| model_name: vwxyzjn/EleutherAI_pythia-1b-deduped__ppo_left_padding_new_nowhiten_reward__tldr | |
| model_revisions: ["ppo_left_padding_new_nowhiten_reward__55513__1709671967"] | |
| gen_dtype: bfloat16 | |
| wandb_log_id: EleutherAI_pythia-1b-deduped__ppo_left_padding_new_nowhiten_reward__tldr_55513 | |
| 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: 53 | |
| max_length: 565 | |
| temperature: 0.010001 | |