| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.329, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.4e-06, | |
| "loss": 0.8997, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.4e-06, | |
| "loss": 0.2863, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2519, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3038, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2015, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1834, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2019, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-05, | |
| "loss": 0.197, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1499, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1695, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.146, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1643, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1822, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1506, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1486, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1588, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1e-05, | |
| "loss": 0.152, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2014, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1674, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1711, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1271, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1157, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1077, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1195, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1502, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1706, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1524, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0954, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.079, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0845, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1013, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0703, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0669, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0772, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 1e-05, | |
| "loss": 0.057, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0546, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.056, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0522, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0592, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0686, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 0.20645689964294434, | |
| "eval_runtime": 2856.486, | |
| "eval_samples_per_second": 3.761, | |
| "eval_steps_per_second": 0.235, | |
| "eval_wer": 11.786082500535915, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "step": 1000, | |
| "total_flos": 9.23473281024e+18, | |
| "train_loss": 0.15881791234016418, | |
| "train_runtime": 6379.5137, | |
| "train_samples_per_second": 5.016, | |
| "train_steps_per_second": 0.157 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 9.23473281024e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |