| { | |
| "best_metric": 15.703064185124902, | |
| "best_model_checkpoint": "./checkpoint-1000", | |
| "epoch": 5.026, | |
| "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": 4.2000000000000006e-07, | |
| "loss": 4.163, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.200000000000001e-07, | |
| "loss": 3.2393, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.42e-06, | |
| "loss": 2.1044, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9200000000000003e-06, | |
| "loss": 1.3638, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.42e-06, | |
| "loss": 1.1844, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.92e-06, | |
| "loss": 1.009, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.4200000000000007e-06, | |
| "loss": 0.8762, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.920000000000001e-06, | |
| "loss": 0.8188, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.42e-06, | |
| "loss": 0.6994, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.92e-06, | |
| "loss": 0.3518, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.420000000000001e-06, | |
| "loss": 0.2302, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.92e-06, | |
| "loss": 0.2269, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 6.42e-06, | |
| "loss": 0.1694, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.92e-06, | |
| "loss": 0.1352, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 7.420000000000001e-06, | |
| "loss": 0.1625, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 7.92e-06, | |
| "loss": 0.1407, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.42e-06, | |
| "loss": 0.1125, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 8.920000000000001e-06, | |
| "loss": 0.1035, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.42e-06, | |
| "loss": 0.1027, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.920000000000002e-06, | |
| "loss": 0.0734, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.953333333333333e-06, | |
| "loss": 0.0636, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 9.89777777777778e-06, | |
| "loss": 0.0785, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 9.842222222222223e-06, | |
| "loss": 0.0641, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 9.786666666666667e-06, | |
| "loss": 0.053, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 9.731111111111113e-06, | |
| "loss": 0.0498, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 9.675555555555555e-06, | |
| "loss": 0.0464, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 9.620000000000001e-06, | |
| "loss": 0.0349, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 9.564444444444445e-06, | |
| "loss": 0.0306, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.508888888888889e-06, | |
| "loss": 0.037, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.453333333333335e-06, | |
| "loss": 0.0337, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 9.397777777777779e-06, | |
| "loss": 0.0263, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 9.342222222222223e-06, | |
| "loss": 0.0279, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 9.286666666666667e-06, | |
| "loss": 0.0247, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 9.231111111111111e-06, | |
| "loss": 0.0171, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9.175555555555557e-06, | |
| "loss": 0.017, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 9.12e-06, | |
| "loss": 0.0213, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 9.064444444444447e-06, | |
| "loss": 0.0173, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 9.008888888888889e-06, | |
| "loss": 0.0156, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 8.953333333333335e-06, | |
| "loss": 0.0162, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 8.897777777777779e-06, | |
| "loss": 0.0137, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "eval_loss": 0.2068425565958023, | |
| "eval_runtime": 1070.693, | |
| "eval_samples_per_second": 3.604, | |
| "eval_steps_per_second": 0.451, | |
| "eval_wer": 15.703064185124902, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 5000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 1.84290636644352e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |