|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-v0.3 |
|
model-index: |
|
- name: mistral_7b_v_MetaMathQA_40K_ortho_eye |
|
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_v_MetaMathQA_40K_ortho_eye |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4403 |
|
|
|
## 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: 0.0001 |
|
- 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_steps: 0.02 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.7124 | 0.0211 | 13 | 0.5905 | |
|
| 0.5476 | 0.0421 | 26 | 0.5631 | |
|
| 0.5329 | 0.0632 | 39 | 0.5495 | |
|
| 0.523 | 0.0842 | 52 | 0.5404 | |
|
| 0.5078 | 0.1053 | 65 | 0.5362 | |
|
| 0.5097 | 0.1264 | 78 | 0.5276 | |
|
| 0.494 | 0.1474 | 91 | 0.5230 | |
|
| 0.5066 | 0.1685 | 104 | 0.5173 | |
|
| 0.4881 | 0.1896 | 117 | 0.5167 | |
|
| 0.4963 | 0.2106 | 130 | 0.5138 | |
|
| 0.4841 | 0.2317 | 143 | 0.5092 | |
|
| 0.4676 | 0.2527 | 156 | 0.5046 | |
|
| 0.4722 | 0.2738 | 169 | 0.5045 | |
|
| 0.4791 | 0.2949 | 182 | 0.4997 | |
|
| 0.477 | 0.3159 | 195 | 0.4962 | |
|
| 0.4791 | 0.3370 | 208 | 0.4947 | |
|
| 0.4621 | 0.3580 | 221 | 0.4909 | |
|
| 0.4647 | 0.3791 | 234 | 0.4885 | |
|
| 0.4584 | 0.4002 | 247 | 0.4858 | |
|
| 0.4651 | 0.4212 | 260 | 0.4814 | |
|
| 0.4761 | 0.4423 | 273 | 0.4792 | |
|
| 0.4621 | 0.4633 | 286 | 0.4783 | |
|
| 0.4556 | 0.4844 | 299 | 0.4758 | |
|
| 0.4556 | 0.5055 | 312 | 0.4726 | |
|
| 0.4551 | 0.5265 | 325 | 0.4674 | |
|
| 0.4554 | 0.5476 | 338 | 0.4637 | |
|
| 0.4486 | 0.5687 | 351 | 0.4620 | |
|
| 0.4413 | 0.5897 | 364 | 0.4619 | |
|
| 0.4416 | 0.6108 | 377 | 0.4611 | |
|
| 0.4358 | 0.6318 | 390 | 0.4559 | |
|
| 0.4399 | 0.6529 | 403 | 0.4538 | |
|
| 0.4324 | 0.6740 | 416 | 0.4535 | |
|
| 0.4217 | 0.6950 | 429 | 0.4506 | |
|
| 0.4423 | 0.7161 | 442 | 0.4488 | |
|
| 0.4281 | 0.7371 | 455 | 0.4469 | |
|
| 0.4402 | 0.7582 | 468 | 0.4456 | |
|
| 0.4363 | 0.7793 | 481 | 0.4447 | |
|
| 0.4385 | 0.8003 | 494 | 0.4433 | |
|
| 0.429 | 0.8214 | 507 | 0.4435 | |
|
| 0.4199 | 0.8424 | 520 | 0.4421 | |
|
| 0.4223 | 0.8635 | 533 | 0.4415 | |
|
| 0.4158 | 0.8846 | 546 | 0.4412 | |
|
| 0.4369 | 0.9056 | 559 | 0.4408 | |
|
| 0.432 | 0.9267 | 572 | 0.4407 | |
|
| 0.4202 | 0.9478 | 585 | 0.4403 | |
|
| 0.4239 | 0.9688 | 598 | 0.4403 | |
|
| 0.4228 | 0.9899 | 611 | 0.4403 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.40.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |