| { | |
| "best_metric": 0.5028899908065796, | |
| "best_model_checkpoint": "ai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-idmt-2_8k/checkpoint-459", | |
| "epoch": 100.0, | |
| "global_step": 900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 101.80458068847656, | |
| "eval_runtime": 2.5283, | |
| "eval_samples_per_second": 6.724, | |
| "eval_steps_per_second": 1.978, | |
| "eval_wer": 0.98, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 7e-05, | |
| "loss": 17.4958, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 82.49200439453125, | |
| "eval_runtime": 2.6724, | |
| "eval_samples_per_second": 6.361, | |
| "eval_steps_per_second": 1.871, | |
| "eval_wer": 1.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.00015999999999999999, | |
| "loss": 16.2087, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 36.138763427734375, | |
| "eval_runtime": 2.6141, | |
| "eval_samples_per_second": 6.503, | |
| "eval_steps_per_second": 1.913, | |
| "eval_wer": 1.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.00026, | |
| "loss": 6.2942, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 8.326688766479492, | |
| "eval_runtime": 2.6808, | |
| "eval_samples_per_second": 6.341, | |
| "eval_steps_per_second": 1.865, | |
| "eval_wer": 1.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 0.0002979310344827586, | |
| "loss": 2.0411, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 6.8215179443359375, | |
| "eval_runtime": 2.696, | |
| "eval_samples_per_second": 6.306, | |
| "eval_steps_per_second": 1.855, | |
| "eval_wer": 1.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 0.00029448275862068964, | |
| "loss": 1.554, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 5.384669780731201, | |
| "eval_runtime": 2.7298, | |
| "eval_samples_per_second": 6.228, | |
| "eval_steps_per_second": 1.832, | |
| "eval_wer": 1.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 0.00029103448275862064, | |
| "loss": 1.6215, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 4.4644598960876465, | |
| "eval_runtime": 2.6233, | |
| "eval_samples_per_second": 6.48, | |
| "eval_steps_per_second": 1.906, | |
| "eval_wer": 1.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 0.0002875862068965517, | |
| "loss": 1.4962, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 3.221142053604126, | |
| "eval_runtime": 2.7171, | |
| "eval_samples_per_second": 6.257, | |
| "eval_steps_per_second": 1.84, | |
| "eval_wer": 1.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 0.00028413793103448275, | |
| "loss": 1.3825, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.5513429641723633, | |
| "eval_runtime": 2.6858, | |
| "eval_samples_per_second": 6.329, | |
| "eval_steps_per_second": 1.862, | |
| "eval_wer": 1.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.00028068965517241375, | |
| "loss": 1.3443, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.8581652641296387, | |
| "eval_runtime": 2.7157, | |
| "eval_samples_per_second": 6.26, | |
| "eval_steps_per_second": 1.841, | |
| "eval_wer": 1.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 2.544593572616577, | |
| "eval_runtime": 2.6215, | |
| "eval_samples_per_second": 6.485, | |
| "eval_steps_per_second": 1.907, | |
| "eval_wer": 1.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 0.0002772413793103448, | |
| "loss": 1.3096, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 2.021075963973999, | |
| "eval_runtime": 2.6505, | |
| "eval_samples_per_second": 6.414, | |
| "eval_steps_per_second": 1.886, | |
| "eval_wer": 0.9955555555555555, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 12.22, | |
| "learning_rate": 0.0002737931034482758, | |
| "loss": 1.3361, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.8110406398773193, | |
| "eval_runtime": 2.6015, | |
| "eval_samples_per_second": 6.535, | |
| "eval_steps_per_second": 1.922, | |
| "eval_wer": 0.9944444444444445, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 0.00027034482758620687, | |
| "loss": 1.2862, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.7796473503112793, | |
| "eval_runtime": 2.6116, | |
| "eval_samples_per_second": 6.509, | |
| "eval_steps_per_second": 1.915, | |
| "eval_wer": 0.9933333333333333, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 0.0002668965517241379, | |
| "loss": 1.2556, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.730082631111145, | |
| "eval_runtime": 2.5934, | |
| "eval_samples_per_second": 6.555, | |
| "eval_steps_per_second": 1.928, | |
| "eval_wer": 0.9922222222222222, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "learning_rate": 0.0002634482758620689, | |
| "loss": 1.1959, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.4244635105133057, | |
| "eval_runtime": 2.6511, | |
| "eval_samples_per_second": 6.412, | |
| "eval_steps_per_second": 1.886, | |
| "eval_wer": 0.9988888888888889, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 0.00026, | |
| "loss": 1.1161, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.1931955814361572, | |
| "eval_runtime": 2.6143, | |
| "eval_samples_per_second": 6.503, | |
| "eval_steps_per_second": 1.913, | |
| "eval_wer": 0.5677777777777778, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "learning_rate": 0.00025655172413793103, | |
| "loss": 0.8853, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.2725539207458496, | |
| "eval_runtime": 2.6031, | |
| "eval_samples_per_second": 6.531, | |
| "eval_steps_per_second": 1.921, | |
| "eval_wer": 0.4922222222222222, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 18.89, | |
| "learning_rate": 0.00025310344827586203, | |
| "loss": 0.7996, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.0841138362884521, | |
| "eval_runtime": 2.6115, | |
| "eval_samples_per_second": 6.51, | |
| "eval_steps_per_second": 1.915, | |
| "eval_wer": 0.5511111111111111, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.0002496551724137931, | |
| "loss": 0.8165, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.406151294708252, | |
| "eval_runtime": 2.6236, | |
| "eval_samples_per_second": 6.48, | |
| "eval_steps_per_second": 1.906, | |
| "eval_wer": 0.4411111111111111, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 1.4218931198120117, | |
| "eval_runtime": 2.6036, | |
| "eval_samples_per_second": 6.529, | |
| "eval_steps_per_second": 1.92, | |
| "eval_wer": 0.33666666666666667, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 21.11, | |
| "learning_rate": 0.0002462068965517241, | |
| "loss": 0.6807, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 1.2106943130493164, | |
| "eval_runtime": 2.6208, | |
| "eval_samples_per_second": 6.486, | |
| "eval_steps_per_second": 1.908, | |
| "eval_wer": 0.33444444444444443, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 0.00024275862068965515, | |
| "loss": 0.7315, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 1.1419602632522583, | |
| "eval_runtime": 2.6272, | |
| "eval_samples_per_second": 6.471, | |
| "eval_steps_per_second": 1.903, | |
| "eval_wer": 0.3188888888888889, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 23.33, | |
| "learning_rate": 0.00023931034482758617, | |
| "loss": 0.6203, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 1.0770384073257446, | |
| "eval_runtime": 2.6173, | |
| "eval_samples_per_second": 6.495, | |
| "eval_steps_per_second": 1.91, | |
| "eval_wer": 0.37777777777777777, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 24.44, | |
| "learning_rate": 0.00023586206896551723, | |
| "loss": 0.6552, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 1.1095293760299683, | |
| "eval_runtime": 2.6206, | |
| "eval_samples_per_second": 6.487, | |
| "eval_steps_per_second": 1.908, | |
| "eval_wer": 0.3788888888888889, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 25.56, | |
| "learning_rate": 0.00023241379310344826, | |
| "loss": 0.5618, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 1.0003583431243896, | |
| "eval_runtime": 2.6097, | |
| "eval_samples_per_second": 6.514, | |
| "eval_steps_per_second": 1.916, | |
| "eval_wer": 0.3477777777777778, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "learning_rate": 0.0002289655172413793, | |
| "loss": 0.5311, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.8810951113700867, | |
| "eval_runtime": 2.705, | |
| "eval_samples_per_second": 6.285, | |
| "eval_steps_per_second": 1.848, | |
| "eval_wer": 0.33111111111111113, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 27.78, | |
| "learning_rate": 0.00022551724137931031, | |
| "loss": 0.5391, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.8162650465965271, | |
| "eval_runtime": 2.6062, | |
| "eval_samples_per_second": 6.523, | |
| "eval_steps_per_second": 1.919, | |
| "eval_wer": 0.36777777777777776, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "learning_rate": 0.00022206896551724134, | |
| "loss": 0.5275, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.9999949336051941, | |
| "eval_runtime": 2.6225, | |
| "eval_samples_per_second": 6.482, | |
| "eval_steps_per_second": 1.907, | |
| "eval_wer": 0.33111111111111113, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 0.0002186206896551724, | |
| "loss": 0.4965, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.7320018410682678, | |
| "eval_runtime": 2.6343, | |
| "eval_samples_per_second": 6.453, | |
| "eval_steps_per_second": 1.898, | |
| "eval_wer": 0.37, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 0.9642557501792908, | |
| "eval_runtime": 2.6199, | |
| "eval_samples_per_second": 6.489, | |
| "eval_steps_per_second": 1.909, | |
| "eval_wer": 0.3388888888888889, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 31.11, | |
| "learning_rate": 0.00021517241379310343, | |
| "loss": 0.4909, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 0.7662584185600281, | |
| "eval_runtime": 2.6092, | |
| "eval_samples_per_second": 6.515, | |
| "eval_steps_per_second": 1.916, | |
| "eval_wer": 0.35888888888888887, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 32.22, | |
| "learning_rate": 0.00021172413793103445, | |
| "loss": 0.5218, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 0.9004315733909607, | |
| "eval_runtime": 2.6009, | |
| "eval_samples_per_second": 6.536, | |
| "eval_steps_per_second": 1.922, | |
| "eval_wer": 0.3488888888888889, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 0.0002082758620689655, | |
| "loss": 0.4991, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 0.7342296242713928, | |
| "eval_runtime": 2.6253, | |
| "eval_samples_per_second": 6.475, | |
| "eval_steps_per_second": 1.905, | |
| "eval_wer": 0.38, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 34.44, | |
| "learning_rate": 0.00020482758620689654, | |
| "loss": 0.4883, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 0.7959361672401428, | |
| "eval_runtime": 2.6169, | |
| "eval_samples_per_second": 6.496, | |
| "eval_steps_per_second": 1.911, | |
| "eval_wer": 0.3388888888888889, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 35.56, | |
| "learning_rate": 0.0002013793103448276, | |
| "loss": 0.4902, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 0.6891648173332214, | |
| "eval_runtime": 2.6322, | |
| "eval_samples_per_second": 6.458, | |
| "eval_steps_per_second": 1.9, | |
| "eval_wer": 0.3377777777777778, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 36.67, | |
| "learning_rate": 0.0001979310344827586, | |
| "loss": 0.4447, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 0.6479607224464417, | |
| "eval_runtime": 2.5996, | |
| "eval_samples_per_second": 6.539, | |
| "eval_steps_per_second": 1.923, | |
| "eval_wer": 0.3333333333333333, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 37.78, | |
| "learning_rate": 0.00019448275862068962, | |
| "loss": 0.4458, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 0.6198386549949646, | |
| "eval_runtime": 2.6161, | |
| "eval_samples_per_second": 6.498, | |
| "eval_steps_per_second": 1.911, | |
| "eval_wer": 0.3333333333333333, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 38.89, | |
| "learning_rate": 0.00019103448275862068, | |
| "loss": 0.4607, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 0.6080996990203857, | |
| "eval_runtime": 2.6354, | |
| "eval_samples_per_second": 6.451, | |
| "eval_steps_per_second": 1.897, | |
| "eval_wer": 0.3111111111111111, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 0.0001875862068965517, | |
| "loss": 0.4352, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 0.6748089790344238, | |
| "eval_runtime": 2.6402, | |
| "eval_samples_per_second": 6.439, | |
| "eval_steps_per_second": 1.894, | |
| "eval_wer": 0.31555555555555553, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 0.6885289549827576, | |
| "eval_runtime": 2.6179, | |
| "eval_samples_per_second": 6.494, | |
| "eval_steps_per_second": 1.91, | |
| "eval_wer": 0.32555555555555554, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 41.11, | |
| "learning_rate": 0.00018413793103448273, | |
| "loss": 0.4286, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 0.6806181073188782, | |
| "eval_runtime": 2.614, | |
| "eval_samples_per_second": 6.504, | |
| "eval_steps_per_second": 1.913, | |
| "eval_wer": 0.3333333333333333, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 42.22, | |
| "learning_rate": 0.0001806896551724138, | |
| "loss": 0.4314, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 0.7854954600334167, | |
| "eval_runtime": 2.5985, | |
| "eval_samples_per_second": 6.542, | |
| "eval_steps_per_second": 1.924, | |
| "eval_wer": 0.32222222222222224, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 43.33, | |
| "learning_rate": 0.00017724137931034482, | |
| "loss": 0.4476, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 0.6569249629974365, | |
| "eval_runtime": 2.5902, | |
| "eval_samples_per_second": 6.563, | |
| "eval_steps_per_second": 1.93, | |
| "eval_wer": 0.31444444444444447, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "learning_rate": 0.00017379310344827587, | |
| "loss": 0.4815, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 0.5388519167900085, | |
| "eval_runtime": 2.6157, | |
| "eval_samples_per_second": 6.499, | |
| "eval_steps_per_second": 1.912, | |
| "eval_wer": 0.30333333333333334, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 45.56, | |
| "learning_rate": 0.00017034482758620687, | |
| "loss": 0.36, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 0.5549790263175964, | |
| "eval_runtime": 2.5979, | |
| "eval_samples_per_second": 6.544, | |
| "eval_steps_per_second": 1.925, | |
| "eval_wer": 0.3011111111111111, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 46.67, | |
| "learning_rate": 0.0001668965517241379, | |
| "loss": 0.4516, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 0.5923512578010559, | |
| "eval_runtime": 2.6204, | |
| "eval_samples_per_second": 6.488, | |
| "eval_steps_per_second": 1.908, | |
| "eval_wer": 0.31444444444444447, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 47.78, | |
| "learning_rate": 0.00016344827586206896, | |
| "loss": 0.3682, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 0.727486789226532, | |
| "eval_runtime": 2.6112, | |
| "eval_samples_per_second": 6.51, | |
| "eval_steps_per_second": 1.915, | |
| "eval_wer": 0.3055555555555556, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 48.89, | |
| "learning_rate": 0.00015999999999999999, | |
| "loss": 0.4371, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_loss": 0.7050825357437134, | |
| "eval_runtime": 2.6034, | |
| "eval_samples_per_second": 6.53, | |
| "eval_steps_per_second": 1.921, | |
| "eval_wer": 0.3088888888888889, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 0.00015655172413793101, | |
| "loss": 0.4004, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 0.5668944716453552, | |
| "eval_runtime": 2.6536, | |
| "eval_samples_per_second": 6.406, | |
| "eval_steps_per_second": 1.884, | |
| "eval_wer": 0.30777777777777776, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_loss": 0.5028899908065796, | |
| "eval_runtime": 2.6202, | |
| "eval_samples_per_second": 6.488, | |
| "eval_steps_per_second": 1.908, | |
| "eval_wer": 0.31777777777777777, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 51.11, | |
| "learning_rate": 0.00015310344827586207, | |
| "loss": 0.3298, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_loss": 0.6150208711624146, | |
| "eval_runtime": 2.602, | |
| "eval_samples_per_second": 6.534, | |
| "eval_steps_per_second": 1.922, | |
| "eval_wer": 0.32, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 52.22, | |
| "learning_rate": 0.00014965517241379307, | |
| "loss": 0.4083, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_loss": 0.5881750583648682, | |
| "eval_runtime": 2.6209, | |
| "eval_samples_per_second": 6.486, | |
| "eval_steps_per_second": 1.908, | |
| "eval_wer": 0.33, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 53.33, | |
| "learning_rate": 0.00014620689655172413, | |
| "loss": 0.4022, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_loss": 0.7253018021583557, | |
| "eval_runtime": 2.6223, | |
| "eval_samples_per_second": 6.483, | |
| "eval_steps_per_second": 1.907, | |
| "eval_wer": 0.31444444444444447, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 54.44, | |
| "learning_rate": 0.00014275862068965515, | |
| "loss": 0.4465, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_loss": 0.6807547807693481, | |
| "eval_runtime": 2.6014, | |
| "eval_samples_per_second": 6.535, | |
| "eval_steps_per_second": 1.922, | |
| "eval_wer": 0.3111111111111111, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 55.56, | |
| "learning_rate": 0.0001393103448275862, | |
| "loss": 0.3955, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_loss": 0.6001608967781067, | |
| "eval_runtime": 2.629, | |
| "eval_samples_per_second": 6.466, | |
| "eval_steps_per_second": 1.902, | |
| "eval_wer": 0.31333333333333335, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 56.67, | |
| "learning_rate": 0.0001358620689655172, | |
| "loss": 0.3877, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_loss": 0.7593300938606262, | |
| "eval_runtime": 2.6173, | |
| "eval_samples_per_second": 6.495, | |
| "eval_steps_per_second": 1.91, | |
| "eval_wer": 0.3055555555555556, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 57.78, | |
| "learning_rate": 0.00013241379310344827, | |
| "loss": 0.3486, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_loss": 0.6764330863952637, | |
| "eval_runtime": 2.646, | |
| "eval_samples_per_second": 6.425, | |
| "eval_steps_per_second": 1.89, | |
| "eval_wer": 0.3188888888888889, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 58.89, | |
| "learning_rate": 0.0001289655172413793, | |
| "loss": 0.3782, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_loss": 0.6771883368492126, | |
| "eval_runtime": 2.6301, | |
| "eval_samples_per_second": 6.464, | |
| "eval_steps_per_second": 1.901, | |
| "eval_wer": 0.31333333333333335, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 0.00012551724137931035, | |
| "loss": 0.3599, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_loss": 0.8846335411071777, | |
| "eval_runtime": 2.615, | |
| "eval_samples_per_second": 6.501, | |
| "eval_steps_per_second": 1.912, | |
| "eval_wer": 0.3111111111111111, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_loss": 0.945833683013916, | |
| "eval_runtime": 2.5924, | |
| "eval_samples_per_second": 6.558, | |
| "eval_steps_per_second": 1.929, | |
| "eval_wer": 0.3233333333333333, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 61.11, | |
| "learning_rate": 0.00012206896551724136, | |
| "loss": 0.3424, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_loss": 0.8398585319519043, | |
| "eval_runtime": 2.6035, | |
| "eval_samples_per_second": 6.53, | |
| "eval_steps_per_second": 1.921, | |
| "eval_wer": 0.3233333333333333, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 62.22, | |
| "learning_rate": 0.0001186206896551724, | |
| "loss": 0.3652, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_loss": 0.8266441822052002, | |
| "eval_runtime": 2.6064, | |
| "eval_samples_per_second": 6.522, | |
| "eval_steps_per_second": 1.918, | |
| "eval_wer": 0.31333333333333335, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 63.33, | |
| "learning_rate": 0.00011517241379310343, | |
| "loss": 0.3327, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_loss": 0.7813167572021484, | |
| "eval_runtime": 2.6355, | |
| "eval_samples_per_second": 6.45, | |
| "eval_steps_per_second": 1.897, | |
| "eval_wer": 0.30777777777777776, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 64.44, | |
| "learning_rate": 0.00011172413793103448, | |
| "loss": 0.3603, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_loss": 0.8066079616546631, | |
| "eval_runtime": 2.5997, | |
| "eval_samples_per_second": 6.539, | |
| "eval_steps_per_second": 1.923, | |
| "eval_wer": 0.31555555555555553, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 65.56, | |
| "learning_rate": 0.0001082758620689655, | |
| "loss": 0.3401, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_loss": 0.7959613800048828, | |
| "eval_runtime": 2.6015, | |
| "eval_samples_per_second": 6.535, | |
| "eval_steps_per_second": 1.922, | |
| "eval_wer": 0.30666666666666664, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 66.67, | |
| "learning_rate": 0.00010482758620689655, | |
| "loss": 0.3797, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_loss": 0.8513309955596924, | |
| "eval_runtime": 2.6257, | |
| "eval_samples_per_second": 6.474, | |
| "eval_steps_per_second": 1.904, | |
| "eval_wer": 0.29888888888888887, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 67.78, | |
| "learning_rate": 0.00010137931034482757, | |
| "loss": 0.3353, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_loss": 0.8319157361984253, | |
| "eval_runtime": 2.5993, | |
| "eval_samples_per_second": 6.54, | |
| "eval_steps_per_second": 1.924, | |
| "eval_wer": 0.2722222222222222, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 68.89, | |
| "learning_rate": 9.793103448275862e-05, | |
| "loss": 0.3909, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_loss": 0.8244246244430542, | |
| "eval_runtime": 2.6313, | |
| "eval_samples_per_second": 6.461, | |
| "eval_steps_per_second": 1.9, | |
| "eval_wer": 0.2877777777777778, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 9.448275862068964e-05, | |
| "loss": 0.3263, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_loss": 0.9538501501083374, | |
| "eval_runtime": 2.6379, | |
| "eval_samples_per_second": 6.445, | |
| "eval_steps_per_second": 1.895, | |
| "eval_wer": 0.3022222222222222, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_loss": 1.002958059310913, | |
| "eval_runtime": 2.6816, | |
| "eval_samples_per_second": 6.34, | |
| "eval_steps_per_second": 1.865, | |
| "eval_wer": 0.2922222222222222, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 71.11, | |
| "learning_rate": 9.103448275862069e-05, | |
| "loss": 0.3102, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_loss": 0.9874680638313293, | |
| "eval_runtime": 2.5977, | |
| "eval_samples_per_second": 6.544, | |
| "eval_steps_per_second": 1.925, | |
| "eval_wer": 0.30444444444444446, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 72.22, | |
| "learning_rate": 8.758620689655171e-05, | |
| "loss": 0.3577, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_loss": 0.9030035138130188, | |
| "eval_runtime": 2.6088, | |
| "eval_samples_per_second": 6.516, | |
| "eval_steps_per_second": 1.917, | |
| "eval_wer": 0.29777777777777775, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 73.33, | |
| "learning_rate": 8.413793103448276e-05, | |
| "loss": 0.2953, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_loss": 0.9392061233520508, | |
| "eval_runtime": 2.5966, | |
| "eval_samples_per_second": 6.547, | |
| "eval_steps_per_second": 1.926, | |
| "eval_wer": 0.28888888888888886, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 74.44, | |
| "learning_rate": 8.068965517241378e-05, | |
| "loss": 0.3644, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_loss": 0.9088665843009949, | |
| "eval_runtime": 2.6416, | |
| "eval_samples_per_second": 6.436, | |
| "eval_steps_per_second": 1.893, | |
| "eval_wer": 0.2877777777777778, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 75.56, | |
| "learning_rate": 7.724137931034483e-05, | |
| "loss": 0.3231, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_loss": 0.926447868347168, | |
| "eval_runtime": 2.61, | |
| "eval_samples_per_second": 6.513, | |
| "eval_steps_per_second": 1.916, | |
| "eval_wer": 0.28444444444444444, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 76.67, | |
| "learning_rate": 7.379310344827585e-05, | |
| "loss": 0.3078, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_loss": 1.0535814762115479, | |
| "eval_runtime": 2.597, | |
| "eval_samples_per_second": 6.546, | |
| "eval_steps_per_second": 1.925, | |
| "eval_wer": 0.2911111111111111, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 77.78, | |
| "learning_rate": 7.034482758620688e-05, | |
| "loss": 0.4503, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_loss": 0.9473001956939697, | |
| "eval_runtime": 2.6482, | |
| "eval_samples_per_second": 6.42, | |
| "eval_steps_per_second": 1.888, | |
| "eval_wer": 0.2966666666666667, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 78.89, | |
| "learning_rate": 6.689655172413792e-05, | |
| "loss": 0.3492, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_loss": 0.8909215331077576, | |
| "eval_runtime": 2.6344, | |
| "eval_samples_per_second": 6.453, | |
| "eval_steps_per_second": 1.898, | |
| "eval_wer": 0.3088888888888889, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 6.344827586206895e-05, | |
| "loss": 0.347, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_loss": 0.8532315492630005, | |
| "eval_runtime": 2.6434, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 1.891, | |
| "eval_wer": 0.30666666666666664, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_loss": 0.9552628993988037, | |
| "eval_runtime": 2.651, | |
| "eval_samples_per_second": 6.413, | |
| "eval_steps_per_second": 1.886, | |
| "eval_wer": 0.2833333333333333, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 81.11, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.2949, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_loss": 1.0111045837402344, | |
| "eval_runtime": 2.6252, | |
| "eval_samples_per_second": 6.476, | |
| "eval_steps_per_second": 1.905, | |
| "eval_wer": 0.2866666666666667, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 82.22, | |
| "learning_rate": 5.655172413793103e-05, | |
| "loss": 0.3447, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_loss": 0.9160183072090149, | |
| "eval_runtime": 2.6434, | |
| "eval_samples_per_second": 6.431, | |
| "eval_steps_per_second": 1.892, | |
| "eval_wer": 0.3011111111111111, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 83.33, | |
| "learning_rate": 5.3103448275862065e-05, | |
| "loss": 0.2878, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_loss": 0.8401439785957336, | |
| "eval_runtime": 2.7557, | |
| "eval_samples_per_second": 6.169, | |
| "eval_steps_per_second": 1.814, | |
| "eval_wer": 0.29888888888888887, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 84.44, | |
| "learning_rate": 4.96551724137931e-05, | |
| "loss": 0.3229, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_loss": 0.8815315961837769, | |
| "eval_runtime": 2.6105, | |
| "eval_samples_per_second": 6.512, | |
| "eval_steps_per_second": 1.915, | |
| "eval_wer": 0.2911111111111111, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 85.56, | |
| "learning_rate": 4.6206896551724135e-05, | |
| "loss": 0.276, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_loss": 0.8801678419113159, | |
| "eval_runtime": 2.6513, | |
| "eval_samples_per_second": 6.412, | |
| "eval_steps_per_second": 1.886, | |
| "eval_wer": 0.2911111111111111, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 86.67, | |
| "learning_rate": 4.275862068965517e-05, | |
| "loss": 0.3469, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_loss": 0.9121254682540894, | |
| "eval_runtime": 2.6394, | |
| "eval_samples_per_second": 6.441, | |
| "eval_steps_per_second": 1.894, | |
| "eval_wer": 0.29, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 87.78, | |
| "learning_rate": 3.9310344827586205e-05, | |
| "loss": 0.3044, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_loss": 0.8933728337287903, | |
| "eval_runtime": 2.6251, | |
| "eval_samples_per_second": 6.476, | |
| "eval_steps_per_second": 1.905, | |
| "eval_wer": 0.29333333333333333, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 88.89, | |
| "learning_rate": 3.586206896551724e-05, | |
| "loss": 0.2885, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_loss": 0.8806433081626892, | |
| "eval_runtime": 2.618, | |
| "eval_samples_per_second": 6.494, | |
| "eval_steps_per_second": 1.91, | |
| "eval_wer": 0.2966666666666667, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 3.2413793103448275e-05, | |
| "loss": 0.3365, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_loss": 0.9036632180213928, | |
| "eval_runtime": 2.654, | |
| "eval_samples_per_second": 6.406, | |
| "eval_steps_per_second": 1.884, | |
| "eval_wer": 0.28444444444444444, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_loss": 0.9217983484268188, | |
| "eval_runtime": 2.636, | |
| "eval_samples_per_second": 6.449, | |
| "eval_steps_per_second": 1.897, | |
| "eval_wer": 0.2866666666666667, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 91.11, | |
| "learning_rate": 2.8965517241379307e-05, | |
| "loss": 0.3239, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_loss": 0.9227918386459351, | |
| "eval_runtime": 2.6278, | |
| "eval_samples_per_second": 6.469, | |
| "eval_steps_per_second": 1.903, | |
| "eval_wer": 0.28444444444444444, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 92.22, | |
| "learning_rate": 2.551724137931034e-05, | |
| "loss": 0.3219, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_loss": 0.9166781902313232, | |
| "eval_runtime": 2.652, | |
| "eval_samples_per_second": 6.41, | |
| "eval_steps_per_second": 1.885, | |
| "eval_wer": 0.28444444444444444, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 93.33, | |
| "learning_rate": 2.2068965517241377e-05, | |
| "loss": 0.2736, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_loss": 0.9494596123695374, | |
| "eval_runtime": 2.6316, | |
| "eval_samples_per_second": 6.46, | |
| "eval_steps_per_second": 1.9, | |
| "eval_wer": 0.2877777777777778, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 94.44, | |
| "learning_rate": 1.862068965517241e-05, | |
| "loss": 0.3587, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_loss": 0.9997347593307495, | |
| "eval_runtime": 2.657, | |
| "eval_samples_per_second": 6.398, | |
| "eval_steps_per_second": 1.882, | |
| "eval_wer": 0.28444444444444444, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 95.56, | |
| "learning_rate": 1.5172413793103447e-05, | |
| "loss": 0.3386, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_loss": 0.9977498650550842, | |
| "eval_runtime": 2.674, | |
| "eval_samples_per_second": 6.358, | |
| "eval_steps_per_second": 1.87, | |
| "eval_wer": 0.28555555555555556, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 96.67, | |
| "learning_rate": 1.1724137931034482e-05, | |
| "loss": 0.2895, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_loss": 0.9963868260383606, | |
| "eval_runtime": 2.6883, | |
| "eval_samples_per_second": 6.324, | |
| "eval_steps_per_second": 1.86, | |
| "eval_wer": 0.28888888888888886, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 97.78, | |
| "learning_rate": 8.275862068965517e-06, | |
| "loss": 0.3496, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_loss": 0.9764975309371948, | |
| "eval_runtime": 2.6679, | |
| "eval_samples_per_second": 6.372, | |
| "eval_steps_per_second": 1.874, | |
| "eval_wer": 0.28888888888888886, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 98.89, | |
| "learning_rate": 4.827586206896552e-06, | |
| "loss": 0.2789, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_loss": 0.9712777733802795, | |
| "eval_runtime": 2.6523, | |
| "eval_samples_per_second": 6.41, | |
| "eval_steps_per_second": 1.885, | |
| "eval_wer": 0.2877777777777778, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 1.379310344827586e-06, | |
| "loss": 0.3284, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_loss": 0.9687079191207886, | |
| "eval_runtime": 2.6458, | |
| "eval_samples_per_second": 6.425, | |
| "eval_steps_per_second": 1.89, | |
| "eval_wer": 0.28888888888888886, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 900, | |
| "total_flos": 1.389987159899058e+18, | |
| "train_loss": 0.9807351756095887, | |
| "train_runtime": 3338.9131, | |
| "train_samples_per_second": 4.223, | |
| "train_steps_per_second": 0.27 | |
| } | |
| ], | |
| "max_steps": 900, | |
| "num_train_epochs": 100, | |
| "total_flos": 1.389987159899058e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |