| { | |
| "best_metric": 7.136237256719184, | |
| "best_model_checkpoint": "CHECKPOINTS/checkpoint-59160", | |
| "epoch": 1.0000319284802044, | |
| "global_step": 62640, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9310344827586207e-06, | |
| "loss": 2.0236, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.931034482758621e-06, | |
| "loss": 0.5343, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.9310344827586205e-06, | |
| "loss": 0.4203, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.93103448275862e-06, | |
| "loss": 0.3676, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.931034482758622e-06, | |
| "loss": 0.3277, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 0.42336705327033997, | |
| "eval_runtime": 820.7641, | |
| "eval_samples_per_second": 2.088, | |
| "eval_steps_per_second": 0.262, | |
| "eval_wer": 58.4491813407476, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.981952948759265e-06, | |
| "loss": 0.3055, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.963261359974218e-06, | |
| "loss": 0.2803, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.944569771189173e-06, | |
| "loss": 0.2546, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.925878182404126e-06, | |
| "loss": 0.2365, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.90718659361908e-06, | |
| "loss": 0.2238, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 0.3460919260978699, | |
| "eval_runtime": 799.3208, | |
| "eval_samples_per_second": 2.144, | |
| "eval_steps_per_second": 0.269, | |
| "eval_wer": 42.02450828956853, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.888495004834032e-06, | |
| "loss": 0.2156, | |
| "step": 1276 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.869803416048985e-06, | |
| "loss": 0.2058, | |
| "step": 1392 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.85111182726394e-06, | |
| "loss": 0.1976, | |
| "step": 1508 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.832420238478893e-06, | |
| "loss": 0.1788, | |
| "step": 1624 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.813728649693846e-06, | |
| "loss": 0.1861, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 0.2978155016899109, | |
| "eval_runtime": 789.7073, | |
| "eval_samples_per_second": 2.17, | |
| "eval_steps_per_second": 0.272, | |
| "eval_wer": 33.662856554422824, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.795037060908799e-06, | |
| "loss": 0.174, | |
| "step": 1856 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.776345472123752e-06, | |
| "loss": 0.1739, | |
| "step": 1972 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.757653883338705e-06, | |
| "loss": 0.1683, | |
| "step": 2088 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.738962294553658e-06, | |
| "loss": 0.1606, | |
| "step": 2204 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.720270705768611e-06, | |
| "loss": 0.1572, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 0.27300673723220825, | |
| "eval_runtime": 786.9048, | |
| "eval_samples_per_second": 2.178, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 34.06446298012563, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.701579116983564e-06, | |
| "loss": 0.1498, | |
| "step": 2436 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.682887528198517e-06, | |
| "loss": 0.1475, | |
| "step": 2552 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.664195939413472e-06, | |
| "loss": 0.1421, | |
| "step": 2668 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.645504350628425e-06, | |
| "loss": 0.1416, | |
| "step": 2784 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.626812761843378e-06, | |
| "loss": 0.1416, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 0.2491539865732193, | |
| "eval_runtime": 790.6324, | |
| "eval_samples_per_second": 2.168, | |
| "eval_steps_per_second": 0.272, | |
| "eval_wer": 33.508392544537124, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.608121173058331e-06, | |
| "loss": 0.1359, | |
| "step": 3016 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.589429584273284e-06, | |
| "loss": 0.1324, | |
| "step": 3132 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.570737995488239e-06, | |
| "loss": 0.1388, | |
| "step": 3248 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.552046406703192e-06, | |
| "loss": 0.1353, | |
| "step": 3364 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.533354817918145e-06, | |
| "loss": 0.1293, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.24061298370361328, | |
| "eval_runtime": 785.4078, | |
| "eval_samples_per_second": 2.182, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 32.01524044897539, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.514663229133098e-06, | |
| "loss": 0.1293, | |
| "step": 3596 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.49597164034805e-06, | |
| "loss": 0.1234, | |
| "step": 3712 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.477280051563005e-06, | |
| "loss": 0.1165, | |
| "step": 3828 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.458588462777958e-06, | |
| "loss": 0.1221, | |
| "step": 3944 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.439896873992912e-06, | |
| "loss": 0.1212, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.24251143634319305, | |
| "eval_runtime": 789.4621, | |
| "eval_samples_per_second": 2.171, | |
| "eval_steps_per_second": 0.272, | |
| "eval_wer": 31.366491607455465, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.421205285207865e-06, | |
| "loss": 0.121, | |
| "step": 4176 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.402513696422818e-06, | |
| "loss": 0.1118, | |
| "step": 4292 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.38382210763777e-06, | |
| "loss": 0.1093, | |
| "step": 4408 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.365130518852724e-06, | |
| "loss": 0.1155, | |
| "step": 4524 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.346438930067677e-06, | |
| "loss": 0.1102, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 0.22580939531326294, | |
| "eval_runtime": 787.0585, | |
| "eval_samples_per_second": 2.178, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 30.810421171866953, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.32774734128263e-06, | |
| "loss": 0.1057, | |
| "step": 4756 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.309055752497583e-06, | |
| "loss": 0.1053, | |
| "step": 4872 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.290364163712537e-06, | |
| "loss": 0.1007, | |
| "step": 4988 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.27167257492749e-06, | |
| "loss": 0.1076, | |
| "step": 5104 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.252980986142443e-06, | |
| "loss": 0.1058, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 0.21304036676883698, | |
| "eval_runtime": 789.6831, | |
| "eval_samples_per_second": 2.17, | |
| "eval_steps_per_second": 0.272, | |
| "eval_wer": 27.66965297085779, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.234289397357396e-06, | |
| "loss": 0.1027, | |
| "step": 5336 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.21559780857235e-06, | |
| "loss": 0.1013, | |
| "step": 5452 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.196906219787304e-06, | |
| "loss": 0.1011, | |
| "step": 5568 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.178214631002257e-06, | |
| "loss": 0.0987, | |
| "step": 5684 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.15952304221721e-06, | |
| "loss": 0.0981, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 0.20962001383304596, | |
| "eval_runtime": 788.0578, | |
| "eval_samples_per_second": 2.175, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 30.151374729687987, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.140831453432163e-06, | |
| "loss": 0.0984, | |
| "step": 5916 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.122139864647116e-06, | |
| "loss": 0.0928, | |
| "step": 6032 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.10344827586207e-06, | |
| "loss": 0.095, | |
| "step": 6148 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.084756687077024e-06, | |
| "loss": 0.0988, | |
| "step": 6264 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.066065098291977e-06, | |
| "loss": 0.0987, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.2030366212129593, | |
| "eval_runtime": 791.7115, | |
| "eval_samples_per_second": 2.165, | |
| "eval_steps_per_second": 0.272, | |
| "eval_wer": 29.23488827103285, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.04737350950693e-06, | |
| "loss": 0.0889, | |
| "step": 6496 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.028681920721883e-06, | |
| "loss": 0.0866, | |
| "step": 6612 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.009990331936836e-06, | |
| "loss": 0.088, | |
| "step": 6728 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.991298743151789e-06, | |
| "loss": 0.0886, | |
| "step": 6844 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.972607154366742e-06, | |
| "loss": 0.0879, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 0.2006106823682785, | |
| "eval_runtime": 788.215, | |
| "eval_samples_per_second": 2.175, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 26.814952116156938, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.953915565581695e-06, | |
| "loss": 0.0865, | |
| "step": 7076 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.935223976796648e-06, | |
| "loss": 0.0881, | |
| "step": 7192 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.916532388011603e-06, | |
| "loss": 0.0872, | |
| "step": 7308 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.897840799226556e-06, | |
| "loss": 0.0848, | |
| "step": 7424 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.879149210441509e-06, | |
| "loss": 0.0817, | |
| "step": 7540 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.20483049750328064, | |
| "eval_runtime": 791.5631, | |
| "eval_samples_per_second": 2.165, | |
| "eval_steps_per_second": 0.272, | |
| "eval_wer": 28.89506744928432, | |
| "step": 7540 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.860457621656462e-06, | |
| "loss": 0.0831, | |
| "step": 7656 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.841766032871415e-06, | |
| "loss": 0.0847, | |
| "step": 7772 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.82307444408637e-06, | |
| "loss": 0.0864, | |
| "step": 7888 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.804382855301323e-06, | |
| "loss": 0.0812, | |
| "step": 8004 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.785691266516276e-06, | |
| "loss": 0.0806, | |
| "step": 8120 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 0.19857698678970337, | |
| "eval_runtime": 798.8422, | |
| "eval_samples_per_second": 2.146, | |
| "eval_steps_per_second": 0.269, | |
| "eval_wer": 29.821851508598495, | |
| "step": 8120 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.767160812117308e-06, | |
| "loss": 0.0772, | |
| "step": 8236 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.74846922333226e-06, | |
| "loss": 0.082, | |
| "step": 8352 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.729777634547214e-06, | |
| "loss": 0.0782, | |
| "step": 8468 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.711086045762167e-06, | |
| "loss": 0.0797, | |
| "step": 8584 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.69239445697712e-06, | |
| "loss": 0.0766, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 0.19560863077640533, | |
| "eval_runtime": 782.2802, | |
| "eval_samples_per_second": 2.191, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 28.998043455874782, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.673702868192073e-06, | |
| "loss": 0.0811, | |
| "step": 8816 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.655011279407026e-06, | |
| "loss": 0.0754, | |
| "step": 8932 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.636319690621979e-06, | |
| "loss": 0.078, | |
| "step": 9048 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.617628101836932e-06, | |
| "loss": 0.0799, | |
| "step": 9164 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.598936513051886e-06, | |
| "loss": 0.0758, | |
| "step": 9280 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.1869840919971466, | |
| "eval_runtime": 788.0306, | |
| "eval_samples_per_second": 2.175, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 27.031201729996912, | |
| "step": 9280 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.58024492426684e-06, | |
| "loss": 0.0687, | |
| "step": 9396 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.561553335481792e-06, | |
| "loss": 0.0758, | |
| "step": 9512 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.542861746696746e-06, | |
| "loss": 0.0739, | |
| "step": 9628 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.524170157911699e-06, | |
| "loss": 0.0735, | |
| "step": 9744 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.505478569126653e-06, | |
| "loss": 0.0749, | |
| "step": 9860 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.18276962637901306, | |
| "eval_runtime": 787.0753, | |
| "eval_samples_per_second": 2.178, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 29.63649469673566, | |
| "step": 9860 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.486786980341606e-06, | |
| "loss": 0.0742, | |
| "step": 9976 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.46809539155656e-06, | |
| "loss": 0.0702, | |
| "step": 10092 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.449403802771512e-06, | |
| "loss": 0.0693, | |
| "step": 10208 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.430712213986465e-06, | |
| "loss": 0.0725, | |
| "step": 10324 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.412181759587497e-06, | |
| "loss": 0.0713, | |
| "step": 10440 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.18643251061439514, | |
| "eval_runtime": 785.1719, | |
| "eval_samples_per_second": 2.183, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 25.98084646277417, | |
| "step": 10440 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.39349017080245e-06, | |
| "loss": 0.0734, | |
| "step": 10556 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.374798582017403e-06, | |
| "loss": 0.072, | |
| "step": 10672 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.356106993232356e-06, | |
| "loss": 0.0704, | |
| "step": 10788 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.33741540444731e-06, | |
| "loss": 0.0684, | |
| "step": 10904 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.318884950048341e-06, | |
| "loss": 0.0634, | |
| "step": 11020 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.18063540756702423, | |
| "eval_runtime": 785.7442, | |
| "eval_samples_per_second": 2.181, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 26.681083307589333, | |
| "step": 11020 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.300193361263294e-06, | |
| "loss": 0.0681, | |
| "step": 11136 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.281501772478247e-06, | |
| "loss": 0.0677, | |
| "step": 11252 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.2628101836932e-06, | |
| "loss": 0.0701, | |
| "step": 11368 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.244118594908153e-06, | |
| "loss": 0.0648, | |
| "step": 11484 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.225427006123108e-06, | |
| "loss": 0.0682, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 0.1769612729549408, | |
| "eval_runtime": 783.3099, | |
| "eval_samples_per_second": 2.188, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 26.71197610956647, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.20673541733806e-06, | |
| "loss": 0.065, | |
| "step": 11716 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.188043828553014e-06, | |
| "loss": 0.0648, | |
| "step": 11832 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.169352239767967e-06, | |
| "loss": 0.0659, | |
| "step": 11948 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.15066065098292e-06, | |
| "loss": 0.0672, | |
| "step": 12064 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.131969062197875e-06, | |
| "loss": 0.0607, | |
| "step": 12180 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 0.1819377839565277, | |
| "eval_runtime": 783.0783, | |
| "eval_samples_per_second": 2.189, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 26.990011327360726, | |
| "step": 12180 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.113277473412828e-06, | |
| "loss": 0.0672, | |
| "step": 12296 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.09458588462778e-06, | |
| "loss": 0.0602, | |
| "step": 12412 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.075894295842734e-06, | |
| "loss": 0.0638, | |
| "step": 12528 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.057202707057687e-06, | |
| "loss": 0.0635, | |
| "step": 12644 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.038511118272641e-06, | |
| "loss": 0.0635, | |
| "step": 12760 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.17338888347148895, | |
| "eval_runtime": 785.414, | |
| "eval_samples_per_second": 2.182, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 26.578107300998866, | |
| "step": 12760 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.019819529487594e-06, | |
| "loss": 0.0656, | |
| "step": 12876 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.001127940702547e-06, | |
| "loss": 0.0608, | |
| "step": 12992 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.9824363519175e-06, | |
| "loss": 0.0588, | |
| "step": 13108 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.963744763132453e-06, | |
| "loss": 0.058, | |
| "step": 13224 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.945053174347406e-06, | |
| "loss": 0.061, | |
| "step": 13340 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 0.16947728395462036, | |
| "eval_runtime": 785.6425, | |
| "eval_samples_per_second": 2.182, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 27.6490577695397, | |
| "step": 13340 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.92636158556236e-06, | |
| "loss": 0.0579, | |
| "step": 13456 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.907669996777313e-06, | |
| "loss": 0.0639, | |
| "step": 13572 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.888978407992266e-06, | |
| "loss": 0.0625, | |
| "step": 13688 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.870286819207219e-06, | |
| "loss": 0.0611, | |
| "step": 13804 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.851595230422173e-06, | |
| "loss": 0.0623, | |
| "step": 13920 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 0.16918495297431946, | |
| "eval_runtime": 781.9171, | |
| "eval_samples_per_second": 2.192, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 27.422510555040674, | |
| "step": 13920 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.832903641637126e-06, | |
| "loss": 0.056, | |
| "step": 14036 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.81421205285208e-06, | |
| "loss": 0.0563, | |
| "step": 14152 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.795520464067032e-06, | |
| "loss": 0.054, | |
| "step": 14268 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.776828875281985e-06, | |
| "loss": 0.0536, | |
| "step": 14384 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.75813728649694e-06, | |
| "loss": 0.0583, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 0.17885711789131165, | |
| "eval_runtime": 782.2797, | |
| "eval_samples_per_second": 2.191, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 27.679950571516837, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.739445697711893e-06, | |
| "loss": 0.0562, | |
| "step": 14616 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.720754108926846e-06, | |
| "loss": 0.0586, | |
| "step": 14732 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.702062520141799e-06, | |
| "loss": 0.056, | |
| "step": 14848 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.683370931356752e-06, | |
| "loss": 0.0508, | |
| "step": 14964 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.664679342571705e-06, | |
| "loss": 0.0594, | |
| "step": 15080 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.16561517119407654, | |
| "eval_runtime": 794.3578, | |
| "eval_samples_per_second": 2.158, | |
| "eval_steps_per_second": 0.271, | |
| "eval_wer": 25.12614560807332, | |
| "step": 15080 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.645987753786658e-06, | |
| "loss": 0.0535, | |
| "step": 15196 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.627296165001612e-06, | |
| "loss": 0.0554, | |
| "step": 15312 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.608604576216565e-06, | |
| "loss": 0.0514, | |
| "step": 15428 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.589912987431518e-06, | |
| "loss": 0.0537, | |
| "step": 15544 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.571221398646472e-06, | |
| "loss": 0.0548, | |
| "step": 15660 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.1662958413362503, | |
| "eval_runtime": 783.8667, | |
| "eval_samples_per_second": 2.187, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 25.90876325816085, | |
| "step": 15660 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.552529809861425e-06, | |
| "loss": 0.0562, | |
| "step": 15776 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.533838221076378e-06, | |
| "loss": 0.0579, | |
| "step": 15892 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.515146632291331e-06, | |
| "loss": 0.0563, | |
| "step": 16008 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.496455043506284e-06, | |
| "loss": 0.0508, | |
| "step": 16124 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.477763454721239e-06, | |
| "loss": 0.0546, | |
| "step": 16240 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 0.15785543620586395, | |
| "eval_runtime": 781.6726, | |
| "eval_samples_per_second": 2.193, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 26.289774482545567, | |
| "step": 16240 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.459071865936192e-06, | |
| "loss": 0.0496, | |
| "step": 16356 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.440380277151145e-06, | |
| "loss": 0.0531, | |
| "step": 16472 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.421849822752177e-06, | |
| "loss": 0.0523, | |
| "step": 16588 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.40315823396713e-06, | |
| "loss": 0.0565, | |
| "step": 16704 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.384466645182083e-06, | |
| "loss": 0.0547, | |
| "step": 16820 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 0.16302894055843353, | |
| "eval_runtime": 785.7904, | |
| "eval_samples_per_second": 2.181, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 27.020904129337865, | |
| "step": 16820 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.365775056397036e-06, | |
| "loss": 0.0532, | |
| "step": 16936 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.3470834676119895e-06, | |
| "loss": 0.0557, | |
| "step": 17052 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.3283918788269426e-06, | |
| "loss": 0.0529, | |
| "step": 17168 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.309700290041896e-06, | |
| "loss": 0.0516, | |
| "step": 17284 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.291008701256849e-06, | |
| "loss": 0.0543, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.16456177830696106, | |
| "eval_runtime": 783.0024, | |
| "eval_samples_per_second": 2.189, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 26.444238492431264, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.272317112471802e-06, | |
| "loss": 0.054, | |
| "step": 17516 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.2536255236867555e-06, | |
| "loss": 0.0515, | |
| "step": 17632 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.2349339349017085e-06, | |
| "loss": 0.0564, | |
| "step": 17748 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.2162423461166616e-06, | |
| "loss": 0.0523, | |
| "step": 17864 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.197550757331615e-06, | |
| "loss": 0.0496, | |
| "step": 17980 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 0.16263148188591003, | |
| "eval_runtime": 783.5956, | |
| "eval_samples_per_second": 2.187, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 23.96251673360107, | |
| "step": 17980 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.1788591685465684e-06, | |
| "loss": 0.051, | |
| "step": 18096 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.160167579761522e-06, | |
| "loss": 0.0546, | |
| "step": 18212 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.141475990976475e-06, | |
| "loss": 0.0486, | |
| "step": 18328 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.122784402191428e-06, | |
| "loss": 0.0502, | |
| "step": 18444 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.104092813406381e-06, | |
| "loss": 0.0494, | |
| "step": 18560 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.15693338215351105, | |
| "eval_runtime": 786.4458, | |
| "eval_samples_per_second": 2.179, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 18.69014519616929, | |
| "step": 18560 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.085401224621334e-06, | |
| "loss": 0.0482, | |
| "step": 18676 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.066709635836288e-06, | |
| "loss": 0.0487, | |
| "step": 18792 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.048018047051241e-06, | |
| "loss": 0.0462, | |
| "step": 18908 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.029326458266194e-06, | |
| "loss": 0.0488, | |
| "step": 19024 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.010634869481147e-06, | |
| "loss": 0.0477, | |
| "step": 19140 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 0.15665055811405182, | |
| "eval_runtime": 789.4798, | |
| "eval_samples_per_second": 2.171, | |
| "eval_steps_per_second": 0.272, | |
| "eval_wer": 26.176500875296053, | |
| "step": 19140 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.9919432806961e-06, | |
| "loss": 0.0505, | |
| "step": 19256 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.973251691911055e-06, | |
| "loss": 0.0488, | |
| "step": 19372 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.954560103126008e-06, | |
| "loss": 0.0487, | |
| "step": 19488 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.935868514340961e-06, | |
| "loss": 0.0454, | |
| "step": 19604 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.917176925555914e-06, | |
| "loss": 0.0439, | |
| "step": 19720 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 0.15991590917110443, | |
| "eval_runtime": 784.4279, | |
| "eval_samples_per_second": 2.185, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 26.7840593141798, | |
| "step": 19720 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.898485336770867e-06, | |
| "loss": 0.0462, | |
| "step": 19836 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.879954882371899e-06, | |
| "loss": 0.0524, | |
| "step": 19952 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.861263293586852e-06, | |
| "loss": 0.0506, | |
| "step": 20068 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.842571704801805e-06, | |
| "loss": 0.0461, | |
| "step": 20184 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.823880116016759e-06, | |
| "loss": 0.0465, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.14981767535209656, | |
| "eval_runtime": 785.1354, | |
| "eval_samples_per_second": 2.183, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 25.692513644320876, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.805188527231712e-06, | |
| "loss": 0.0449, | |
| "step": 20416 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.786496938446665e-06, | |
| "loss": 0.0451, | |
| "step": 20532 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.767805349661618e-06, | |
| "loss": 0.0478, | |
| "step": 20648 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.749113760876571e-06, | |
| "loss": 0.0431, | |
| "step": 20764 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.730422172091526e-06, | |
| "loss": 0.0439, | |
| "step": 20880 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.1557285338640213, | |
| "eval_runtime": 784.9439, | |
| "eval_samples_per_second": 2.184, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 26.403048089795078, | |
| "step": 20880 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.711730583306479e-06, | |
| "loss": 0.0485, | |
| "step": 20996 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.693038994521432e-06, | |
| "loss": 0.0435, | |
| "step": 21112 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.674347405736385e-06, | |
| "loss": 0.0389, | |
| "step": 21228 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.655655816951338e-06, | |
| "loss": 0.0444, | |
| "step": 21344 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.636964228166292e-06, | |
| "loss": 0.0438, | |
| "step": 21460 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.15771810710430145, | |
| "eval_runtime": 783.9278, | |
| "eval_samples_per_second": 2.186, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 26.51632169704459, | |
| "step": 21460 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.618272639381245e-06, | |
| "loss": 0.0439, | |
| "step": 21576 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.599581050596198e-06, | |
| "loss": 0.0458, | |
| "step": 21692 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.580889461811151e-06, | |
| "loss": 0.0472, | |
| "step": 21808 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.562197873026104e-06, | |
| "loss": 0.0433, | |
| "step": 21924 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.5435062842410576e-06, | |
| "loss": 0.0443, | |
| "step": 22040 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.14860232174396515, | |
| "eval_runtime": 783.2253, | |
| "eval_samples_per_second": 2.188, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 25.96025126145608, | |
| "step": 22040 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.5249758298420885e-06, | |
| "loss": 0.0409, | |
| "step": 22156 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.506284241057042e-06, | |
| "loss": 0.0402, | |
| "step": 22272 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.487592652271995e-06, | |
| "loss": 0.0432, | |
| "step": 22388 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.468901063486948e-06, | |
| "loss": 0.0407, | |
| "step": 22504 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.450209474701901e-06, | |
| "loss": 0.0431, | |
| "step": 22620 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 0.15237173438072205, | |
| "eval_runtime": 782.7057, | |
| "eval_samples_per_second": 2.19, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 25.898465657501802, | |
| "step": 22620 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.4315178859168544e-06, | |
| "loss": 0.0444, | |
| "step": 22736 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.412826297131809e-06, | |
| "loss": 0.0436, | |
| "step": 22852 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.394134708346762e-06, | |
| "loss": 0.0448, | |
| "step": 22968 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.375443119561715e-06, | |
| "loss": 0.04, | |
| "step": 23084 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.356751530776668e-06, | |
| "loss": 0.0406, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 0.15666086971759796, | |
| "eval_runtime": 787.7061, | |
| "eval_samples_per_second": 2.176, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 26.33096488518175, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.338059941991621e-06, | |
| "loss": 0.0436, | |
| "step": 23316 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.319368353206575e-06, | |
| "loss": 0.0395, | |
| "step": 23432 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.300676764421528e-06, | |
| "loss": 0.0368, | |
| "step": 23548 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.281985175636481e-06, | |
| "loss": 0.0438, | |
| "step": 23664 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.263293586851434e-06, | |
| "loss": 0.0406, | |
| "step": 23780 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.15179598331451416, | |
| "eval_runtime": 785.8287, | |
| "eval_samples_per_second": 2.181, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 24.786324786324787, | |
| "step": 23780 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.244601998066387e-06, | |
| "loss": 0.0444, | |
| "step": 23896 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.225910409281342e-06, | |
| "loss": 0.0415, | |
| "step": 24012 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.207218820496295e-06, | |
| "loss": 0.0454, | |
| "step": 24128 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.188527231711248e-06, | |
| "loss": 0.0414, | |
| "step": 24244 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.169835642926201e-06, | |
| "loss": 0.0405, | |
| "step": 24360 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 0.14717231690883636, | |
| "eval_runtime": 783.1318, | |
| "eval_samples_per_second": 2.189, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 19.77139326536917, | |
| "step": 24360 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.151305188527233e-06, | |
| "loss": 0.0419, | |
| "step": 24476 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.132613599742186e-06, | |
| "loss": 0.0397, | |
| "step": 24592 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.113922010957139e-06, | |
| "loss": 0.0389, | |
| "step": 24708 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.095230422172092e-06, | |
| "loss": 0.0374, | |
| "step": 24824 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.076538833387046e-06, | |
| "loss": 0.0382, | |
| "step": 24940 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.14440029859542847, | |
| "eval_runtime": 783.3674, | |
| "eval_samples_per_second": 2.188, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 20.656986922047164, | |
| "step": 24940 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.057847244601999e-06, | |
| "loss": 0.0416, | |
| "step": 25056 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.039155655816952e-06, | |
| "loss": 0.0422, | |
| "step": 25172 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.020464067031905e-06, | |
| "loss": 0.0369, | |
| "step": 25288 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.001772478246858e-06, | |
| "loss": 0.0414, | |
| "step": 25404 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5.983080889461812e-06, | |
| "loss": 0.0389, | |
| "step": 25520 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 0.1415482610464096, | |
| "eval_runtime": 783.7026, | |
| "eval_samples_per_second": 2.187, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 21.944187004427967, | |
| "step": 25520 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5.964389300676765e-06, | |
| "loss": 0.0416, | |
| "step": 25636 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5.945697711891718e-06, | |
| "loss": 0.0386, | |
| "step": 25752 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5.927006123106671e-06, | |
| "loss": 0.0373, | |
| "step": 25868 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5.9083145343216254e-06, | |
| "loss": 0.0407, | |
| "step": 25984 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 5.8896229455365785e-06, | |
| "loss": 0.0383, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.14374086260795593, | |
| "eval_runtime": 787.1, | |
| "eval_samples_per_second": 2.178, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 21.408711770157556, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 5.8709313567515315e-06, | |
| "loss": 0.0405, | |
| "step": 26216 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 5.8522397679664845e-06, | |
| "loss": 0.0414, | |
| "step": 26332 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 5.8335481791814375e-06, | |
| "loss": 0.0398, | |
| "step": 26448 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 5.815017724782469e-06, | |
| "loss": 0.0421, | |
| "step": 26564 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 5.796326135997422e-06, | |
| "loss": 0.036, | |
| "step": 26680 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 0.14346691966056824, | |
| "eval_runtime": 787.9907, | |
| "eval_samples_per_second": 2.175, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 21.50139017608897, | |
| "step": 26680 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 5.777634547212375e-06, | |
| "loss": 0.0383, | |
| "step": 26796 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 5.758942958427329e-06, | |
| "loss": 0.0399, | |
| "step": 26912 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 5.740251369642282e-06, | |
| "loss": 0.0368, | |
| "step": 27028 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 5.721559780857235e-06, | |
| "loss": 0.0386, | |
| "step": 27144 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.702868192072188e-06, | |
| "loss": 0.0357, | |
| "step": 27260 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.1420992761850357, | |
| "eval_runtime": 784.1914, | |
| "eval_samples_per_second": 2.186, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 23.663886314488725, | |
| "step": 27260 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.684176603287141e-06, | |
| "loss": 0.0395, | |
| "step": 27376 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.665485014502096e-06, | |
| "loss": 0.0348, | |
| "step": 27492 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.646793425717049e-06, | |
| "loss": 0.0361, | |
| "step": 27608 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.628101836932002e-06, | |
| "loss": 0.0369, | |
| "step": 27724 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.609410248146955e-06, | |
| "loss": 0.0369, | |
| "step": 27840 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.14183476567268372, | |
| "eval_runtime": 784.9371, | |
| "eval_samples_per_second": 2.184, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 23.911028730305837, | |
| "step": 27840 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.590718659361908e-06, | |
| "loss": 0.0372, | |
| "step": 27956 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.572027070576862e-06, | |
| "loss": 0.0355, | |
| "step": 28072 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.553335481791815e-06, | |
| "loss": 0.0354, | |
| "step": 28188 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.534643893006768e-06, | |
| "loss": 0.0342, | |
| "step": 28304 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.515952304221721e-06, | |
| "loss": 0.035, | |
| "step": 28420 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 0.13896532356739044, | |
| "eval_runtime": 785.0487, | |
| "eval_samples_per_second": 2.183, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 24.88930079291525, | |
| "step": 28420 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.497260715436674e-06, | |
| "loss": 0.0338, | |
| "step": 28536 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.478569126651628e-06, | |
| "loss": 0.0364, | |
| "step": 28652 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.459877537866582e-06, | |
| "loss": 0.0368, | |
| "step": 28768 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.441185949081535e-06, | |
| "loss": 0.0328, | |
| "step": 28884 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.422494360296488e-06, | |
| "loss": 0.0368, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 0.14057199656963348, | |
| "eval_runtime": 793.8154, | |
| "eval_samples_per_second": 2.159, | |
| "eval_steps_per_second": 0.271, | |
| "eval_wer": 23.334363093399237, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 5.403802771511441e-06, | |
| "loss": 0.0366, | |
| "step": 29116 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.385111182726395e-06, | |
| "loss": 0.0336, | |
| "step": 29232 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.366419593941348e-06, | |
| "loss": 0.0343, | |
| "step": 29348 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.347728005156301e-06, | |
| "loss": 0.0334, | |
| "step": 29464 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.329036416371254e-06, | |
| "loss": 0.0323, | |
| "step": 29580 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.1342051774263382, | |
| "eval_runtime": 783.5326, | |
| "eval_samples_per_second": 2.188, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 21.975079806405105, | |
| "step": 29580 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 5.310344827586207e-06, | |
| "loss": 0.0349, | |
| "step": 29696 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.291653238801161e-06, | |
| "loss": 0.0311, | |
| "step": 29812 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.272961650016114e-06, | |
| "loss": 0.0322, | |
| "step": 29928 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.254270061231067e-06, | |
| "loss": 0.0341, | |
| "step": 30044 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.2368675475346446e-06, | |
| "loss": 0.1425, | |
| "step": 30160 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.1378883421421051, | |
| "eval_runtime": 787.4376, | |
| "eval_samples_per_second": 2.177, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 15.343424981979197, | |
| "step": 30160 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.218175958749598e-06, | |
| "loss": 0.0322, | |
| "step": 30276 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.1994843699645515e-06, | |
| "loss": 0.0351, | |
| "step": 30392 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.1807927811795045e-06, | |
| "loss": 0.0362, | |
| "step": 30508 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.1621011923944575e-06, | |
| "loss": 0.0333, | |
| "step": 30624 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.1434096036094105e-06, | |
| "loss": 0.0324, | |
| "step": 30740 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 0.1346246302127838, | |
| "eval_runtime": 783.3435, | |
| "eval_samples_per_second": 2.188, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 10.513850272886417, | |
| "step": 30740 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.1247180148243635e-06, | |
| "loss": 0.035, | |
| "step": 30856 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.106026426039317e-06, | |
| "loss": 0.0353, | |
| "step": 30972 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.0873348372542704e-06, | |
| "loss": 0.0315, | |
| "step": 31088 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.0686432484692235e-06, | |
| "loss": 0.0355, | |
| "step": 31204 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.0499516596841765e-06, | |
| "loss": 0.0303, | |
| "step": 31320 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.13406488299369812, | |
| "eval_runtime": 785.1703, | |
| "eval_samples_per_second": 2.183, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 10.24611265575121, | |
| "step": 31320 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.03126007089913e-06, | |
| "loss": 0.0326, | |
| "step": 31436 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.012568482114084e-06, | |
| "loss": 0.0303, | |
| "step": 31552 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.993876893329036e-06, | |
| "loss": 0.0342, | |
| "step": 31668 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.97518530454399e-06, | |
| "loss": 0.0297, | |
| "step": 31784 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.956493715758943e-06, | |
| "loss": 0.0298, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.13156923651695251, | |
| "eval_runtime": 788.5054, | |
| "eval_samples_per_second": 2.174, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 9.535578210277006, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.937802126973897e-06, | |
| "loss": 0.0333, | |
| "step": 32016 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.91911053818885e-06, | |
| "loss": 0.0314, | |
| "step": 32132 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.900418949403803e-06, | |
| "loss": 0.0303, | |
| "step": 32248 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.881727360618756e-06, | |
| "loss": 0.0332, | |
| "step": 32364 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.863035771833709e-06, | |
| "loss": 0.0308, | |
| "step": 32480 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 0.13265329599380493, | |
| "eval_runtime": 782.9581, | |
| "eval_samples_per_second": 2.189, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 9.514983008958913, | |
| "step": 32480 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.844344183048663e-06, | |
| "loss": 0.033, | |
| "step": 32596 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.825652594263616e-06, | |
| "loss": 0.0328, | |
| "step": 32712 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.806961005478569e-06, | |
| "loss": 0.0303, | |
| "step": 32828 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.788269416693523e-06, | |
| "loss": 0.0297, | |
| "step": 32944 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.769577827908476e-06, | |
| "loss": 0.0312, | |
| "step": 33060 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 0.1312318742275238, | |
| "eval_runtime": 783.4807, | |
| "eval_samples_per_second": 2.188, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 10.019565441252189, | |
| "step": 33060 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.75088623912343e-06, | |
| "loss": 0.0305, | |
| "step": 33176 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.732194650338383e-06, | |
| "loss": 0.0306, | |
| "step": 33292 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.713503061553336e-06, | |
| "loss": 0.0297, | |
| "step": 33408 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.694811472768289e-06, | |
| "loss": 0.0287, | |
| "step": 33524 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.676119883983242e-06, | |
| "loss": 0.0316, | |
| "step": 33640 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 0.12888002395629883, | |
| "eval_runtime": 787.0374, | |
| "eval_samples_per_second": 2.178, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 9.298733395118937, | |
| "step": 33640 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.657428295198196e-06, | |
| "loss": 0.0299, | |
| "step": 33756 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.638736706413149e-06, | |
| "loss": 0.0305, | |
| "step": 33872 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.620045117628103e-06, | |
| "loss": 0.0312, | |
| "step": 33988 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.601353528843056e-06, | |
| "loss": 0.0294, | |
| "step": 34104 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.582661940058009e-06, | |
| "loss": 0.0318, | |
| "step": 34220 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.12854613363742828, | |
| "eval_runtime": 782.7642, | |
| "eval_samples_per_second": 2.19, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 9.309030995777984, | |
| "step": 34220 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.563970351272962e-06, | |
| "loss": 0.0315, | |
| "step": 34336 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.545278762487915e-06, | |
| "loss": 0.0299, | |
| "step": 34452 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.526587173702869e-06, | |
| "loss": 0.029, | |
| "step": 34568 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.507895584917822e-06, | |
| "loss": 0.0294, | |
| "step": 34684 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.489203996132775e-06, | |
| "loss": 0.0305, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 0.12825001776218414, | |
| "eval_runtime": 786.5669, | |
| "eval_samples_per_second": 2.179, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 9.422304603027493, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.470512407347729e-06, | |
| "loss": 0.0278, | |
| "step": 34916 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.451820818562682e-06, | |
| "loss": 0.0287, | |
| "step": 35032 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.4331292297776355e-06, | |
| "loss": 0.0268, | |
| "step": 35148 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.4144376409925886e-06, | |
| "loss": 0.0275, | |
| "step": 35264 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.395746052207542e-06, | |
| "loss": 0.0279, | |
| "step": 35380 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 0.12600964307785034, | |
| "eval_runtime": 794.742, | |
| "eval_samples_per_second": 2.157, | |
| "eval_steps_per_second": 0.271, | |
| "eval_wer": 9.14426938523324, | |
| "step": 35380 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.377054463422495e-06, | |
| "loss": 0.0286, | |
| "step": 35496 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.358362874637448e-06, | |
| "loss": 0.0276, | |
| "step": 35612 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.3396712858524015e-06, | |
| "loss": 0.0314, | |
| "step": 35728 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.3209796970673545e-06, | |
| "loss": 0.0336, | |
| "step": 35844 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.3022881082823075e-06, | |
| "loss": 0.0253, | |
| "step": 35960 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 0.12685632705688477, | |
| "eval_runtime": 785.8668, | |
| "eval_samples_per_second": 2.181, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 9.49438780764082, | |
| "step": 35960 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.283596519497261e-06, | |
| "loss": 0.0276, | |
| "step": 36076 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.2649049307122144e-06, | |
| "loss": 0.0283, | |
| "step": 36192 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.2462133419271675e-06, | |
| "loss": 0.0313, | |
| "step": 36308 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.2275217531421205e-06, | |
| "loss": 0.0281, | |
| "step": 36424 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.2088301643570735e-06, | |
| "loss": 0.026, | |
| "step": 36540 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.1278238743543625, | |
| "eval_runtime": 782.8112, | |
| "eval_samples_per_second": 2.19, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 9.597363814231285, | |
| "step": 36540 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.190138575572027e-06, | |
| "loss": 0.0267, | |
| "step": 36656 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.17144698678698e-06, | |
| "loss": 0.0237, | |
| "step": 36772 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.152755398001934e-06, | |
| "loss": 0.0281, | |
| "step": 36888 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.134063809216887e-06, | |
| "loss": 0.0287, | |
| "step": 37004 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.11537222043184e-06, | |
| "loss": 0.0309, | |
| "step": 37120 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 0.12141475081443787, | |
| "eval_runtime": 786.3376, | |
| "eval_samples_per_second": 2.18, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 9.257542992482753, | |
| "step": 37120 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.096680631646794e-06, | |
| "loss": 0.0282, | |
| "step": 37236 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.077989042861747e-06, | |
| "loss": 0.0274, | |
| "step": 37352 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.0592974540767e-06, | |
| "loss": 0.0267, | |
| "step": 37468 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.040605865291653e-06, | |
| "loss": 0.0277, | |
| "step": 37584 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.021914276506606e-06, | |
| "loss": 0.0264, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.12097407132387161, | |
| "eval_runtime": 784.7681, | |
| "eval_samples_per_second": 2.184, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 9.113376583256102, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.00322268772156e-06, | |
| "loss": 0.0274, | |
| "step": 37816 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.984531098936513e-06, | |
| "loss": 0.0274, | |
| "step": 37932 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.965839510151467e-06, | |
| "loss": 0.0272, | |
| "step": 38048 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.94714792136642e-06, | |
| "loss": 0.0247, | |
| "step": 38164 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.928456332581373e-06, | |
| "loss": 0.0267, | |
| "step": 38280 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 0.11954796314239502, | |
| "eval_runtime": 787.0916, | |
| "eval_samples_per_second": 2.178, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 8.691174956235196, | |
| "step": 38280 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.909764743796327e-06, | |
| "loss": 0.0258, | |
| "step": 38396 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.89107315501128e-06, | |
| "loss": 0.027, | |
| "step": 38512 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.872381566226233e-06, | |
| "loss": 0.0218, | |
| "step": 38628 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.853689977441186e-06, | |
| "loss": 0.0271, | |
| "step": 38744 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.834998388656139e-06, | |
| "loss": 0.0265, | |
| "step": 38860 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 0.122675821185112, | |
| "eval_runtime": 782.1019, | |
| "eval_samples_per_second": 2.192, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 8.938317372052312, | |
| "step": 38860 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.816306799871093e-06, | |
| "loss": 0.0262, | |
| "step": 38976 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.797615211086046e-06, | |
| "loss": 0.0247, | |
| "step": 39092 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.7789236223009994e-06, | |
| "loss": 0.0244, | |
| "step": 39208 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.7602320335159524e-06, | |
| "loss": 0.0238, | |
| "step": 39324 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.7415404447309054e-06, | |
| "loss": 0.0249, | |
| "step": 39440 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 0.12250470370054245, | |
| "eval_runtime": 786.0666, | |
| "eval_samples_per_second": 2.18, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 9.020698177324684, | |
| "step": 39440 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.7228488559458593e-06, | |
| "loss": 0.0212, | |
| "step": 39556 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.7041572671608123e-06, | |
| "loss": 0.0245, | |
| "step": 39672 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.6854656783757658e-06, | |
| "loss": 0.0248, | |
| "step": 39788 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.6667740895907188e-06, | |
| "loss": 0.0246, | |
| "step": 39904 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.6480825008056726e-06, | |
| "loss": 0.0243, | |
| "step": 40020 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.11990202963352203, | |
| "eval_runtime": 783.4725, | |
| "eval_samples_per_second": 2.188, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 8.608794150962826, | |
| "step": 40020 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.6293909120206257e-06, | |
| "loss": 0.0254, | |
| "step": 40136 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.6106993232355787e-06, | |
| "loss": 0.0232, | |
| "step": 40252 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.592007734450532e-06, | |
| "loss": 0.0228, | |
| "step": 40368 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.573316145665485e-06, | |
| "loss": 0.0235, | |
| "step": 40484 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.554624556880439e-06, | |
| "loss": 0.028, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.11790936440229416, | |
| "eval_runtime": 795.6896, | |
| "eval_samples_per_second": 2.154, | |
| "eval_steps_per_second": 0.27, | |
| "eval_wer": 8.722067758212336, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.535932968095392e-06, | |
| "loss": 0.0245, | |
| "step": 40716 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.517241379310345e-06, | |
| "loss": 0.0244, | |
| "step": 40832 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.4985497905252985e-06, | |
| "loss": 0.0248, | |
| "step": 40948 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.4798582017402515e-06, | |
| "loss": 0.0247, | |
| "step": 41064 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.461166612955205e-06, | |
| "loss": 0.0237, | |
| "step": 41180 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 0.1159593015909195, | |
| "eval_runtime": 782.6245, | |
| "eval_samples_per_second": 2.19, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 8.752960560189475, | |
| "step": 41180 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.442475024170158e-06, | |
| "loss": 0.0271, | |
| "step": 41296 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.4237834353851115e-06, | |
| "loss": 0.0243, | |
| "step": 41412 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.405091846600065e-06, | |
| "loss": 0.0239, | |
| "step": 41528 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.386400257815018e-06, | |
| "loss": 0.0262, | |
| "step": 41644 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.3677086690299714e-06, | |
| "loss": 0.025, | |
| "step": 41760 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.11735337227582932, | |
| "eval_runtime": 784.0887, | |
| "eval_samples_per_second": 2.186, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 9.010400576665637, | |
| "step": 41760 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.3490170802449244e-06, | |
| "loss": 0.0267, | |
| "step": 41876 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.3303254914598774e-06, | |
| "loss": 0.0211, | |
| "step": 41992 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.3116339026748313e-06, | |
| "loss": 0.0213, | |
| "step": 42108 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.2929423138897843e-06, | |
| "loss": 0.0229, | |
| "step": 42224 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.2742507251047378e-06, | |
| "loss": 0.0222, | |
| "step": 42340 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.12385321408510208, | |
| "eval_runtime": 782.3158, | |
| "eval_samples_per_second": 2.191, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 8.794150962825661, | |
| "step": 42340 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.2555591363196908e-06, | |
| "loss": 0.0217, | |
| "step": 42456 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.236867547534644e-06, | |
| "loss": 0.0214, | |
| "step": 42572 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.2181759587495977e-06, | |
| "loss": 0.0245, | |
| "step": 42688 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.1994843699645507e-06, | |
| "loss": 0.0247, | |
| "step": 42804 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.180792781179504e-06, | |
| "loss": 0.0231, | |
| "step": 42920 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 0.11846602708101273, | |
| "eval_runtime": 793.246, | |
| "eval_samples_per_second": 2.161, | |
| "eval_steps_per_second": 0.271, | |
| "eval_wer": 8.299866131191433, | |
| "step": 42920 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.162101192394457e-06, | |
| "loss": 0.0237, | |
| "step": 43036 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.14340960360941e-06, | |
| "loss": 0.0255, | |
| "step": 43152 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.124718014824364e-06, | |
| "loss": 0.0229, | |
| "step": 43268 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.106026426039317e-06, | |
| "loss": 0.0255, | |
| "step": 43384 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.0873348372542705e-06, | |
| "loss": 0.0241, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 0.11603421717882156, | |
| "eval_runtime": 782.7894, | |
| "eval_samples_per_second": 2.19, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 8.474925342395222, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.0686432484692235e-06, | |
| "loss": 0.023, | |
| "step": 43616 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.0499516596841766e-06, | |
| "loss": 0.0206, | |
| "step": 43732 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.03126007089913e-06, | |
| "loss": 0.0214, | |
| "step": 43848 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.0125684821140835e-06, | |
| "loss": 0.0248, | |
| "step": 43964 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.993876893329037e-06, | |
| "loss": 0.0222, | |
| "step": 44080 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.11518887430429459, | |
| "eval_runtime": 778.913, | |
| "eval_samples_per_second": 2.201, | |
| "eval_steps_per_second": 0.276, | |
| "eval_wer": 8.382246936463805, | |
| "step": 44080 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.97518530454399e-06, | |
| "loss": 0.026, | |
| "step": 44196 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.956493715758943e-06, | |
| "loss": 0.0238, | |
| "step": 44312 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.9378021269738964e-06, | |
| "loss": 0.0225, | |
| "step": 44428 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.9191105381888494e-06, | |
| "loss": 0.0223, | |
| "step": 44544 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.9004189494038033e-06, | |
| "loss": 0.0217, | |
| "step": 44660 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 0.11238180845975876, | |
| "eval_runtime": 790.4158, | |
| "eval_samples_per_second": 2.168, | |
| "eval_steps_per_second": 0.272, | |
| "eval_wer": 8.629389352280919, | |
| "step": 44660 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.8817273606187563e-06, | |
| "loss": 0.022, | |
| "step": 44776 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.8630357718337093e-06, | |
| "loss": 0.0229, | |
| "step": 44892 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.8443441830486628e-06, | |
| "loss": 0.0195, | |
| "step": 45008 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.825652594263616e-06, | |
| "loss": 0.0198, | |
| "step": 45124 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.8069610054785697e-06, | |
| "loss": 0.0212, | |
| "step": 45240 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.11343366652727127, | |
| "eval_runtime": 788.7719, | |
| "eval_samples_per_second": 2.173, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 8.299866131191433, | |
| "step": 45240 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.7882694166935227e-06, | |
| "loss": 0.0216, | |
| "step": 45356 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.7695778279084757e-06, | |
| "loss": 0.0214, | |
| "step": 45472 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.750886239123429e-06, | |
| "loss": 0.0199, | |
| "step": 45588 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.732194650338382e-06, | |
| "loss": 0.022, | |
| "step": 45704 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.713503061553336e-06, | |
| "loss": 0.019, | |
| "step": 45820 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 0.11607277393341064, | |
| "eval_runtime": 785.504, | |
| "eval_samples_per_second": 2.182, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 8.196890124600968, | |
| "step": 45820 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.694811472768289e-06, | |
| "loss": 0.0222, | |
| "step": 45936 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.6761198839832425e-06, | |
| "loss": 0.0205, | |
| "step": 46052 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.6574282951981955e-06, | |
| "loss": 0.0217, | |
| "step": 46168 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.6387367064131486e-06, | |
| "loss": 0.0222, | |
| "step": 46284 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.620045117628102e-06, | |
| "loss": 0.0198, | |
| "step": 46400 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.11315659433603287, | |
| "eval_runtime": 783.5623, | |
| "eval_samples_per_second": 2.187, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 8.413139738440943, | |
| "step": 46400 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.6013535288430555e-06, | |
| "loss": 0.0225, | |
| "step": 46516 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.582661940058009e-06, | |
| "loss": 0.0234, | |
| "step": 46632 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.563970351272962e-06, | |
| "loss": 0.0225, | |
| "step": 46748 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.545278762487915e-06, | |
| "loss": 0.0194, | |
| "step": 46864 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.5265871737028684e-06, | |
| "loss": 0.0239, | |
| "step": 46980 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.11144877225160599, | |
| "eval_runtime": 793.7955, | |
| "eval_samples_per_second": 2.159, | |
| "eval_steps_per_second": 0.271, | |
| "eval_wer": 8.10421171866955, | |
| "step": 46980 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.5078955849178214e-06, | |
| "loss": 0.0188, | |
| "step": 47096 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.489203996132775e-06, | |
| "loss": 0.0215, | |
| "step": 47212 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.4705124073477283e-06, | |
| "loss": 0.0192, | |
| "step": 47328 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.4518208185626818e-06, | |
| "loss": 0.0209, | |
| "step": 47444 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.4331292297776348e-06, | |
| "loss": 0.0195, | |
| "step": 47560 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.11171752959489822, | |
| "eval_runtime": 787.1503, | |
| "eval_samples_per_second": 2.177, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 8.227782926578108, | |
| "step": 47560 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.414437640992588e-06, | |
| "loss": 0.0193, | |
| "step": 47676 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.3957460522075413e-06, | |
| "loss": 0.0177, | |
| "step": 47792 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2.3770544634224947e-06, | |
| "loss": 0.0194, | |
| "step": 47908 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.3583628746374477e-06, | |
| "loss": 0.0192, | |
| "step": 48024 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.339671285852401e-06, | |
| "loss": 0.0208, | |
| "step": 48140 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 0.10952310264110565, | |
| "eval_runtime": 788.6548, | |
| "eval_samples_per_second": 2.173, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 8.042426114715271, | |
| "step": 48140 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.320979697067354e-06, | |
| "loss": 0.0197, | |
| "step": 48256 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.3022881082823076e-06, | |
| "loss": 0.0192, | |
| "step": 48372 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.283757653883339e-06, | |
| "loss": 0.0178, | |
| "step": 48488 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.2650660650982924e-06, | |
| "loss": 0.0186, | |
| "step": 48604 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.2463744763132454e-06, | |
| "loss": 0.0201, | |
| "step": 48720 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 0.10950493812561035, | |
| "eval_runtime": 783.1853, | |
| "eval_samples_per_second": 2.188, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 7.867366903511481, | |
| "step": 48720 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.2276828875281985e-06, | |
| "loss": 0.0191, | |
| "step": 48836 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.208991298743152e-06, | |
| "loss": 0.0194, | |
| "step": 48952 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.1902997099581054e-06, | |
| "loss": 0.0204, | |
| "step": 49068 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.1716081211730584e-06, | |
| "loss": 0.0205, | |
| "step": 49184 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.152916532388012e-06, | |
| "loss": 0.0191, | |
| "step": 49300 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.11016014218330383, | |
| "eval_runtime": 787.2967, | |
| "eval_samples_per_second": 2.177, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 8.052723715374317, | |
| "step": 49300 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.134224943602965e-06, | |
| "loss": 0.0186, | |
| "step": 49416 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.1155333548179183e-06, | |
| "loss": 0.0177, | |
| "step": 49532 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.0968417660328717e-06, | |
| "loss": 0.019, | |
| "step": 49648 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.0781501772478248e-06, | |
| "loss": 0.02, | |
| "step": 49764 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.059458588462778e-06, | |
| "loss": 0.0192, | |
| "step": 49880 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.10825244337320328, | |
| "eval_runtime": 784.2924, | |
| "eval_samples_per_second": 2.185, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 7.908557306147667, | |
| "step": 49880 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.0407669996777312e-06, | |
| "loss": 0.0223, | |
| "step": 49996 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.0220754108926847e-06, | |
| "loss": 0.0178, | |
| "step": 50112 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.003383822107638e-06, | |
| "loss": 0.017, | |
| "step": 50228 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.984692233322591e-06, | |
| "loss": 0.0175, | |
| "step": 50344 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.9661617789236225e-06, | |
| "loss": 0.0201, | |
| "step": 50460 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 0.10784495621919632, | |
| "eval_runtime": 782.5124, | |
| "eval_samples_per_second": 2.19, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 7.805581299557203, | |
| "step": 50460 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.9474701901385755e-06, | |
| "loss": 0.0184, | |
| "step": 50576 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.928778601353529e-06, | |
| "loss": 0.0175, | |
| "step": 50692 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.9100870125684824e-06, | |
| "loss": 0.0191, | |
| "step": 50808 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.8913954237834356e-06, | |
| "loss": 0.0169, | |
| "step": 50924 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.8727038349983889e-06, | |
| "loss": 0.0186, | |
| "step": 51040 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 0.10628069937229156, | |
| "eval_runtime": 794.0691, | |
| "eval_samples_per_second": 2.159, | |
| "eval_steps_per_second": 0.271, | |
| "eval_wer": 7.527546081762949, | |
| "step": 51040 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.8540122462133419e-06, | |
| "loss": 0.0172, | |
| "step": 51156 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.8353206574282953e-06, | |
| "loss": 0.0182, | |
| "step": 51272 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.8166290686432486e-06, | |
| "loss": 0.0175, | |
| "step": 51388 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.797937479858202e-06, | |
| "loss": 0.0181, | |
| "step": 51504 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.7792458910731552e-06, | |
| "loss": 0.0172, | |
| "step": 51620 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 0.10713626444339752, | |
| "eval_runtime": 787.3756, | |
| "eval_samples_per_second": 2.177, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 7.898259705488621, | |
| "step": 51620 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.7605543022881083e-06, | |
| "loss": 0.0165, | |
| "step": 51736 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.7418627135030617e-06, | |
| "loss": 0.0189, | |
| "step": 51852 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.723171124718015e-06, | |
| "loss": 0.0182, | |
| "step": 51968 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.7044795359329682e-06, | |
| "loss": 0.0171, | |
| "step": 52084 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.6857879471479216e-06, | |
| "loss": 0.0163, | |
| "step": 52200 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 0.10758110135793686, | |
| "eval_runtime": 786.0519, | |
| "eval_samples_per_second": 2.181, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 7.64081968901246, | |
| "step": 52200 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.6670963583628746e-06, | |
| "loss": 0.018, | |
| "step": 52316 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.6484047695778279e-06, | |
| "loss": 0.0169, | |
| "step": 52432 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.6297131807927813e-06, | |
| "loss": 0.0172, | |
| "step": 52548 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.6110215920077346e-06, | |
| "loss": 0.0146, | |
| "step": 52664 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.592330003222688e-06, | |
| "loss": 0.0161, | |
| "step": 52780 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 0.10708160698413849, | |
| "eval_runtime": 786.9909, | |
| "eval_samples_per_second": 2.178, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 7.92915250746576, | |
| "step": 52780 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.5736384144376412e-06, | |
| "loss": 0.0168, | |
| "step": 52896 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.5551079600386724e-06, | |
| "loss": 0.0166, | |
| "step": 53012 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.5364163712536256e-06, | |
| "loss": 0.0162, | |
| "step": 53128 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.517724782468579e-06, | |
| "loss": 0.0176, | |
| "step": 53244 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.4990331936835323e-06, | |
| "loss": 0.0189, | |
| "step": 53360 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.1049240455031395, | |
| "eval_runtime": 784.1212, | |
| "eval_samples_per_second": 2.186, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 7.589331685717228, | |
| "step": 53360 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.4803416048984853e-06, | |
| "loss": 0.0152, | |
| "step": 53476 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.4616500161134387e-06, | |
| "loss": 0.0193, | |
| "step": 53592 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.442958427328392e-06, | |
| "loss": 0.0165, | |
| "step": 53708 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.4242668385433452e-06, | |
| "loss": 0.0175, | |
| "step": 53824 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.4055752497582987e-06, | |
| "loss": 0.0167, | |
| "step": 53940 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 0.10481404513120651, | |
| "eval_runtime": 784.2538, | |
| "eval_samples_per_second": 2.186, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 7.568736484399135, | |
| "step": 53940 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.386883660973252e-06, | |
| "loss": 0.0138, | |
| "step": 54056 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.368192072188205e-06, | |
| "loss": 0.0183, | |
| "step": 54172 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.3495004834031584e-06, | |
| "loss": 0.0158, | |
| "step": 54288 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.3308088946181116e-06, | |
| "loss": 0.018, | |
| "step": 54404 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.312117305833065e-06, | |
| "loss": 0.016, | |
| "step": 54520 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 0.10257178544998169, | |
| "eval_runtime": 779.3466, | |
| "eval_samples_per_second": 2.199, | |
| "eval_steps_per_second": 0.276, | |
| "eval_wer": 7.537843682421997, | |
| "step": 54520 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.2934257170480183e-06, | |
| "loss": 0.0182, | |
| "step": 54636 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.2747341282629713e-06, | |
| "loss": 0.0167, | |
| "step": 54752 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.2560425394779247e-06, | |
| "loss": 0.0182, | |
| "step": 54868 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.237350950692878e-06, | |
| "loss": 0.0173, | |
| "step": 54984 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.2186593619078312e-06, | |
| "loss": 0.016, | |
| "step": 55100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 0.1033649742603302, | |
| "eval_runtime": 792.3552, | |
| "eval_samples_per_second": 2.163, | |
| "eval_steps_per_second": 0.271, | |
| "eval_wer": 7.403974873854392, | |
| "step": 55100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.1999677731227845e-06, | |
| "loss": 0.0169, | |
| "step": 55216 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.181276184337738e-06, | |
| "loss": 0.0151, | |
| "step": 55332 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.162584595552691e-06, | |
| "loss": 0.0167, | |
| "step": 55448 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.1438930067676444e-06, | |
| "loss": 0.015, | |
| "step": 55564 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.1252014179825976e-06, | |
| "loss": 0.015, | |
| "step": 55680 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 0.10430463403463364, | |
| "eval_runtime": 785.9691, | |
| "eval_samples_per_second": 2.181, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 7.424570075172484, | |
| "step": 55680 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.1065098291975508e-06, | |
| "loss": 0.0183, | |
| "step": 55796 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.087818240412504e-06, | |
| "loss": 0.0173, | |
| "step": 55912 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.0691266516274573e-06, | |
| "loss": 0.015, | |
| "step": 56028 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.0504350628424108e-06, | |
| "loss": 0.0156, | |
| "step": 56144 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.031743474057364e-06, | |
| "loss": 0.0163, | |
| "step": 56260 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.10278747975826263, | |
| "eval_runtime": 787.108, | |
| "eval_samples_per_second": 2.178, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 7.5481412830810415, | |
| "step": 56260 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.0130518852723172e-06, | |
| "loss": 0.0176, | |
| "step": 56376 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.943602964872705e-07, | |
| "loss": 0.0157, | |
| "step": 56492 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.75668707702224e-07, | |
| "loss": 0.0138, | |
| "step": 56608 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.56977118917177e-07, | |
| "loss": 0.015, | |
| "step": 56724 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.382855301321303e-07, | |
| "loss": 0.0154, | |
| "step": 56840 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 0.1029290109872818, | |
| "eval_runtime": 783.9469, | |
| "eval_samples_per_second": 2.186, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 7.455462877149624, | |
| "step": 56840 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.197550757331615e-07, | |
| "loss": 0.017, | |
| "step": 56956 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.010634869481148e-07, | |
| "loss": 0.0156, | |
| "step": 57072 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 8.82371898163068e-07, | |
| "loss": 0.016, | |
| "step": 57188 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 8.636803093780213e-07, | |
| "loss": 0.0144, | |
| "step": 57304 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 8.449887205929746e-07, | |
| "loss": 0.0176, | |
| "step": 57420 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 0.1018747016787529, | |
| "eval_runtime": 783.2187, | |
| "eval_samples_per_second": 2.188, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 7.49665327978581, | |
| "step": 57420 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 8.262971318079279e-07, | |
| "loss": 0.018, | |
| "step": 57536 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 8.076055430228811e-07, | |
| "loss": 0.0162, | |
| "step": 57652 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 7.889139542378344e-07, | |
| "loss": 0.0146, | |
| "step": 57768 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 7.702223654527877e-07, | |
| "loss": 0.0133, | |
| "step": 57884 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 7.51530776667741e-07, | |
| "loss": 0.0167, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 0.10182846337556839, | |
| "eval_runtime": 789.1997, | |
| "eval_samples_per_second": 2.172, | |
| "eval_steps_per_second": 0.272, | |
| "eval_wer": 7.445165276490577, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 7.328391878826942e-07, | |
| "loss": 0.0164, | |
| "step": 58116 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 7.141475990976475e-07, | |
| "loss": 0.0151, | |
| "step": 58232 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 6.954560103126008e-07, | |
| "loss": 0.0136, | |
| "step": 58348 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 6.76764421527554e-07, | |
| "loss": 0.0136, | |
| "step": 58464 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 6.580728327425073e-07, | |
| "loss": 0.0163, | |
| "step": 58580 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 0.1013648584485054, | |
| "eval_runtime": 785.0865, | |
| "eval_samples_per_second": 2.183, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 7.445165276490577, | |
| "step": 58580 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 6.393812439574605e-07, | |
| "loss": 0.014, | |
| "step": 58696 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 6.206896551724139e-07, | |
| "loss": 0.0144, | |
| "step": 58812 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 6.019980663873671e-07, | |
| "loss": 0.0147, | |
| "step": 58928 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 5.834676119883983e-07, | |
| "loss": 0.013, | |
| "step": 59044 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 5.647760232033517e-07, | |
| "loss": 0.0132, | |
| "step": 59160 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 0.10131796449422836, | |
| "eval_runtime": 782.9945, | |
| "eval_samples_per_second": 2.189, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 7.136237256719184, | |
| "step": 59160 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 5.460844344183049e-07, | |
| "loss": 0.0125, | |
| "step": 59276 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 5.273928456332581e-07, | |
| "loss": 0.0118, | |
| "step": 59392 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 5.087012568482115e-07, | |
| "loss": 0.0156, | |
| "step": 59508 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.900096680631647e-07, | |
| "loss": 0.0164, | |
| "step": 59624 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.7147921366419595e-07, | |
| "loss": 0.0143, | |
| "step": 59740 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 0.10116977989673615, | |
| "eval_runtime": 781.1213, | |
| "eval_samples_per_second": 2.194, | |
| "eval_steps_per_second": 0.275, | |
| "eval_wer": 7.383379672536298, | |
| "step": 59740 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.527876248791493e-07, | |
| "loss": 0.0128, | |
| "step": 59856 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.340960360941025e-07, | |
| "loss": 0.015, | |
| "step": 59972 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.1540444730905576e-07, | |
| "loss": 0.0134, | |
| "step": 60088 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.9671285852400905e-07, | |
| "loss": 0.0148, | |
| "step": 60204 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.780212697389624e-07, | |
| "loss": 0.0159, | |
| "step": 60320 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.10068144649267197, | |
| "eval_runtime": 785.2541, | |
| "eval_samples_per_second": 2.183, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 7.311296467922975, | |
| "step": 60320 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.593296809539156e-07, | |
| "loss": 0.0145, | |
| "step": 60436 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.4063809216886885e-07, | |
| "loss": 0.0149, | |
| "step": 60552 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.2194650338382214e-07, | |
| "loss": 0.0158, | |
| "step": 60668 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.0325491459877543e-07, | |
| "loss": 0.0161, | |
| "step": 60784 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.8456332581372866e-07, | |
| "loss": 0.0127, | |
| "step": 60900 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.10017982870340347, | |
| "eval_runtime": 783.6716, | |
| "eval_samples_per_second": 2.187, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 7.290701266604881, | |
| "step": 60900 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.6587173702868195e-07, | |
| "loss": 0.0146, | |
| "step": 61016 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.471801482436352e-07, | |
| "loss": 0.0155, | |
| "step": 61132 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.284885594585885e-07, | |
| "loss": 0.0125, | |
| "step": 61248 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 2.0979697067354173e-07, | |
| "loss": 0.0161, | |
| "step": 61364 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.9110538188849505e-07, | |
| "loss": 0.0134, | |
| "step": 61480 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 0.10023297369480133, | |
| "eval_runtime": 783.3354, | |
| "eval_samples_per_second": 2.188, | |
| "eval_steps_per_second": 0.274, | |
| "eval_wer": 7.249510863968696, | |
| "step": 61480 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.7241379310344828e-07, | |
| "loss": 0.0153, | |
| "step": 61596 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.5372220431840157e-07, | |
| "loss": 0.0154, | |
| "step": 61712 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.3503061553335483e-07, | |
| "loss": 0.013, | |
| "step": 61828 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.163390267483081e-07, | |
| "loss": 0.0135, | |
| "step": 61944 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 9.764743796326138e-08, | |
| "loss": 0.0147, | |
| "step": 62060 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 0.10011597722768784, | |
| "eval_runtime": 799.7654, | |
| "eval_samples_per_second": 2.143, | |
| "eval_steps_per_second": 0.269, | |
| "eval_wer": 7.300998867263927, | |
| "step": 62060 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.895584917821464e-08, | |
| "loss": 0.0146, | |
| "step": 62176 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 6.02642603931679e-08, | |
| "loss": 0.0151, | |
| "step": 62292 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.157267160812117e-08, | |
| "loss": 0.0136, | |
| "step": 62408 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.2881082823074446e-08, | |
| "loss": 0.0123, | |
| "step": 62524 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.189494038027715e-09, | |
| "loss": 0.0144, | |
| "step": 62640 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.09998083859682083, | |
| "eval_runtime": 786.9298, | |
| "eval_samples_per_second": 2.178, | |
| "eval_steps_per_second": 0.273, | |
| "eval_wer": 7.280403665945835, | |
| "step": 62640 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 62640, | |
| "total_flos": 2.1279417860837375e+21, | |
| "train_loss": 0.051935346220949447, | |
| "train_runtime": 527672.5015, | |
| "train_samples_per_second": 1.899, | |
| "train_steps_per_second": 0.119 | |
| } | |
| ], | |
| "max_steps": 62640, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 2.1279417860837375e+21, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |