# model_revisions: ['sft__55513__1708611267'] model_name: mnoukhov/dpo2_costa_1b_20k_fp16.yml_91ead4b5862c14e701bb164c36d54628 model_revisions: ['step1'] base_model_name: vwxyzjn/EleutherAI_pythia-1b-deduped__sft__tldr base_model_revision: sft__55513__1706646024 wandb_log_id: model_name # model_name: mnoukhov/EleutherAI_pythia-1b-deduped__sft__tldr_dpo_20konly_1b_fp16.yml_24e9f83_merged # model_revisions: ['step1'] # wandb_log_id: 06936e8694635c9d13ec2d47abdeb0aa split: validation[:10] tokenizer_name: EleutherAI/pythia-1b-deduped dataset_name: vwxyzjn/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1706381144 gen_dtype: bfloat16 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: 565