| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4877057508636456, | |
| "eval_steps": 100, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.994130006901536e-06, | |
| "loss": 0.3053, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 8.976535341747906e-06, | |
| "loss": 0.1363, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.947261907011569e-06, | |
| "loss": 0.1087, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 8.906386073741352e-06, | |
| "loss": 0.106, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 8.85401448231912e-06, | |
| "loss": 0.0791, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 8.790283764247187e-06, | |
| "loss": 0.0702, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.715360185692326e-06, | |
| "loss": 0.0773, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.629439213716327e-06, | |
| "loss": 0.0583, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.532745006324751e-06, | |
| "loss": 0.0637, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.425529827664287e-06, | |
| "loss": 0.0554, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 7.870811641330633e-11, | |
| "eval_runtime": 51.3409, | |
| "eval_samples_per_second": 85.195, | |
| "eval_steps_per_second": 10.654, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.308073389894399e-06, | |
| "loss": 0.0666, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.18068212345023e-06, | |
| "loss": 0.0598, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.043688377600596e-06, | |
| "loss": 0.0423, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.897449553386683e-06, | |
| "loss": 0.0311, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.742347171203542e-06, | |
| "loss": 0.0527, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.578785875456937e-06, | |
| "loss": 0.0847, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.407192378892295e-06, | |
| "loss": 0.0595, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.2280143493498716e-06, | |
| "loss": 0.0327, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.041719241850471e-06, | |
| "loss": 0.0877, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.848793079058672e-06, | |
| "loss": 0.0356, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 9.303278147854144e-08, | |
| "eval_runtime": 53.2016, | |
| "eval_samples_per_second": 82.216, | |
| "eval_steps_per_second": 10.282, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.649739183305183e-06, | |
| "loss": 0.0332, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.445076863476361e-06, | |
| "loss": 0.0537, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.235340060196612e-06, | |
| "loss": 0.0548, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.021075952838263e-06, | |
| "loss": 0.0485, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5.802843531993069e-06, | |
| "loss": 0.041, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 5.581212141129573e-06, | |
| "loss": 0.0266, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.3567599912410075e-06, | |
| "loss": 0.0421, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.130072652358832e-06, | |
| "loss": 0.0522, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.901741525867374e-06, | |
| "loss": 0.0302, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.67236230160516e-06, | |
| "loss": 0.0741, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 2.2148276457301108e-07, | |
| "eval_runtime": 51.7845, | |
| "eval_samples_per_second": 84.465, | |
| "eval_steps_per_second": 10.563, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 615, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |