| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 29.357798165137616, | |
| "global_step": 3200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 5.0456, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "eval_loss": 2.805786609649658, | |
| "eval_runtime": 214.876, | |
| "eval_samples_per_second": 7.665, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 0.0002675090252707581, | |
| "loss": 0.8437, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "eval_loss": 0.437711238861084, | |
| "eval_runtime": 217.8287, | |
| "eval_samples_per_second": 7.561, | |
| "eval_wer": 0.5915636809314677, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 0.00022418772563176893, | |
| "loss": 0.2449, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "eval_loss": 0.3937138020992279, | |
| "eval_runtime": 222.9363, | |
| "eval_samples_per_second": 7.388, | |
| "eval_wer": 0.5292615667449698, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "learning_rate": 0.00018086642599277977, | |
| "loss": 0.1486, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 14.68, | |
| "eval_loss": 0.411156564950943, | |
| "eval_runtime": 224.0258, | |
| "eval_samples_per_second": 7.352, | |
| "eval_wer": 0.5094474517413952, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 18.35, | |
| "learning_rate": 0.00013754512635379062, | |
| "loss": 0.1077, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 18.35, | |
| "eval_loss": 0.41311565041542053, | |
| "eval_runtime": 224.2133, | |
| "eval_samples_per_second": 7.346, | |
| "eval_wer": 0.49474006740884485, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 9.422382671480144e-05, | |
| "loss": 0.0791, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "eval_loss": 0.43790802359580994, | |
| "eval_runtime": 224.8995, | |
| "eval_samples_per_second": 7.323, | |
| "eval_wer": 0.48707997140230824, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 25.69, | |
| "learning_rate": 5.090252707581227e-05, | |
| "loss": 0.0722, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 25.69, | |
| "eval_loss": 0.4185827076435089, | |
| "eval_runtime": 222.949, | |
| "eval_samples_per_second": 7.387, | |
| "eval_wer": 0.46798079869267695, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 29.36, | |
| "learning_rate": 7.581227436823104e-06, | |
| "loss": 0.0601, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 29.36, | |
| "eval_loss": 0.41515499353408813, | |
| "eval_runtime": 225.7543, | |
| "eval_samples_per_second": 7.296, | |
| "eval_wer": 0.4620569911142886, | |
| "step": 3200 | |
| } | |
| ], | |
| "max_steps": 3270, | |
| "num_train_epochs": 30, | |
| "total_flos": 1.260196128535726e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |