| { | |
| "best_metric": 5215.41095890411, | |
| "best_model_checkpoint": "./20230912-output\\checkpoint-1000", | |
| "epoch": 8.390141583639224, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.8e-07, | |
| "loss": 18.9312, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.8e-07, | |
| "loss": 17.0566, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.3800000000000001e-06, | |
| "loss": 13.4189, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.8800000000000002e-06, | |
| "loss": 10.4803, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 2.38e-06, | |
| "loss": 9.3304, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.88e-06, | |
| "loss": 8.3203, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 3.3600000000000004e-06, | |
| "loss": 8.9822, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.86e-06, | |
| "loss": 10.7581, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 4.360000000000001e-06, | |
| "loss": 13.2164, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 4.86e-06, | |
| "loss": 12.7052, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 5.36e-06, | |
| "loss": 10.3904, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 5.86e-06, | |
| "loss": 8.2617, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 6.360000000000001e-06, | |
| "loss": 6.8613, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 6.860000000000001e-06, | |
| "loss": 6.1093, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 7.360000000000001e-06, | |
| "loss": 5.8769, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 7.860000000000001e-06, | |
| "loss": 5.6272, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 8.36e-06, | |
| "loss": 5.674, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 8.860000000000002e-06, | |
| "loss": 5.5667, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 9.360000000000002e-06, | |
| "loss": 5.4705, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 9.86e-06, | |
| "loss": 5.1703, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 9.967272727272728e-06, | |
| "loss": 5.1044, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 9.921818181818183e-06, | |
| "loss": 4.9244, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 9.876363636363637e-06, | |
| "loss": 4.8602, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 9.830909090909092e-06, | |
| "loss": 4.6437, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 9.785454545454546e-06, | |
| "loss": 4.0014, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 9.74e-06, | |
| "loss": 3.8653, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 9.694545454545455e-06, | |
| "loss": 3.8299, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 9.64909090909091e-06, | |
| "loss": 3.6928, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 9.603636363636365e-06, | |
| "loss": 3.1672, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 9.558181818181818e-06, | |
| "loss": 2.5309, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 9.512727272727274e-06, | |
| "loss": 2.4801, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "learning_rate": 9.467272727272727e-06, | |
| "loss": 2.2236, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 9.421818181818183e-06, | |
| "loss": 2.3091, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 9.376363636363637e-06, | |
| "loss": 1.9126, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 9.330909090909092e-06, | |
| "loss": 1.4071, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "learning_rate": 9.285454545454546e-06, | |
| "loss": 1.5367, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 9.240000000000001e-06, | |
| "loss": 1.3686, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 9.194545454545455e-06, | |
| "loss": 1.3177, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 9.14909090909091e-06, | |
| "loss": 0.9167, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 9.103636363636364e-06, | |
| "loss": 0.9502, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "eval_loss": 3.2547426223754883, | |
| "eval_runtime": 507.4588, | |
| "eval_samples_per_second": 1.255, | |
| "eval_steps_per_second": 0.158, | |
| "eval_wer": 5215.41095890411, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 6000, | |
| "num_train_epochs": 51, | |
| "total_flos": 4.62371528392704e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |