| { | |
| "best_metric": 0.027737604454159737, | |
| "best_model_checkpoint": "/home/cloudwalker/ASVmodel/wavlm-base_5/checkpoint-100", | |
| "epoch": 9.98109640831758, | |
| "eval_steps": 100, | |
| "global_step": 3960, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.575757575757576e-05, | |
| "loss": 0.3764, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.9947673482530993, | |
| "eval_loss": 0.027737604454159737, | |
| "eval_runtime": 497.2467, | |
| "eval_samples_per_second": 49.963, | |
| "eval_steps_per_second": 24.982, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00015151515151515152, | |
| "loss": 0.1211, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.998108195137659, | |
| "eval_loss": 0.02966056950390339, | |
| "eval_runtime": 498.935, | |
| "eval_samples_per_second": 49.794, | |
| "eval_steps_per_second": 24.897, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00022727272727272725, | |
| "loss": 0.2525, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.9168008372242795, | |
| "eval_loss": 1.283957839012146, | |
| "eval_runtime": 499.0992, | |
| "eval_samples_per_second": 49.778, | |
| "eval_steps_per_second": 24.889, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00029966329966329963, | |
| "loss": 0.784, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.34426796436309814, | |
| "eval_runtime": 499.2746, | |
| "eval_samples_per_second": 49.76, | |
| "eval_steps_per_second": 24.88, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00029124579124579125, | |
| "loss": 0.6053, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.3957619071006775, | |
| "eval_runtime": 499.3187, | |
| "eval_samples_per_second": 49.756, | |
| "eval_steps_per_second": 24.878, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0002828282828282828, | |
| "loss": 0.6038, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.4848286509513855, | |
| "eval_runtime": 499.175, | |
| "eval_samples_per_second": 49.77, | |
| "eval_steps_per_second": 24.885, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0002744107744107744, | |
| "loss": 0.5996, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.39541468024253845, | |
| "eval_runtime": 499.7897, | |
| "eval_samples_per_second": 49.709, | |
| "eval_steps_per_second": 24.854, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.00026599326599326595, | |
| "loss": 0.5914, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.3970233201980591, | |
| "eval_runtime": 499.6888, | |
| "eval_samples_per_second": 49.719, | |
| "eval_steps_per_second": 24.859, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.00025757575757575756, | |
| "loss": 0.6077, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.4722130298614502, | |
| "eval_runtime": 499.722, | |
| "eval_samples_per_second": 49.716, | |
| "eval_steps_per_second": 24.858, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.00024915824915824913, | |
| "loss": 0.5991, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.43623748421669006, | |
| "eval_runtime": 499.9532, | |
| "eval_samples_per_second": 49.693, | |
| "eval_steps_per_second": 24.846, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.00024074074074074072, | |
| "loss": 0.5813, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.38707101345062256, | |
| "eval_runtime": 499.9678, | |
| "eval_samples_per_second": 49.691, | |
| "eval_steps_per_second": 24.846, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0002323232323232323, | |
| "loss": 0.5953, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.40134623646736145, | |
| "eval_runtime": 499.6897, | |
| "eval_samples_per_second": 49.719, | |
| "eval_steps_per_second": 24.859, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.0002239057239057239, | |
| "loss": 0.5957, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.46927762031555176, | |
| "eval_runtime": 499.7933, | |
| "eval_samples_per_second": 49.709, | |
| "eval_steps_per_second": 24.854, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 0.00021548821548821544, | |
| "loss": 0.5852, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.387899786233902, | |
| "eval_runtime": 499.9294, | |
| "eval_samples_per_second": 49.695, | |
| "eval_steps_per_second": 24.848, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 0.00020707070707070703, | |
| "loss": 0.6066, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.42799168825149536, | |
| "eval_runtime": 499.9481, | |
| "eval_samples_per_second": 49.693, | |
| "eval_steps_per_second": 24.847, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.00019865319865319862, | |
| "loss": 0.6085, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.4358781576156616, | |
| "eval_runtime": 499.7505, | |
| "eval_samples_per_second": 49.713, | |
| "eval_steps_per_second": 24.856, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 0.00019023569023569022, | |
| "loss": 0.5944, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.41665858030319214, | |
| "eval_runtime": 499.6545, | |
| "eval_samples_per_second": 49.722, | |
| "eval_steps_per_second": 24.861, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 0.0001818181818181818, | |
| "loss": 0.5994, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.4139242172241211, | |
| "eval_runtime": 499.4729, | |
| "eval_samples_per_second": 49.74, | |
| "eval_steps_per_second": 24.87, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 0.0001734006734006734, | |
| "loss": 0.5953, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.42556148767471313, | |
| "eval_runtime": 499.5722, | |
| "eval_samples_per_second": 49.731, | |
| "eval_steps_per_second": 24.865, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 0.000164983164983165, | |
| "loss": 0.5929, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.4370674192905426, | |
| "eval_runtime": 499.6245, | |
| "eval_samples_per_second": 49.725, | |
| "eval_steps_per_second": 24.863, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 0.00015656565656565653, | |
| "loss": 0.6067, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.4254782199859619, | |
| "eval_runtime": 499.8266, | |
| "eval_samples_per_second": 49.705, | |
| "eval_steps_per_second": 24.853, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 0.00014814814814814812, | |
| "loss": 0.5944, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.41206374764442444, | |
| "eval_runtime": 499.9874, | |
| "eval_samples_per_second": 49.689, | |
| "eval_steps_per_second": 24.845, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 0.0001397306397306397, | |
| "loss": 0.5926, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.42098236083984375, | |
| "eval_runtime": 499.6375, | |
| "eval_samples_per_second": 49.724, | |
| "eval_steps_per_second": 24.862, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 0.0001313131313131313, | |
| "loss": 0.594, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.40572819113731384, | |
| "eval_runtime": 499.6473, | |
| "eval_samples_per_second": 49.723, | |
| "eval_steps_per_second": 24.862, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 0.0001228956228956229, | |
| "loss": 0.6042, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.42515799403190613, | |
| "eval_runtime": 499.6019, | |
| "eval_samples_per_second": 49.728, | |
| "eval_steps_per_second": 24.864, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 0.00011447811447811446, | |
| "loss": 0.5971, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.395828515291214, | |
| "eval_runtime": 500.1612, | |
| "eval_samples_per_second": 49.672, | |
| "eval_steps_per_second": 24.836, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 0.00010606060606060605, | |
| "loss": 0.597, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.41235631704330444, | |
| "eval_runtime": 499.5804, | |
| "eval_samples_per_second": 49.73, | |
| "eval_steps_per_second": 24.865, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 9.764309764309764e-05, | |
| "loss": 0.5816, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.41006505489349365, | |
| "eval_runtime": 499.6536, | |
| "eval_samples_per_second": 49.722, | |
| "eval_steps_per_second": 24.861, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 8.92255892255892e-05, | |
| "loss": 0.5944, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.42578616738319397, | |
| "eval_runtime": 499.7205, | |
| "eval_samples_per_second": 49.716, | |
| "eval_steps_per_second": 24.858, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 8.08080808080808e-05, | |
| "loss": 0.6053, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.4414595365524292, | |
| "eval_runtime": 499.6011, | |
| "eval_samples_per_second": 49.728, | |
| "eval_steps_per_second": 24.864, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 7.239057239057239e-05, | |
| "loss": 0.5894, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.40666893124580383, | |
| "eval_runtime": 499.6727, | |
| "eval_samples_per_second": 49.721, | |
| "eval_steps_per_second": 24.86, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 6.397306397306397e-05, | |
| "loss": 0.5987, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.41087645292282104, | |
| "eval_runtime": 499.5755, | |
| "eval_samples_per_second": 49.73, | |
| "eval_steps_per_second": 24.865, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 5.5555555555555545e-05, | |
| "loss": 0.5846, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.4095437824726105, | |
| "eval_runtime": 499.7301, | |
| "eval_samples_per_second": 49.715, | |
| "eval_steps_per_second": 24.857, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 4.7138047138047136e-05, | |
| "loss": 0.5982, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.41868552565574646, | |
| "eval_runtime": 499.638, | |
| "eval_samples_per_second": 49.724, | |
| "eval_steps_per_second": 24.862, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 3.8720538720538714e-05, | |
| "loss": 0.5932, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.4124181866645813, | |
| "eval_runtime": 499.6303, | |
| "eval_samples_per_second": 49.725, | |
| "eval_steps_per_second": 24.862, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 3.03030303030303e-05, | |
| "loss": 0.6007, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.42121654748916626, | |
| "eval_runtime": 499.864, | |
| "eval_samples_per_second": 49.702, | |
| "eval_steps_per_second": 24.851, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 2.1885521885521884e-05, | |
| "loss": 0.6041, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.4257338345050812, | |
| "eval_runtime": 499.3339, | |
| "eval_samples_per_second": 49.754, | |
| "eval_steps_per_second": 24.877, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 1.3468013468013465e-05, | |
| "loss": 0.5859, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.4176446497440338, | |
| "eval_runtime": 499.7293, | |
| "eval_samples_per_second": 49.715, | |
| "eval_steps_per_second": 24.857, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 5.05050505050505e-06, | |
| "loss": 0.5842, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "eval_accuracy": 0.8974400257607471, | |
| "eval_loss": 0.41514307260513306, | |
| "eval_runtime": 499.5922, | |
| "eval_samples_per_second": 49.729, | |
| "eval_steps_per_second": 24.864, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "step": 3960, | |
| "total_flos": 1.506420070651024e+19, | |
| "train_loss": 0.5747933341999246, | |
| "train_runtime": 22880.3496, | |
| "train_samples_per_second": 11.092, | |
| "train_steps_per_second": 0.173 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 3960, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "total_flos": 1.506420070651024e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |