|
--- |
|
base_model: unsloth/Qwen2-7B |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Qwen2-7B_metamath_default |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# Qwen2-7B_metamath_default |
|
|
|
This model is a fine-tuned version of [unsloth/Qwen2-7B](https://huggingface.co/unsloth/Qwen2-7B) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2149 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.0003 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.02 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.1753 | 0.0211 | 13 | 0.1875 | |
|
| 0.2034 | 0.0421 | 26 | 0.2488 | |
|
| 0.2604 | 0.0632 | 39 | 0.2850 | |
|
| 0.2823 | 0.0842 | 52 | 0.3067 | |
|
| 0.2953 | 0.1053 | 65 | 0.3213 | |
|
| 0.3151 | 0.1264 | 78 | 0.3321 | |
|
| 0.3224 | 0.1474 | 91 | 0.3354 | |
|
| 0.3144 | 0.1685 | 104 | 0.3366 | |
|
| 0.3291 | 0.1896 | 117 | 0.3428 | |
|
| 0.3233 | 0.2106 | 130 | 0.3447 | |
|
| 0.3342 | 0.2317 | 143 | 0.3455 | |
|
| 0.3292 | 0.2527 | 156 | 0.3393 | |
|
| 0.3322 | 0.2738 | 169 | 0.3418 | |
|
| 0.3225 | 0.2949 | 182 | 0.3334 | |
|
| 0.3306 | 0.3159 | 195 | 0.3326 | |
|
| 0.315 | 0.3370 | 208 | 0.3303 | |
|
| 0.3135 | 0.3580 | 221 | 0.3307 | |
|
| 0.3131 | 0.3791 | 234 | 0.3264 | |
|
| 0.3114 | 0.4002 | 247 | 0.3211 | |
|
| 0.3065 | 0.4212 | 260 | 0.3160 | |
|
| 0.315 | 0.4423 | 273 | 0.3122 | |
|
| 0.296 | 0.4633 | 286 | 0.3074 | |
|
| 0.306 | 0.4844 | 299 | 0.2980 | |
|
| 0.2821 | 0.5055 | 312 | 0.2968 | |
|
| 0.2861 | 0.5265 | 325 | 0.2924 | |
|
| 0.2717 | 0.5476 | 338 | 0.2850 | |
|
| 0.2704 | 0.5687 | 351 | 0.2784 | |
|
| 0.2693 | 0.5897 | 364 | 0.2716 | |
|
| 0.2612 | 0.6108 | 377 | 0.2652 | |
|
| 0.2512 | 0.6318 | 390 | 0.2601 | |
|
| 0.2537 | 0.6529 | 403 | 0.2543 | |
|
| 0.2543 | 0.6740 | 416 | 0.2498 | |
|
| 0.2443 | 0.6950 | 429 | 0.2463 | |
|
| 0.2441 | 0.7161 | 442 | 0.2407 | |
|
| 0.2286 | 0.7371 | 455 | 0.2362 | |
|
| 0.2298 | 0.7582 | 468 | 0.2327 | |
|
| 0.2304 | 0.7793 | 481 | 0.2300 | |
|
| 0.2266 | 0.8003 | 494 | 0.2270 | |
|
| 0.2127 | 0.8214 | 507 | 0.2231 | |
|
| 0.2193 | 0.8424 | 520 | 0.2205 | |
|
| 0.2136 | 0.8635 | 533 | 0.2190 | |
|
| 0.2099 | 0.8846 | 546 | 0.2176 | |
|
| 0.2042 | 0.9056 | 559 | 0.2165 | |
|
| 0.2077 | 0.9267 | 572 | 0.2158 | |
|
| 0.2136 | 0.9478 | 585 | 0.2152 | |
|
| 0.2131 | 0.9688 | 598 | 0.2150 | |
|
| 0.2124 | 0.9899 | 611 | 0.2149 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
