---
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- alignment_handbook-handbook
- generated_from_trainer
datasets:
- princeton-nlp/llama3-ultrafeedback
model-index:
- name: Meta-Llama-3-8B-Instruct-6e-7
  results: []
---



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 princeton-nlp/llama3-ultrafeedback dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2416
- Rewards/chosen: -0.3361
- Rewards/rejected: -0.4013
- Rewards/accuracies: 0.5915
- Rewards/margins: 0.0652
- Logps/rejected: -0.4013
- Logps/chosen: -0.3361
- Logits/rejected: 0.0031
- Logits/chosen: 0.0123

## 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: 6e-07
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 1.2443        | 0.8550 | 400  | 1.2416          | -0.3361        | -0.4013          | 0.5915             | 0.0652          | -0.4013        | -0.3361      | 0.0031          | 0.0123        |


### Framework versions

- Transformers 4.42.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.19.1