| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 1546, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.5050000000000002e-05, | |
| "loss": 0.3435, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.7639751552795031, | |
| "eval_loss": 0.2686764597892761, | |
| "eval_runtime": 13.08, | |
| "eval_samples_per_second": 209.94, | |
| "eval_steps_per_second": 6.575, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1e-07, | |
| "loss": 0.1946, | |
| "step": 1546 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.7826714801444044, | |
| "eval_loss": 0.2808539569377899, | |
| "eval_runtime": 13.1089, | |
| "eval_samples_per_second": 209.475, | |
| "eval_steps_per_second": 6.56, | |
| "step": 1546 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 1546, | |
| "total_flos": 1.300610568855552e+16, | |
| "train_loss": 0.2690811354623575, | |
| "train_runtime": 674.5814, | |
| "train_samples_per_second": 73.278, | |
| "train_steps_per_second": 2.292 | |
| } | |
| ], | |
| "max_steps": 1546, | |
| "num_train_epochs": 2, | |
| "total_flos": 1.300610568855552e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |