|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 7.041, |
|
"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": 6.505149978319905e-06, |
|
"loss": 0.4821, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 8.266062568876717e-06, |
|
"loss": 0.2576, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.225490200071284e-06, |
|
"loss": 0.2123, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 9.888618026444238e-06, |
|
"loss": 0.1984, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 9.78888888888889e-06, |
|
"loss": 0.1729, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 9.511111111111112e-06, |
|
"loss": 0.1765, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 9.233333333333334e-06, |
|
"loss": 0.1454, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 8.955555555555555e-06, |
|
"loss": 0.0988, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 8.677777777777779e-06, |
|
"loss": 0.0867, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 8.400000000000001e-06, |
|
"loss": 0.0755, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 8.122222222222223e-06, |
|
"loss": 0.0758, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 7.844444444444446e-06, |
|
"loss": 0.0776, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 7.566666666666667e-06, |
|
"loss": 0.0565, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 7.28888888888889e-06, |
|
"loss": 0.0462, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 7.011111111111112e-06, |
|
"loss": 0.0417, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 6.733333333333334e-06, |
|
"loss": 0.0375, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 6.455555555555556e-06, |
|
"loss": 0.0382, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 6.177777777777778e-06, |
|
"loss": 0.0341, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 3.06, |
|
"learning_rate": 5.9e-06, |
|
"loss": 0.0257, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 3.09, |
|
"learning_rate": 5.622222222222222e-06, |
|
"loss": 0.021, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 3.11, |
|
"learning_rate": 5.344444444444446e-06, |
|
"loss": 0.0202, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 5.0666666666666676e-06, |
|
"loss": 0.0188, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"learning_rate": 4.7888888888888894e-06, |
|
"loss": 0.0133, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 4.05, |
|
"learning_rate": 4.511111111111111e-06, |
|
"loss": 0.009, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 4.08, |
|
"learning_rate": 4.233333333333334e-06, |
|
"loss": 0.0093, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 4.1, |
|
"learning_rate": 3.955555555555556e-06, |
|
"loss": 0.0114, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 4.13, |
|
"learning_rate": 3.6777777777777778e-06, |
|
"loss": 0.0155, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 5.01, |
|
"learning_rate": 3.4000000000000005e-06, |
|
"loss": 0.0086, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 5.04, |
|
"learning_rate": 3.1222222222222228e-06, |
|
"loss": 0.006, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 5.07, |
|
"learning_rate": 2.8444444444444446e-06, |
|
"loss": 0.0051, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 5.09, |
|
"learning_rate": 2.566666666666667e-06, |
|
"loss": 0.005, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 5.12, |
|
"learning_rate": 2.2888888888888892e-06, |
|
"loss": 0.0056, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 2.011111111111111e-06, |
|
"loss": 0.0058, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 6.03, |
|
"learning_rate": 1.7333333333333336e-06, |
|
"loss": 0.0032, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 6.05, |
|
"learning_rate": 1.4555555555555557e-06, |
|
"loss": 0.0034, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 6.08, |
|
"learning_rate": 1.1777777777777778e-06, |
|
"loss": 0.0028, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 6.1, |
|
"learning_rate": 9.000000000000001e-07, |
|
"loss": 0.0026, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 6.13, |
|
"learning_rate": 6.222222222222223e-07, |
|
"loss": 0.0026, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 7.02, |
|
"learning_rate": 3.444444444444445e-07, |
|
"loss": 0.0024, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 7.04, |
|
"learning_rate": 6.666666666666668e-08, |
|
"loss": 0.0023, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 7.04, |
|
"eval_loss": 0.32080078125, |
|
"eval_runtime": 606.4457, |
|
"eval_samples_per_second": 2.998, |
|
"eval_steps_per_second": 0.188, |
|
"eval_wer": 13.404004711425205, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 7.04, |
|
"step": 1000, |
|
"total_flos": 6.751046955557716e+19, |
|
"train_loss": 0.0628205451965332, |
|
"train_runtime": 8449.4829, |
|
"train_samples_per_second": 3.787, |
|
"train_steps_per_second": 0.118 |
|
} |
|
], |
|
"max_steps": 1000, |
|
"num_train_epochs": 9223372036854775807, |
|
"total_flos": 6.751046955557716e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|