| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 23.83828382838284, | |
| "global_step": 3600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 6.5741, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 3.4423439502716064, | |
| "eval_runtime": 231.306, | |
| "eval_samples_per_second": 9.459, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 0.0002711907810499359, | |
| "loss": 1.6231, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "eval_loss": 0.6918022036552429, | |
| "eval_runtime": 234.8428, | |
| "eval_samples_per_second": 9.317, | |
| "eval_wer": 0.7177260916407884, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 0.00023277848911651725, | |
| "loss": 0.5103, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "eval_loss": 0.5981740951538086, | |
| "eval_runtime": 233.6413, | |
| "eval_samples_per_second": 9.365, | |
| "eval_wer": 0.6444007858546169, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.59, | |
| "learning_rate": 0.0001943661971830986, | |
| "loss": 0.316, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 10.59, | |
| "eval_loss": 0.6127611398696899, | |
| "eval_runtime": 239.3303, | |
| "eval_samples_per_second": 9.142, | |
| "eval_wer": 0.6053615564991445, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 0.0001559539052496799, | |
| "loss": 0.227, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "eval_loss": 0.6392495036125183, | |
| "eval_runtime": 236.7294, | |
| "eval_samples_per_second": 9.243, | |
| "eval_wer": 0.5767158882058432, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 15.89, | |
| "learning_rate": 0.00011754161331626119, | |
| "loss": 0.1783, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 15.89, | |
| "eval_loss": 0.6448690891265869, | |
| "eval_runtime": 240.8912, | |
| "eval_samples_per_second": 9.083, | |
| "eval_wer": 0.5625831801761836, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 18.54, | |
| "learning_rate": 7.91293213828425e-05, | |
| "loss": 0.1346, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 18.54, | |
| "eval_loss": 0.6509573459625244, | |
| "eval_runtime": 238.9168, | |
| "eval_samples_per_second": 9.158, | |
| "eval_wer": 0.5524431206033336, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 21.19, | |
| "learning_rate": 4.071702944942381e-05, | |
| "loss": 0.1149, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 21.19, | |
| "eval_loss": 0.7118895053863525, | |
| "eval_runtime": 239.1827, | |
| "eval_samples_per_second": 9.148, | |
| "eval_wer": 0.5582736548577223, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 23.84, | |
| "learning_rate": 2.3047375160051214e-06, | |
| "loss": 0.1024, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 23.84, | |
| "eval_loss": 0.6984374523162842, | |
| "eval_runtime": 239.7197, | |
| "eval_samples_per_second": 9.127, | |
| "eval_wer": 0.5488307243805057, | |
| "step": 3600 | |
| } | |
| ], | |
| "max_steps": 3624, | |
| "num_train_epochs": 24, | |
| "total_flos": 1.4828294022260212e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |