---
license: other
base_model: yahma/llama-7b-hf
tags:
- generated_from_trainer
model-index:
- name: V0305P1
  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. -->

# V0305P1

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: 0.0697

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.0736        | 0.09  | 10   | 0.1558          |
| 0.1607        | 0.17  | 20   | 0.1576          |
| 0.1576        | 0.26  | 30   | 0.1518          |
| 0.1522        | 0.34  | 40   | 0.1504          |
| 0.1506        | 0.43  | 50   | 0.1494          |
| 0.1561        | 0.51  | 60   | 0.1507          |
| 0.1516        | 0.6   | 70   | 0.1495          |
| 0.1528        | 0.68  | 80   | 0.1480          |
| 0.1481        | 0.77  | 90   | 0.1435          |
| 0.1513        | 0.85  | 100  | 0.1445          |
| 0.1463        | 0.94  | 110  | 0.1142          |
| 0.1277        | 1.02  | 120  | 0.1126          |
| 0.119         | 1.11  | 130  | 0.1112          |
| 0.1092        | 1.19  | 140  | 0.0969          |
| 0.1113        | 1.28  | 150  | 0.0965          |
| 0.1033        | 1.37  | 160  | 0.0991          |
| 0.1025        | 1.45  | 170  | 0.0881          |
| 0.0922        | 1.54  | 180  | 0.0878          |
| 0.0931        | 1.62  | 190  | 0.0811          |
| 0.0909        | 1.71  | 200  | 0.0786          |
| 0.087         | 1.79  | 210  | 0.0755          |
| 0.0868        | 1.88  | 220  | 0.0745          |
| 0.0825        | 1.96  | 230  | 0.0832          |
| 0.0636        | 2.05  | 240  | 0.0820          |
| 0.0504        | 2.13  | 250  | 0.0864          |
| 0.0463        | 2.22  | 260  | 0.0876          |
| 0.0449        | 2.3   | 270  | 0.0847          |
| 0.0529        | 2.39  | 280  | 0.0711          |
| 0.0489        | 2.47  | 290  | 0.0693          |
| 0.05          | 2.56  | 300  | 0.0699          |
| 0.0519        | 2.65  | 310  | 0.0686          |
| 0.0411        | 2.73  | 320  | 0.0688          |
| 0.0473        | 2.82  | 330  | 0.0695          |
| 0.0471        | 2.9   | 340  | 0.0697          |
| 0.0452        | 2.99  | 350  | 0.0697          |


### Framework versions

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