|
--- |
|
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_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. --> |
|
|
|
# Mistral-7B-v0.3_metamath_default |
|
|
|
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: 4.3239 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.7439 | 0.0211 | 13 | 4.5181 | |
|
| 8.6977 | 0.0421 | 26 | 6.6816 | |
|
| 6.6139 | 0.0632 | 39 | 6.4690 | |
|
| 6.3559 | 0.0842 | 52 | 6.4403 | |
|
| 6.2844 | 0.1053 | 65 | 6.3007 | |
|
| 6.1379 | 0.1264 | 78 | 6.0592 | |
|
| 5.9506 | 0.1474 | 91 | 5.9143 | |
|
| 5.8886 | 0.1685 | 104 | 5.9890 | |
|
| 5.7387 | 0.1896 | 117 | 5.6559 | |
|
| 5.672 | 0.2106 | 130 | 5.7240 | |
|
| 5.5425 | 0.2317 | 143 | 5.5165 | |
|
| 5.473 | 0.2527 | 156 | 5.4238 | |
|
| 5.328 | 0.2738 | 169 | 5.3434 | |
|
| 5.241 | 0.2949 | 182 | 5.2088 | |
|
| 5.2491 | 0.3159 | 195 | 5.3291 | |
|
| 5.2994 | 0.3370 | 208 | 5.1687 | |
|
| 5.1595 | 0.3580 | 221 | 5.0797 | |
|
| 5.0592 | 0.3791 | 234 | 5.0005 | |
|
| 4.9674 | 0.4002 | 247 | 4.9525 | |
|
| 4.9663 | 0.4212 | 260 | 4.9704 | |
|
| 5.0169 | 0.4423 | 273 | 4.9718 | |
|
| 4.9333 | 0.4633 | 286 | 4.8277 | |
|
| 4.8687 | 0.4844 | 299 | 4.8131 | |
|
| 4.7215 | 0.5055 | 312 | 4.7606 | |
|
| 4.7602 | 0.5265 | 325 | 4.7049 | |
|
| 4.7033 | 0.5476 | 338 | 4.7817 | |
|
| 4.7179 | 0.5687 | 351 | 4.6428 | |
|
| 4.6525 | 0.5897 | 364 | 4.5964 | |
|
| 4.5923 | 0.6108 | 377 | 4.5608 | |
|
| 4.5936 | 0.6318 | 390 | 4.5676 | |
|
| 4.5142 | 0.6529 | 403 | 4.5016 | |
|
| 4.4717 | 0.6740 | 416 | 4.4422 | |
|
| 4.5539 | 0.6950 | 429 | 4.5177 | |
|
| 4.5129 | 0.7161 | 442 | 4.5397 | |
|
| 4.4162 | 0.7371 | 455 | 4.4050 | |
|
| 4.4328 | 0.7582 | 468 | 4.4244 | |
|
| 4.3949 | 0.7793 | 481 | 4.4013 | |
|
| 4.3946 | 0.8003 | 494 | 4.3721 | |
|
| 4.393 | 0.8214 | 507 | 4.3586 | |
|
| 4.3872 | 0.8424 | 520 | 4.3552 | |
|
| 4.3787 | 0.8635 | 533 | 4.4043 | |
|
| 4.3477 | 0.8846 | 546 | 4.3537 | |
|
| 4.3957 | 0.9056 | 559 | 4.3334 | |
|
| 4.3634 | 0.9267 | 572 | 4.3088 | |
|
| 4.2898 | 0.9478 | 585 | 4.3342 | |
|
| 4.355 | 0.9688 | 598 | 4.3202 | |
|
| 4.3331 | 0.9899 | 611 | 4.3239 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
