| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 79.992, | |
| "global_step": 4960, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 5.8789, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "eval_loss": 3.1512646675109863, | |
| "eval_runtime": 167.7164, | |
| "eval_samples_per_second": 9.82, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 0.00029327354260089687, | |
| "loss": 1.8544, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "eval_loss": 0.4943191707134247, | |
| "eval_runtime": 170.9272, | |
| "eval_samples_per_second": 9.636, | |
| "eval_wer": 0.5103553299492386, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 14.51, | |
| "learning_rate": 0.0002730941704035874, | |
| "loss": 0.2628, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.51, | |
| "eval_loss": 0.46906277537345886, | |
| "eval_runtime": 172.4339, | |
| "eval_samples_per_second": 9.551, | |
| "eval_wer": 0.43147208121827413, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "learning_rate": 0.000252914798206278, | |
| "loss": 0.124, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "eval_loss": 0.4130130708217621, | |
| "eval_runtime": 172.8773, | |
| "eval_samples_per_second": 9.527, | |
| "eval_wer": 0.36, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 24.19, | |
| "learning_rate": 0.0002327354260089686, | |
| "loss": 0.0857, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.19, | |
| "eval_loss": 0.43019285798072815, | |
| "eval_runtime": 176.7931, | |
| "eval_samples_per_second": 9.316, | |
| "eval_wer": 0.3513705583756345, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 29.03, | |
| "learning_rate": 0.00021255605381165918, | |
| "loss": 0.0653, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 29.03, | |
| "eval_loss": 0.4362075626850128, | |
| "eval_runtime": 190.6223, | |
| "eval_samples_per_second": 8.64, | |
| "eval_wer": 0.3595939086294416, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 33.86, | |
| "learning_rate": 0.00019237668161434975, | |
| "loss": 0.0632, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 33.86, | |
| "eval_loss": 0.4273272156715393, | |
| "eval_runtime": 177.8151, | |
| "eval_samples_per_second": 9.262, | |
| "eval_wer": 0.33390862944162436, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 38.7, | |
| "learning_rate": 0.00017219730941704035, | |
| "loss": 0.0499, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 38.7, | |
| "eval_loss": 0.4455905258655548, | |
| "eval_runtime": 177.4805, | |
| "eval_samples_per_second": 9.28, | |
| "eval_wer": 0.32558375634517767, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 43.54, | |
| "learning_rate": 0.00015201793721973095, | |
| "loss": 0.0412, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 43.54, | |
| "eval_loss": 0.4279979467391968, | |
| "eval_runtime": 179.3129, | |
| "eval_samples_per_second": 9.185, | |
| "eval_wer": 0.3316751269035533, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 48.38, | |
| "learning_rate": 0.00013183856502242152, | |
| "loss": 0.0428, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 48.38, | |
| "eval_loss": 0.42648839950561523, | |
| "eval_runtime": 179.9053, | |
| "eval_samples_per_second": 9.155, | |
| "eval_wer": 0.3197969543147208, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 53.22, | |
| "learning_rate": 0.0001116591928251121, | |
| "loss": 0.0345, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 53.22, | |
| "eval_loss": 0.46762773394584656, | |
| "eval_runtime": 179.9553, | |
| "eval_samples_per_second": 9.152, | |
| "eval_wer": 0.31228426395939085, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 58.06, | |
| "learning_rate": 9.147982062780269e-05, | |
| "loss": 0.0335, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 58.06, | |
| "eval_loss": 0.4403984248638153, | |
| "eval_runtime": 181.1578, | |
| "eval_samples_per_second": 9.092, | |
| "eval_wer": 0.3096446700507614, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 62.9, | |
| "learning_rate": 7.130044843049327e-05, | |
| "loss": 0.0308, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 62.9, | |
| "eval_loss": 0.4584444463253021, | |
| "eval_runtime": 182.2608, | |
| "eval_samples_per_second": 9.036, | |
| "eval_wer": 0.3082233502538071, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 67.74, | |
| "learning_rate": 5.112107623318385e-05, | |
| "loss": 0.0253, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 67.74, | |
| "eval_loss": 0.4203069806098938, | |
| "eval_runtime": 182.5783, | |
| "eval_samples_per_second": 9.021, | |
| "eval_wer": 0.3001015228426396, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 72.58, | |
| "learning_rate": 3.094170403587444e-05, | |
| "loss": 0.0243, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 72.58, | |
| "eval_loss": 0.43954339623451233, | |
| "eval_runtime": 183.1424, | |
| "eval_samples_per_second": 8.993, | |
| "eval_wer": 0.29736040609137054, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 77.42, | |
| "learning_rate": 1.0762331838565022e-05, | |
| "loss": 0.0229, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 77.42, | |
| "eval_loss": 0.44123971462249756, | |
| "eval_runtime": 183.8976, | |
| "eval_samples_per_second": 8.956, | |
| "eval_wer": 0.29218274111675124, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 79.99, | |
| "step": 4960, | |
| "total_flos": 3.4759190857567523e+19, | |
| "train_runtime": 32940.4351, | |
| "train_samples_per_second": 0.151 | |
| } | |
| ], | |
| "max_steps": 4960, | |
| "num_train_epochs": 80, | |
| "total_flos": 3.4759190857567523e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |