| model_name: mnoukhov/dpo2_pythia2.8b_tldr.yml_7692b3a0462f2e8fd35cc26b99936469 | |
| wandb_log_id: model_name | |
| gen_dtype: bfloat16 | |
| tokenizer_name: EleutherAI/pythia-1b-deduped | |
| dataset_name: vwxyzjn/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1706381144 | |
| gold_model_name: vwxyzjn/EleutherAI_pythia-6.9b-deduped__reward__tldr | |
| gold_model_revision: reward__55513__1708628552 | |
| eval_dtype: bfloat16 | |
| max_new_tokens: 128 | |
| max_length: 640 | |
| temperature: 0.010001 | |