| model_name: /home/toolkit/huggingface/tldr_sft_pythia410m_fp32_trainall_3epochs | |
| dataset_name: mnoukhov/openai_summarize_comparisons_relabel_pythia1b | |
| beta: 0.5 | |
| num_train_epochs: 3 | |
| eval_steps: 750 | |
| load_in_8bit: False | |
| bf16: False | |
| fp16: True | |
| learning_rate: 1e-5 | |
| use_peft: True | |
| lora_all_linear: True | |
| lora_r: 8 | |
| lora_alpha: 32 | |
| lora_dropout: 0.05 | |
| gradient_accumulation_steps: 4 | |
| per_device_train_batch_size: 4 | |
| warmup_steps: 150 | |
| eval_steps: 10 | |
| save_steps: 10 | |