| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.13, | |
| "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": 7.90139129823451e-06, | |
| "loss": 1.2152, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.841832720226257e-06, | |
| "loss": 1.0108, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.683, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.231, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1816, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.15, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1104, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0922, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0921, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0851, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.09, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0751, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0519, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0508, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0505, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0508, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0515, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0383, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0281, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1e-05, | |
| "loss": 0.026, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0266, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0283, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0294, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0186, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0141, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0135, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0135, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0153, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0157, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.009, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0069, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0072, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0079, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 1e-05, | |
| "loss": 0.009, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0079, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0051, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0042, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0042, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 1e-05, | |
| "loss": 0.004, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0056, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_loss": 0.1322021484375, | |
| "eval_runtime": 2453.1998, | |
| "eval_samples_per_second": 1.019, | |
| "eval_steps_per_second": 0.064, | |
| "eval_wer": 43.47641759406466, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "step": 1000, | |
| "total_flos": 9.196639645008396e+18, | |
| "train_loss": 0.11525779342651367, | |
| "train_runtime": 11116.9995, | |
| "train_samples_per_second": 2.878, | |
| "train_steps_per_second": 0.09 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 9.196639645008396e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |