|
--- |
|
base_model: unsloth/mistral-7b-v0.3 |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Mistral-7B-v0.3_metamath_reverse |
|
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. --> |
|
|
|
# Mistral-7B-v0.3_metamath_reverse |
|
|
|
This model is a fine-tuned version of [unsloth/mistral-7b-v0.3](https://huggingface.co/unsloth/mistral-7b-v0.3) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.4478 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.7436 | 0.0211 | 13 | 7.4054 | |
|
| 9.1068 | 0.0421 | 26 | 6.9800 | |
|
| 6.6988 | 0.0632 | 39 | 6.4271 | |
|
| 6.4684 | 0.0842 | 52 | 6.2893 | |
|
| 6.1245 | 0.1053 | 65 | 6.1245 | |
|
| 5.9117 | 0.1264 | 78 | 5.8770 | |
|
| 5.8448 | 0.1474 | 91 | 5.7834 | |
|
| 5.742 | 0.1685 | 104 | 5.8941 | |
|
| 5.6054 | 0.1896 | 117 | 6.0972 | |
|
| 5.6465 | 0.2106 | 130 | 5.4808 | |
|
| 5.5659 | 0.2317 | 143 | 5.5371 | |
|
| 5.4175 | 0.2527 | 156 | 5.5688 | |
|
| 5.3148 | 0.2738 | 169 | 5.3646 | |
|
| 5.2376 | 0.2949 | 182 | 5.2052 | |
|
| 5.2313 | 0.3159 | 195 | 5.1473 | |
|
| 5.1381 | 0.3370 | 208 | 5.2471 | |
|
| 5.0545 | 0.3580 | 221 | 5.0579 | |
|
| 5.0218 | 0.3791 | 234 | 5.0434 | |
|
| 5.1901 | 0.4002 | 247 | 5.1862 | |
|
| 5.0809 | 0.4212 | 260 | 5.0103 | |
|
| 5.0357 | 0.4423 | 273 | 5.0488 | |
|
| 5.0375 | 0.4633 | 286 | 5.0026 | |
|
| 5.0348 | 0.4844 | 299 | 5.0081 | |
|
| 4.8927 | 0.5055 | 312 | 4.8912 | |
|
| 4.878 | 0.5265 | 325 | 4.8665 | |
|
| 4.8092 | 0.5476 | 338 | 4.8402 | |
|
| 4.8342 | 0.5687 | 351 | 4.7689 | |
|
| 4.7834 | 0.5897 | 364 | 4.7842 | |
|
| 4.7428 | 0.6108 | 377 | 4.7396 | |
|
| 4.7318 | 0.6318 | 390 | 4.6987 | |
|
| 4.6442 | 0.6529 | 403 | 4.6854 | |
|
| 4.6454 | 0.6740 | 416 | 4.6917 | |
|
| 4.7075 | 0.6950 | 429 | 4.6419 | |
|
| 4.6744 | 0.7161 | 442 | 4.5826 | |
|
| 4.5861 | 0.7371 | 455 | 4.5793 | |
|
| 4.5707 | 0.7582 | 468 | 4.5944 | |
|
| 4.5675 | 0.7793 | 481 | 4.5611 | |
|
| 4.5286 | 0.8003 | 494 | 4.5216 | |
|
| 4.5302 | 0.8214 | 507 | 4.5140 | |
|
| 4.5191 | 0.8424 | 520 | 4.5084 | |
|
| 4.5023 | 0.8635 | 533 | 4.4878 | |
|
| 4.4661 | 0.8846 | 546 | 4.4593 | |
|
| 4.4942 | 0.9056 | 559 | 4.4660 | |
|
| 4.4691 | 0.9267 | 572 | 4.4433 | |
|
| 4.4153 | 0.9478 | 585 | 4.4531 | |
|
| 4.4609 | 0.9688 | 598 | 4.4450 | |
|
| 4.4444 | 0.9899 | 611 | 4.4478 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
