| { | |
| "best_metric": 0.5760026574134827, | |
| "best_model_checkpoint": "ai-light-dance_singing2_ft_wav2vec2-large-xlsr-53-v1/checkpoint-2128", | |
| "epoch": 39.99888517279822, | |
| "global_step": 4480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.6731, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.6923, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.6707, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.6669, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6685, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.669, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.8e-05, | |
| "loss": 1.6255, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 1.6338, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.6468, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.96e-05, | |
| "loss": 1.653, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.9917808219178084e-05, | |
| "loss": 1.656, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.762465476989746, | |
| "eval_runtime": 227.2609, | |
| "eval_samples_per_second": 8.774, | |
| "eval_steps_per_second": 0.88, | |
| "eval_wer": 0.9264513777075675, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.982648401826484e-05, | |
| "loss": 1.6323, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.97351598173516e-05, | |
| "loss": 1.5681, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.964383561643836e-05, | |
| "loss": 1.5729, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.955251141552512e-05, | |
| "loss": 1.4911, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 3.9461187214611876e-05, | |
| "loss": 1.4653, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 3.936986301369863e-05, | |
| "loss": 1.4765, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 3.927853881278539e-05, | |
| "loss": 1.4356, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.9187214611872154e-05, | |
| "loss": 1.4152, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.9095890410958904e-05, | |
| "loss": 1.4193, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.900456621004567e-05, | |
| "loss": 1.427, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 3.8913242009132425e-05, | |
| "loss": 1.3693, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.51346755027771, | |
| "eval_runtime": 229.1152, | |
| "eval_samples_per_second": 8.703, | |
| "eval_steps_per_second": 0.873, | |
| "eval_wer": 0.9243248169638788, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.882191780821918e-05, | |
| "loss": 1.4403, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.873059360730594e-05, | |
| "loss": 1.3155, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 3.8639269406392696e-05, | |
| "loss": 1.3129, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 3.854794520547945e-05, | |
| "loss": 1.2924, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 3.845662100456622e-05, | |
| "loss": 1.2861, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.836529680365297e-05, | |
| "loss": 1.2856, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 3.827397260273973e-05, | |
| "loss": 1.2469, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.818264840182649e-05, | |
| "loss": 1.225, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 3.8091324200913245e-05, | |
| "loss": 1.2471, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 3.8e-05, | |
| "loss": 1.2351, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.790867579908676e-05, | |
| "loss": 1.2172, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.2657241821289062, | |
| "eval_runtime": 228.6552, | |
| "eval_samples_per_second": 8.721, | |
| "eval_steps_per_second": 0.875, | |
| "eval_wer": 0.8533280675638728, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 3.7817351598173516e-05, | |
| "loss": 1.2289, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 3.772602739726028e-05, | |
| "loss": 1.1428, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 3.763470319634703e-05, | |
| "loss": 1.1727, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 3.7543378995433794e-05, | |
| "loss": 1.1311, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 3.745205479452055e-05, | |
| "loss": 1.1217, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 3.736073059360731e-05, | |
| "loss": 1.0888, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 3.7269406392694065e-05, | |
| "loss": 1.1147, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 3.717808219178082e-05, | |
| "loss": 1.0944, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 3.7086757990867586e-05, | |
| "loss": 1.0851, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 3.699543378995434e-05, | |
| "loss": 1.0709, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 3.69041095890411e-05, | |
| "loss": 1.0456, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.0892952680587769, | |
| "eval_runtime": 229.0174, | |
| "eval_samples_per_second": 8.707, | |
| "eval_steps_per_second": 0.873, | |
| "eval_wer": 0.7690858826746059, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 3.681278538812786e-05, | |
| "loss": 1.0713, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 3.6721461187214614e-05, | |
| "loss": 1.0165, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 3.663013698630137e-05, | |
| "loss": 1.0003, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 3.653881278538813e-05, | |
| "loss": 1.0148, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 3.6447488584474885e-05, | |
| "loss": 0.9741, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 3.635616438356165e-05, | |
| "loss": 0.9607, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 3.6264840182648406e-05, | |
| "loss": 0.9792, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 3.617351598173516e-05, | |
| "loss": 0.9451, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 3.608219178082192e-05, | |
| "loss": 0.916, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 3.599086757990868e-05, | |
| "loss": 0.9305, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 3.589954337899544e-05, | |
| "loss": 0.9255, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.580821917808219e-05, | |
| "loss": 0.9385, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.0109813213348389, | |
| "eval_runtime": 228.5891, | |
| "eval_samples_per_second": 8.723, | |
| "eval_steps_per_second": 0.875, | |
| "eval_wer": 0.7097244584864963, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 3.5716894977168955e-05, | |
| "loss": 0.9097, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 3.562557077625571e-05, | |
| "loss": 0.8809, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 3.553424657534247e-05, | |
| "loss": 0.886, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.36, | |
| "learning_rate": 3.5442922374429226e-05, | |
| "loss": 0.8571, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 3.535159817351598e-05, | |
| "loss": 0.8642, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 3.526027397260274e-05, | |
| "loss": 0.875, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 3.5168949771689504e-05, | |
| "loss": 0.8296, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 3.5077625570776254e-05, | |
| "loss": 0.823, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 3.498630136986302e-05, | |
| "loss": 0.8408, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 3.4894977168949775e-05, | |
| "loss": 0.8288, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 3.480365296803653e-05, | |
| "loss": 0.8165, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.9242711067199707, | |
| "eval_runtime": 229.5196, | |
| "eval_samples_per_second": 8.688, | |
| "eval_steps_per_second": 0.871, | |
| "eval_wer": 0.6682261445453717, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 3.471232876712329e-05, | |
| "loss": 0.8096, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 3.4621004566210046e-05, | |
| "loss": 0.7775, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 3.452968036529681e-05, | |
| "loss": 0.7988, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 3.443835616438357e-05, | |
| "loss": 0.7705, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 3.434703196347032e-05, | |
| "loss": 0.7682, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 3.425570776255708e-05, | |
| "loss": 0.7895, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 3.416438356164384e-05, | |
| "loss": 0.7551, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 3.4073059360730595e-05, | |
| "loss": 0.7705, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 3.398173515981735e-05, | |
| "loss": 0.7731, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 3.389041095890411e-05, | |
| "loss": 0.7423, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 3.379908675799087e-05, | |
| "loss": 0.7491, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.8947959542274475, | |
| "eval_runtime": 230.3886, | |
| "eval_samples_per_second": 8.655, | |
| "eval_steps_per_second": 0.868, | |
| "eval_wer": 0.6582920679284261, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 3.370776255707763e-05, | |
| "loss": 0.761, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 3.361643835616439e-05, | |
| "loss": 0.7195, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 3.3525114155251144e-05, | |
| "loss": 0.7192, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 3.34337899543379e-05, | |
| "loss": 0.7107, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 3.3342465753424665e-05, | |
| "loss": 0.697, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 3.3251141552511416e-05, | |
| "loss": 0.7244, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 3.315981735159817e-05, | |
| "loss": 0.6812, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 3.3068493150684936e-05, | |
| "loss": 0.6818, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 3.2977168949771693e-05, | |
| "loss": 0.7117, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 3.288584474885845e-05, | |
| "loss": 0.701, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 3.279452054794521e-05, | |
| "loss": 0.6772, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.7893749475479126, | |
| "eval_runtime": 230.2029, | |
| "eval_samples_per_second": 8.662, | |
| "eval_steps_per_second": 0.869, | |
| "eval_wer": 0.6006926512136586, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 3.2703196347031965e-05, | |
| "loss": 0.7046, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 3.261187214611873e-05, | |
| "loss": 0.6475, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 3.252054794520548e-05, | |
| "loss": 0.6294, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 3.242922374429224e-05, | |
| "loss": 0.6585, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 3.2337899543379e-05, | |
| "loss": 0.6298, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 3.2246575342465757e-05, | |
| "loss": 0.6553, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 3.2155251141552514e-05, | |
| "loss": 0.6374, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 3.206392694063927e-05, | |
| "loss": 0.6361, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 3.197260273972603e-05, | |
| "loss": 0.6861, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 3.188127853881279e-05, | |
| "loss": 0.6188, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 3.178995433789954e-05, | |
| "loss": 0.6096, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.7683572173118591, | |
| "eval_runtime": 229.8867, | |
| "eval_samples_per_second": 8.674, | |
| "eval_steps_per_second": 0.87, | |
| "eval_wer": 0.5663335054834888, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 3.1698630136986306e-05, | |
| "loss": 0.6474, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 9.11, | |
| "learning_rate": 3.160730593607306e-05, | |
| "loss": 0.5958, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 3.151598173515982e-05, | |
| "loss": 0.5893, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 3.142465753424658e-05, | |
| "loss": 0.6225, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 3.1333333333333334e-05, | |
| "loss": 0.5937, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "learning_rate": 3.12420091324201e-05, | |
| "loss": 0.581, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 3.1150684931506855e-05, | |
| "loss": 0.6059, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 3.105936073059361e-05, | |
| "loss": 0.5728, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 3.096803652968037e-05, | |
| "loss": 0.5728, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 3.0876712328767126e-05, | |
| "loss": 0.6019, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 3.078538812785388e-05, | |
| "loss": 0.5575, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.069406392694064e-05, | |
| "loss": 0.5714, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.6978363394737244, | |
| "eval_runtime": 228.8208, | |
| "eval_samples_per_second": 8.714, | |
| "eval_steps_per_second": 0.874, | |
| "eval_wer": 0.4826077710605462, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 10.09, | |
| "learning_rate": 3.06027397260274e-05, | |
| "loss": 0.5365, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 10.18, | |
| "learning_rate": 3.0511415525114157e-05, | |
| "loss": 0.5259, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 10.27, | |
| "learning_rate": 3.0420091324200918e-05, | |
| "loss": 0.5526, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 10.36, | |
| "learning_rate": 3.032876712328767e-05, | |
| "loss": 0.5558, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "learning_rate": 3.0237442922374432e-05, | |
| "loss": 0.5243, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 10.54, | |
| "learning_rate": 3.0146118721461192e-05, | |
| "loss": 0.5452, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 3.005479452054795e-05, | |
| "loss": 0.5273, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 2.9963470319634703e-05, | |
| "loss": 0.5123, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "learning_rate": 2.9872146118721463e-05, | |
| "loss": 0.5523, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 10.89, | |
| "learning_rate": 2.9780821917808224e-05, | |
| "loss": 0.5049, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "learning_rate": 2.968949771689498e-05, | |
| "loss": 0.5213, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.8432782292366028, | |
| "eval_runtime": 229.9511, | |
| "eval_samples_per_second": 8.671, | |
| "eval_steps_per_second": 0.87, | |
| "eval_wer": 0.4927241243126652, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 11.07, | |
| "learning_rate": 2.9598173515981738e-05, | |
| "loss": 0.5322, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 2.9506849315068495e-05, | |
| "loss": 0.4949, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "learning_rate": 2.9415525114155255e-05, | |
| "loss": 0.5076, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 11.34, | |
| "learning_rate": 2.9324200913242012e-05, | |
| "loss": 0.5035, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 2.923287671232877e-05, | |
| "loss": 0.4936, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 2.9141552511415526e-05, | |
| "loss": 0.5135, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 2.9050228310502287e-05, | |
| "loss": 0.4765, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 2.8958904109589044e-05, | |
| "loss": 0.4743, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 11.78, | |
| "learning_rate": 2.88675799086758e-05, | |
| "loss": 0.5072, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "learning_rate": 2.8776255707762558e-05, | |
| "loss": 0.4826, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 11.96, | |
| "learning_rate": 2.868493150684932e-05, | |
| "loss": 0.4624, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.6695169806480408, | |
| "eval_runtime": 229.3877, | |
| "eval_samples_per_second": 8.693, | |
| "eval_steps_per_second": 0.872, | |
| "eval_wer": 0.4469119300057721, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "learning_rate": 2.859360730593608e-05, | |
| "loss": 0.4908, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 2.8502283105022832e-05, | |
| "loss": 0.4444, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 12.23, | |
| "learning_rate": 2.8410958904109593e-05, | |
| "loss": 0.4469, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 2.831963470319635e-05, | |
| "loss": 0.4508, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 12.41, | |
| "learning_rate": 2.822831050228311e-05, | |
| "loss": 0.4419, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 2.8136986301369864e-05, | |
| "loss": 0.4662, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 12.59, | |
| "learning_rate": 2.8045662100456624e-05, | |
| "loss": 0.4345, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 12.68, | |
| "learning_rate": 2.795433789954338e-05, | |
| "loss": 0.4385, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "learning_rate": 2.7863013698630142e-05, | |
| "loss": 0.4686, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 2.7771689497716896e-05, | |
| "loss": 0.4212, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "learning_rate": 2.7680365296803656e-05, | |
| "loss": 0.4298, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.6568945050239563, | |
| "eval_runtime": 227.6777, | |
| "eval_samples_per_second": 8.758, | |
| "eval_steps_per_second": 0.878, | |
| "eval_wer": 0.3867910198377738, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 2.7589041095890413e-05, | |
| "loss": 0.4542, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 2.7497716894977173e-05, | |
| "loss": 0.4113, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 13.21, | |
| "learning_rate": 2.7406392694063927e-05, | |
| "loss": 0.4044, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 13.3, | |
| "learning_rate": 2.7315068493150688e-05, | |
| "loss": 0.4223, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 2.7223744292237445e-05, | |
| "loss": 0.3966, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 13.48, | |
| "learning_rate": 2.7132420091324205e-05, | |
| "loss": 0.4006, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 2.704109589041096e-05, | |
| "loss": 0.4131, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 2.694977168949772e-05, | |
| "loss": 0.4038, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 2.685844748858448e-05, | |
| "loss": 0.4206, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 13.84, | |
| "learning_rate": 2.6767123287671237e-05, | |
| "loss": 0.4033, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 2.6675799086757994e-05, | |
| "loss": 0.3939, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.6632619500160217, | |
| "eval_runtime": 229.2783, | |
| "eval_samples_per_second": 8.697, | |
| "eval_steps_per_second": 0.872, | |
| "eval_wer": 0.36935322173952667, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 2.658447488584475e-05, | |
| "loss": 0.4353, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 14.11, | |
| "learning_rate": 2.649315068493151e-05, | |
| "loss": 0.3605, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 14.2, | |
| "learning_rate": 2.6401826484018268e-05, | |
| "loss": 0.3648, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 2.6310502283105025e-05, | |
| "loss": 0.3958, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 14.37, | |
| "learning_rate": 2.6219178082191782e-05, | |
| "loss": 0.3665, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 14.46, | |
| "learning_rate": 2.6127853881278543e-05, | |
| "loss": 0.3608, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 2.60365296803653e-05, | |
| "loss": 0.3904, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 14.64, | |
| "learning_rate": 2.5945205479452057e-05, | |
| "loss": 0.3659, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 2.5853881278538814e-05, | |
| "loss": 0.3674, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 14.82, | |
| "learning_rate": 2.5762557077625574e-05, | |
| "loss": 0.4027, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 2.5671232876712328e-05, | |
| "loss": 0.3636, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.5579908675799088e-05, | |
| "loss": 0.3803, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.6375618577003479, | |
| "eval_runtime": 229.7813, | |
| "eval_samples_per_second": 8.678, | |
| "eval_steps_per_second": 0.87, | |
| "eval_wer": 0.39198590394021326, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 15.09, | |
| "learning_rate": 2.5488584474885845e-05, | |
| "loss": 0.359, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 15.18, | |
| "learning_rate": 2.5397260273972606e-05, | |
| "loss": 0.3545, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 2.530593607305936e-05, | |
| "loss": 0.3631, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 2.521461187214612e-05, | |
| "loss": 0.3339, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 15.45, | |
| "learning_rate": 2.512328767123288e-05, | |
| "loss": 0.343, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 2.5031963470319637e-05, | |
| "loss": 0.3652, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 15.62, | |
| "learning_rate": 2.494063926940639e-05, | |
| "loss": 0.3397, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 2.484931506849315e-05, | |
| "loss": 0.3195, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "learning_rate": 2.4757990867579912e-05, | |
| "loss": 0.3655, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 15.89, | |
| "learning_rate": 2.466666666666667e-05, | |
| "loss": 0.3402, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 15.98, | |
| "learning_rate": 2.4575342465753426e-05, | |
| "loss": 0.3415, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.6463210582733154, | |
| "eval_runtime": 229.9077, | |
| "eval_samples_per_second": 8.673, | |
| "eval_steps_per_second": 0.87, | |
| "eval_wer": 0.3413737582404229, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 16.07, | |
| "learning_rate": 2.4484018264840183e-05, | |
| "loss": 0.3488, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 2.4392694063926943e-05, | |
| "loss": 0.3255, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "learning_rate": 2.43013698630137e-05, | |
| "loss": 0.3384, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 16.34, | |
| "learning_rate": 2.4210045662100457e-05, | |
| "loss": 0.3056, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 16.43, | |
| "learning_rate": 2.4118721461187214e-05, | |
| "loss": 0.3073, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 16.52, | |
| "learning_rate": 2.4027397260273975e-05, | |
| "loss": 0.3429, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 16.61, | |
| "learning_rate": 2.3936073059360735e-05, | |
| "loss": 0.3106, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 16.7, | |
| "learning_rate": 2.384474885844749e-05, | |
| "loss": 0.3089, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 16.78, | |
| "learning_rate": 2.3753424657534246e-05, | |
| "loss": 0.3406, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 16.87, | |
| "learning_rate": 2.3662100456621006e-05, | |
| "loss": 0.3171, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 2.3570776255707767e-05, | |
| "loss": 0.3239, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.5841062068939209, | |
| "eval_runtime": 230.1162, | |
| "eval_samples_per_second": 8.665, | |
| "eval_steps_per_second": 0.869, | |
| "eval_wer": 0.319713218093994, | |
| "step": 1904 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "learning_rate": 2.347945205479452e-05, | |
| "loss": 0.3472, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 2.338812785388128e-05, | |
| "loss": 0.2911, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 17.23, | |
| "learning_rate": 2.3296803652968038e-05, | |
| "loss": 0.3009, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 17.32, | |
| "learning_rate": 2.32054794520548e-05, | |
| "loss": 0.3148, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 17.41, | |
| "learning_rate": 2.3114155251141552e-05, | |
| "loss": 0.2912, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 2.3022831050228312e-05, | |
| "loss": 0.3179, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 17.59, | |
| "learning_rate": 2.293150684931507e-05, | |
| "loss": 0.2922, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 17.68, | |
| "learning_rate": 2.284018264840183e-05, | |
| "loss": 0.307, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 17.77, | |
| "learning_rate": 2.2748858447488584e-05, | |
| "loss": 0.3153, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 2.2657534246575344e-05, | |
| "loss": 0.3008, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "learning_rate": 2.25662100456621e-05, | |
| "loss": 0.2946, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.5947784781455994, | |
| "eval_runtime": 229.4394, | |
| "eval_samples_per_second": 8.691, | |
| "eval_steps_per_second": 0.872, | |
| "eval_wer": 0.3112373545584349, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 18.04, | |
| "learning_rate": 2.247488584474886e-05, | |
| "loss": 0.3084, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 18.12, | |
| "learning_rate": 2.2383561643835615e-05, | |
| "loss": 0.2772, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 18.21, | |
| "learning_rate": 2.2292237442922376e-05, | |
| "loss": 0.2733, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 18.3, | |
| "learning_rate": 2.2200913242009136e-05, | |
| "loss": 0.2988, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 18.39, | |
| "learning_rate": 2.2109589041095893e-05, | |
| "loss": 0.2659, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 18.48, | |
| "learning_rate": 2.2018264840182647e-05, | |
| "loss": 0.2705, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 18.57, | |
| "learning_rate": 2.1926940639269407e-05, | |
| "loss": 0.2902, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 18.66, | |
| "learning_rate": 2.1835616438356168e-05, | |
| "loss": 0.2777, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 2.1744292237442925e-05, | |
| "loss": 0.3032, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 18.84, | |
| "learning_rate": 2.165296803652968e-05, | |
| "loss": 0.2805, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 18.93, | |
| "learning_rate": 2.156164383561644e-05, | |
| "loss": 0.2751, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.5760026574134827, | |
| "eval_runtime": 229.0041, | |
| "eval_samples_per_second": 8.707, | |
| "eval_steps_per_second": 0.873, | |
| "eval_wer": 0.2905489564662636, | |
| "step": 2128 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 2.14703196347032e-05, | |
| "loss": 0.2978, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 19.11, | |
| "learning_rate": 2.1378995433789956e-05, | |
| "loss": 0.2586, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 2.1287671232876713e-05, | |
| "loss": 0.2573, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "learning_rate": 2.119634703196347e-05, | |
| "loss": 0.279, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 19.37, | |
| "learning_rate": 2.110502283105023e-05, | |
| "loss": 0.2511, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 19.46, | |
| "learning_rate": 2.101369863013699e-05, | |
| "loss": 0.2543, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 19.55, | |
| "learning_rate": 2.0922374429223745e-05, | |
| "loss": 0.2808, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 19.64, | |
| "learning_rate": 2.0831050228310502e-05, | |
| "loss": 0.2555, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 19.73, | |
| "learning_rate": 2.0739726027397262e-05, | |
| "loss": 0.2528, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 19.82, | |
| "learning_rate": 2.0648401826484023e-05, | |
| "loss": 0.2741, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "learning_rate": 2.0557077625570776e-05, | |
| "loss": 0.2473, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.0465753424657537e-05, | |
| "loss": 0.2834, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.5883628726005554, | |
| "eval_runtime": 229.7604, | |
| "eval_samples_per_second": 8.679, | |
| "eval_steps_per_second": 0.87, | |
| "eval_wer": 0.29750584804204516, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 20.09, | |
| "learning_rate": 2.0374429223744294e-05, | |
| "loss": 0.2415, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 20.18, | |
| "learning_rate": 2.0283105022831054e-05, | |
| "loss": 0.2374, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 20.27, | |
| "learning_rate": 2.0191780821917808e-05, | |
| "loss": 0.2678, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 20.36, | |
| "learning_rate": 2.0100456621004568e-05, | |
| "loss": 0.237, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 20.45, | |
| "learning_rate": 2.0009132420091325e-05, | |
| "loss": 0.2392, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 20.54, | |
| "learning_rate": 1.9917808219178082e-05, | |
| "loss": 0.2623, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 20.62, | |
| "learning_rate": 1.9826484018264843e-05, | |
| "loss": 0.2415, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 20.71, | |
| "learning_rate": 1.97351598173516e-05, | |
| "loss": 0.2368, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 1.9643835616438357e-05, | |
| "loss": 0.2648, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 20.89, | |
| "learning_rate": 1.9552511415525114e-05, | |
| "loss": 0.2463, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 20.98, | |
| "learning_rate": 1.9461187214611874e-05, | |
| "loss": 0.2383, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.5989164710044861, | |
| "eval_runtime": 229.5452, | |
| "eval_samples_per_second": 8.687, | |
| "eval_steps_per_second": 0.871, | |
| "eval_wer": 0.2775465564905672, | |
| "step": 2352 | |
| }, | |
| { | |
| "epoch": 21.07, | |
| "learning_rate": 1.936986301369863e-05, | |
| "loss": 0.2505, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 21.16, | |
| "learning_rate": 1.9278538812785392e-05, | |
| "loss": 0.2216, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 21.25, | |
| "learning_rate": 1.9187214611872145e-05, | |
| "loss": 0.2433, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 21.34, | |
| "learning_rate": 1.9095890410958906e-05, | |
| "loss": 0.2283, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 1.9004566210045663e-05, | |
| "loss": 0.2225, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 21.52, | |
| "learning_rate": 1.8913242009132423e-05, | |
| "loss": 0.2397, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 21.61, | |
| "learning_rate": 1.882191780821918e-05, | |
| "loss": 0.2153, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 21.7, | |
| "learning_rate": 1.8730593607305937e-05, | |
| "loss": 0.2309, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 21.78, | |
| "learning_rate": 1.8639269406392694e-05, | |
| "loss": 0.247, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 21.87, | |
| "learning_rate": 1.8547945205479455e-05, | |
| "loss": 0.2313, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 21.96, | |
| "learning_rate": 1.8456621004566212e-05, | |
| "loss": 0.2265, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.6150508522987366, | |
| "eval_runtime": 228.3778, | |
| "eval_samples_per_second": 8.731, | |
| "eval_steps_per_second": 0.876, | |
| "eval_wer": 0.2853236929246286, | |
| "step": 2464 | |
| }, | |
| { | |
| "epoch": 22.05, | |
| "learning_rate": 1.836529680365297e-05, | |
| "loss": 0.242, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 22.14, | |
| "learning_rate": 1.8273972602739726e-05, | |
| "loss": 0.2084, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 22.23, | |
| "learning_rate": 1.8182648401826486e-05, | |
| "loss": 0.224, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 22.32, | |
| "learning_rate": 1.8091324200913243e-05, | |
| "loss": 0.23, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 22.41, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.212, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "learning_rate": 1.7908675799086757e-05, | |
| "loss": 0.2389, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 22.59, | |
| "learning_rate": 1.7817351598173518e-05, | |
| "loss": 0.2076, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 22.68, | |
| "learning_rate": 1.7726027397260275e-05, | |
| "loss": 0.217, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 22.77, | |
| "learning_rate": 1.7634703196347035e-05, | |
| "loss": 0.2347, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 1.7543378995433792e-05, | |
| "loss": 0.2012, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 22.95, | |
| "learning_rate": 1.745205479452055e-05, | |
| "loss": 0.2158, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.5842714905738831, | |
| "eval_runtime": 223.4604, | |
| "eval_samples_per_second": 8.923, | |
| "eval_steps_per_second": 0.895, | |
| "eval_wer": 0.267035270528906, | |
| "step": 2576 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 1.7360730593607307e-05, | |
| "loss": 0.2268, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 23.12, | |
| "learning_rate": 1.7269406392694067e-05, | |
| "loss": 0.2014, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 23.21, | |
| "learning_rate": 1.7178082191780824e-05, | |
| "loss": 0.2006, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 23.3, | |
| "learning_rate": 1.708675799086758e-05, | |
| "loss": 0.2215, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 23.39, | |
| "learning_rate": 1.6995433789954338e-05, | |
| "loss": 0.208, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 23.48, | |
| "learning_rate": 1.69041095890411e-05, | |
| "loss": 0.1958, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 23.57, | |
| "learning_rate": 1.6812785388127856e-05, | |
| "loss": 0.218, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 23.66, | |
| "learning_rate": 1.6721461187214613e-05, | |
| "loss": 0.2024, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 23.75, | |
| "learning_rate": 1.663013698630137e-05, | |
| "loss": 0.2249, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 23.84, | |
| "learning_rate": 1.653881278538813e-05, | |
| "loss": 0.205, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 23.93, | |
| "learning_rate": 1.6447488584474887e-05, | |
| "loss": 0.2015, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.6621034741401672, | |
| "eval_runtime": 224.0191, | |
| "eval_samples_per_second": 8.901, | |
| "eval_steps_per_second": 0.893, | |
| "eval_wer": 0.27380988546951424, | |
| "step": 2688 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 1.6356164383561644e-05, | |
| "loss": 0.2197, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 24.11, | |
| "learning_rate": 1.62648401826484e-05, | |
| "loss": 0.1858, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 24.2, | |
| "learning_rate": 1.617351598173516e-05, | |
| "loss": 0.1936, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 24.29, | |
| "learning_rate": 1.608219178082192e-05, | |
| "loss": 0.2104, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 24.37, | |
| "learning_rate": 1.599086757990868e-05, | |
| "loss": 0.186, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 24.46, | |
| "learning_rate": 1.5899543378995436e-05, | |
| "loss": 0.1929, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 24.55, | |
| "learning_rate": 1.5808219178082193e-05, | |
| "loss": 0.2061, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 1.571689497716895e-05, | |
| "loss": 0.187, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 24.73, | |
| "learning_rate": 1.562557077625571e-05, | |
| "loss": 0.2, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 24.82, | |
| "learning_rate": 1.5534246575342468e-05, | |
| "loss": 0.2065, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "learning_rate": 1.5442922374429225e-05, | |
| "loss": 0.198, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 1.5351598173515982e-05, | |
| "loss": 0.215, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.6068045496940613, | |
| "eval_runtime": 223.6951, | |
| "eval_samples_per_second": 8.914, | |
| "eval_steps_per_second": 0.894, | |
| "eval_wer": 0.2651821247379773, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 25.09, | |
| "learning_rate": 1.5260273972602742e-05, | |
| "loss": 0.1834, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 25.18, | |
| "learning_rate": 1.51689497716895e-05, | |
| "loss": 0.1777, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 25.27, | |
| "learning_rate": 1.5077625570776258e-05, | |
| "loss": 0.1974, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 25.36, | |
| "learning_rate": 1.4986301369863015e-05, | |
| "loss": 0.1763, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 25.45, | |
| "learning_rate": 1.4894977168949774e-05, | |
| "loss": 0.1824, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 25.54, | |
| "learning_rate": 1.480365296803653e-05, | |
| "loss": 0.1997, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 25.62, | |
| "learning_rate": 1.471232876712329e-05, | |
| "loss": 0.1762, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 1.4621004566210046e-05, | |
| "loss": 0.1784, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 25.8, | |
| "learning_rate": 1.4529680365296805e-05, | |
| "loss": 0.2031, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 25.89, | |
| "learning_rate": 1.4438356164383562e-05, | |
| "loss": 0.1765, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 25.98, | |
| "learning_rate": 1.4347031963470321e-05, | |
| "loss": 0.1859, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.6136422157287598, | |
| "eval_runtime": 229.3437, | |
| "eval_samples_per_second": 8.694, | |
| "eval_steps_per_second": 0.872, | |
| "eval_wer": 0.25701005559437373, | |
| "step": 2912 | |
| }, | |
| { | |
| "epoch": 26.07, | |
| "learning_rate": 1.4255707762557078e-05, | |
| "loss": 0.1896, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 26.16, | |
| "learning_rate": 1.4164383561643837e-05, | |
| "loss": 0.1752, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 26.25, | |
| "learning_rate": 1.4073059360730594e-05, | |
| "loss": 0.1969, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 26.34, | |
| "learning_rate": 1.3981735159817354e-05, | |
| "loss": 0.1688, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 26.43, | |
| "learning_rate": 1.389041095890411e-05, | |
| "loss": 0.1741, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 26.52, | |
| "learning_rate": 1.379908675799087e-05, | |
| "loss": 0.1968, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 26.61, | |
| "learning_rate": 1.3707762557077627e-05, | |
| "loss": 0.171, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 26.7, | |
| "learning_rate": 1.3616438356164386e-05, | |
| "loss": 0.1692, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 26.78, | |
| "learning_rate": 1.3525114155251143e-05, | |
| "loss": 0.1875, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 26.87, | |
| "learning_rate": 1.3433789954337902e-05, | |
| "loss": 0.1659, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 26.96, | |
| "learning_rate": 1.3342465753424659e-05, | |
| "loss": 0.1745, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.6190728545188904, | |
| "eval_runtime": 232.5977, | |
| "eval_samples_per_second": 8.573, | |
| "eval_steps_per_second": 0.86, | |
| "eval_wer": 0.2624479752103776, | |
| "step": 3024 | |
| }, | |
| { | |
| "epoch": 27.05, | |
| "learning_rate": 1.3251141552511417e-05, | |
| "loss": 0.1997, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 27.14, | |
| "learning_rate": 1.3159817351598174e-05, | |
| "loss": 0.1618, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 27.23, | |
| "learning_rate": 1.3068493150684933e-05, | |
| "loss": 0.1668, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 27.32, | |
| "learning_rate": 1.297716894977169e-05, | |
| "loss": 0.1811, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 27.41, | |
| "learning_rate": 1.2885844748858449e-05, | |
| "loss": 0.1605, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "learning_rate": 1.2794520547945206e-05, | |
| "loss": 0.192, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 27.59, | |
| "learning_rate": 1.2703196347031965e-05, | |
| "loss": 0.1587, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 27.68, | |
| "learning_rate": 1.2611872146118722e-05, | |
| "loss": 0.1624, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 27.77, | |
| "learning_rate": 1.252054794520548e-05, | |
| "loss": 0.1811, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 27.86, | |
| "learning_rate": 1.2429223744292237e-05, | |
| "loss": 0.1658, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 27.95, | |
| "learning_rate": 1.2337899543378998e-05, | |
| "loss": 0.1611, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.6364021897315979, | |
| "eval_runtime": 229.7698, | |
| "eval_samples_per_second": 8.678, | |
| "eval_steps_per_second": 0.87, | |
| "eval_wer": 0.2577999210134581, | |
| "step": 3136 | |
| }, | |
| { | |
| "epoch": 28.04, | |
| "learning_rate": 1.2246575342465753e-05, | |
| "loss": 0.1764, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 28.12, | |
| "learning_rate": 1.2155251141552514e-05, | |
| "loss": 0.1501, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 28.21, | |
| "learning_rate": 1.206392694063927e-05, | |
| "loss": 0.1543, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 28.3, | |
| "learning_rate": 1.197260273972603e-05, | |
| "loss": 0.179, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 28.39, | |
| "learning_rate": 1.1881278538812786e-05, | |
| "loss": 0.1521, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 1.1789954337899545e-05, | |
| "loss": 0.1686, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 1.1698630136986302e-05, | |
| "loss": 0.1666, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 28.66, | |
| "learning_rate": 1.1607305936073061e-05, | |
| "loss": 0.1565, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 28.75, | |
| "learning_rate": 1.1525114155251143e-05, | |
| "loss": 0.1816, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 28.84, | |
| "learning_rate": 1.1433789954337899e-05, | |
| "loss": 0.1635, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 28.93, | |
| "learning_rate": 1.1342465753424659e-05, | |
| "loss": 0.1513, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.6402228474617004, | |
| "eval_runtime": 228.6093, | |
| "eval_samples_per_second": 8.722, | |
| "eval_steps_per_second": 0.875, | |
| "eval_wer": 0.2535467995260807, | |
| "step": 3248 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 1.1251141552511416e-05, | |
| "loss": 0.1754, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 29.11, | |
| "learning_rate": 1.1159817351598175e-05, | |
| "loss": 0.1455, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 29.2, | |
| "learning_rate": 1.1068493150684932e-05, | |
| "loss": 0.1475, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 29.29, | |
| "learning_rate": 1.097716894977169e-05, | |
| "loss": 0.1684, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 29.37, | |
| "learning_rate": 1.0885844748858448e-05, | |
| "loss": 0.154, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 29.46, | |
| "learning_rate": 1.0794520547945206e-05, | |
| "loss": 0.1479, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 29.55, | |
| "learning_rate": 1.0703196347031963e-05, | |
| "loss": 0.1732, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 29.64, | |
| "learning_rate": 1.0611872146118722e-05, | |
| "loss": 0.1542, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 29.73, | |
| "learning_rate": 1.052054794520548e-05, | |
| "loss": 0.1619, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 29.82, | |
| "learning_rate": 1.0429223744292238e-05, | |
| "loss": 0.1631, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 29.91, | |
| "learning_rate": 1.0337899543378995e-05, | |
| "loss": 0.1495, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 1.0246575342465754e-05, | |
| "loss": 0.172, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.6329947113990784, | |
| "eval_runtime": 230.6517, | |
| "eval_samples_per_second": 8.645, | |
| "eval_steps_per_second": 0.867, | |
| "eval_wer": 0.24996202570100556, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 30.09, | |
| "learning_rate": 1.015525114155251e-05, | |
| "loss": 0.1479, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 30.18, | |
| "learning_rate": 1.006392694063927e-05, | |
| "loss": 0.1449, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 30.27, | |
| "learning_rate": 9.972602739726028e-06, | |
| "loss": 0.1605, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 30.36, | |
| "learning_rate": 9.881278538812787e-06, | |
| "loss": 0.1411, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 30.45, | |
| "learning_rate": 9.789954337899544e-06, | |
| "loss": 0.1386, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 30.54, | |
| "learning_rate": 9.698630136986303e-06, | |
| "loss": 0.1654, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 30.62, | |
| "learning_rate": 9.60730593607306e-06, | |
| "loss": 0.147, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 30.71, | |
| "learning_rate": 9.515981735159819e-06, | |
| "loss": 0.1467, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 30.8, | |
| "learning_rate": 9.424657534246576e-06, | |
| "loss": 0.1677, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 30.89, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 0.1423, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 30.98, | |
| "learning_rate": 9.242009132420093e-06, | |
| "loss": 0.1488, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 0.6274679899215698, | |
| "eval_runtime": 230.128, | |
| "eval_samples_per_second": 8.665, | |
| "eval_steps_per_second": 0.869, | |
| "eval_wer": 0.25211896588388977, | |
| "step": 3472 | |
| }, | |
| { | |
| "epoch": 31.07, | |
| "learning_rate": 9.15068493150685e-06, | |
| "loss": 0.1546, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 31.16, | |
| "learning_rate": 9.059360730593609e-06, | |
| "loss": 0.1408, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 31.25, | |
| "learning_rate": 8.968036529680366e-06, | |
| "loss": 0.1613, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 31.34, | |
| "learning_rate": 8.876712328767125e-06, | |
| "loss": 0.1359, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 8.785388127853882e-06, | |
| "loss": 0.1391, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 31.52, | |
| "learning_rate": 8.69406392694064e-06, | |
| "loss": 0.1547, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 31.61, | |
| "learning_rate": 8.602739726027397e-06, | |
| "loss": 0.1424, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 31.7, | |
| "learning_rate": 8.511415525114156e-06, | |
| "loss": 0.1348, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 31.78, | |
| "learning_rate": 8.420091324200915e-06, | |
| "loss": 0.164, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 31.87, | |
| "learning_rate": 8.328767123287672e-06, | |
| "loss": 0.1371, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 31.96, | |
| "learning_rate": 8.23744292237443e-06, | |
| "loss": 0.1371, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 0.6538846492767334, | |
| "eval_runtime": 231.0287, | |
| "eval_samples_per_second": 8.631, | |
| "eval_steps_per_second": 0.866, | |
| "eval_wer": 0.2539721116748185, | |
| "step": 3584 | |
| }, | |
| { | |
| "epoch": 32.05, | |
| "learning_rate": 8.146118721461188e-06, | |
| "loss": 0.1605, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 32.14, | |
| "learning_rate": 8.054794520547946e-06, | |
| "loss": 0.1316, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 32.23, | |
| "learning_rate": 7.963470319634703e-06, | |
| "loss": 0.1312, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 32.32, | |
| "learning_rate": 7.872146118721462e-06, | |
| "loss": 0.1507, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 32.41, | |
| "learning_rate": 7.78082191780822e-06, | |
| "loss": 0.1275, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "learning_rate": 7.689497716894978e-06, | |
| "loss": 0.1507, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 32.59, | |
| "learning_rate": 7.598173515981736e-06, | |
| "loss": 0.1341, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 32.68, | |
| "learning_rate": 7.506849315068494e-06, | |
| "loss": 0.1369, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 32.77, | |
| "learning_rate": 7.415525114155252e-06, | |
| "loss": 0.1642, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "learning_rate": 7.32420091324201e-06, | |
| "loss": 0.1349, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 32.95, | |
| "learning_rate": 7.232876712328768e-06, | |
| "loss": 0.1356, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 0.654354989528656, | |
| "eval_runtime": 229.8838, | |
| "eval_samples_per_second": 8.674, | |
| "eval_steps_per_second": 0.87, | |
| "eval_wer": 0.24905064252513898, | |
| "step": 3696 | |
| }, | |
| { | |
| "epoch": 33.04, | |
| "learning_rate": 7.141552511415526e-06, | |
| "loss": 0.1524, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 33.12, | |
| "learning_rate": 7.050228310502284e-06, | |
| "loss": 0.1293, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 33.21, | |
| "learning_rate": 6.958904109589042e-06, | |
| "loss": 0.1315, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 33.3, | |
| "learning_rate": 6.8675799086758e-06, | |
| "loss": 0.1529, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 33.39, | |
| "learning_rate": 6.776255707762558e-06, | |
| "loss": 0.1299, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 33.48, | |
| "learning_rate": 6.684931506849316e-06, | |
| "loss": 0.1314, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 33.57, | |
| "learning_rate": 6.593607305936074e-06, | |
| "loss": 0.1362, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 33.66, | |
| "learning_rate": 6.502283105022832e-06, | |
| "loss": 0.133, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 33.75, | |
| "learning_rate": 6.41095890410959e-06, | |
| "loss": 0.1487, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 33.84, | |
| "learning_rate": 6.319634703196348e-06, | |
| "loss": 0.1283, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 33.93, | |
| "learning_rate": 6.228310502283106e-06, | |
| "loss": 0.1319, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 0.6544836163520813, | |
| "eval_runtime": 230.1134, | |
| "eval_samples_per_second": 8.665, | |
| "eval_steps_per_second": 0.869, | |
| "eval_wer": 0.24908102196433454, | |
| "step": 3808 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "learning_rate": 6.136986301369864e-06, | |
| "loss": 0.1506, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 34.11, | |
| "learning_rate": 6.045662100456622e-06, | |
| "loss": 0.1261, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 34.2, | |
| "learning_rate": 5.9543378995433795e-06, | |
| "loss": 0.1238, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "learning_rate": 5.863013698630137e-06, | |
| "loss": 0.1364, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 34.37, | |
| "learning_rate": 5.771689497716896e-06, | |
| "loss": 0.1301, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 34.46, | |
| "learning_rate": 5.680365296803654e-06, | |
| "loss": 0.1263, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 34.55, | |
| "learning_rate": 5.589041095890412e-06, | |
| "loss": 0.1435, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 34.64, | |
| "learning_rate": 5.49771689497717e-06, | |
| "loss": 0.1273, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 34.73, | |
| "learning_rate": 5.406392694063928e-06, | |
| "loss": 0.1332, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 34.82, | |
| "learning_rate": 5.3150684931506856e-06, | |
| "loss": 0.1392, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 34.91, | |
| "learning_rate": 5.2237442922374435e-06, | |
| "loss": 0.1275, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 5.132420091324201e-06, | |
| "loss": 0.1465, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 0.6573231220245361, | |
| "eval_runtime": 229.9173, | |
| "eval_samples_per_second": 8.673, | |
| "eval_steps_per_second": 0.87, | |
| "eval_wer": 0.24950633411307227, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 35.09, | |
| "learning_rate": 5.04109589041096e-06, | |
| "loss": 0.126, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 35.18, | |
| "learning_rate": 4.949771689497717e-06, | |
| "loss": 0.1195, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 35.27, | |
| "learning_rate": 4.858447488584475e-06, | |
| "loss": 0.1362, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 35.36, | |
| "learning_rate": 4.767123287671233e-06, | |
| "loss": 0.1187, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 35.45, | |
| "learning_rate": 4.675799086757991e-06, | |
| "loss": 0.1269, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 35.54, | |
| "learning_rate": 4.5844748858447495e-06, | |
| "loss": 0.1364, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 35.62, | |
| "learning_rate": 4.493150684931507e-06, | |
| "loss": 0.1288, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 35.71, | |
| "learning_rate": 4.401826484018265e-06, | |
| "loss": 0.1255, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 35.8, | |
| "learning_rate": 4.310502283105023e-06, | |
| "loss": 0.1393, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 35.89, | |
| "learning_rate": 4.219178082191781e-06, | |
| "loss": 0.1183, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 35.98, | |
| "learning_rate": 4.127853881278539e-06, | |
| "loss": 0.13, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 0.6593734622001648, | |
| "eval_runtime": 230.854, | |
| "eval_samples_per_second": 8.637, | |
| "eval_steps_per_second": 0.866, | |
| "eval_wer": 0.24935443691709452, | |
| "step": 4032 | |
| }, | |
| { | |
| "epoch": 36.07, | |
| "learning_rate": 4.036529680365297e-06, | |
| "loss": 0.1288, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 36.16, | |
| "learning_rate": 3.945205479452055e-06, | |
| "loss": 0.1167, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 36.25, | |
| "learning_rate": 3.853881278538813e-06, | |
| "loss": 0.142, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 36.34, | |
| "learning_rate": 3.762557077625571e-06, | |
| "loss": 0.1217, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 36.43, | |
| "learning_rate": 3.671232876712329e-06, | |
| "loss": 0.1249, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 36.52, | |
| "learning_rate": 3.579908675799087e-06, | |
| "loss": 0.1303, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 36.61, | |
| "learning_rate": 3.488584474885845e-06, | |
| "loss": 0.119, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 36.7, | |
| "learning_rate": 3.397260273972603e-06, | |
| "loss": 0.1217, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 36.78, | |
| "learning_rate": 3.3059360730593608e-06, | |
| "loss": 0.1417, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 36.87, | |
| "learning_rate": 3.214611872146119e-06, | |
| "loss": 0.1129, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 36.96, | |
| "learning_rate": 3.123287671232877e-06, | |
| "loss": 0.1244, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 0.6650938987731934, | |
| "eval_runtime": 228.9827, | |
| "eval_samples_per_second": 8.708, | |
| "eval_steps_per_second": 0.873, | |
| "eval_wer": 0.24756205000455692, | |
| "step": 4144 | |
| }, | |
| { | |
| "epoch": 37.05, | |
| "learning_rate": 3.031963470319635e-06, | |
| "loss": 0.1373, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 37.14, | |
| "learning_rate": 2.9406392694063927e-06, | |
| "loss": 0.1155, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 37.23, | |
| "learning_rate": 2.849315068493151e-06, | |
| "loss": 0.1261, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 37.32, | |
| "learning_rate": 2.757990867579909e-06, | |
| "loss": 0.1288, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 37.41, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.1194, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 2.5753424657534247e-06, | |
| "loss": 0.1408, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 37.59, | |
| "learning_rate": 2.484018264840183e-06, | |
| "loss": 0.1131, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 37.68, | |
| "learning_rate": 2.392694063926941e-06, | |
| "loss": 0.1151, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 37.77, | |
| "learning_rate": 2.301369863013699e-06, | |
| "loss": 0.1381, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 37.86, | |
| "learning_rate": 2.2100456621004567e-06, | |
| "loss": 0.1177, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 37.95, | |
| "learning_rate": 2.1187214611872146e-06, | |
| "loss": 0.1228, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 0.67536461353302, | |
| "eval_runtime": 229.8367, | |
| "eval_samples_per_second": 8.676, | |
| "eval_steps_per_second": 0.87, | |
| "eval_wer": 0.24965823130905004, | |
| "step": 4256 | |
| }, | |
| { | |
| "epoch": 38.04, | |
| "learning_rate": 2.027397260273973e-06, | |
| "loss": 0.1357, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 38.12, | |
| "learning_rate": 1.9360730593607308e-06, | |
| "loss": 0.1169, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 38.21, | |
| "learning_rate": 1.8447488584474887e-06, | |
| "loss": 0.1139, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 38.3, | |
| "learning_rate": 1.7534246575342468e-06, | |
| "loss": 0.1275, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 38.39, | |
| "learning_rate": 1.6621004566210046e-06, | |
| "loss": 0.11, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 38.48, | |
| "learning_rate": 1.5707762557077627e-06, | |
| "loss": 0.1182, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 38.57, | |
| "learning_rate": 1.4794520547945206e-06, | |
| "loss": 0.1286, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 38.66, | |
| "learning_rate": 1.3881278538812787e-06, | |
| "loss": 0.1161, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 38.75, | |
| "learning_rate": 1.2968036529680366e-06, | |
| "loss": 0.1348, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 38.84, | |
| "learning_rate": 1.2054794520547947e-06, | |
| "loss": 0.1163, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 38.93, | |
| "learning_rate": 1.1141552511415526e-06, | |
| "loss": 0.1181, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 0.6683635115623474, | |
| "eval_runtime": 230.5717, | |
| "eval_samples_per_second": 8.648, | |
| "eval_steps_per_second": 0.867, | |
| "eval_wer": 0.2468025640246681, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 1.0228310502283107e-06, | |
| "loss": 0.1305, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 39.11, | |
| "learning_rate": 9.315068493150686e-07, | |
| "loss": 0.1119, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 39.2, | |
| "learning_rate": 8.401826484018266e-07, | |
| "loss": 0.1073, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 39.29, | |
| "learning_rate": 7.488584474885845e-07, | |
| "loss": 0.132, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 39.37, | |
| "learning_rate": 6.575342465753425e-07, | |
| "loss": 0.1151, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 39.46, | |
| "learning_rate": 5.662100456621006e-07, | |
| "loss": 0.112, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 39.55, | |
| "learning_rate": 4.748858447488585e-07, | |
| "loss": 0.1277, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 39.64, | |
| "learning_rate": 3.835616438356165e-07, | |
| "loss": 0.1098, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 39.73, | |
| "learning_rate": 2.922374429223744e-07, | |
| "loss": 0.1194, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 39.82, | |
| "learning_rate": 2.0091324200913244e-07, | |
| "loss": 0.1326, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 39.91, | |
| "learning_rate": 1.0958904109589042e-07, | |
| "loss": 0.1124, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.82648401826484e-08, | |
| "loss": 0.1338, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 0.6712809205055237, | |
| "eval_runtime": 230.7582, | |
| "eval_samples_per_second": 8.641, | |
| "eval_steps_per_second": 0.867, | |
| "eval_wer": 0.2471367378558192, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "step": 4480, | |
| "total_flos": 2.1744313988908705e+20, | |
| "train_loss": 0.42816097148294957, | |
| "train_runtime": 135691.4721, | |
| "train_samples_per_second": 5.288, | |
| "train_steps_per_second": 0.033 | |
| } | |
| ], | |
| "max_steps": 4480, | |
| "num_train_epochs": 40, | |
| "total_flos": 2.1744313988908705e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |