| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 4647, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.78480740262535e-05, | |
| "loss": 0.5131, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.5696148052506995e-05, | |
| "loss": 0.4138, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.3544222078760491e-05, | |
| "loss": 0.4095, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.139229610501399e-05, | |
| "loss": 0.3721, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.240370131267486e-06, | |
| "loss": 0.3653, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.088444157520982e-06, | |
| "loss": 0.3526, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 4.936518183774478e-06, | |
| "loss": 0.3358, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 2.7845922100279753e-06, | |
| "loss": 0.329, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 6.32666236281472e-07, | |
| "loss": 0.3183, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 4647, | |
| "total_flos": 1093572179186688.0, | |
| "train_loss": 0.3768685761384613, | |
| "train_runtime": 506.9261, | |
| "train_samples_per_second": 293.309, | |
| "train_steps_per_second": 9.167 | |
| } | |
| ], | |
| "max_steps": 4647, | |
| "num_train_epochs": 3, | |
| "total_flos": 1093572179186688.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |