|
--- |
|
base_model: unsloth/Qwen2-7B |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Qwen2-7B_metamath_ortho |
|
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_ortho |
|
|
|
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: 0.2069 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.1901 | 0.0211 | 13 | 0.1745 | |
|
| 0.1805 | 0.0421 | 26 | 0.2131 | |
|
| 0.2166 | 0.0632 | 39 | 0.2354 | |
|
| 0.2322 | 0.0842 | 52 | 0.2523 | |
|
| 0.2419 | 0.1053 | 65 | 0.2642 | |
|
| 0.2577 | 0.1264 | 78 | 0.2728 | |
|
| 0.2667 | 0.1474 | 91 | 0.2756 | |
|
| 0.2586 | 0.1685 | 104 | 0.2777 | |
|
| 0.2699 | 0.1896 | 117 | 0.2833 | |
|
| 0.268 | 0.2106 | 130 | 0.2879 | |
|
| 0.2792 | 0.2317 | 143 | 0.2897 | |
|
| 0.2717 | 0.2527 | 156 | 0.2865 | |
|
| 0.2823 | 0.2738 | 169 | 0.2875 | |
|
| 0.2717 | 0.2949 | 182 | 0.2862 | |
|
| 0.2771 | 0.3159 | 195 | 0.2840 | |
|
| 0.2703 | 0.3370 | 208 | 0.2814 | |
|
| 0.2684 | 0.3580 | 221 | 0.2790 | |
|
| 0.2685 | 0.3791 | 234 | 0.2772 | |
|
| 0.2659 | 0.4002 | 247 | 0.2726 | |
|
| 0.2665 | 0.4212 | 260 | 0.2728 | |
|
| 0.2702 | 0.4423 | 273 | 0.2701 | |
|
| 0.258 | 0.4633 | 286 | 0.2680 | |
|
| 0.2649 | 0.4844 | 299 | 0.2631 | |
|
| 0.2465 | 0.5055 | 312 | 0.2600 | |
|
| 0.2497 | 0.5265 | 325 | 0.2575 | |
|
| 0.2403 | 0.5476 | 338 | 0.2532 | |
|
| 0.2409 | 0.5687 | 351 | 0.2501 | |
|
| 0.2425 | 0.5897 | 364 | 0.2451 | |
|
| 0.2357 | 0.6108 | 377 | 0.2408 | |
|
| 0.2294 | 0.6318 | 390 | 0.2359 | |
|
| 0.2306 | 0.6529 | 403 | 0.2337 | |
|
| 0.2337 | 0.6740 | 416 | 0.2299 | |
|
| 0.2249 | 0.6950 | 429 | 0.2261 | |
|
| 0.2271 | 0.7161 | 442 | 0.2221 | |
|
| 0.2123 | 0.7371 | 455 | 0.2190 | |
|
| 0.2137 | 0.7582 | 468 | 0.2166 | |
|
| 0.2185 | 0.7793 | 481 | 0.2152 | |
|
| 0.2132 | 0.8003 | 494 | 0.2141 | |
|
| 0.2008 | 0.8214 | 507 | 0.2118 | |
|
| 0.2083 | 0.8424 | 520 | 0.2098 | |
|
| 0.2045 | 0.8635 | 533 | 0.2093 | |
|
| 0.2011 | 0.8846 | 546 | 0.2086 | |
|
| 0.1969 | 0.9056 | 559 | 0.2078 | |
|
| 0.1979 | 0.9267 | 572 | 0.2074 | |
|
| 0.203 | 0.9478 | 585 | 0.2071 | |
|
| 0.2037 | 0.9688 | 598 | 0.2068 | |
|
| 0.2047 | 0.9899 | 611 | 0.2069 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
