• Model creator: https://huggingface.co/ShenaoZ/
• Original model: https://huggingface.co/ShenaoZ/0.001_ablation_4iters_bs256_decalpha_iter_4/

Original model description:

• alignment-handbook
• generated_from_trainer
• trl
• dpo
• generated_from_trainer datasets:
• updated
• original model-index:
• name: 0.001_ablation_4iters_bs256_decalpha_iter_4 results: []

0.001_ablation_4iters_bs256_decalpha_iter_4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 5e-07
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• total_eval_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 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.14.6
• Tokenizers 0.15.2