---
library_name: transformers
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: IE_L3_1000steps_1e5rate_SFT
  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. -->

# IE_L3_1000steps_1e5rate_SFT

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: 2.5960

## 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-05
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.5579        | 0.4   | 50   | 1.5074          |
| 1.6682        | 0.8   | 100  | 1.5842          |
| 1.1462        | 1.2   | 150  | 1.6953          |
| 1.1094        | 1.6   | 200  | 1.7268          |
| 1.1658        | 2.0   | 250  | 1.6667          |
| 0.4474        | 2.4   | 300  | 1.9842          |
| 0.437         | 2.8   | 350  | 1.9593          |
| 0.1509        | 3.2   | 400  | 2.1876          |
| 0.1546        | 3.6   | 450  | 2.2019          |
| 0.1572        | 4.0   | 500  | 2.1880          |
| 0.0608        | 4.4   | 550  | 2.3708          |
| 0.0654        | 4.8   | 600  | 2.3631          |
| 0.0315        | 5.2   | 650  | 2.5034          |
| 0.0311        | 5.6   | 700  | 2.4365          |
| 0.0315        | 6.0   | 750  | 2.4699          |
| 0.0235        | 6.4   | 800  | 2.5549          |
| 0.0193        | 6.8   | 850  | 2.5882          |
| 0.017         | 7.2   | 900  | 2.5931          |
| 0.0179        | 7.6   | 950  | 2.5959          |
| 0.0163        | 8.0   | 1000 | 2.5960          |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.0.0+cu117
- Datasets 3.0.0
- Tokenizers 0.19.1