| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 30.0, | |
| "global_step": 960, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 7.5e-05, | |
| "loss": 13.0978, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 13.780136108398438, | |
| "eval_runtime": 82.8799, | |
| "eval_samples_per_second": 7.891, | |
| "eval_wer": 1.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.00015, | |
| "loss": 7.3093, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_loss": 3.198237419128418, | |
| "eval_runtime": 81.5893, | |
| "eval_samples_per_second": 8.016, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 0.000225, | |
| "loss": 3.0745, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "eval_loss": 3.1082892417907715, | |
| "eval_runtime": 82.4037, | |
| "eval_samples_per_second": 7.937, | |
| "eval_wer": 1.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 0.0003, | |
| "loss": 3.0551, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "eval_loss": 3.0994772911071777, | |
| "eval_runtime": 82.7226, | |
| "eval_samples_per_second": 7.906, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 0.00028026315789473683, | |
| "loss": 3.0632, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "eval_loss": 3.0916755199432373, | |
| "eval_runtime": 83.5323, | |
| "eval_samples_per_second": 7.829, | |
| "eval_wer": 1.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 0.0002605263157894737, | |
| "loss": 3.0391, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "eval_loss": 3.0707435607910156, | |
| "eval_runtime": 82.7328, | |
| "eval_samples_per_second": 7.905, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 10.94, | |
| "learning_rate": 0.00024078947368421052, | |
| "loss": 3.0321, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 10.94, | |
| "eval_loss": 3.0443670749664307, | |
| "eval_runtime": 84.1437, | |
| "eval_samples_per_second": 7.772, | |
| "eval_wer": 1.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 0.00022105263157894733, | |
| "loss": 3.0069, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "eval_loss": 2.998474359512329, | |
| "eval_runtime": 83.9178, | |
| "eval_samples_per_second": 7.793, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 0.0002013157894736842, | |
| "loss": 2.9623, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "eval_loss": 2.866849184036255, | |
| "eval_runtime": 82.5906, | |
| "eval_samples_per_second": 7.919, | |
| "eval_wer": 1.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 15.62, | |
| "learning_rate": 0.00018157894736842105, | |
| "loss": 2.4771, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 15.62, | |
| "eval_loss": 1.5367902517318726, | |
| "eval_runtime": 85.6456, | |
| "eval_samples_per_second": 7.636, | |
| "eval_wer": 0.9838912133891213, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 17.19, | |
| "learning_rate": 0.00016184210526315788, | |
| "loss": 1.0561, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 17.19, | |
| "eval_loss": 0.6924143433570862, | |
| "eval_runtime": 85.1658, | |
| "eval_samples_per_second": 7.679, | |
| "eval_wer": 0.7548117154811715, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 0.0001421052631578947, | |
| "loss": 0.5288, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "eval_loss": 0.5334728956222534, | |
| "eval_runtime": 83.737, | |
| "eval_samples_per_second": 7.81, | |
| "eval_wer": 0.6569037656903766, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 20.31, | |
| "learning_rate": 0.00012236842105263157, | |
| "loss": 0.3581, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 20.31, | |
| "eval_loss": 0.48591092228889465, | |
| "eval_runtime": 86.2479, | |
| "eval_samples_per_second": 7.583, | |
| "eval_wer": 0.605857740585774, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 21.88, | |
| "learning_rate": 0.00010263157894736841, | |
| "loss": 0.2638, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 21.88, | |
| "eval_loss": 0.4631027579307556, | |
| "eval_runtime": 84.0825, | |
| "eval_samples_per_second": 7.778, | |
| "eval_wer": 0.5648535564853556, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 23.44, | |
| "learning_rate": 8.289473684210526e-05, | |
| "loss": 0.2284, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 23.44, | |
| "eval_loss": 0.4597685933113098, | |
| "eval_runtime": 86.122, | |
| "eval_samples_per_second": 7.594, | |
| "eval_wer": 0.5594142259414226, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 6.315789473684209e-05, | |
| "loss": 0.1965, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.4614764153957367, | |
| "eval_runtime": 86.0272, | |
| "eval_samples_per_second": 7.602, | |
| "eval_wer": 0.5535564853556485, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 4.342105263157895e-05, | |
| "loss": 0.1837, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "eval_loss": 0.4499300718307495, | |
| "eval_runtime": 89.3292, | |
| "eval_samples_per_second": 7.321, | |
| "eval_wer": 0.5349372384937239, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 28.12, | |
| "learning_rate": 2.3684210526315787e-05, | |
| "loss": 0.187, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 28.12, | |
| "eval_loss": 0.45425695180892944, | |
| "eval_runtime": 85.6275, | |
| "eval_samples_per_second": 7.638, | |
| "eval_wer": 0.5345188284518828, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 29.69, | |
| "learning_rate": 3.947368421052631e-06, | |
| "loss": 0.1568, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 29.69, | |
| "eval_loss": 0.4458238184452057, | |
| "eval_runtime": 84.9753, | |
| "eval_samples_per_second": 7.696, | |
| "eval_wer": 0.5290794979079498, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 960, | |
| "total_flos": 8.556740517881789e+18, | |
| "train_runtime": 8781.3793, | |
| "train_samples_per_second": 0.109 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.4455166161060333, | |
| "eval_runtime": 81.4513, | |
| "eval_samples_per_second": 8.029, | |
| "eval_wer": 0.5288702928870292, | |
| "step": 960 | |
| } | |
| ], | |
| "max_steps": 960, | |
| "num_train_epochs": 30, | |
| "total_flos": 8.556740517881789e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |