• Model creator: https://huggingface.co/saminyeasar/
• Original model: https://huggingface.co/saminyeasar/rloo-pythia-1b-deduped-tldr-preference-sft-trl-style-20241104-225709/

Original model description:

• trl
• rloo
• generated_from_trainer model-index:
• name: rloo-pythia-1b-deduped-tldr-preference-sft-trl-style-20241104-225709 results: []

rloo-pythia-1b-deduped-tldr-preference-sft-trl-style-20241104-225709

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 3e-06
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 64
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1.0

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.14.6
• Tokenizers 0.19.1