| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.38, | |
| "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": 6.712113404111031e-06, | |
| "loss": 0.4636, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.360489289678585e-06, | |
| "loss": 0.291, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.28666248215634e-06, | |
| "loss": 0.2413, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.911356165197841e-06, | |
| "loss": 0.2598, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.777777777777779e-06, | |
| "loss": 0.2503, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.5e-06, | |
| "loss": 0.313, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.222222222222224e-06, | |
| "loss": 0.2482, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.944444444444446e-06, | |
| "loss": 0.2711, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.666666666666668e-06, | |
| "loss": 0.2772, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.2383, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.122222222222223e-06, | |
| "loss": 0.2205, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.844444444444446e-06, | |
| "loss": 0.1983, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.566666666666667e-06, | |
| "loss": 0.1831, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.28888888888889e-06, | |
| "loss": 0.203, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.011111111111112e-06, | |
| "loss": 0.2367, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.733333333333334e-06, | |
| "loss": 0.2178, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.455555555555556e-06, | |
| "loss": 0.2264, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.177777777777778e-06, | |
| "loss": 0.2275, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.9e-06, | |
| "loss": 0.1827, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.622222222222222e-06, | |
| "loss": 0.1653, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.344444444444446e-06, | |
| "loss": 0.1843, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.0666666666666676e-06, | |
| "loss": 0.1774, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.7888888888888894e-06, | |
| "loss": 0.1619, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.511111111111111e-06, | |
| "loss": 0.1438, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.233333333333334e-06, | |
| "loss": 0.1546, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.955555555555556e-06, | |
| "loss": 0.1713, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.6777777777777778e-06, | |
| "loss": 0.1324, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.4000000000000005e-06, | |
| "loss": 0.1132, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.1222222222222228e-06, | |
| "loss": 0.1181, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 2.8444444444444446e-06, | |
| "loss": 0.1062, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2.566666666666667e-06, | |
| "loss": 0.1316, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 2.2888888888888892e-06, | |
| "loss": 0.1089, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.011111111111111e-06, | |
| "loss": 0.1184, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 1.7333333333333336e-06, | |
| "loss": 0.113, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.4555555555555557e-06, | |
| "loss": 0.0999, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.1777777777777778e-06, | |
| "loss": 0.0976, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 9.000000000000001e-07, | |
| "loss": 0.0746, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 6.222222222222223e-07, | |
| "loss": 0.0754, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.444444444444445e-07, | |
| "loss": 0.0924, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 6.666666666666668e-08, | |
| "loss": 0.1078, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 0.206787109375, | |
| "eval_runtime": 2390.8973, | |
| "eval_samples_per_second": 3.005, | |
| "eval_steps_per_second": 0.188, | |
| "eval_wer": 10.043535294005817, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "step": 1000, | |
| "total_flos": 6.792236475328391e+19, | |
| "train_loss": 0.1849537353515625, | |
| "train_runtime": 10231.9595, | |
| "train_samples_per_second": 3.127, | |
| "train_steps_per_second": 0.098 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 6.792236475328391e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |