---
license: other
base_model: yahma/llama-7b-hf
tags:
- generated_from_trainer
model-index:
- name: V0305P6
  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. -->

# V0305P6

This model is a fine-tuned version of [yahma/llama-7b-hf](https://huggingface.co/yahma/llama-7b-hf) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0736

## 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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 20
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.7001        | 0.09  | 10   | 0.5244          |
| 0.2134        | 0.17  | 20   | 0.1572          |
| 0.1574        | 0.26  | 30   | 0.1549          |
| 0.1522        | 0.34  | 40   | 0.1488          |
| 0.1501        | 0.43  | 50   | 0.1488          |
| 0.1553        | 0.51  | 60   | 0.1484          |
| 0.1482        | 0.6   | 70   | 0.1376          |
| 0.144         | 0.68  | 80   | 0.1298          |
| 0.131         | 0.77  | 90   | 0.1147          |
| 0.1268        | 0.85  | 100  | 0.1112          |
| 0.1196        | 0.94  | 110  | 0.0988          |
| 0.115         | 1.02  | 120  | 0.1008          |
| 0.1083        | 1.11  | 130  | 0.0982          |
| 0.102         | 1.19  | 140  | 0.0943          |
| 0.0984        | 1.28  | 150  | 0.0875          |
| 0.0964        | 1.37  | 160  | 0.0853          |
| 0.0953        | 1.45  | 170  | 0.0855          |
| 0.0888        | 1.54  | 180  | 0.0825          |
| 0.089         | 1.62  | 190  | 0.0839          |
| 0.0955        | 1.71  | 200  | 0.0811          |
| 0.094         | 1.79  | 210  | 0.0784          |
| 0.0901        | 1.88  | 220  | 0.0729          |
| 0.0856        | 1.96  | 230  | 0.0771          |
| 0.0717        | 2.05  | 240  | 0.0744          |
| 0.0648        | 2.13  | 250  | 0.0730          |
| 0.061         | 2.22  | 260  | 0.0720          |
| 0.0589        | 2.3   | 270  | 0.0759          |
| 0.0664        | 2.39  | 280  | 0.0702          |
| 0.0676        | 2.47  | 290  | 0.0693          |
| 0.0636        | 2.56  | 300  | 0.0699          |
| 0.0667        | 2.65  | 310  | 0.0711          |
| 0.0585        | 2.73  | 320  | 0.0726          |
| 0.0619        | 2.82  | 330  | 0.0732          |
| 0.0613        | 2.9   | 340  | 0.0735          |
| 0.0611        | 2.99  | 350  | 0.0736          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1