| { | |
| "best_metric": 0.3556511701122888, | |
| "best_model_checkpoint": "./checkpoint-jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn-2024-05-22-18:06:11/checkpoint-3800", | |
| "epoch": 5.993690851735016, | |
| "eval_steps": 100, | |
| "global_step": 3800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15772870662460567, | |
| "learning_rate": 0.0001, | |
| "loss": 1698.5084, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15772870662460567, | |
| "eval_cer": 0.6674362472452513, | |
| "eval_loss": 1785.6148681640625, | |
| "eval_runtime": 52.9664, | |
| "eval_samples_per_second": 20.145, | |
| "eval_steps_per_second": 0.642, | |
| "eval_wer": 1.0099234476892542, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31545741324921134, | |
| "learning_rate": 0.0001, | |
| "loss": 1042.5306, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.31545741324921134, | |
| "eval_cer": 0.5899884562913212, | |
| "eval_loss": 1540.8310546875, | |
| "eval_runtime": 51.9115, | |
| "eval_samples_per_second": 20.554, | |
| "eval_steps_per_second": 0.655, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47318611987381703, | |
| "learning_rate": 0.0001, | |
| "loss": 854.3348, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.47318611987381703, | |
| "eval_cer": 0.5380942386399412, | |
| "eval_loss": 1377.9049072265625, | |
| "eval_runtime": 51.2852, | |
| "eval_samples_per_second": 20.805, | |
| "eval_steps_per_second": 0.663, | |
| "eval_wer": 0.9960306209242983, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6309148264984227, | |
| "learning_rate": 0.0001, | |
| "loss": 774.3192, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6309148264984227, | |
| "eval_cer": 0.5107566376324902, | |
| "eval_loss": 1288.8304443359375, | |
| "eval_runtime": 51.8048, | |
| "eval_samples_per_second": 20.597, | |
| "eval_steps_per_second": 0.656, | |
| "eval_wer": 0.9914941876949248, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7886435331230284, | |
| "learning_rate": 0.0001, | |
| "loss": 757.7506, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7886435331230284, | |
| "eval_cer": 0.5178927484520937, | |
| "eval_loss": 1314.91796875, | |
| "eval_runtime": 51.7443, | |
| "eval_samples_per_second": 20.621, | |
| "eval_steps_per_second": 0.657, | |
| "eval_wer": 1.0036858519988658, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9463722397476341, | |
| "learning_rate": 0.0001, | |
| "loss": 722.0188, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9463722397476341, | |
| "eval_cer": 0.4853604785391961, | |
| "eval_loss": 1224.3736572265625, | |
| "eval_runtime": 51.6891, | |
| "eval_samples_per_second": 20.643, | |
| "eval_steps_per_second": 0.658, | |
| "eval_wer": 0.989509498157074, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.1041009463722398, | |
| "learning_rate": 0.0001, | |
| "loss": 724.7426, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.1041009463722398, | |
| "eval_cer": 0.47895896736278726, | |
| "eval_loss": 1209.853515625, | |
| "eval_runtime": 51.8256, | |
| "eval_samples_per_second": 20.588, | |
| "eval_steps_per_second": 0.656, | |
| "eval_wer": 1.0036858519988658, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.2618296529968454, | |
| "learning_rate": 0.0001, | |
| "loss": 649.6804, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2618296529968454, | |
| "eval_cer": 0.48992549060761886, | |
| "eval_loss": 1224.6180419921875, | |
| "eval_runtime": 66.2056, | |
| "eval_samples_per_second": 16.116, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.9699461298554012, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.4195583596214512, | |
| "learning_rate": 0.0001, | |
| "loss": 655.4617, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.4195583596214512, | |
| "eval_cer": 0.4708258998845629, | |
| "eval_loss": 1187.83837890625, | |
| "eval_runtime": 66.188, | |
| "eval_samples_per_second": 16.121, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.9849730649277006, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.5772870662460567, | |
| "learning_rate": 0.0001, | |
| "loss": 618.5408, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.5772870662460567, | |
| "eval_cer": 0.4704586000629657, | |
| "eval_loss": 1160.8505859375, | |
| "eval_runtime": 51.6326, | |
| "eval_samples_per_second": 20.665, | |
| "eval_steps_per_second": 0.658, | |
| "eval_wer": 0.9713637652395803, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.7350157728706623, | |
| "learning_rate": 0.0001, | |
| "loss": 593.1705, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.7350157728706623, | |
| "eval_cer": 0.45030958127820336, | |
| "eval_loss": 1104.7032470703125, | |
| "eval_runtime": 51.2994, | |
| "eval_samples_per_second": 20.799, | |
| "eval_steps_per_second": 0.663, | |
| "eval_wer": 0.9798695775446555, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.8927444794952681, | |
| "learning_rate": 0.0001, | |
| "loss": 573.3853, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.8927444794952681, | |
| "eval_cer": 0.4453247979850981, | |
| "eval_loss": 1097.029052734375, | |
| "eval_runtime": 51.3008, | |
| "eval_samples_per_second": 20.799, | |
| "eval_steps_per_second": 0.663, | |
| "eval_wer": 0.9679614403175504, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.050473186119874, | |
| "learning_rate": 0.0001, | |
| "loss": 538.3213, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.050473186119874, | |
| "eval_cer": 0.4455346835974394, | |
| "eval_loss": 1102.0858154296875, | |
| "eval_runtime": 51.521, | |
| "eval_samples_per_second": 20.71, | |
| "eval_steps_per_second": 0.66, | |
| "eval_wer": 0.9727814006237596, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.2082018927444795, | |
| "learning_rate": 0.0001, | |
| "loss": 531.1298, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.2082018927444795, | |
| "eval_cer": 0.44096967152901667, | |
| "eval_loss": 1078.82421875, | |
| "eval_runtime": 68.5709, | |
| "eval_samples_per_second": 15.561, | |
| "eval_steps_per_second": 0.496, | |
| "eval_wer": 0.9605897363198186, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.365930599369085, | |
| "learning_rate": 0.0001, | |
| "loss": 542.7701, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.365930599369085, | |
| "eval_cer": 0.42979326267184387, | |
| "eval_loss": 1048.210693359375, | |
| "eval_runtime": 64.358, | |
| "eval_samples_per_second": 16.579, | |
| "eval_steps_per_second": 0.528, | |
| "eval_wer": 0.9489651261695492, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.5236593059936907, | |
| "learning_rate": 0.0001, | |
| "loss": 498.9634, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.5236593059936907, | |
| "eval_cer": 0.42816664917619895, | |
| "eval_loss": 1044.7041015625, | |
| "eval_runtime": 51.3166, | |
| "eval_samples_per_second": 20.792, | |
| "eval_steps_per_second": 0.663, | |
| "eval_wer": 0.9620073717039977, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.6813880126182967, | |
| "learning_rate": 0.0001, | |
| "loss": 509.265, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.6813880126182967, | |
| "eval_cer": 0.4282715919823696, | |
| "eval_loss": 1051.6734619140625, | |
| "eval_runtime": 50.9836, | |
| "eval_samples_per_second": 20.928, | |
| "eval_steps_per_second": 0.667, | |
| "eval_wer": 0.9381910972497873, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.8391167192429023, | |
| "learning_rate": 0.0001, | |
| "loss": 539.8557, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.8391167192429023, | |
| "eval_cer": 0.42737957812991917, | |
| "eval_loss": 1050.7423095703125, | |
| "eval_runtime": 51.2405, | |
| "eval_samples_per_second": 20.823, | |
| "eval_steps_per_second": 0.664, | |
| "eval_wer": 0.9376240430961157, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.996845425867508, | |
| "learning_rate": 0.0001, | |
| "loss": 480.5731, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.996845425867508, | |
| "eval_cer": 0.4285339489977962, | |
| "eval_loss": 1051.7239990234375, | |
| "eval_runtime": 50.559, | |
| "eval_samples_per_second": 21.104, | |
| "eval_steps_per_second": 0.672, | |
| "eval_wer": 0.9520839240147434, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.1545741324921135, | |
| "learning_rate": 0.0001, | |
| "loss": 461.9688, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.1545741324921135, | |
| "eval_cer": 0.41510126980795464, | |
| "eval_loss": 1022.7216796875, | |
| "eval_runtime": 51.7333, | |
| "eval_samples_per_second": 20.625, | |
| "eval_steps_per_second": 0.657, | |
| "eval_wer": 0.9466969095548625, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.312302839116719, | |
| "learning_rate": 0.0001, | |
| "loss": 456.1502, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.312302839116719, | |
| "eval_cer": 0.4104313149333613, | |
| "eval_loss": 1006.2450561523438, | |
| "eval_runtime": 51.333, | |
| "eval_samples_per_second": 20.786, | |
| "eval_steps_per_second": 0.662, | |
| "eval_wer": 0.9364899347887723, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.470031545741325, | |
| "learning_rate": 0.0001, | |
| "loss": 456.8266, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.470031545741325, | |
| "eval_cer": 0.40544653164025607, | |
| "eval_loss": 986.6710205078125, | |
| "eval_runtime": 50.4751, | |
| "eval_samples_per_second": 21.139, | |
| "eval_steps_per_second": 0.674, | |
| "eval_wer": 0.9396087326339665, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.6277602523659307, | |
| "learning_rate": 0.0001, | |
| "loss": 449.4439, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.6277602523659307, | |
| "eval_cer": 0.3981530066113968, | |
| "eval_loss": 991.7250366210938, | |
| "eval_runtime": 54.1894, | |
| "eval_samples_per_second": 19.69, | |
| "eval_steps_per_second": 0.627, | |
| "eval_wer": 0.9438616387865041, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.7854889589905363, | |
| "learning_rate": 0.0001, | |
| "loss": 430.7997, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.7854889589905363, | |
| "eval_cer": 0.40665337391121836, | |
| "eval_loss": 991.326171875, | |
| "eval_runtime": 52.5258, | |
| "eval_samples_per_second": 20.314, | |
| "eval_steps_per_second": 0.647, | |
| "eval_wer": 0.9407428409413099, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.943217665615142, | |
| "learning_rate": 0.0001, | |
| "loss": 449.0868, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.943217665615142, | |
| "eval_cer": 0.3951621366355336, | |
| "eval_loss": 964.4004516601562, | |
| "eval_runtime": 53.5761, | |
| "eval_samples_per_second": 19.916, | |
| "eval_steps_per_second": 0.635, | |
| "eval_wer": 0.9296852849447123, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.100946372239748, | |
| "learning_rate": 0.0001, | |
| "loss": 443.7041, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.100946372239748, | |
| "eval_cer": 0.39070206737328156, | |
| "eval_loss": 954.4678955078125, | |
| "eval_runtime": 52.8115, | |
| "eval_samples_per_second": 20.204, | |
| "eval_steps_per_second": 0.644, | |
| "eval_wer": 0.9259994329458463, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.2586750788643535, | |
| "learning_rate": 0.0001, | |
| "loss": 427.484, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 4.2586750788643535, | |
| "eval_cer": 0.4036100325322699, | |
| "eval_loss": 976.2208862304688, | |
| "eval_runtime": 53.0341, | |
| "eval_samples_per_second": 20.119, | |
| "eval_steps_per_second": 0.641, | |
| "eval_wer": 0.937056988942444, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 4.416403785488959, | |
| "learning_rate": 0.0001, | |
| "loss": 414.0316, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.416403785488959, | |
| "eval_cer": 0.39316822331829154, | |
| "eval_loss": 954.1862182617188, | |
| "eval_runtime": 52.8807, | |
| "eval_samples_per_second": 20.177, | |
| "eval_steps_per_second": 0.643, | |
| "eval_wer": 0.9217465267933087, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.574132492113565, | |
| "learning_rate": 0.0001, | |
| "loss": 403.1846, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 4.574132492113565, | |
| "eval_cer": 0.38566481267709096, | |
| "eval_loss": 925.2608032226562, | |
| "eval_runtime": 52.9173, | |
| "eval_samples_per_second": 20.164, | |
| "eval_steps_per_second": 0.643, | |
| "eval_wer": 0.9240147434079955, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 4.73186119873817, | |
| "learning_rate": 0.0001, | |
| "loss": 396.0723, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.73186119873817, | |
| "eval_cer": 0.3791058872914262, | |
| "eval_loss": 919.0806274414062, | |
| "eval_runtime": 53.2725, | |
| "eval_samples_per_second": 20.029, | |
| "eval_steps_per_second": 0.638, | |
| "eval_wer": 0.9203288914091295, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.889589905362776, | |
| "learning_rate": 0.0001, | |
| "loss": 395.4377, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 4.889589905362776, | |
| "eval_cer": 0.37422604680449156, | |
| "eval_loss": 890.70263671875, | |
| "eval_runtime": 53.49, | |
| "eval_samples_per_second": 19.948, | |
| "eval_steps_per_second": 0.636, | |
| "eval_wer": 0.9129571874113978, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 5.047318611987381, | |
| "learning_rate": 0.0001, | |
| "loss": 371.9726, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 5.047318611987381, | |
| "eval_cer": 0.3725994333088467, | |
| "eval_loss": 898.53515625, | |
| "eval_runtime": 51.3357, | |
| "eval_samples_per_second": 20.785, | |
| "eval_steps_per_second": 0.662, | |
| "eval_wer": 0.9135242415650695, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 5.205047318611987, | |
| "learning_rate": 0.0001, | |
| "loss": 360.3298, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 5.205047318611987, | |
| "eval_cer": 0.37726938818344, | |
| "eval_loss": 910.59228515625, | |
| "eval_runtime": 51.4827, | |
| "eval_samples_per_second": 20.725, | |
| "eval_steps_per_second": 0.66, | |
| "eval_wer": 0.9206124184859654, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 5.3627760252365935, | |
| "learning_rate": 0.0001, | |
| "loss": 347.3557, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.3627760252365935, | |
| "eval_cer": 0.3718648336656522, | |
| "eval_loss": 895.6106567382812, | |
| "eval_runtime": 51.0316, | |
| "eval_samples_per_second": 20.909, | |
| "eval_steps_per_second": 0.666, | |
| "eval_wer": 0.9095548624893678, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.520504731861199, | |
| "learning_rate": 0.0001, | |
| "loss": 363.2754, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.520504731861199, | |
| "eval_cer": 0.3706579913946899, | |
| "eval_loss": 892.8668212890625, | |
| "eval_runtime": 51.0894, | |
| "eval_samples_per_second": 20.885, | |
| "eval_steps_per_second": 0.666, | |
| "eval_wer": 0.9166430394102637, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.678233438485805, | |
| "learning_rate": 0.0001, | |
| "loss": 371.9467, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.678233438485805, | |
| "eval_cer": 0.37307167593661456, | |
| "eval_loss": 910.8128051757812, | |
| "eval_runtime": 51.025, | |
| "eval_samples_per_second": 20.911, | |
| "eval_steps_per_second": 0.666, | |
| "eval_wer": 0.9163595123334278, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.83596214511041, | |
| "learning_rate": 0.0001, | |
| "loss": 356.735, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 5.83596214511041, | |
| "eval_cer": 0.3681918354496799, | |
| "eval_loss": 875.8790283203125, | |
| "eval_runtime": 51.2056, | |
| "eval_samples_per_second": 20.838, | |
| "eval_steps_per_second": 0.664, | |
| "eval_wer": 0.9104054437198752, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 5.993690851735016, | |
| "learning_rate": 0.0001, | |
| "loss": 328.0254, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 5.993690851735016, | |
| "eval_cer": 0.3556511701122888, | |
| "eval_loss": 860.9888916015625, | |
| "eval_runtime": 51.149, | |
| "eval_samples_per_second": 20.861, | |
| "eval_steps_per_second": 0.665, | |
| "eval_wer": 0.903884320952651, | |
| "step": 3800 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 126800, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 200, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.326393516025028e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |