| { | |
| "best_metric": 197.54339821146766, | |
| "best_model_checkpoint": "./checkpoint-1000", | |
| "epoch": 15.002, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.2e-09, | |
| "loss": 4.0163, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.2e-09, | |
| "loss": 3.9266, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.4199999999999998e-08, | |
| "loss": 3.8847, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.92e-08, | |
| "loss": 3.9306, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.4199999999999998e-08, | |
| "loss": 3.9051, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.9199999999999997e-08, | |
| "loss": 3.8691, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 3.42e-08, | |
| "loss": 3.7792, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.92e-08, | |
| "loss": 3.7109, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 4.42e-08, | |
| "loss": 3.6114, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 4.92e-08, | |
| "loss": 3.475, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 5.42e-08, | |
| "loss": 3.342, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 5.9199999999999994e-08, | |
| "loss": 3.1764, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 6.419999999999999e-08, | |
| "loss": 3.0853, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 6.92e-08, | |
| "loss": 2.9605, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 7.419999999999999e-08, | |
| "loss": 2.8524, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.92e-08, | |
| "loss": 2.7282, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 8.42e-08, | |
| "loss": 2.6852, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 8.919999999999999e-08, | |
| "loss": 2.5189, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 9.42e-08, | |
| "loss": 2.4286, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 9.919999999999999e-08, | |
| "loss": 2.3425, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 9.953333333333332e-08, | |
| "loss": 2.2299, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.897777777777777e-08, | |
| "loss": 2.1313, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 9.842222222222222e-08, | |
| "loss": 1.967, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 9.786666666666667e-08, | |
| "loss": 1.8323, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 9.73111111111111e-08, | |
| "loss": 1.7521, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 9.675555555555554e-08, | |
| "loss": 1.6346, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 9.619999999999999e-08, | |
| "loss": 1.5736, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 9.564444444444444e-08, | |
| "loss": 1.5367, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 9.508888888888888e-08, | |
| "loss": 1.4935, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 9.453333333333333e-08, | |
| "loss": 1.4747, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 9.397777777777778e-08, | |
| "loss": 1.4071, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 9.342222222222222e-08, | |
| "loss": 1.3692, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 9.286666666666666e-08, | |
| "loss": 1.383, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 9.231111111111111e-08, | |
| "loss": 1.3336, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 9.175555555555555e-08, | |
| "loss": 1.316, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 9.12e-08, | |
| "loss": 1.2831, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 9.064444444444444e-08, | |
| "loss": 1.2845, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 9.008888888888888e-08, | |
| "loss": 1.2834, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 8.953333333333333e-08, | |
| "loss": 1.2358, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 8.897777777777778e-08, | |
| "loss": 1.22, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.223775029182434, | |
| "eval_runtime": 3040.7291, | |
| "eval_samples_per_second": 0.701, | |
| "eval_steps_per_second": 0.022, | |
| "eval_wer": 197.54339821146766, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 5000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 1.84088626864128e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |