{ "best_metric": 28.34865729677184, "best_model_checkpoint": "./checkpoint-1000", "epoch": 0.2, "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": 4.6000000000000004e-07, "loss": 1.4182, "step": 25 }, { "epoch": 0.01, "learning_rate": 9.400000000000001e-07, "loss": 1.292, "step": 50 }, { "epoch": 0.01, "learning_rate": 1.44e-06, "loss": 1.0018, "step": 75 }, { "epoch": 0.02, "learning_rate": 1.94e-06, "loss": 0.7765, "step": 100 }, { "epoch": 0.03, "learning_rate": 2.4400000000000004e-06, "loss": 0.7103, "step": 125 }, { "epoch": 0.03, "learning_rate": 2.9400000000000002e-06, "loss": 0.6597, "step": 150 }, { "epoch": 0.04, "learning_rate": 3.44e-06, "loss": 0.6657, "step": 175 }, { "epoch": 0.04, "learning_rate": 3.94e-06, "loss": 0.5853, "step": 200 }, { "epoch": 0.04, "learning_rate": 4.440000000000001e-06, "loss": 0.5273, "step": 225 }, { "epoch": 0.05, "learning_rate": 4.94e-06, "loss": 0.5979, "step": 250 }, { "epoch": 0.06, "learning_rate": 5.4400000000000004e-06, "loss": 0.5861, "step": 275 }, { "epoch": 0.06, "learning_rate": 5.94e-06, "loss": 0.5085, "step": 300 }, { "epoch": 0.07, "learning_rate": 6.440000000000001e-06, "loss": 0.4827, "step": 325 }, { "epoch": 0.07, "learning_rate": 6.9400000000000005e-06, "loss": 0.4909, "step": 350 }, { "epoch": 0.07, "learning_rate": 7.440000000000001e-06, "loss": 0.4651, "step": 375 }, { "epoch": 0.08, "learning_rate": 7.94e-06, "loss": 0.494, "step": 400 }, { "epoch": 0.09, "learning_rate": 8.44e-06, "loss": 0.4188, "step": 425 }, { "epoch": 0.09, "learning_rate": 8.94e-06, "loss": 0.3849, "step": 450 }, { "epoch": 0.1, "learning_rate": 9.440000000000001e-06, "loss": 0.4577, "step": 475 }, { "epoch": 0.1, "learning_rate": 9.940000000000001e-06, "loss": 0.4415, "step": 500 }, { "epoch": 0.1, "learning_rate": 9.951111111111111e-06, "loss": 0.4615, "step": 525 }, { "epoch": 0.11, "learning_rate": 9.895555555555557e-06, "loss": 0.4282, "step": 550 }, { "epoch": 0.12, "learning_rate": 9.842222222222223e-06, "loss": 0.4481, "step": 575 }, { "epoch": 0.12, "learning_rate": 9.786666666666667e-06, "loss": 0.4441, "step": 600 }, { "epoch": 0.12, "learning_rate": 9.731111111111113e-06, "loss": 0.4238, "step": 625 }, { "epoch": 0.13, "learning_rate": 9.675555555555555e-06, "loss": 0.4245, "step": 650 }, { "epoch": 0.14, "learning_rate": 9.620000000000001e-06, "loss": 0.4118, "step": 675 }, { "epoch": 0.14, "learning_rate": 9.564444444444445e-06, "loss": 0.4111, "step": 700 }, { "epoch": 0.14, "learning_rate": 9.508888888888889e-06, "loss": 0.3642, "step": 725 }, { "epoch": 0.15, "learning_rate": 9.453333333333335e-06, "loss": 0.401, "step": 750 }, { "epoch": 0.15, "learning_rate": 9.397777777777779e-06, "loss": 0.3855, "step": 775 }, { "epoch": 0.16, "learning_rate": 9.342222222222223e-06, "loss": 0.3668, "step": 800 }, { "epoch": 0.17, "learning_rate": 9.286666666666667e-06, "loss": 0.3794, "step": 825 }, { "epoch": 0.17, "learning_rate": 9.231111111111111e-06, "loss": 0.4296, "step": 850 }, { "epoch": 0.17, "learning_rate": 9.175555555555557e-06, "loss": 0.4003, "step": 875 }, { "epoch": 0.18, "learning_rate": 9.12e-06, "loss": 0.374, "step": 900 }, { "epoch": 0.18, "learning_rate": 9.064444444444447e-06, "loss": 0.4051, "step": 925 }, { "epoch": 0.19, "learning_rate": 9.008888888888889e-06, "loss": 0.3806, "step": 950 }, { "epoch": 0.2, "learning_rate": 8.953333333333335e-06, "loss": 0.4161, "step": 975 }, { "epoch": 0.2, "learning_rate": 8.897777777777779e-06, "loss": 0.4198, "step": 1000 }, { "epoch": 0.2, "eval_loss": 0.41016528010368347, "eval_runtime": 1814.0427, "eval_samples_per_second": 3.633, "eval_steps_per_second": 0.454, "eval_wer": 28.34865729677184, "step": 1000 } ], "max_steps": 5000, "num_train_epochs": 9223372036854775807, "total_flos": 4.08241963008e+18, "trial_name": null, "trial_params": null }