|
--- |
|
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_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. --> |
|
|
|
# Mistral-7B-v0.3_metamath_ortho |
|
|
|
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: 3.7040 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.7777 | 0.0211 | 13 | 0.8341 | |
|
| 7.0293 | 0.0421 | 26 | 6.8513 | |
|
| 6.701 | 0.0632 | 39 | 6.3677 | |
|
| 6.2243 | 0.0842 | 52 | 6.0330 | |
|
| 5.8724 | 0.1053 | 65 | 5.7326 | |
|
| 5.6516 | 0.1264 | 78 | 5.5358 | |
|
| 5.4706 | 0.1474 | 91 | 5.4924 | |
|
| 5.4721 | 0.1685 | 104 | 5.4835 | |
|
| 5.3039 | 0.1896 | 117 | 5.2730 | |
|
| 5.2205 | 0.2106 | 130 | 5.3434 | |
|
| 5.2713 | 0.2317 | 143 | 5.1822 | |
|
| 5.3149 | 0.2527 | 156 | 5.1724 | |
|
| 5.0644 | 0.2738 | 169 | 4.9613 | |
|
| 4.9846 | 0.2949 | 182 | 4.9757 | |
|
| 5.0517 | 0.3159 | 195 | 4.9266 | |
|
| 4.865 | 0.3370 | 208 | 4.8010 | |
|
| 4.7282 | 0.3580 | 221 | 4.6863 | |
|
| 4.7043 | 0.3791 | 234 | 4.8179 | |
|
| 4.625 | 0.4002 | 247 | 4.7745 | |
|
| 4.6588 | 0.4212 | 260 | 4.5501 | |
|
| 4.5945 | 0.4423 | 273 | 4.6777 | |
|
| 4.5486 | 0.4633 | 286 | 4.4474 | |
|
| 4.5306 | 0.4844 | 299 | 4.2966 | |
|
| 4.2913 | 0.5055 | 312 | 4.3590 | |
|
| 4.2849 | 0.5265 | 325 | 4.2581 | |
|
| 4.2128 | 0.5476 | 338 | 4.2430 | |
|
| 4.2097 | 0.5687 | 351 | 4.1542 | |
|
| 4.1464 | 0.5897 | 364 | 4.0493 | |
|
| 4.0945 | 0.6108 | 377 | 4.1035 | |
|
| 4.1179 | 0.6318 | 390 | 4.0137 | |
|
| 3.985 | 0.6529 | 403 | 4.0483 | |
|
| 3.8947 | 0.6740 | 416 | 3.9081 | |
|
| 3.9839 | 0.6950 | 429 | 3.9723 | |
|
| 3.9361 | 0.7161 | 442 | 3.9275 | |
|
| 3.8458 | 0.7371 | 455 | 3.8235 | |
|
| 3.8545 | 0.7582 | 468 | 3.8504 | |
|
| 3.7774 | 0.7793 | 481 | 3.8078 | |
|
| 3.8065 | 0.8003 | 494 | 3.8017 | |
|
| 3.7724 | 0.8214 | 507 | 3.7487 | |
|
| 3.7569 | 0.8424 | 520 | 3.7663 | |
|
| 3.742 | 0.8635 | 533 | 3.7698 | |
|
| 3.7114 | 0.8846 | 546 | 3.7603 | |
|
| 3.7752 | 0.9056 | 559 | 3.7105 | |
|
| 3.6945 | 0.9267 | 572 | 3.7041 | |
|
| 3.6581 | 0.9478 | 585 | 3.7017 | |
|
| 3.6615 | 0.9688 | 598 | 3.7050 | |
|
| 3.6688 | 0.9899 | 611 | 3.7040 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
