---
license: llama3
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B-Instruct
datasets:
- generator
model-index:
- name: cls_train_llama3_v1
  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. -->

# cls_train_llama3_v1

This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6482

## 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: 0.0002
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 2
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.8592        | 0.2146 | 50   | 0.8151          |
| 0.7874        | 0.4292 | 100  | 0.7651          |
| 0.6932        | 0.6438 | 150  | 0.7275          |
| 0.6738        | 0.8584 | 200  | 0.7003          |
| 0.5692        | 1.0730 | 250  | 0.6846          |
| 0.5493        | 1.2876 | 300  | 0.6756          |
| 0.5267        | 1.5021 | 350  | 0.6653          |
| 0.595         | 1.7167 | 400  | 0.6550          |
| 0.5441        | 1.9313 | 450  | 0.6482          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1