| { | |
| "best_metric": 0.8950359984842744, | |
| "best_model_checkpoint": "wavlm-large/checkpoint-15000", | |
| "epoch": 31.998484082870135, | |
| "global_step": 15808, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 9.487666034155598e-06, | |
| "loss": 4.7405, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_accuracy": 0.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 5.152532577514648, | |
| "eval_precision": 0.0, | |
| "eval_runtime": 231.7392, | |
| "eval_samples_per_second": 11.388, | |
| "eval_steps_per_second": 0.949, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.8975332068311197e-05, | |
| "loss": 4.4299, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_accuracy": 0.0, | |
| "eval_f1": 0.0, | |
| "eval_loss": 5.896852016448975, | |
| "eval_precision": 0.0, | |
| "eval_runtime": 229.527, | |
| "eval_samples_per_second": 11.498, | |
| "eval_steps_per_second": 0.958, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 2.846299810246679e-05, | |
| "loss": 4.2868, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_accuracy": 0.0018946570670708603, | |
| "eval_f1": 0.002260186233515175, | |
| "eval_loss": 4.930444717407227, | |
| "eval_precision": 0.0030713084224438304, | |
| "eval_runtime": 224.9204, | |
| "eval_samples_per_second": 11.733, | |
| "eval_steps_per_second": 0.978, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 2.9116468686300697e-05, | |
| "loss": 3.6242, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "eval_accuracy": 0.04092459264873058, | |
| "eval_f1": 0.023734423060596616, | |
| "eval_loss": 4.339611053466797, | |
| "eval_precision": 0.02235030209371723, | |
| "eval_runtime": 231.3364, | |
| "eval_samples_per_second": 11.408, | |
| "eval_steps_per_second": 0.951, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 2.8062135376396992e-05, | |
| "loss": 2.686, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "eval_accuracy": 0.054945054945054944, | |
| "eval_f1": 0.030815499275931264, | |
| "eval_loss": 3.9399423599243164, | |
| "eval_precision": 0.03198760556742773, | |
| "eval_runtime": 229.8015, | |
| "eval_samples_per_second": 11.484, | |
| "eval_steps_per_second": 0.957, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 2.700780206649329e-05, | |
| "loss": 1.9284, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "eval_accuracy": 0.05001894657067071, | |
| "eval_f1": 0.044225493965773466, | |
| "eval_loss": 3.7735581398010254, | |
| "eval_precision": 0.07786075378351333, | |
| "eval_runtime": 229.6709, | |
| "eval_samples_per_second": 11.49, | |
| "eval_steps_per_second": 0.958, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 2.5953468756589585e-05, | |
| "loss": 1.3936, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "eval_accuracy": 0.094732853353543, | |
| "eval_f1": 0.09155559566994678, | |
| "eval_loss": 3.537994146347046, | |
| "eval_precision": 0.13805010974816684, | |
| "eval_runtime": 222.7345, | |
| "eval_samples_per_second": 11.848, | |
| "eval_steps_per_second": 0.988, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 2.489913544668588e-05, | |
| "loss": 1.0764, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "eval_accuracy": 0.15839333080712392, | |
| "eval_f1": 0.1838779712805326, | |
| "eval_loss": 3.328141689300537, | |
| "eval_precision": 0.35144388335355753, | |
| "eval_runtime": 231.5928, | |
| "eval_samples_per_second": 11.395, | |
| "eval_steps_per_second": 0.95, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 2.3844802136782175e-05, | |
| "loss": 0.872, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "eval_accuracy": 0.2754831375521031, | |
| "eval_f1": 0.33153761364278084, | |
| "eval_loss": 2.959165096282959, | |
| "eval_precision": 0.6026709651704474, | |
| "eval_runtime": 229.3101, | |
| "eval_samples_per_second": 11.508, | |
| "eval_steps_per_second": 0.959, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 10.12, | |
| "learning_rate": 2.279046882687847e-05, | |
| "loss": 0.7026, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 10.12, | |
| "eval_accuracy": 0.3971201212580523, | |
| "eval_f1": 0.4587007542105457, | |
| "eval_loss": 2.504917860031128, | |
| "eval_precision": 0.6970861611172207, | |
| "eval_runtime": 229.0193, | |
| "eval_samples_per_second": 11.523, | |
| "eval_steps_per_second": 0.961, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 2.1736135516974768e-05, | |
| "loss": 0.603, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "eval_accuracy": 0.5479348237968927, | |
| "eval_f1": 0.6128796045577696, | |
| "eval_loss": 2.1484670639038086, | |
| "eval_precision": 0.8073946450067734, | |
| "eval_runtime": 226.9343, | |
| "eval_samples_per_second": 11.629, | |
| "eval_steps_per_second": 0.969, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 2.0681802207071063e-05, | |
| "loss": 0.5042, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "eval_accuracy": 0.7014020462296324, | |
| "eval_f1": 0.7543542303794953, | |
| "eval_loss": 1.6532080173492432, | |
| "eval_precision": 0.8604295269195706, | |
| "eval_runtime": 229.9455, | |
| "eval_samples_per_second": 11.477, | |
| "eval_steps_per_second": 0.957, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 1.9627468897167357e-05, | |
| "loss": 0.4542, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "eval_accuracy": 0.7434634331186055, | |
| "eval_f1": 0.7989946253783239, | |
| "eval_loss": 1.4056562185287476, | |
| "eval_precision": 0.8941430548214513, | |
| "eval_runtime": 223.4311, | |
| "eval_samples_per_second": 11.811, | |
| "eval_steps_per_second": 0.985, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 14.17, | |
| "learning_rate": 1.8573135587263652e-05, | |
| "loss": 0.388, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 14.17, | |
| "eval_accuracy": 0.7802197802197802, | |
| "eval_f1": 0.8331608145111185, | |
| "eval_loss": 1.233764410018921, | |
| "eval_precision": 0.92185981522448, | |
| "eval_runtime": 231.0616, | |
| "eval_samples_per_second": 11.421, | |
| "eval_steps_per_second": 0.952, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 15.18, | |
| "learning_rate": 1.751880227735995e-05, | |
| "loss": 0.3515, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 15.18, | |
| "eval_accuracy": 0.8169761273209549, | |
| "eval_f1": 0.8681431492951, | |
| "eval_loss": 0.9898241758346558, | |
| "eval_precision": 0.9432737435443141, | |
| "eval_runtime": 229.2806, | |
| "eval_samples_per_second": 11.51, | |
| "eval_steps_per_second": 0.96, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 16.19, | |
| "learning_rate": 1.6464468967456245e-05, | |
| "loss": 0.3195, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 16.19, | |
| "eval_accuracy": 0.8067449791587723, | |
| "eval_f1": 0.8635483223798979, | |
| "eval_loss": 1.1404353380203247, | |
| "eval_precision": 0.9523356531691418, | |
| "eval_runtime": 224.231, | |
| "eval_samples_per_second": 11.769, | |
| "eval_steps_per_second": 0.981, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 17.21, | |
| "learning_rate": 1.541013565755254e-05, | |
| "loss": 0.2882, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 17.21, | |
| "eval_accuracy": 0.8177339901477833, | |
| "eval_f1": 0.8745687675592978, | |
| "eval_loss": 0.9810923933982849, | |
| "eval_precision": 0.9540040162889087, | |
| "eval_runtime": 230.2032, | |
| "eval_samples_per_second": 11.464, | |
| "eval_steps_per_second": 0.956, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 18.22, | |
| "learning_rate": 1.4355802347648837e-05, | |
| "loss": 0.2695, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 18.22, | |
| "eval_accuracy": 0.8317544524441076, | |
| "eval_f1": 0.8877909926292662, | |
| "eval_loss": 0.9483387470245361, | |
| "eval_precision": 0.9615575975196211, | |
| "eval_runtime": 227.4444, | |
| "eval_samples_per_second": 11.603, | |
| "eval_steps_per_second": 0.967, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 1.3301469037745133e-05, | |
| "loss": 0.2535, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "eval_accuracy": 0.8844259189086775, | |
| "eval_f1": 0.9198466869617786, | |
| "eval_loss": 0.6694388389587402, | |
| "eval_precision": 0.9692367120798446, | |
| "eval_runtime": 229.887, | |
| "eval_samples_per_second": 11.48, | |
| "eval_steps_per_second": 0.957, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 20.24, | |
| "learning_rate": 1.2247135727841428e-05, | |
| "loss": 0.2437, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 20.24, | |
| "eval_accuracy": 0.870026525198939, | |
| "eval_f1": 0.9124563736238709, | |
| "eval_loss": 0.7545726299285889, | |
| "eval_precision": 0.9655808349316077, | |
| "eval_runtime": 228.7826, | |
| "eval_samples_per_second": 11.535, | |
| "eval_steps_per_second": 0.962, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 21.25, | |
| "learning_rate": 1.1192802417937724e-05, | |
| "loss": 0.2376, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 21.25, | |
| "eval_accuracy": 0.88101553618795, | |
| "eval_f1": 0.9202319275311999, | |
| "eval_loss": 0.669846773147583, | |
| "eval_precision": 0.9694585382786844, | |
| "eval_runtime": 225.8023, | |
| "eval_samples_per_second": 11.687, | |
| "eval_steps_per_second": 0.974, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 22.27, | |
| "learning_rate": 1.013846910803402e-05, | |
| "loss": 0.2214, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 22.27, | |
| "eval_accuracy": 0.8726790450928382, | |
| "eval_f1": 0.9174460541012326, | |
| "eval_loss": 0.7156072854995728, | |
| "eval_precision": 0.972619503520754, | |
| "eval_runtime": 230.4418, | |
| "eval_samples_per_second": 11.452, | |
| "eval_steps_per_second": 0.955, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 23.28, | |
| "learning_rate": 9.084135798130316e-06, | |
| "loss": 0.2148, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 23.28, | |
| "eval_accuracy": 0.8931413414172035, | |
| "eval_f1": 0.9285879507962082, | |
| "eval_loss": 0.5982441902160645, | |
| "eval_precision": 0.9711102757838663, | |
| "eval_runtime": 229.8221, | |
| "eval_samples_per_second": 11.483, | |
| "eval_steps_per_second": 0.957, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 24.29, | |
| "learning_rate": 8.029802488226612e-06, | |
| "loss": 0.2087, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 24.29, | |
| "eval_accuracy": 0.8813944676013642, | |
| "eval_f1": 0.9242728727643769, | |
| "eval_loss": 0.7108510732650757, | |
| "eval_precision": 0.975723189780374, | |
| "eval_runtime": 223.4291, | |
| "eval_samples_per_second": 11.811, | |
| "eval_steps_per_second": 0.985, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 25.3, | |
| "learning_rate": 6.975469178322908e-06, | |
| "loss": 0.2039, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 25.3, | |
| "eval_accuracy": 0.8897309586964759, | |
| "eval_f1": 0.93059059028571, | |
| "eval_loss": 0.6577169895172119, | |
| "eval_precision": 0.9799317453490524, | |
| "eval_runtime": 229.7405, | |
| "eval_samples_per_second": 11.487, | |
| "eval_steps_per_second": 0.958, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 26.32, | |
| "learning_rate": 5.9211358684192026e-06, | |
| "loss": 0.1997, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 26.32, | |
| "eval_accuracy": 0.874573702159909, | |
| "eval_f1": 0.9203192830080359, | |
| "eval_loss": 0.7307356595993042, | |
| "eval_precision": 0.9774472205704657, | |
| "eval_runtime": 226.7422, | |
| "eval_samples_per_second": 11.639, | |
| "eval_steps_per_second": 0.97, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 27.33, | |
| "learning_rate": 4.866802558515498e-06, | |
| "loss": 0.1896, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 27.33, | |
| "eval_accuracy": 0.8904888215233043, | |
| "eval_f1": 0.9289821714067877, | |
| "eval_loss": 0.614262044429779, | |
| "eval_precision": 0.9747583516326127, | |
| "eval_runtime": 226.7104, | |
| "eval_samples_per_second": 11.64, | |
| "eval_steps_per_second": 0.97, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 28.34, | |
| "learning_rate": 3.8124692486117947e-06, | |
| "loss": 0.1869, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 28.34, | |
| "eval_accuracy": 0.8908677529367185, | |
| "eval_f1": 0.9286976343726923, | |
| "eval_loss": 0.637986958026886, | |
| "eval_precision": 0.9738854766344701, | |
| "eval_runtime": 229.6341, | |
| "eval_samples_per_second": 11.492, | |
| "eval_steps_per_second": 0.958, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 29.35, | |
| "learning_rate": 2.7581359387080904e-06, | |
| "loss": 0.185, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 29.35, | |
| "eval_accuracy": 0.8870784388025768, | |
| "eval_f1": 0.9288845844124958, | |
| "eval_loss": 0.6932182908058167, | |
| "eval_precision": 0.979135119670676, | |
| "eval_runtime": 223.3771, | |
| "eval_samples_per_second": 11.814, | |
| "eval_steps_per_second": 0.985, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 30.36, | |
| "learning_rate": 1.7038026288043862e-06, | |
| "loss": 0.1813, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 30.36, | |
| "eval_accuracy": 0.8950359984842744, | |
| "eval_f1": 0.9333589015381497, | |
| "eval_loss": 0.5935563445091248, | |
| "eval_precision": 0.9789140060741345, | |
| "eval_runtime": 231.0332, | |
| "eval_samples_per_second": 11.423, | |
| "eval_steps_per_second": 0.952, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 31.38, | |
| "learning_rate": 6.494693189006819e-07, | |
| "loss": 0.1801, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 31.38, | |
| "eval_accuracy": 0.8946570670708601, | |
| "eval_f1": 0.9334021717198819, | |
| "eval_loss": 0.6150190234184265, | |
| "eval_precision": 0.9800558320669844, | |
| "eval_runtime": 224.8697, | |
| "eval_samples_per_second": 11.736, | |
| "eval_steps_per_second": 0.978, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "step": 15808, | |
| "total_flos": 1.2697230517064026e+20, | |
| "train_loss": 1.0038429288729, | |
| "train_runtime": 86553.4289, | |
| "train_samples_per_second": 8.78, | |
| "train_steps_per_second": 0.183 | |
| } | |
| ], | |
| "max_steps": 15808, | |
| "num_train_epochs": 32, | |
| "total_flos": 1.2697230517064026e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |