| { | |
| "best_metric": 0.0, | |
| "best_model_checkpoint": "output/T5_base_finetune_soroco_temp/checkpoint-1", | |
| "epoch": 0.014814814814814815, | |
| "global_step": 1, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.997014925373135e-06, | |
| "loss": 5.0171, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_META_TUNING/soroco.cfg/acc": 0.0, | |
| "eval_avr": 0.0, | |
| "eval_loss": 4.31452751159668, | |
| "eval_runtime": 236.5988, | |
| "eval_samples_per_second": 1.627, | |
| "step": 1 | |
| } | |
| ], | |
| "max_steps": 3350, | |
| "num_train_epochs": 50, | |
| "total_flos": 44782684471296.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |