| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 8.474576271186441, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.600000000000001e-06, | |
| "loss": 0.9141, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 0.3615, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 9.533333333333334e-06, | |
| "loss": 0.2375, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 8.977777777777778e-06, | |
| "loss": 0.1874, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 8.422222222222223e-06, | |
| "loss": 0.1611, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.866666666666667e-06, | |
| "loss": 0.103, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 7.3111111111111125e-06, | |
| "loss": 0.1012, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 6.755555555555556e-06, | |
| "loss": 0.0549, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 6.200000000000001e-06, | |
| "loss": 0.055, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 5.6444444444444445e-06, | |
| "loss": 0.038, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 5.088888888888889e-06, | |
| "loss": 0.0305, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 4.533333333333334e-06, | |
| "loss": 0.0272, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 3.977777777777778e-06, | |
| "loss": 0.012, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 3.4222222222222224e-06, | |
| "loss": 0.0133, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 2.866666666666667e-06, | |
| "loss": 0.0077, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 2.311111111111111e-06, | |
| "loss": 0.0058, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 1.7555555555555556e-06, | |
| "loss": 0.0039, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 0.0019, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 6.444444444444445e-07, | |
| "loss": 0.0016, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 8.88888888888889e-08, | |
| "loss": 0.0008, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "eval_loss": 0.3451443016529083, | |
| "eval_runtime": 1585.5901, | |
| "eval_samples_per_second": 0.194, | |
| "eval_steps_per_second": 0.025, | |
| "eval_wer": 23.69608373939722, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "step": 500, | |
| "total_flos": 1.68834559574016e+19, | |
| "train_loss": 0.11590570814907551, | |
| "train_runtime": 3725.2193, | |
| "train_samples_per_second": 2.148, | |
| "train_steps_per_second": 0.134 | |
| } | |
| ], | |
| "max_steps": 500, | |
| "num_train_epochs": 9, | |
| "total_flos": 1.68834559574016e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |