README.md

metadata

license: llama3.1
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
tags:
  - alignment-handbook
  - trl
  - orpo
  - generated_from_trainer
  - trl
  - orpo
  - generated_from_trainer
datasets:
  - ORPO/uf-l31-base-iter0-armo
model-index:
  - name: uf-l31-orpo-base-armo-iter1
    results: []

uf-l31-orpo-base-armo-iter1

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the ORPO/uf-l31-base-iter0-armo dataset.

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-06
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• 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

Framework versions

• Transformers 4.44.0
• Pytorch 2.2.2+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1