| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.357, | |
| "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": 1.2779, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.4e-06, | |
| "loss": 0.7695, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6055, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5285, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4858, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4907, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4579, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3847, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4227, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3831, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4203, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3367, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2877, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 1e-05, | |
| "loss": 0.319, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4077, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3476, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2846, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2915, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2933, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1e-05, | |
| "loss": 0.331, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3539, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3225, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3011, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2291, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2438, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3122, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3015, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2722, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2212, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2457, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2073, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2281, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1952, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1821, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1829, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2021, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1806, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1508, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1416, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1644, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 0.4277667999267578, | |
| "eval_runtime": 3572.8062, | |
| "eval_samples_per_second": 2.88, | |
| "eval_steps_per_second": 0.18, | |
| "eval_wer": 35.51342198040141, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "step": 1000, | |
| "total_flos": 9.23473281024e+18, | |
| "train_loss": 0.3440979962348938, | |
| "train_runtime": 7035.6898, | |
| "train_samples_per_second": 4.548, | |
| "train_steps_per_second": 0.142 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 9.23473281024e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |