
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.0651272942569567,
|
| 734 |
+
"grad_norm": 1.1953125,
|
| 735 |
+
"learning_rate": 9.43485292938739e-06,
|
| 736 |
+
"loss": 0.07794994711875916,
|
| 737 |
+
"step": 900,
|
| 738 |
+
"token_acc": 0.970647931303669
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.0769686204854945,
|
| 742 |
+
"grad_norm": 1.0234375,
|
| 743 |
+
"learning_rate": 9.243597403586145e-06,
|
| 744 |
+
"loss": 0.0824435293674469,
|
| 745 |
+
"step": 910,
|
| 746 |
+
"token_acc": 0.9683633516053249
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 1.088809946714032,
|
| 750 |
+
"grad_norm": 0.91796875,
|
| 751 |
+
"learning_rate": 9.052619773309318e-06,
|
| 752 |
+
"loss": 0.07359167337417602,
|
| 753 |
+
"step": 920,
|
| 754 |
+
"token_acc": 0.9754111198120595
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.1006512729425695,
|
| 758 |
+
"grad_norm": 1.0625,
|
| 759 |
+
"learning_rate": 8.861990202024046e-06,
|
| 760 |
+
"loss": 0.07806094288825989,
|
| 761 |
+
"step": 930,
|
| 762 |
+
"token_acc": 0.9696922355881894
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.1124925991711072,
|
| 766 |
+
"grad_norm": 2.0,
|
| 767 |
+
"learning_rate": 8.67177872532372e-06,
|
| 768 |
+
"loss": 0.07662028670310975,
|
| 769 |
+
"step": 940,
|
| 770 |
+
"token_acc": 0.9707960433349034
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 1.1243339253996447,
|
| 774 |
+
"grad_norm": 1.5,
|
| 775 |
+
"learning_rate": 8.482055225197532e-06,
|
| 776 |
+
"loss": 0.07939339876174926,
|
| 777 |
+
"step": 950,
|
| 778 |
+
"token_acc": 0.9700156985871271
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.1361752516281824,
|
| 782 |
+
"grad_norm": 2.046875,
|
| 783 |
+
"learning_rate": 8.292889404356461e-06,
|
| 784 |
+
"loss": 0.07178534269332885,
|
| 785 |
+
"step": 960,
|
| 786 |
+
"token_acc": 0.9713704630788486
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.14801657785672,
|
| 790 |
+
"grad_norm": 1.453125,
|
| 791 |
+
"learning_rate": 8.104350760625122e-06,
|
| 792 |
+
"loss": 0.07578552961349487,
|
| 793 |
+
"step": 970,
|
| 794 |
+
"token_acc": 0.9700093720712277
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.1598579040852575,
|
| 798 |
+
"grad_norm": 1.3828125,
|
| 799 |
+
"learning_rate": 7.916508561408892e-06,
|
| 800 |
+
"loss": 0.07551709413528443,
|
| 801 |
+
"step": 980,
|
| 802 |
+
"token_acc": 0.9736513875896476
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.1716992303137952,
|
| 806 |
+
"grad_norm": 1.0625,
|
| 807 |
+
"learning_rate": 7.729431818245678e-06,
|
| 808 |
+
"loss": 0.06962672472000123,
|
| 809 |
+
"step": 990,
|
| 810 |
+
"token_acc": 0.9749726263100266
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.1835405565423327,
|
| 814 |
+
"grad_norm": 1.546875,
|
| 815 |
+
"learning_rate": 7.543189261451716e-06,
|
| 816 |
+
"loss": 0.07484488487243653,
|
| 817 |
+
"step": 1000,
|
| 818 |
+
"token_acc": 0.9705790297339593
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.1953818827708704,
|
| 822 |
+
"grad_norm": 1.328125,
|
| 823 |
+
"learning_rate": 7.35784931487064e-06,
|
| 824 |
+
"loss": 0.07622098922729492,
|
| 825 |
+
"step": 1010,
|
| 826 |
+
"token_acc": 0.970372680492749
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.207223208999408,
|
| 830 |
+
"grad_norm": 2.390625,
|
| 831 |
+
"learning_rate": 7.173480070735209e-06,
|
| 832 |
+
"loss": 0.07499848604202271,
|
| 833 |
+
"step": 1020,
|
| 834 |
+
"token_acc": 0.9686574146265399
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.2190645352279454,
|
| 838 |
+
"grad_norm": 1.2109375,
|
| 839 |
+
"learning_rate": 6.990149264650814e-06,
|
| 840 |
+
"loss": 0.07203071117401123,
|
| 841 |
+
"step": 1030,
|
| 842 |
+
"token_acc": 0.972574831531108
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.2309058614564832,
|
| 846 |
+
"grad_norm": 1.375,
|
| 847 |
+
"learning_rate": 6.807924250710019e-06,
|
| 848 |
+
"loss": 0.07002646923065185,
|
| 849 |
+
"step": 1040,
|
| 850 |
+
"token_acc": 0.9741379310344828
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.2427471876850207,
|
| 854 |
+
"grad_norm": 1.328125,
|
| 855 |
+
"learning_rate": 6.626871976747289e-06,
|
| 856 |
+
"loss": 0.07481561303138733,
|
| 857 |
+
"step": 1050,
|
| 858 |
+
"token_acc": 0.9709576138147566
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.2545885139135584,
|
| 862 |
+
"grad_norm": 1.2734375,
|
| 863 |
+
"learning_rate": 6.44705895974294e-06,
|
| 864 |
+
"loss": 0.06933027505874634,
|
| 865 |
+
"step": 1060,
|
| 866 |
+
"token_acc": 0.9734443746071653
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.266429840142096,
|
| 870 |
+
"grad_norm": 1.5625,
|
| 871 |
+
"learning_rate": 6.268551261385414e-06,
|
| 872 |
+
"loss": 0.0675657868385315,
|
| 873 |
+
"step": 1070,
|
| 874 |
+
"token_acc": 0.9746320075164422
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.2782711663706334,
|
| 878 |
+
"grad_norm": 1.5546875,
|
| 879 |
+
"learning_rate": 6.091414463800789e-06,
|
| 880 |
+
"loss": 0.07069060802459717,
|
| 881 |
+
"step": 1080,
|
| 882 |
+
"token_acc": 0.973655323819978
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.2901124925991712,
|
| 886 |
+
"grad_norm": 1.125,
|
| 887 |
+
"learning_rate": 5.915713645458514e-06,
|
| 888 |
+
"loss": 0.07225958108901978,
|
| 889 |
+
"step": 1090,
|
| 890 |
+
"token_acc": 0.9728201099764336
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.3019538188277087,
|
| 894 |
+
"grad_norm": 1.6171875,
|
| 895 |
+
"learning_rate": 5.741513357262147e-06,
|
| 896 |
+
"loss": 0.07490838170051575,
|
| 897 |
+
"step": 1100,
|
| 898 |
+
"token_acc": 0.970542149796302
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.3137951450562464,
|
| 902 |
+
"grad_norm": 1.3359375,
|
| 903 |
+
"learning_rate": 5.568877598833935e-06,
|
| 904 |
+
"loss": 0.07528679370880127,
|
| 905 |
+
"step": 1110,
|
| 906 |
+
"token_acc": 0.970496409615985
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.325636471284784,
|
| 910 |
+
"grad_norm": 1.453125,
|
| 911 |
+
"learning_rate": 5.3978697950019484e-06,
|
| 912 |
+
"loss": 0.07579593658447266,
|
| 913 |
+
"step": 1120,
|
| 914 |
+
"token_acc": 0.9716936625255543
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 1.3374777975133214,
|
| 918 |
+
"grad_norm": 1.6640625,
|
| 919 |
+
"learning_rate": 5.228552772498335e-06,
|
| 920 |
+
"loss": 0.06750929355621338,
|
| 921 |
+
"step": 1130,
|
| 922 |
+
"token_acc": 0.9741029641185648
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.3493191237418591,
|
| 926 |
+
"grad_norm": 1.6875,
|
| 927 |
+
"learning_rate": 5.060988736877366e-06,
|
| 928 |
+
"loss": 0.07841302156448364,
|
| 929 |
+
"step": 1140,
|
| 930 |
+
"token_acc": 0.9696400625978091
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.3611604499703966,
|
| 934 |
+
"grad_norm": 1.3671875,
|
| 935 |
+
"learning_rate": 4.895239249661662e-06,
|
| 936 |
+
"loss": 0.08451638221740723,
|
| 937 |
+
"step": 1150,
|
| 938 |
+
"token_acc": 0.967736883320282
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 1.3730017761989344,
|
| 942 |
+
"grad_norm": 1.0234375,
|
| 943 |
+
"learning_rate": 4.731365205725056e-06,
|
| 944 |
+
"loss": 0.074539315700531,
|
| 945 |
+
"step": 1160,
|
| 946 |
+
"token_acc": 0.9703715315880233
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.3848431024274719,
|
| 950 |
+
"grad_norm": 1.3359375,
|
| 951 |
+
"learning_rate": 4.569426810920347e-06,
|
| 952 |
+
"loss": 0.068775475025177,
|
| 953 |
+
"step": 1170,
|
| 954 |
+
"token_acc": 0.9716523101018011
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.3966844286560094,
|
| 958 |
+
"grad_norm": 1.2265625,
|
| 959 |
+
"learning_rate": 4.409483559960221e-06,
|
| 960 |
+
"loss": 0.07150940299034118,
|
| 961 |
+
"step": 1180,
|
| 962 |
+
"token_acc": 0.9737005913476502
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.4085257548845471,
|
| 966 |
+
"grad_norm": 1.890625,
|
| 967 |
+
"learning_rate": 4.251594214559416e-06,
|
| 968 |
+
"loss": 0.08267040252685547,
|
| 969 |
+
"step": 1190,
|
| 970 |
+
"token_acc": 0.9680350987151363
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.4203670811130846,
|
| 974 |
+
"grad_norm": 1.46875,
|
| 975 |
+
"learning_rate": 4.095816781846219e-06,
|
| 976 |
+
"loss": 0.0697063684463501,
|
| 977 |
+
"step": 1200,
|
| 978 |
+
"token_acc": 0.9751095804633688
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 1.4322084073416224,
|
| 982 |
+
"grad_norm": 1.203125,
|
| 983 |
+
"learning_rate": 3.942208493051137e-06,
|
| 984 |
+
"loss": 0.07361778020858764,
|
| 985 |
+
"step": 1210,
|
| 986 |
+
"token_acc": 0.9734901960784313
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 1.4440497335701599,
|
| 990 |
+
"grad_norm": 1.4609375,
|
| 991 |
+
"learning_rate": 3.7908257824806814e-06,
|
| 992 |
+
"loss": 0.07019197940826416,
|
| 993 |
+
"step": 1220,
|
| 994 |
+
"token_acc": 0.9710122218740207
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.4558910597986974,
|
| 998 |
+
"grad_norm": 1.5859375,
|
| 999 |
+
"learning_rate": 3.6417242667838917e-06,
|
| 1000 |
+
"loss": 0.07444216012954712,
|
| 1001 |
+
"step": 1230,
|
| 1002 |
+
"token_acc": 0.9728040012503908
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.467732386027235,
|
| 1006 |
+
"grad_norm": 1.4375,
|
| 1007 |
+
"learning_rate": 3.4949587245192983e-06,
|
| 1008 |
+
"loss": 0.06847925186157226,
|
| 1009 |
+
"step": 1240,
|
| 1010 |
+
"token_acc": 0.9746320075164422
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.4795737122557726,
|
| 1014 |
+
"grad_norm": 1.625,
|
| 1015 |
+
"learning_rate": 3.3505830760297543e-06,
|
| 1016 |
+
"loss": 0.0696124255657196,
|
| 1017 |
+
"step": 1250,
|
| 1018 |
+
"token_acc": 0.9730534231552561
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.4914150384843103,
|
| 1022 |
+
"grad_norm": 1.3203125,
|
| 1023 |
+
"learning_rate": 3.2086503636325895e-06,
|
| 1024 |
+
"loss": 0.07145707607269287,
|
| 1025 |
+
"step": 1260,
|
| 1026 |
+
"token_acc": 0.9749294891883422
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.5032563647128478,
|
| 1030 |
+
"grad_norm": 1.8515625,
|
| 1031 |
+
"learning_rate": 3.069212732132345e-06,
|
| 1032 |
+
"loss": 0.07296675443649292,
|
| 1033 |
+
"step": 1270,
|
| 1034 |
+
"token_acc": 0.9725662329518734
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 1.5150976909413854,
|
| 1038 |
+
"grad_norm": 2.625,
|
| 1039 |
+
"learning_rate": 2.9323214096632335e-06,
|
| 1040 |
+
"loss": 0.07637610435485839,
|
| 1041 |
+
"step": 1280,
|
| 1042 |
+
"token_acc": 0.9721566776781501
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.526939017169923,
|
| 1046 |
+
"grad_norm": 1.4375,
|
| 1047 |
+
"learning_rate": 2.798026688868386e-06,
|
| 1048 |
+
"loss": 0.07028791308403015,
|
| 1049 |
+
"step": 1290,
|
| 1050 |
+
"token_acc": 0.9726801695713613
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.5387803433984606,
|
| 1054 |
+
"grad_norm": 1.7578125,
|
| 1055 |
+
"learning_rate": 2.6663779084227926e-06,
|
| 1056 |
+
"loss": 0.0738570511341095,
|
| 1057 |
+
"step": 1300,
|
| 1058 |
+
"token_acc": 0.9717247879359096
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.5506216696269983,
|
| 1062 |
+
"grad_norm": 2.046875,
|
| 1063 |
+
"learning_rate": 2.5374234349066985e-06,
|
| 1064 |
+
"loss": 0.07539566755294799,
|
| 1065 |
+
"step": 1310,
|
| 1066 |
+
"token_acc": 0.9680968096809681
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.5624629958555358,
|
| 1070 |
+
"grad_norm": 1.09375,
|
| 1071 |
+
"learning_rate": 2.411210645036173e-06,
|
| 1072 |
+
"loss": 0.07291572093963623,
|
| 1073 |
+
"step": 1320,
|
| 1074 |
+
"token_acc": 0.972758405977584
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.5743043220840733,
|
| 1078 |
+
"grad_norm": 1.6484375,
|
| 1079 |
+
"learning_rate": 2.2877859082573194e-06,
|
| 1080 |
+
"loss": 0.07078194618225098,
|
| 1081 |
+
"step": 1330,
|
| 1082 |
+
"token_acc": 0.9733229329173166
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 1.586145648312611,
|
| 1086 |
+
"grad_norm": 1.53125,
|
| 1087 |
+
"learning_rate": 2.16719456971057e-06,
|
| 1088 |
+
"loss": 0.07727055549621582,
|
| 1089 |
+
"step": 1340,
|
| 1090 |
+
"token_acc": 0.9690154136520919
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.5979869745411486,
|
| 1094 |
+
"grad_norm": 1.125,
|
| 1095 |
+
"learning_rate": 2.0494809335712697e-06,
|
| 1096 |
+
"loss": 0.06905415058135986,
|
| 1097 |
+
"step": 1350,
|
| 1098 |
+
"token_acc": 0.9750783699059561
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.6098283007696863,
|
| 1102 |
+
"grad_norm": 1.8046875,
|
| 1103 |
+
"learning_rate": 1.9346882467727323e-06,
|
| 1104 |
+
"loss": 0.07434183359146118,
|
| 1105 |
+
"step": 1360,
|
| 1106 |
+
"token_acc": 0.9726091720143998
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 1.6216696269982238,
|
| 1110 |
+
"grad_norm": 0.96875,
|
| 1111 |
+
"learning_rate": 1.8228586831177032e-06,
|
| 1112 |
+
"loss": 0.06618231534957886,
|
| 1113 |
+
"step": 1370,
|
| 1114 |
+
"token_acc": 0.9750900830330566
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.6335109532267613,
|
| 1118 |
+
"grad_norm": 1.34375,
|
| 1119 |
+
"learning_rate": 1.7140333277840837e-06,
|
| 1120 |
+
"loss": 0.07258784770965576,
|
| 1121 |
+
"step": 1380,
|
| 1122 |
+
"token_acc": 0.9727699530516432
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.6453522794552988,
|
| 1126 |
+
"grad_norm": 1.1875,
|
| 1127 |
+
"learning_rate": 1.6082521622306003e-06,
|
| 1128 |
+
"loss": 0.0752481460571289,
|
| 1129 |
+
"step": 1390,
|
| 1130 |
+
"token_acc": 0.9715364050951407
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.6571936056838366,
|
| 1134 |
+
"grad_norm": 1.3984375,
|
| 1135 |
+
"learning_rate": 1.5055540495079802e-06,
|
| 1136 |
+
"loss": 0.06541621685028076,
|
| 1137 |
+
"step": 1400,
|
| 1138 |
+
"token_acc": 0.9767806714778788
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 1.6690349319123743,
|
| 1142 |
+
"grad_norm": 1.90625,
|
| 1143 |
+
"learning_rate": 1.4059767199810125e-06,
|
| 1144 |
+
"loss": 0.0707894206047058,
|
| 1145 |
+
"step": 1410,
|
| 1146 |
+
"token_acc": 0.9731301068510371
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 1.6808762581409118,
|
| 1150 |
+
"grad_norm": 1.3203125,
|
| 1151 |
+
"learning_rate": 1.3095567574667589e-06,
|
| 1152 |
+
"loss": 0.07458854913711548,
|
| 1153 |
+
"step": 1420,
|
| 1154 |
+
"token_acc": 0.9726630007855459
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.6927175843694493,
|
| 1158 |
+
"grad_norm": 1.65625,
|
| 1159 |
+
"learning_rate": 1.216329585793975e-06,
|
| 1160 |
+
"loss": 0.06724110841751099,
|
| 1161 |
+
"step": 1430,
|
| 1162 |
+
"token_acc": 0.9734000938820216
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 1.7045589105979868,
|
| 1166 |
+
"grad_norm": 1.46875,
|
| 1167 |
+
"learning_rate": 1.1263294557887216e-06,
|
| 1168 |
+
"loss": 0.07588486671447754,
|
| 1169 |
+
"step": 1440,
|
| 1170 |
+
"token_acc": 0.9710873664362036
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.7164002368265245,
|
| 1174 |
+
"grad_norm": 2.046875,
|
| 1175 |
+
"learning_rate": 1.0395894326909163e-06,
|
| 1176 |
+
"loss": 0.07099611163139344,
|
| 1177 |
+
"step": 1450,
|
| 1178 |
+
"token_acc": 0.9723091364205256
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.7282415630550623,
|
| 1182 |
+
"grad_norm": 1.921875,
|
| 1183 |
+
"learning_rate": 9.561413840064637e-07,
|
| 1184 |
+
"loss": 0.06974682807922364,
|
| 1185 |
+
"step": 1460,
|
| 1186 |
+
"token_acc": 0.9720609009574636
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.7400828892835998,
|
| 1190 |
+
"grad_norm": 1.2578125,
|
| 1191 |
+
"learning_rate": 8.760159677994174e-07,
|
| 1192 |
+
"loss": 0.06880149841308594,
|
| 1193 |
+
"step": 1470,
|
| 1194 |
+
"token_acc": 0.9749019607843137
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 1.7519242155121373,
|
| 1198 |
+
"grad_norm": 1.90625,
|
| 1199 |
+
"learning_rate": 7.992426214284787e-07,
|
| 1200 |
+
"loss": 0.07654795646667481,
|
| 1201 |
+
"step": 1480,
|
| 1202 |
+
"token_acc": 0.969967151572032
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 1.7637655417406748,
|
| 1206 |
+
"grad_norm": 1.3671875,
|
| 1207 |
+
"learning_rate": 7.258495507319885e-07,
|
| 1208 |
+
"loss": 0.06865710020065308,
|
| 1209 |
+
"step": 1490,
|
| 1210 |
+
"token_acc": 0.9735068192506663
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 1.7756068679692125,
|
| 1214 |
+
"grad_norm": 1.34375,
|
| 1215 |
+
"learning_rate": 6.558637196653372e-07,
|
| 1216 |
+
"loss": 0.06818960905075074,
|
| 1217 |
+
"step": 1500,
|
| 1218 |
+
"token_acc": 0.9739225484072455
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 1.7874481941977503,
|
| 1222 |
+
"grad_norm": 1.7578125,
|
| 1223 |
+
"learning_rate": 5.893108403946634e-07,
|
| 1224 |
+
"loss": 0.07731307148933411,
|
| 1225 |
+
"step": 1510,
|
| 1226 |
+
"token_acc": 0.9705836332342357
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 1.7992895204262878,
|
| 1230 |
+
"grad_norm": 1.1484375,
|
| 1231 |
+
"learning_rate": 5.262153638504286e-07,
|
| 1232 |
+
"loss": 0.07072955965995789,
|
| 1233 |
+
"step": 1520,
|
| 1234 |
+
"token_acc": 0.9747514596812372
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.8111308466548253,
|
| 1238 |
+
"grad_norm": 1.40625,
|
| 1239 |
+
"learning_rate": 4.6660047074436945e-07,
|
| 1240 |
+
"loss": 0.07091631889343261,
|
| 1241 |
+
"step": 1530,
|
| 1242 |
+
"token_acc": 0.9746914544602406
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.8229721728833628,
|
| 1246 |
+
"grad_norm": 1.6328125,
|
| 1247 |
+
"learning_rate": 4.10488063053105e-07,
|
| 1248 |
+
"loss": 0.062443327903747556,
|
| 1249 |
+
"step": 1540,
|
| 1250 |
+
"token_acc": 0.976577139287945
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.8348134991119005,
|
| 1254 |
+
"grad_norm": 1.6015625,
|
| 1255 |
+
"learning_rate": 3.57898755971553e-07,
|
| 1256 |
+
"loss": 0.07588485479354859,
|
| 1257 |
+
"step": 1550,
|
| 1258 |
+
"token_acc": 0.973754100921731
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 1.8466548253404382,
|
| 1262 |
+
"grad_norm": 1.4375,
|
| 1263 |
+
"learning_rate": 3.088518703390908e-07,
|
| 1264 |
+
"loss": 0.07371261715888977,
|
| 1265 |
+
"step": 1560,
|
| 1266 |
+
"token_acc": 0.9696590553644041
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 1.8584961515689757,
|
| 1270 |
+
"grad_norm": 1.1484375,
|
| 1271 |
+
"learning_rate": 2.633654255412554e-07,
|
| 1272 |
+
"loss": 0.06826964616775513,
|
| 1273 |
+
"step": 1570,
|
| 1274 |
+
"token_acc": 0.9750783699059561
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 1.8703374777975132,
|
| 1278 |
+
"grad_norm": 1.5078125,
|
| 1279 |
+
"learning_rate": 2.214561328895748e-07,
|
| 1280 |
+
"loss": 0.06952533721923829,
|
| 1281 |
+
"step": 1580,
|
| 1282 |
+
"token_acc": 0.9716478696741855
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 1.8821788040260508,
|
| 1286 |
+
"grad_norm": 1.7890625,
|
| 1287 |
+
"learning_rate": 1.8313938948198884e-07,
|
| 1288 |
+
"loss": 0.07293472290039063,
|
| 1289 |
+
"step": 1590,
|
| 1290 |
+
"token_acc": 0.9714820009350164
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.8940201302545885,
|
| 1294 |
+
"grad_norm": 1.625,
|
| 1295 |
+
"learning_rate": 1.484292725460934e-07,
|
| 1296 |
+
"loss": 0.07688854336738586,
|
| 1297 |
+
"step": 1600,
|
| 1298 |
+
"token_acc": 0.9702054257487847
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.9058614564831262,
|
| 1302 |
+
"grad_norm": 1.3359375,
|
| 1303 |
+
"learning_rate": 1.173385342672917e-07,
|
| 1304 |
+
"loss": 0.07143334150314332,
|
| 1305 |
+
"step": 1610,
|
| 1306 |
+
"token_acc": 0.970491288651703
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.9177027827116637,
|
| 1310 |
+
"grad_norm": 1.921875,
|
| 1311 |
+
"learning_rate": 8.987859710375524e-08,
|
| 1312 |
+
"loss": 0.081912100315094,
|
| 1313 |
+
"step": 1620,
|
| 1314 |
+
"token_acc": 0.9685150375939849
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 1.9295441089402012,
|
| 1318 |
+
"grad_norm": 1.8203125,
|
| 1319 |
+
"learning_rate": 6.605954958991523e-08,
|
| 1320 |
+
"loss": 0.07874792218208312,
|
| 1321 |
+
"step": 1630,
|
| 1322 |
+
"token_acc": 0.9696588586700204
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 1.9413854351687387,
|
| 1326 |
+
"grad_norm": 1.5546875,
|
| 1327 |
+
"learning_rate": 4.5890142630027336e-08,
|
| 1328 |
+
"loss": 0.0735186517238617,
|
| 1329 |
+
"step": 1640,
|
| 1330 |
+
"token_acc": 0.9709894934922377
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 1.9532267613972765,
|
| 1334 |
+
"grad_norm": 1.9765625,
|
| 1335 |
+
"learning_rate": 2.9377786283167897e-08,
|
| 1336 |
+
"loss": 0.0773587942123413,
|
| 1337 |
+
"step": 1650,
|
| 1338 |
+
"token_acc": 0.9692741809060982
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 1.9650680876258142,
|
| 1342 |
+
"grad_norm": 1.796875,
|
| 1343 |
+
"learning_rate": 1.6528547040842724e-08,
|
| 1344 |
+
"loss": 0.06999446153640747,
|
| 1345 |
+
"step": 1660,
|
| 1346 |
+
"token_acc": 0.9743669896842764
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.9769094138543517,
|
| 1350 |
+
"grad_norm": 1.5859375,
|
| 1351 |
+
"learning_rate": 7.3471455982143665e-09,
|
| 1352 |
+
"loss": 0.07299281358718872,
|
| 1353 |
+
"step": 1670,
|
| 1354 |
+
"token_acc": 0.9729179711959924
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.9887507400828892,
|
| 1358 |
+
"grad_norm": 1.34375,
|
| 1359 |
+
"learning_rate": 1.8369551197594538e-09,
|
| 1360 |
+
"loss": 0.067216557264328,
|
| 1361 |
+
"step": 1680,
|
| 1362 |
+
"token_acc": 0.9730407523510972
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.0,
|
| 1366 |
+
"grad_norm": 2.65625,
|
| 1367 |
+
"learning_rate": 0.0,
|
| 1368 |
+
"loss": 0.07405292987823486,
|
| 1369 |
+
"step": 1690,
|
| 1370 |
+
"token_acc": 0.9716838024608124
|
| 1371 |
+
}
|
| 1372 |
+
],
|
| 1373 |
+
"logging_steps": 10,
|
| 1374 |
+
"max_steps": 1690,
|
| 1375 |
+
"num_input_tokens_seen": 0,
|
| 1376 |
+
"num_train_epochs": 2,
|
| 1377 |
+
"save_steps": 500,
|
| 1378 |
+
"stateful_callbacks": {
|
| 1379 |
+
"TrainerControl": {
|
| 1380 |
+
"args": {
|
| 1381 |
+
"should_epoch_stop": false,
|
| 1382 |
+
"should_evaluate": false,
|
| 1383 |
+
"should_log": false,
|
| 1384 |
+
"should_save": true,
|
| 1385 |
+
"should_training_stop": true
|
| 1386 |
+
},
|
| 1387 |
+
"attributes": {}
|
| 1388 |
+
}
|
| 1389 |
+
},
|
| 1390 |
+
"total_flos": 1.7276889282044232e+18,
|
| 1391 |
+
"train_batch_size": 8,
|
| 1392 |
+
"trial_name": null,
|
| 1393 |
+
"trial_params": null
|
| 1394 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e7fbd87625cc50123815e7aff873d4789ca3015538e01899b3d2b9db87882bd
|
| 3 |
+
size 7057
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|