---
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_scale15
  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_scale15

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: 0.4337

## 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.7222        | 0.0211 | 13   | 0.5929          |
| 0.5524        | 0.0421 | 26   | 0.5670          |
| 0.5394        | 0.0632 | 39   | 0.5550          |
| 0.5277        | 0.0842 | 52   | 0.5458          |
| 0.5128        | 0.1053 | 65   | 0.5396          |
| 0.5149        | 0.1264 | 78   | 0.5328          |
| 0.4985        | 0.1474 | 91   | 0.5263          |
| 0.5106        | 0.1685 | 104  | 0.5242          |
| 0.497         | 0.1896 | 117  | 0.5265          |
| 0.5026        | 0.2106 | 130  | 0.5169          |
| 0.4923        | 0.2317 | 143  | 0.5151          |
| 0.4736        | 0.2527 | 156  | 0.5093          |
| 0.4763        | 0.2738 | 169  | 0.5057          |
| 0.4842        | 0.2949 | 182  | 0.5039          |
| 0.4821        | 0.3159 | 195  | 0.5020          |
| 0.4845        | 0.3370 | 208  | 0.5017          |
| 0.4639        | 0.3580 | 221  | 0.4959          |
| 0.4695        | 0.3791 | 234  | 0.4931          |
| 0.4603        | 0.4002 | 247  | 0.4872          |
| 0.4706        | 0.4212 | 260  | 0.4854          |
| 0.4797        | 0.4423 | 273  | 0.4825          |
| 0.4674        | 0.4633 | 286  | 0.4796          |
| 0.458         | 0.4844 | 299  | 0.4772          |
| 0.4553        | 0.5055 | 312  | 0.4715          |
| 0.4554        | 0.5265 | 325  | 0.4674          |
| 0.455         | 0.5476 | 338  | 0.4639          |
| 0.4522        | 0.5687 | 351  | 0.4622          |
| 0.4412        | 0.5897 | 364  | 0.4576          |
| 0.4401        | 0.6108 | 377  | 0.4574          |
| 0.4341        | 0.6318 | 390  | 0.4545          |
| 0.441         | 0.6529 | 403  | 0.4491          |
| 0.4299        | 0.6740 | 416  | 0.4497          |
| 0.4195        | 0.6950 | 429  | 0.4478          |
| 0.4401        | 0.7161 | 442  | 0.4445          |
| 0.4255        | 0.7371 | 455  | 0.4428          |
| 0.4401        | 0.7582 | 468  | 0.4400          |
| 0.4323        | 0.7793 | 481  | 0.4395          |
| 0.4372        | 0.8003 | 494  | 0.4381          |
| 0.4261        | 0.8214 | 507  | 0.4373          |
| 0.4167        | 0.8424 | 520  | 0.4368          |
| 0.4221        | 0.8635 | 533  | 0.4356          |
| 0.4143        | 0.8846 | 546  | 0.4349          |
| 0.4331        | 0.9056 | 559  | 0.4345          |
| 0.4288        | 0.9267 | 572  | 0.4341          |
| 0.4174        | 0.9478 | 585  | 0.4338          |
| 0.4202        | 0.9688 | 598  | 0.4337          |
| 0.4195        | 0.9899 | 611  | 0.4337          |


### Framework versions

- PEFT 0.7.1
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1