---
library_name: transformers
base_model: meta-llama/Meta-Llama-3-8B
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- Anthropic/hh-rlhf
model-index:
- name: llama-3-8b-base-sft-hh-harmless-8xh200-20260410-140525
  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. -->

# llama-3-8b-base-sft-hh-harmless-8xh200-20260410-140525

This model is a fine-tuned version of [/scratch/feng.yulu/dynamic-dpo-v4/base_models/Meta-Llama-3-8B](https://huggingface.co//scratch/feng.yulu/dynamic-dpo-v4/base_models/Meta-Llama-3-8B) on the Anthropic/hh-rlhf dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5660

## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 128
- total_eval_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.5418        | 0.9615 | 100  | 1.5660          |


### Framework versions

- Transformers 4.51.0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.21.4