|
--- |
|
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: 4.4642 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.7438 | 0.0211 | 13 | 8.7190 | |
|
| 10.0767 | 0.0421 | 26 | 7.4982 | |
|
| 7.2515 | 0.0632 | 39 | 6.8837 | |
|
| 6.576 | 0.0842 | 52 | 6.7953 | |
|
| 6.2957 | 0.1053 | 65 | 6.2733 | |
|
| 6.0661 | 0.1264 | 78 | 6.0673 | |
|
| 5.9255 | 0.1474 | 91 | 5.8718 | |
|
| 5.8505 | 0.1685 | 104 | 5.7501 | |
|
| 5.8001 | 0.1896 | 117 | 5.7454 | |
|
| 5.6299 | 0.2106 | 130 | 5.6950 | |
|
| 5.5865 | 0.2317 | 143 | 5.5759 | |
|
| 5.5062 | 0.2527 | 156 | 5.4837 | |
|
| 5.4305 | 0.2738 | 169 | 5.4409 | |
|
| 5.4209 | 0.2949 | 182 | 5.4429 | |
|
| 5.4976 | 0.3159 | 195 | 5.4370 | |
|
| 5.3972 | 0.3370 | 208 | 5.4192 | |
|
| 5.2896 | 0.3580 | 221 | 5.3299 | |
|
| 5.2499 | 0.3791 | 234 | 5.3241 | |
|
| 5.2422 | 0.4002 | 247 | 5.2642 | |
|
| 5.2269 | 0.4212 | 260 | 5.1857 | |
|
| 5.1564 | 0.4423 | 273 | 5.1017 | |
|
| 5.1019 | 0.4633 | 286 | 5.0316 | |
|
| 5.0642 | 0.4844 | 299 | 5.0160 | |
|
| 4.9382 | 0.5055 | 312 | 4.9836 | |
|
| 4.8985 | 0.5265 | 325 | 4.9845 | |
|
| 4.8274 | 0.5476 | 338 | 4.8632 | |
|
| 4.8791 | 0.5687 | 351 | 4.8729 | |
|
| 4.8399 | 0.5897 | 364 | 4.8246 | |
|
| 4.843 | 0.6108 | 377 | 4.7545 | |
|
| 4.78 | 0.6318 | 390 | 4.7345 | |
|
| 4.6772 | 0.6529 | 403 | 4.7334 | |
|
| 4.6519 | 0.6740 | 416 | 4.6307 | |
|
| 4.6692 | 0.6950 | 429 | 4.6488 | |
|
| 4.6636 | 0.7161 | 442 | 4.6318 | |
|
| 4.5804 | 0.7371 | 455 | 4.5739 | |
|
| 4.566 | 0.7582 | 468 | 4.5556 | |
|
| 4.5466 | 0.7793 | 481 | 4.5450 | |
|
| 4.5555 | 0.8003 | 494 | 4.5170 | |
|
| 4.5352 | 0.8214 | 507 | 4.5036 | |
|
| 4.5827 | 0.8424 | 520 | 4.4868 | |
|
| 4.5218 | 0.8635 | 533 | 4.5077 | |
|
| 4.4692 | 0.8846 | 546 | 4.5098 | |
|
| 4.522 | 0.9056 | 559 | 4.4963 | |
|
| 4.5072 | 0.9267 | 572 | 4.4704 | |
|
| 4.4346 | 0.9478 | 585 | 4.4707 | |
|
| 4.4893 | 0.9688 | 598 | 4.4659 | |
|
| 4.4587 | 0.9899 | 611 | 4.4642 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
