---
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Summary_L3_200steps_1e6rate_SFT2
  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. -->

# Summary_L3_200steps_1e6rate_SFT2

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 an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6178

## 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: 1e-06
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 1000

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.7359        | 0.2   | 50   | 1.5809          |
| 0.7502        | 0.4   | 100  | 0.6751          |
| 0.685         | 0.6   | 150  | 0.6561          |
| 0.6695        | 0.8   | 200  | 0.6460          |
| 0.6389        | 1.0   | 250  | 0.6380          |
| 0.617         | 1.2   | 300  | 0.6335          |
| 0.7064        | 1.4   | 350  | 0.6293          |
| 0.6194        | 1.6   | 400  | 0.6248          |
| 0.5743        | 1.8   | 450  | 0.6220          |
| 0.6479        | 2.0   | 500  | 0.6194          |
| 0.5995        | 2.2   | 550  | 0.6206          |
| 0.5824        | 2.4   | 600  | 0.6204          |
| 0.6111        | 2.6   | 650  | 0.6181          |
| 0.5764        | 2.8   | 700  | 0.6180          |
| 0.5772        | 3.0   | 750  | 0.6173          |
| 0.5683        | 3.2   | 800  | 0.6178          |
| 0.5971        | 3.4   | 850  | 0.6178          |
| 0.6369        | 3.6   | 900  | 0.6178          |
| 0.5811        | 3.8   | 950  | 0.6178          |
| 0.5674        | 4.0   | 1000 | 0.6178          |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.0.0+cu117
- Datasets 2.19.2
- Tokenizers 0.19.1