| { | |
| "best_metric": 25.293262636395276, | |
| "best_model_checkpoint": "whisper-base-nl-2/checkpoint-1000", | |
| "epoch": 0.2139495079161318, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 1.3206, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.8e-07, | |
| "loss": 1.247, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.3800000000000001e-06, | |
| "loss": 1.1224, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.8800000000000002e-06, | |
| "loss": 0.9567, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.38e-06, | |
| "loss": 0.964, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.88e-06, | |
| "loss": 0.7427, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.3800000000000007e-06, | |
| "loss": 0.6921, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.88e-06, | |
| "loss": 0.6178, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.38e-06, | |
| "loss": 0.6377, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.880000000000001e-06, | |
| "loss": 0.5442, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5.380000000000001e-06, | |
| "loss": 0.483, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5.8800000000000005e-06, | |
| "loss": 0.5293, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 6.380000000000001e-06, | |
| "loss": 0.5293, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 6.88e-06, | |
| "loss": 0.5213, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 7.3800000000000005e-06, | |
| "loss": 0.4849, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 7.88e-06, | |
| "loss": 0.5068, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8.380000000000001e-06, | |
| "loss": 0.4787, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8.880000000000001e-06, | |
| "loss": 0.4744, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.38e-06, | |
| "loss": 0.4914, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.88e-06, | |
| "loss": 0.4643, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.810000000000001e-06, | |
| "loss": 0.4792, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.56e-06, | |
| "loss": 0.4715, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.31e-06, | |
| "loss": 0.4405, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.060000000000001e-06, | |
| "loss": 0.4577, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.81e-06, | |
| "loss": 0.4624, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.560000000000001e-06, | |
| "loss": 0.3639, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 8.31e-06, | |
| "loss": 0.4156, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 8.06e-06, | |
| "loss": 0.4121, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 7.810000000000001e-06, | |
| "loss": 0.3885, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 7.5600000000000005e-06, | |
| "loss": 0.4401, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 7.31e-06, | |
| "loss": 0.4141, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 7.06e-06, | |
| "loss": 0.4179, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 6.810000000000001e-06, | |
| "loss": 0.4299, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 6.560000000000001e-06, | |
| "loss": 0.3733, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 6.3100000000000006e-06, | |
| "loss": 0.429, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 6.0600000000000004e-06, | |
| "loss": 0.3495, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 5.81e-06, | |
| "loss": 0.373, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 5.560000000000001e-06, | |
| "loss": 0.3427, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 5.310000000000001e-06, | |
| "loss": 0.3687, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 5.060000000000001e-06, | |
| "loss": 0.3749, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_cer": 8.575715070233361, | |
| "eval_loss": 0.5007154941558838, | |
| "eval_runtime": 2429.0625, | |
| "eval_samples_per_second": 0.804, | |
| "eval_steps_per_second": 0.402, | |
| "eval_wer": 25.293262636395276, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.8100000000000005e-06, | |
| "loss": 0.3366, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.56e-06, | |
| "loss": 0.3493, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.31e-06, | |
| "loss": 0.3721, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.060000000000001e-06, | |
| "loss": 0.3504, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.8100000000000004e-06, | |
| "loss": 0.3543, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.5600000000000002e-06, | |
| "loss": 0.395, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.3100000000000005e-06, | |
| "loss": 0.3789, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.0600000000000003e-06, | |
| "loss": 0.3223, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.8100000000000006e-06, | |
| "loss": 0.3242, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.56e-06, | |
| "loss": 0.3701, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.3100000000000003e-06, | |
| "loss": 0.3882, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.06e-06, | |
| "loss": 0.3678, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.81e-06, | |
| "loss": 0.3539, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.56e-06, | |
| "loss": 0.3723, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.3100000000000002e-06, | |
| "loss": 0.3184, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.06e-06, | |
| "loss": 0.3204, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.100000000000001e-07, | |
| "loss": 0.3884, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 5.6e-07, | |
| "loss": 0.3948, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.1000000000000005e-07, | |
| "loss": 0.3151, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 6.000000000000001e-08, | |
| "loss": 0.3676, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "step": 1500, | |
| "total_flos": 9.728999424e+16, | |
| "train_loss": 0.4858832302093506, | |
| "train_runtime": 2744.5265, | |
| "train_samples_per_second": 0.547, | |
| "train_steps_per_second": 0.547 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_cer": 8.575715070233361, | |
| "eval_loss": 0.5007154941558838, | |
| "eval_runtime": 2408.5648, | |
| "eval_samples_per_second": 0.811, | |
| "eval_steps_per_second": 0.406, | |
| "eval_wer": 25.293262636395276, | |
| "step": 1500 | |
| } | |
| ], | |
| "max_steps": 1500, | |
| "num_train_epochs": 1, | |
| "total_flos": 9.728999424e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |