---
license: llama3
library_name: peft
tags:
- unsloth
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B
model-index:
- name: meta_llama_3_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. -->

# meta_llama_3_MetaMathQA_40K_ortho_eye

This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5290

## 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 |
|:-------------:|:------:|:----:|:---------------:|
| 0.8833        | 0.0211 | 13   | 0.6741          |
| 0.6218        | 0.0421 | 26   | 0.6424          |
| 0.6067        | 0.0632 | 39   | 0.6220          |
| 0.5945        | 0.0842 | 52   | 0.6132          |
| 0.5574        | 0.1053 | 65   | 0.6053          |
| 0.5705        | 0.1264 | 78   | 0.5994          |
| 0.5778        | 0.1474 | 91   | 0.5945          |
| 0.5612        | 0.1685 | 104  | 0.5892          |
| 0.5419        | 0.1896 | 117  | 0.5858          |
| 0.5428        | 0.2106 | 130  | 0.5830          |
| 0.5404        | 0.2317 | 143  | 0.5804          |
| 0.549         | 0.2527 | 156  | 0.5767          |
| 0.5448        | 0.2738 | 169  | 0.5722          |
| 0.541         | 0.2949 | 182  | 0.5698          |
| 0.5345        | 0.3159 | 195  | 0.5674          |
| 0.5175        | 0.3370 | 208  | 0.5661          |
| 0.5257        | 0.3580 | 221  | 0.5625          |
| 0.5314        | 0.3791 | 234  | 0.5615          |
| 0.5391        | 0.4002 | 247  | 0.5586          |
| 0.5178        | 0.4212 | 260  | 0.5561          |
| 0.5292        | 0.4423 | 273  | 0.5544          |
| 0.5339        | 0.4633 | 286  | 0.5516          |
| 0.5347        | 0.4844 | 299  | 0.5494          |
| 0.5129        | 0.5055 | 312  | 0.5469          |
| 0.5246        | 0.5265 | 325  | 0.5455          |
| 0.5166        | 0.5476 | 338  | 0.5450          |
| 0.5127        | 0.5687 | 351  | 0.5433          |
| 0.4937        | 0.5897 | 364  | 0.5408          |
| 0.5155        | 0.6108 | 377  | 0.5393          |
| 0.5132        | 0.6318 | 390  | 0.5377          |
| 0.5042        | 0.6529 | 403  | 0.5370          |
| 0.5096        | 0.6740 | 416  | 0.5354          |
| 0.5082        | 0.6950 | 429  | 0.5349          |
| 0.514         | 0.7161 | 442  | 0.5341          |
| 0.5045        | 0.7371 | 455  | 0.5328          |
| 0.4919        | 0.7582 | 468  | 0.5323          |
| 0.4941        | 0.7793 | 481  | 0.5317          |
| 0.4885        | 0.8003 | 494  | 0.5311          |
| 0.5244        | 0.8214 | 507  | 0.5305          |
| 0.5109        | 0.8424 | 520  | 0.5299          |
| 0.4972        | 0.8635 | 533  | 0.5298          |
| 0.5194        | 0.8846 | 546  | 0.5295          |
| 0.4996        | 0.9056 | 559  | 0.5293          |
| 0.4959        | 0.9267 | 572  | 0.5291          |
| 0.5119        | 0.9478 | 585  | 0.5290          |
| 0.5176        | 0.9688 | 598  | 0.5290          |
| 0.5146        | 0.9899 | 611  | 0.5290          |


### Framework versions

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