| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 20.0, |
| "global_step": 5780, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03, |
| "learning_rate": 9e-07, |
| "loss": 9.6898, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 1.9e-06, |
| "loss": 8.7005, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 2.9e-06, |
| "loss": 8.1348, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 3.9e-06, |
| "loss": 7.503, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 4.800000000000001e-06, |
| "loss": 6.9816, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 5.7000000000000005e-06, |
| "loss": 7.4437, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 6.700000000000001e-06, |
| "loss": 5.829, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 7.7e-06, |
| "loss": 4.2092, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 8.7e-06, |
| "loss": 3.4239, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 9.7e-06, |
| "loss": 3.2204, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.35, |
| "eval_loss": 3.1422512531280518, |
| "eval_runtime": 74.1776, |
| "eval_samples_per_second": 22.648, |
| "eval_steps_per_second": 22.648, |
| "eval_wer": 1.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 1.0700000000000001e-05, |
| "loss": 3.1405, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 1.1700000000000001e-05, |
| "loss": 3.065, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 1.27e-05, |
| "loss": 3.0218, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 1.3700000000000001e-05, |
| "loss": 3.0161, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 1.47e-05, |
| "loss": 3.0393, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 1.5700000000000002e-05, |
| "loss": 3.0284, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 1.6700000000000003e-05, |
| "loss": 2.9855, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 1.77e-05, |
| "loss": 2.9789, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 1.87e-05, |
| "loss": 2.9672, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 1.97e-05, |
| "loss": 2.9838, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.69, |
| "eval_loss": 2.9912664890289307, |
| "eval_runtime": 64.9215, |
| "eval_samples_per_second": 25.877, |
| "eval_steps_per_second": 25.877, |
| "eval_wer": 1.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 2.07e-05, |
| "loss": 2.9827, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 2.1700000000000002e-05, |
| "loss": 2.9376, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 2.2700000000000003e-05, |
| "loss": 2.9409, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 2.37e-05, |
| "loss": 2.9335, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 2.47e-05, |
| "loss": 2.9425, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 2.57e-05, |
| "loss": 2.9307, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 2.6700000000000002e-05, |
| "loss": 2.9107, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 2.7700000000000002e-05, |
| "loss": 2.9082, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 2.87e-05, |
| "loss": 2.9238, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 2.97e-05, |
| "loss": 2.9174, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.04, |
| "eval_loss": 2.894228458404541, |
| "eval_runtime": 65.0733, |
| "eval_samples_per_second": 25.817, |
| "eval_steps_per_second": 25.817, |
| "eval_wer": 1.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 3.07e-05, |
| "loss": 2.8846, |
| "step": 310 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 3.1700000000000005e-05, |
| "loss": 2.8641, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 3.27e-05, |
| "loss": 2.8533, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 3.3700000000000006e-05, |
| "loss": 2.8394, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 3.4699999999999996e-05, |
| "loss": 2.7793, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 3.57e-05, |
| "loss": 2.6871, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 3.6700000000000004e-05, |
| "loss": 2.5847, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.31, |
| "learning_rate": 3.77e-05, |
| "loss": 2.5019, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 3.8700000000000006e-05, |
| "loss": 2.4443, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 3.97e-05, |
| "loss": 2.2874, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.38, |
| "eval_loss": 2.161102533340454, |
| "eval_runtime": 66.0365, |
| "eval_samples_per_second": 25.44, |
| "eval_steps_per_second": 25.44, |
| "eval_wer": 1.0024119633381572, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 4.07e-05, |
| "loss": 2.0534, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 4.17e-05, |
| "loss": 1.8957, |
| "step": 420 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 4.27e-05, |
| "loss": 1.7273, |
| "step": 430 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 4.3700000000000005e-05, |
| "loss": 1.7921, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 4.47e-05, |
| "loss": 1.5819, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 4.5700000000000006e-05, |
| "loss": 1.3805, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 4.6700000000000003e-05, |
| "loss": 1.2704, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 4.77e-05, |
| "loss": 1.1785, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.7, |
| "learning_rate": 4.87e-05, |
| "loss": 1.3153, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.73, |
| "learning_rate": 4.97e-05, |
| "loss": 1.1147, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.73, |
| "eval_loss": 0.9719416499137878, |
| "eval_runtime": 70.6755, |
| "eval_samples_per_second": 23.771, |
| "eval_steps_per_second": 23.771, |
| "eval_wer": 0.6610157811315553, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 5.0700000000000006e-05, |
| "loss": 0.9066, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.8, |
| "learning_rate": 5.17e-05, |
| "loss": 0.8973, |
| "step": 520 |
| }, |
| { |
| "epoch": 1.83, |
| "learning_rate": 5.270000000000001e-05, |
| "loss": 0.8844, |
| "step": 530 |
| }, |
| { |
| "epoch": 1.87, |
| "learning_rate": 5.3700000000000004e-05, |
| "loss": 1.0412, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.9, |
| "learning_rate": 5.470000000000001e-05, |
| "loss": 0.7701, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.94, |
| "learning_rate": 5.5700000000000005e-05, |
| "loss": 0.6957, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.97, |
| "learning_rate": 5.6699999999999996e-05, |
| "loss": 0.7715, |
| "step": 570 |
| }, |
| { |
| "epoch": 2.01, |
| "learning_rate": 5.77e-05, |
| "loss": 0.9327, |
| "step": 580 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 5.87e-05, |
| "loss": 0.7129, |
| "step": 590 |
| }, |
| { |
| "epoch": 2.08, |
| "learning_rate": 5.97e-05, |
| "loss": 0.5558, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.08, |
| "eval_loss": 0.6217639446258545, |
| "eval_runtime": 67.0042, |
| "eval_samples_per_second": 25.073, |
| "eval_steps_per_second": 25.073, |
| "eval_wer": 0.4536558472882641, |
| "step": 600 |
| }, |
| { |
| "epoch": 2.11, |
| "learning_rate": 6.07e-05, |
| "loss": 0.5767, |
| "step": 610 |
| }, |
| { |
| "epoch": 2.15, |
| "learning_rate": 6.170000000000001e-05, |
| "loss": 0.6019, |
| "step": 620 |
| }, |
| { |
| "epoch": 2.18, |
| "learning_rate": 6.27e-05, |
| "loss": 0.7651, |
| "step": 630 |
| }, |
| { |
| "epoch": 2.21, |
| "learning_rate": 6.37e-05, |
| "loss": 0.5958, |
| "step": 640 |
| }, |
| { |
| "epoch": 2.25, |
| "learning_rate": 6.47e-05, |
| "loss": 0.4904, |
| "step": 650 |
| }, |
| { |
| "epoch": 2.28, |
| "learning_rate": 6.570000000000001e-05, |
| "loss": 0.536, |
| "step": 660 |
| }, |
| { |
| "epoch": 2.32, |
| "learning_rate": 6.670000000000001e-05, |
| "loss": 0.5517, |
| "step": 670 |
| }, |
| { |
| "epoch": 2.35, |
| "learning_rate": 6.77e-05, |
| "loss": 0.7055, |
| "step": 680 |
| }, |
| { |
| "epoch": 2.39, |
| "learning_rate": 6.87e-05, |
| "loss": 0.523, |
| "step": 690 |
| }, |
| { |
| "epoch": 2.42, |
| "learning_rate": 6.97e-05, |
| "loss": 0.4296, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.42, |
| "eval_loss": 0.5137567520141602, |
| "eval_runtime": 66.1171, |
| "eval_samples_per_second": 25.409, |
| "eval_steps_per_second": 25.409, |
| "eval_wer": 0.39494176831369304, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.46, |
| "learning_rate": 7.07e-05, |
| "loss": 0.4845, |
| "step": 710 |
| }, |
| { |
| "epoch": 2.49, |
| "learning_rate": 7.17e-05, |
| "loss": 0.451, |
| "step": 720 |
| }, |
| { |
| "epoch": 2.53, |
| "learning_rate": 7.27e-05, |
| "loss": 0.6705, |
| "step": 730 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 7.37e-05, |
| "loss": 0.4813, |
| "step": 740 |
| }, |
| { |
| "epoch": 2.6, |
| "learning_rate": 7.47e-05, |
| "loss": 0.3811, |
| "step": 750 |
| }, |
| { |
| "epoch": 2.63, |
| "learning_rate": 7.570000000000001e-05, |
| "loss": 0.4096, |
| "step": 760 |
| }, |
| { |
| "epoch": 2.66, |
| "learning_rate": 7.670000000000001e-05, |
| "loss": 0.4373, |
| "step": 770 |
| }, |
| { |
| "epoch": 2.7, |
| "learning_rate": 7.77e-05, |
| "loss": 0.632, |
| "step": 780 |
| }, |
| { |
| "epoch": 2.73, |
| "learning_rate": 7.87e-05, |
| "loss": 0.4003, |
| "step": 790 |
| }, |
| { |
| "epoch": 2.77, |
| "learning_rate": 7.970000000000001e-05, |
| "loss": 0.3731, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.77, |
| "eval_loss": 0.44735369086265564, |
| "eval_runtime": 72.8423, |
| "eval_samples_per_second": 23.064, |
| "eval_steps_per_second": 23.064, |
| "eval_wer": 0.3651023361587761, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.8, |
| "learning_rate": 8.070000000000001e-05, |
| "loss": 0.376, |
| "step": 810 |
| }, |
| { |
| "epoch": 2.84, |
| "learning_rate": 8.17e-05, |
| "loss": 0.4297, |
| "step": 820 |
| }, |
| { |
| "epoch": 2.87, |
| "learning_rate": 8.27e-05, |
| "loss": 0.6339, |
| "step": 830 |
| }, |
| { |
| "epoch": 2.91, |
| "learning_rate": 8.37e-05, |
| "loss": 0.3925, |
| "step": 840 |
| }, |
| { |
| "epoch": 2.94, |
| "learning_rate": 8.47e-05, |
| "loss": 0.343, |
| "step": 850 |
| }, |
| { |
| "epoch": 2.98, |
| "learning_rate": 8.57e-05, |
| "loss": 0.3758, |
| "step": 860 |
| }, |
| { |
| "epoch": 3.01, |
| "learning_rate": 8.67e-05, |
| "loss": 0.5663, |
| "step": 870 |
| }, |
| { |
| "epoch": 3.04, |
| "learning_rate": 8.77e-05, |
| "loss": 0.336, |
| "step": 880 |
| }, |
| { |
| "epoch": 3.08, |
| "learning_rate": 8.87e-05, |
| "loss": 0.2493, |
| "step": 890 |
| }, |
| { |
| "epoch": 3.11, |
| "learning_rate": 8.970000000000001e-05, |
| "loss": 0.315, |
| "step": 900 |
| }, |
| { |
| "epoch": 3.11, |
| "eval_loss": 0.4411050081253052, |
| "eval_runtime": 65.1323, |
| "eval_samples_per_second": 25.794, |
| "eval_steps_per_second": 25.794, |
| "eval_wer": 0.3699262628350906, |
| "step": 900 |
| }, |
| { |
| "epoch": 3.15, |
| "learning_rate": 9.070000000000001e-05, |
| "loss": 0.3042, |
| "step": 910 |
| }, |
| { |
| "epoch": 3.18, |
| "learning_rate": 9.17e-05, |
| "loss": 0.5012, |
| "step": 920 |
| }, |
| { |
| "epoch": 3.22, |
| "learning_rate": 9.27e-05, |
| "loss": 0.2991, |
| "step": 930 |
| }, |
| { |
| "epoch": 3.25, |
| "learning_rate": 9.370000000000001e-05, |
| "loss": 0.2894, |
| "step": 940 |
| }, |
| { |
| "epoch": 3.29, |
| "learning_rate": 9.47e-05, |
| "loss": 0.275, |
| "step": 950 |
| }, |
| { |
| "epoch": 3.32, |
| "learning_rate": 9.57e-05, |
| "loss": 0.3144, |
| "step": 960 |
| }, |
| { |
| "epoch": 3.36, |
| "learning_rate": 9.67e-05, |
| "loss": 0.4902, |
| "step": 970 |
| }, |
| { |
| "epoch": 3.39, |
| "learning_rate": 9.77e-05, |
| "loss": 0.2963, |
| "step": 980 |
| }, |
| { |
| "epoch": 3.43, |
| "learning_rate": 9.87e-05, |
| "loss": 0.2377, |
| "step": 990 |
| }, |
| { |
| "epoch": 3.46, |
| "learning_rate": 9.970000000000001e-05, |
| "loss": 0.2807, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.46, |
| "eval_loss": 0.41331055760383606, |
| "eval_runtime": 65.0064, |
| "eval_samples_per_second": 25.844, |
| "eval_steps_per_second": 25.844, |
| "eval_wer": 0.3384329129625801, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.49, |
| "learning_rate": 9.985355648535565e-05, |
| "loss": 0.3418, |
| "step": 1010 |
| }, |
| { |
| "epoch": 3.53, |
| "learning_rate": 9.964435146443515e-05, |
| "loss": 0.4522, |
| "step": 1020 |
| }, |
| { |
| "epoch": 3.56, |
| "learning_rate": 9.943514644351465e-05, |
| "loss": 0.2756, |
| "step": 1030 |
| }, |
| { |
| "epoch": 3.6, |
| "learning_rate": 9.922594142259415e-05, |
| "loss": 0.2062, |
| "step": 1040 |
| }, |
| { |
| "epoch": 3.63, |
| "learning_rate": 9.901673640167365e-05, |
| "loss": 0.2487, |
| "step": 1050 |
| }, |
| { |
| "epoch": 3.67, |
| "learning_rate": 9.880753138075314e-05, |
| "loss": 0.3234, |
| "step": 1060 |
| }, |
| { |
| "epoch": 3.7, |
| "learning_rate": 9.859832635983264e-05, |
| "loss": 0.5156, |
| "step": 1070 |
| }, |
| { |
| "epoch": 3.74, |
| "learning_rate": 9.838912133891214e-05, |
| "loss": 0.2493, |
| "step": 1080 |
| }, |
| { |
| "epoch": 3.77, |
| "learning_rate": 9.817991631799164e-05, |
| "loss": 0.2426, |
| "step": 1090 |
| }, |
| { |
| "epoch": 3.81, |
| "learning_rate": 9.797071129707114e-05, |
| "loss": 0.2736, |
| "step": 1100 |
| }, |
| { |
| "epoch": 3.81, |
| "eval_loss": 0.384372740983963, |
| "eval_runtime": 65.6187, |
| "eval_samples_per_second": 25.602, |
| "eval_steps_per_second": 25.602, |
| "eval_wer": 0.3123147956722486, |
| "step": 1100 |
| }, |
| { |
| "epoch": 3.84, |
| "learning_rate": 9.776150627615063e-05, |
| "loss": 0.2916, |
| "step": 1110 |
| }, |
| { |
| "epoch": 3.88, |
| "learning_rate": 9.755230125523013e-05, |
| "loss": 0.4548, |
| "step": 1120 |
| }, |
| { |
| "epoch": 3.91, |
| "learning_rate": 9.734309623430963e-05, |
| "loss": 0.2592, |
| "step": 1130 |
| }, |
| { |
| "epoch": 3.94, |
| "learning_rate": 9.713389121338913e-05, |
| "loss": 0.2199, |
| "step": 1140 |
| }, |
| { |
| "epoch": 3.98, |
| "learning_rate": 9.692468619246863e-05, |
| "loss": 0.2869, |
| "step": 1150 |
| }, |
| { |
| "epoch": 4.01, |
| "learning_rate": 9.671548117154812e-05, |
| "loss": 0.3809, |
| "step": 1160 |
| }, |
| { |
| "epoch": 4.05, |
| "learning_rate": 9.650627615062762e-05, |
| "loss": 0.2025, |
| "step": 1170 |
| }, |
| { |
| "epoch": 4.08, |
| "learning_rate": 9.629707112970712e-05, |
| "loss": 0.1505, |
| "step": 1180 |
| }, |
| { |
| "epoch": 4.12, |
| "learning_rate": 9.608786610878662e-05, |
| "loss": 0.1943, |
| "step": 1190 |
| }, |
| { |
| "epoch": 4.15, |
| "learning_rate": 9.587866108786612e-05, |
| "loss": 0.2611, |
| "step": 1200 |
| }, |
| { |
| "epoch": 4.15, |
| "eval_loss": 0.37706834077835083, |
| "eval_runtime": 66.8783, |
| "eval_samples_per_second": 25.12, |
| "eval_steps_per_second": 25.12, |
| "eval_wer": 0.31693198263386396, |
| "step": 1200 |
| }, |
| { |
| "epoch": 4.19, |
| "learning_rate": 9.566945606694561e-05, |
| "loss": 0.3321, |
| "step": 1210 |
| }, |
| { |
| "epoch": 4.22, |
| "learning_rate": 9.546025104602511e-05, |
| "loss": 0.1967, |
| "step": 1220 |
| }, |
| { |
| "epoch": 4.26, |
| "learning_rate": 9.525104602510461e-05, |
| "loss": 0.1723, |
| "step": 1230 |
| }, |
| { |
| "epoch": 4.29, |
| "learning_rate": 9.504184100418411e-05, |
| "loss": 0.2088, |
| "step": 1240 |
| }, |
| { |
| "epoch": 4.33, |
| "learning_rate": 9.48326359832636e-05, |
| "loss": 0.2471, |
| "step": 1250 |
| }, |
| { |
| "epoch": 4.36, |
| "learning_rate": 9.46234309623431e-05, |
| "loss": 0.352, |
| "step": 1260 |
| }, |
| { |
| "epoch": 4.39, |
| "learning_rate": 9.44142259414226e-05, |
| "loss": 0.1973, |
| "step": 1270 |
| }, |
| { |
| "epoch": 4.43, |
| "learning_rate": 9.420502092050209e-05, |
| "loss": 0.1602, |
| "step": 1280 |
| }, |
| { |
| "epoch": 4.46, |
| "learning_rate": 9.399581589958159e-05, |
| "loss": 0.2183, |
| "step": 1290 |
| }, |
| { |
| "epoch": 4.5, |
| "learning_rate": 9.378661087866109e-05, |
| "loss": 0.2243, |
| "step": 1300 |
| }, |
| { |
| "epoch": 4.5, |
| "eval_loss": 0.3722507357597351, |
| "eval_runtime": 66.8482, |
| "eval_samples_per_second": 25.132, |
| "eval_steps_per_second": 25.132, |
| "eval_wer": 0.3054234718489422, |
| "step": 1300 |
| }, |
| { |
| "epoch": 4.53, |
| "learning_rate": 9.357740585774059e-05, |
| "loss": 0.3443, |
| "step": 1310 |
| }, |
| { |
| "epoch": 4.57, |
| "learning_rate": 9.336820083682008e-05, |
| "loss": 0.1783, |
| "step": 1320 |
| }, |
| { |
| "epoch": 4.6, |
| "learning_rate": 9.315899581589958e-05, |
| "loss": 0.156, |
| "step": 1330 |
| }, |
| { |
| "epoch": 4.64, |
| "learning_rate": 9.294979079497908e-05, |
| "loss": 0.2025, |
| "step": 1340 |
| }, |
| { |
| "epoch": 4.67, |
| "learning_rate": 9.274058577405858e-05, |
| "loss": 0.2229, |
| "step": 1350 |
| }, |
| { |
| "epoch": 4.71, |
| "learning_rate": 9.253138075313807e-05, |
| "loss": 0.342, |
| "step": 1360 |
| }, |
| { |
| "epoch": 4.74, |
| "learning_rate": 9.232217573221757e-05, |
| "loss": 0.1755, |
| "step": 1370 |
| }, |
| { |
| "epoch": 4.78, |
| "learning_rate": 9.211297071129707e-05, |
| "loss": 0.1554, |
| "step": 1380 |
| }, |
| { |
| "epoch": 4.81, |
| "learning_rate": 9.190376569037657e-05, |
| "loss": 0.1619, |
| "step": 1390 |
| }, |
| { |
| "epoch": 4.84, |
| "learning_rate": 9.169456066945607e-05, |
| "loss": 0.194, |
| "step": 1400 |
| }, |
| { |
| "epoch": 4.84, |
| "eval_loss": 0.39714711904525757, |
| "eval_runtime": 75.0486, |
| "eval_samples_per_second": 22.385, |
| "eval_steps_per_second": 22.385, |
| "eval_wer": 0.3107297911928881, |
| "step": 1400 |
| }, |
| { |
| "epoch": 4.88, |
| "learning_rate": 9.148535564853556e-05, |
| "loss": 0.2953, |
| "step": 1410 |
| }, |
| { |
| "epoch": 4.91, |
| "learning_rate": 9.127615062761506e-05, |
| "loss": 0.1804, |
| "step": 1420 |
| }, |
| { |
| "epoch": 4.95, |
| "learning_rate": 9.106694560669456e-05, |
| "loss": 0.1564, |
| "step": 1430 |
| }, |
| { |
| "epoch": 4.98, |
| "learning_rate": 9.085774058577406e-05, |
| "loss": 0.2197, |
| "step": 1440 |
| }, |
| { |
| "epoch": 5.02, |
| "learning_rate": 9.064853556485356e-05, |
| "loss": 0.2718, |
| "step": 1450 |
| }, |
| { |
| "epoch": 5.05, |
| "learning_rate": 9.043933054393305e-05, |
| "loss": 0.1304, |
| "step": 1460 |
| }, |
| { |
| "epoch": 5.09, |
| "learning_rate": 9.023012552301255e-05, |
| "loss": 0.1218, |
| "step": 1470 |
| }, |
| { |
| "epoch": 5.12, |
| "learning_rate": 9.002092050209205e-05, |
| "loss": 0.181, |
| "step": 1480 |
| }, |
| { |
| "epoch": 5.16, |
| "learning_rate": 8.981171548117155e-05, |
| "loss": 0.2238, |
| "step": 1490 |
| }, |
| { |
| "epoch": 5.19, |
| "learning_rate": 8.960251046025105e-05, |
| "loss": 0.2497, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.19, |
| "eval_loss": 0.33955928683280945, |
| "eval_runtime": 75.1473, |
| "eval_samples_per_second": 22.356, |
| "eval_steps_per_second": 22.356, |
| "eval_wer": 0.2754462132175591, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.22, |
| "learning_rate": 8.939330543933054e-05, |
| "loss": 0.1349, |
| "step": 1510 |
| }, |
| { |
| "epoch": 5.26, |
| "learning_rate": 8.918410041841004e-05, |
| "loss": 0.1052, |
| "step": 1520 |
| }, |
| { |
| "epoch": 5.29, |
| "learning_rate": 8.897489539748954e-05, |
| "loss": 0.1277, |
| "step": 1530 |
| }, |
| { |
| "epoch": 5.33, |
| "learning_rate": 8.876569037656904e-05, |
| "loss": 0.1745, |
| "step": 1540 |
| }, |
| { |
| "epoch": 5.36, |
| "learning_rate": 8.855648535564855e-05, |
| "loss": 0.2678, |
| "step": 1550 |
| }, |
| { |
| "epoch": 5.4, |
| "learning_rate": 8.834728033472803e-05, |
| "loss": 0.1472, |
| "step": 1560 |
| }, |
| { |
| "epoch": 5.43, |
| "learning_rate": 8.813807531380753e-05, |
| "loss": 0.1037, |
| "step": 1570 |
| }, |
| { |
| "epoch": 5.47, |
| "learning_rate": 8.792887029288703e-05, |
| "loss": 0.1879, |
| "step": 1580 |
| }, |
| { |
| "epoch": 5.5, |
| "learning_rate": 8.771966527196654e-05, |
| "loss": 0.2289, |
| "step": 1590 |
| }, |
| { |
| "epoch": 5.54, |
| "learning_rate": 8.751046025104604e-05, |
| "loss": 0.2441, |
| "step": 1600 |
| }, |
| { |
| "epoch": 5.54, |
| "eval_loss": 0.3601236641407013, |
| "eval_runtime": 67.0675, |
| "eval_samples_per_second": 25.049, |
| "eval_steps_per_second": 25.049, |
| "eval_wer": 0.28585211219075185, |
| "step": 1600 |
| }, |
| { |
| "epoch": 5.57, |
| "learning_rate": 8.730125523012552e-05, |
| "loss": 0.1396, |
| "step": 1610 |
| }, |
| { |
| "epoch": 5.61, |
| "learning_rate": 8.709205020920502e-05, |
| "loss": 0.1012, |
| "step": 1620 |
| }, |
| { |
| "epoch": 5.64, |
| "learning_rate": 8.688284518828453e-05, |
| "loss": 0.1203, |
| "step": 1630 |
| }, |
| { |
| "epoch": 5.67, |
| "learning_rate": 8.667364016736403e-05, |
| "loss": 0.1718, |
| "step": 1640 |
| }, |
| { |
| "epoch": 5.71, |
| "learning_rate": 8.646443514644353e-05, |
| "loss": 0.2381, |
| "step": 1650 |
| }, |
| { |
| "epoch": 5.74, |
| "learning_rate": 8.625523012552301e-05, |
| "loss": 0.1461, |
| "step": 1660 |
| }, |
| { |
| "epoch": 5.78, |
| "learning_rate": 8.604602510460252e-05, |
| "loss": 0.0916, |
| "step": 1670 |
| }, |
| { |
| "epoch": 5.81, |
| "learning_rate": 8.583682008368202e-05, |
| "loss": 0.1538, |
| "step": 1680 |
| }, |
| { |
| "epoch": 5.85, |
| "learning_rate": 8.562761506276152e-05, |
| "loss": 0.1692, |
| "step": 1690 |
| }, |
| { |
| "epoch": 5.88, |
| "learning_rate": 8.541841004184102e-05, |
| "loss": 0.2747, |
| "step": 1700 |
| }, |
| { |
| "epoch": 5.88, |
| "eval_loss": 0.3375290334224701, |
| "eval_runtime": 69.9725, |
| "eval_samples_per_second": 24.009, |
| "eval_steps_per_second": 24.009, |
| "eval_wer": 0.2808214457997381, |
| "step": 1700 |
| }, |
| { |
| "epoch": 5.92, |
| "learning_rate": 8.52092050209205e-05, |
| "loss": 0.1051, |
| "step": 1710 |
| }, |
| { |
| "epoch": 5.95, |
| "learning_rate": 8.5e-05, |
| "loss": 0.1314, |
| "step": 1720 |
| }, |
| { |
| "epoch": 5.99, |
| "learning_rate": 8.479079497907951e-05, |
| "loss": 0.1604, |
| "step": 1730 |
| }, |
| { |
| "epoch": 6.02, |
| "learning_rate": 8.458158995815901e-05, |
| "loss": 0.1953, |
| "step": 1740 |
| }, |
| { |
| "epoch": 6.06, |
| "learning_rate": 8.437238493723851e-05, |
| "loss": 0.0811, |
| "step": 1750 |
| }, |
| { |
| "epoch": 6.09, |
| "learning_rate": 8.4163179916318e-05, |
| "loss": 0.09, |
| "step": 1760 |
| }, |
| { |
| "epoch": 6.12, |
| "learning_rate": 8.39539748953975e-05, |
| "loss": 0.1246, |
| "step": 1770 |
| }, |
| { |
| "epoch": 6.16, |
| "learning_rate": 8.3744769874477e-05, |
| "loss": 0.129, |
| "step": 1780 |
| }, |
| { |
| "epoch": 6.19, |
| "learning_rate": 8.353556485355649e-05, |
| "loss": 0.2322, |
| "step": 1790 |
| }, |
| { |
| "epoch": 6.23, |
| "learning_rate": 8.332635983263599e-05, |
| "loss": 0.1065, |
| "step": 1800 |
| }, |
| { |
| "epoch": 6.23, |
| "eval_loss": 0.35706642270088196, |
| "eval_runtime": 68.155, |
| "eval_samples_per_second": 24.65, |
| "eval_steps_per_second": 24.65, |
| "eval_wer": 0.2649024877679002, |
| "step": 1800 |
| }, |
| { |
| "epoch": 6.26, |
| "learning_rate": 8.311715481171549e-05, |
| "loss": 0.1014, |
| "step": 1810 |
| }, |
| { |
| "epoch": 6.3, |
| "learning_rate": 8.290794979079497e-05, |
| "loss": 0.1544, |
| "step": 1820 |
| }, |
| { |
| "epoch": 6.33, |
| "learning_rate": 8.269874476987448e-05, |
| "loss": 0.1732, |
| "step": 1830 |
| }, |
| { |
| "epoch": 6.37, |
| "learning_rate": 8.248953974895398e-05, |
| "loss": 0.1987, |
| "step": 1840 |
| }, |
| { |
| "epoch": 6.4, |
| "learning_rate": 8.228033472803348e-05, |
| "loss": 0.1157, |
| "step": 1850 |
| }, |
| { |
| "epoch": 6.44, |
| "learning_rate": 8.207112970711296e-05, |
| "loss": 0.1353, |
| "step": 1860 |
| }, |
| { |
| "epoch": 6.47, |
| "learning_rate": 8.186192468619247e-05, |
| "loss": 0.0841, |
| "step": 1870 |
| }, |
| { |
| "epoch": 6.51, |
| "learning_rate": 8.165271966527197e-05, |
| "loss": 0.177, |
| "step": 1880 |
| }, |
| { |
| "epoch": 6.54, |
| "learning_rate": 8.144351464435147e-05, |
| "loss": 0.2255, |
| "step": 1890 |
| }, |
| { |
| "epoch": 6.57, |
| "learning_rate": 8.123430962343097e-05, |
| "loss": 0.0851, |
| "step": 1900 |
| }, |
| { |
| "epoch": 6.57, |
| "eval_loss": 0.3489117920398712, |
| "eval_runtime": 67.4488, |
| "eval_samples_per_second": 24.908, |
| "eval_steps_per_second": 24.908, |
| "eval_wer": 0.2619392185238784, |
| "step": 1900 |
| }, |
| { |
| "epoch": 6.61, |
| "learning_rate": 8.102510460251045e-05, |
| "loss": 0.1009, |
| "step": 1910 |
| }, |
| { |
| "epoch": 6.64, |
| "learning_rate": 8.081589958158996e-05, |
| "loss": 0.1196, |
| "step": 1920 |
| }, |
| { |
| "epoch": 6.68, |
| "learning_rate": 8.060669456066946e-05, |
| "loss": 0.1606, |
| "step": 1930 |
| }, |
| { |
| "epoch": 6.71, |
| "learning_rate": 8.039748953974896e-05, |
| "loss": 0.1851, |
| "step": 1940 |
| }, |
| { |
| "epoch": 6.75, |
| "learning_rate": 8.018828451882846e-05, |
| "loss": 0.1129, |
| "step": 1950 |
| }, |
| { |
| "epoch": 6.78, |
| "learning_rate": 7.997907949790795e-05, |
| "loss": 0.0774, |
| "step": 1960 |
| }, |
| { |
| "epoch": 6.82, |
| "learning_rate": 7.976987447698745e-05, |
| "loss": 0.1054, |
| "step": 1970 |
| }, |
| { |
| "epoch": 6.85, |
| "learning_rate": 7.956066945606695e-05, |
| "loss": 0.1346, |
| "step": 1980 |
| }, |
| { |
| "epoch": 6.89, |
| "learning_rate": 7.935146443514645e-05, |
| "loss": 0.1781, |
| "step": 1990 |
| }, |
| { |
| "epoch": 6.92, |
| "learning_rate": 7.914225941422595e-05, |
| "loss": 0.1059, |
| "step": 2000 |
| }, |
| { |
| "epoch": 6.92, |
| "eval_loss": 0.35294660925865173, |
| "eval_runtime": 76.3386, |
| "eval_samples_per_second": 22.007, |
| "eval_steps_per_second": 22.007, |
| "eval_wer": 0.25435876231824134, |
| "step": 2000 |
| }, |
| { |
| "epoch": 6.96, |
| "learning_rate": 7.893305439330544e-05, |
| "loss": 0.089, |
| "step": 2010 |
| }, |
| { |
| "epoch": 6.99, |
| "learning_rate": 7.872384937238494e-05, |
| "loss": 0.1192, |
| "step": 2020 |
| }, |
| { |
| "epoch": 7.02, |
| "learning_rate": 7.851464435146444e-05, |
| "loss": 0.1731, |
| "step": 2030 |
| }, |
| { |
| "epoch": 7.06, |
| "learning_rate": 7.830543933054394e-05, |
| "loss": 0.0873, |
| "step": 2040 |
| }, |
| { |
| "epoch": 7.09, |
| "learning_rate": 7.809623430962344e-05, |
| "loss": 0.0716, |
| "step": 2050 |
| }, |
| { |
| "epoch": 7.13, |
| "learning_rate": 7.788702928870293e-05, |
| "loss": 0.0862, |
| "step": 2060 |
| }, |
| { |
| "epoch": 7.16, |
| "learning_rate": 7.767782426778243e-05, |
| "loss": 0.1388, |
| "step": 2070 |
| }, |
| { |
| "epoch": 7.2, |
| "learning_rate": 7.746861924686193e-05, |
| "loss": 0.1468, |
| "step": 2080 |
| }, |
| { |
| "epoch": 7.23, |
| "learning_rate": 7.725941422594143e-05, |
| "loss": 0.0878, |
| "step": 2090 |
| }, |
| { |
| "epoch": 7.27, |
| "learning_rate": 7.705020920502093e-05, |
| "loss": 0.087, |
| "step": 2100 |
| }, |
| { |
| "epoch": 7.27, |
| "eval_loss": 0.3823077380657196, |
| "eval_runtime": 68.3528, |
| "eval_samples_per_second": 24.578, |
| "eval_steps_per_second": 24.578, |
| "eval_wer": 0.2565639859416994, |
| "step": 2100 |
| }, |
| { |
| "epoch": 7.3, |
| "learning_rate": 7.684100418410042e-05, |
| "loss": 0.0923, |
| "step": 2110 |
| }, |
| { |
| "epoch": 7.34, |
| "learning_rate": 7.663179916317992e-05, |
| "loss": 0.1424, |
| "step": 2120 |
| }, |
| { |
| "epoch": 7.37, |
| "learning_rate": 7.642259414225942e-05, |
| "loss": 0.2002, |
| "step": 2130 |
| }, |
| { |
| "epoch": 7.4, |
| "learning_rate": 7.621338912133892e-05, |
| "loss": 0.0883, |
| "step": 2140 |
| }, |
| { |
| "epoch": 7.44, |
| "learning_rate": 7.600418410041842e-05, |
| "loss": 0.0803, |
| "step": 2150 |
| }, |
| { |
| "epoch": 7.47, |
| "learning_rate": 7.579497907949791e-05, |
| "loss": 0.079, |
| "step": 2160 |
| }, |
| { |
| "epoch": 7.51, |
| "learning_rate": 7.558577405857741e-05, |
| "loss": 0.1327, |
| "step": 2170 |
| }, |
| { |
| "epoch": 7.54, |
| "learning_rate": 7.537656903765691e-05, |
| "loss": 0.1688, |
| "step": 2180 |
| }, |
| { |
| "epoch": 7.58, |
| "learning_rate": 7.516736401673641e-05, |
| "loss": 0.0936, |
| "step": 2190 |
| }, |
| { |
| "epoch": 7.61, |
| "learning_rate": 7.495815899581591e-05, |
| "loss": 0.0774, |
| "step": 2200 |
| }, |
| { |
| "epoch": 7.61, |
| "eval_loss": 0.3483654260635376, |
| "eval_runtime": 75.3048, |
| "eval_samples_per_second": 22.309, |
| "eval_steps_per_second": 22.309, |
| "eval_wer": 0.2452622148714768, |
| "step": 2200 |
| }, |
| { |
| "epoch": 7.65, |
| "learning_rate": 7.47489539748954e-05, |
| "loss": 0.1017, |
| "step": 2210 |
| }, |
| { |
| "epoch": 7.68, |
| "learning_rate": 7.456066945606695e-05, |
| "loss": 0.1912, |
| "step": 2220 |
| }, |
| { |
| "epoch": 7.72, |
| "learning_rate": 7.435146443514645e-05, |
| "loss": 0.1968, |
| "step": 2230 |
| }, |
| { |
| "epoch": 7.75, |
| "learning_rate": 7.414225941422595e-05, |
| "loss": 0.0889, |
| "step": 2240 |
| }, |
| { |
| "epoch": 7.79, |
| "learning_rate": 7.393305439330545e-05, |
| "loss": 0.0853, |
| "step": 2250 |
| }, |
| { |
| "epoch": 7.82, |
| "learning_rate": 7.372384937238495e-05, |
| "loss": 0.0897, |
| "step": 2260 |
| }, |
| { |
| "epoch": 7.85, |
| "learning_rate": 7.351464435146444e-05, |
| "loss": 0.1517, |
| "step": 2270 |
| }, |
| { |
| "epoch": 7.89, |
| "learning_rate": 7.330543933054394e-05, |
| "loss": 0.1842, |
| "step": 2280 |
| }, |
| { |
| "epoch": 7.92, |
| "learning_rate": 7.309623430962344e-05, |
| "loss": 0.0633, |
| "step": 2290 |
| }, |
| { |
| "epoch": 7.96, |
| "learning_rate": 7.288702928870294e-05, |
| "loss": 0.1029, |
| "step": 2300 |
| }, |
| { |
| "epoch": 7.96, |
| "eval_loss": 0.37655821442604065, |
| "eval_runtime": 66.2166, |
| "eval_samples_per_second": 25.371, |
| "eval_steps_per_second": 25.371, |
| "eval_wer": 0.24843222383019778, |
| "step": 2300 |
| }, |
| { |
| "epoch": 7.99, |
| "learning_rate": 7.267782426778243e-05, |
| "loss": 0.1486, |
| "step": 2310 |
| }, |
| { |
| "epoch": 8.03, |
| "learning_rate": 7.246861924686193e-05, |
| "loss": 0.1307, |
| "step": 2320 |
| }, |
| { |
| "epoch": 8.06, |
| "learning_rate": 7.225941422594143e-05, |
| "loss": 0.0622, |
| "step": 2330 |
| }, |
| { |
| "epoch": 8.1, |
| "learning_rate": 7.205020920502092e-05, |
| "loss": 0.0692, |
| "step": 2340 |
| }, |
| { |
| "epoch": 8.13, |
| "learning_rate": 7.184100418410042e-05, |
| "loss": 0.0787, |
| "step": 2350 |
| }, |
| { |
| "epoch": 8.17, |
| "learning_rate": 7.163179916317992e-05, |
| "loss": 0.1234, |
| "step": 2360 |
| }, |
| { |
| "epoch": 8.2, |
| "learning_rate": 7.142259414225941e-05, |
| "loss": 0.1194, |
| "step": 2370 |
| }, |
| { |
| "epoch": 8.24, |
| "learning_rate": 7.121338912133891e-05, |
| "loss": 0.0804, |
| "step": 2380 |
| }, |
| { |
| "epoch": 8.27, |
| "learning_rate": 7.100418410041841e-05, |
| "loss": 0.0738, |
| "step": 2390 |
| }, |
| { |
| "epoch": 8.3, |
| "learning_rate": 7.079497907949791e-05, |
| "loss": 0.091, |
| "step": 2400 |
| }, |
| { |
| "epoch": 8.3, |
| "eval_loss": 0.3635753095149994, |
| "eval_runtime": 68.6955, |
| "eval_samples_per_second": 24.456, |
| "eval_steps_per_second": 24.456, |
| "eval_wer": 0.25318723726827924, |
| "step": 2400 |
| }, |
| { |
| "epoch": 8.34, |
| "learning_rate": 7.058577405857741e-05, |
| "loss": 0.1578, |
| "step": 2410 |
| }, |
| { |
| "epoch": 8.37, |
| "learning_rate": 7.03765690376569e-05, |
| "loss": 0.1362, |
| "step": 2420 |
| }, |
| { |
| "epoch": 8.41, |
| "learning_rate": 7.01673640167364e-05, |
| "loss": 0.0694, |
| "step": 2430 |
| }, |
| { |
| "epoch": 8.44, |
| "learning_rate": 6.99581589958159e-05, |
| "loss": 0.1059, |
| "step": 2440 |
| }, |
| { |
| "epoch": 8.48, |
| "learning_rate": 6.97489539748954e-05, |
| "loss": 0.079, |
| "step": 2450 |
| }, |
| { |
| "epoch": 8.51, |
| "learning_rate": 6.95397489539749e-05, |
| "loss": 0.1345, |
| "step": 2460 |
| }, |
| { |
| "epoch": 8.55, |
| "learning_rate": 6.933054393305439e-05, |
| "loss": 0.1404, |
| "step": 2470 |
| }, |
| { |
| "epoch": 8.58, |
| "learning_rate": 6.912133891213389e-05, |
| "loss": 0.0728, |
| "step": 2480 |
| }, |
| { |
| "epoch": 8.62, |
| "learning_rate": 6.891213389121339e-05, |
| "loss": 0.0675, |
| "step": 2490 |
| }, |
| { |
| "epoch": 8.65, |
| "learning_rate": 6.870292887029289e-05, |
| "loss": 0.0639, |
| "step": 2500 |
| }, |
| { |
| "epoch": 8.65, |
| "eval_loss": 0.3872681260108948, |
| "eval_runtime": 65.4001, |
| "eval_samples_per_second": 25.688, |
| "eval_steps_per_second": 25.688, |
| "eval_wer": 0.24912135621252843, |
| "step": 2500 |
| }, |
| { |
| "epoch": 8.69, |
| "learning_rate": 6.849372384937239e-05, |
| "loss": 0.1576, |
| "step": 2510 |
| }, |
| { |
| "epoch": 8.72, |
| "learning_rate": 6.828451882845188e-05, |
| "loss": 0.1153, |
| "step": 2520 |
| }, |
| { |
| "epoch": 8.75, |
| "learning_rate": 6.807531380753138e-05, |
| "loss": 0.0712, |
| "step": 2530 |
| }, |
| { |
| "epoch": 8.79, |
| "learning_rate": 6.786610878661088e-05, |
| "loss": 0.0554, |
| "step": 2540 |
| }, |
| { |
| "epoch": 8.82, |
| "learning_rate": 6.765690376569038e-05, |
| "loss": 0.0973, |
| "step": 2550 |
| }, |
| { |
| "epoch": 8.86, |
| "learning_rate": 6.744769874476988e-05, |
| "loss": 0.1796, |
| "step": 2560 |
| }, |
| { |
| "epoch": 8.89, |
| "learning_rate": 6.723849372384937e-05, |
| "loss": 0.1226, |
| "step": 2570 |
| }, |
| { |
| "epoch": 8.93, |
| "learning_rate": 6.702928870292887e-05, |
| "loss": 0.0588, |
| "step": 2580 |
| }, |
| { |
| "epoch": 8.96, |
| "learning_rate": 6.682008368200837e-05, |
| "loss": 0.0657, |
| "step": 2590 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 6.661087866108787e-05, |
| "loss": 0.1364, |
| "step": 2600 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.36837586760520935, |
| "eval_runtime": 66.1276, |
| "eval_samples_per_second": 25.405, |
| "eval_steps_per_second": 25.405, |
| "eval_wer": 0.25029288126249055, |
| "step": 2600 |
| }, |
| { |
| "epoch": 9.03, |
| "learning_rate": 6.640167364016737e-05, |
| "loss": 0.0925, |
| "step": 2610 |
| }, |
| { |
| "epoch": 9.07, |
| "learning_rate": 6.619246861924686e-05, |
| "loss": 0.0427, |
| "step": 2620 |
| }, |
| { |
| "epoch": 9.1, |
| "learning_rate": 6.598326359832636e-05, |
| "loss": 0.056, |
| "step": 2630 |
| }, |
| { |
| "epoch": 9.13, |
| "learning_rate": 6.577405857740586e-05, |
| "loss": 0.0744, |
| "step": 2640 |
| }, |
| { |
| "epoch": 9.17, |
| "learning_rate": 6.556485355648536e-05, |
| "loss": 0.1384, |
| "step": 2650 |
| }, |
| { |
| "epoch": 9.2, |
| "learning_rate": 6.535564853556486e-05, |
| "loss": 0.1063, |
| "step": 2660 |
| }, |
| { |
| "epoch": 9.24, |
| "learning_rate": 6.514644351464435e-05, |
| "loss": 0.0579, |
| "step": 2670 |
| }, |
| { |
| "epoch": 9.27, |
| "learning_rate": 6.493723849372385e-05, |
| "loss": 0.0784, |
| "step": 2680 |
| }, |
| { |
| "epoch": 9.31, |
| "learning_rate": 6.472803347280335e-05, |
| "loss": 0.0637, |
| "step": 2690 |
| }, |
| { |
| "epoch": 9.34, |
| "learning_rate": 6.451882845188285e-05, |
| "loss": 0.134, |
| "step": 2700 |
| }, |
| { |
| "epoch": 9.34, |
| "eval_loss": 0.3780774176120758, |
| "eval_runtime": 66.7383, |
| "eval_samples_per_second": 25.173, |
| "eval_steps_per_second": 25.173, |
| "eval_wer": 0.24939700916546068, |
| "step": 2700 |
| }, |
| { |
| "epoch": 9.38, |
| "learning_rate": 6.430962343096236e-05, |
| "loss": 0.1097, |
| "step": 2710 |
| }, |
| { |
| "epoch": 9.41, |
| "learning_rate": 6.410041841004184e-05, |
| "loss": 0.0529, |
| "step": 2720 |
| }, |
| { |
| "epoch": 9.45, |
| "learning_rate": 6.389121338912134e-05, |
| "loss": 0.0664, |
| "step": 2730 |
| }, |
| { |
| "epoch": 9.48, |
| "learning_rate": 6.368200836820084e-05, |
| "loss": 0.0752, |
| "step": 2740 |
| }, |
| { |
| "epoch": 9.52, |
| "learning_rate": 6.347280334728035e-05, |
| "loss": 0.1329, |
| "step": 2750 |
| }, |
| { |
| "epoch": 9.55, |
| "learning_rate": 6.326359832635985e-05, |
| "loss": 0.1045, |
| "step": 2760 |
| }, |
| { |
| "epoch": 9.58, |
| "learning_rate": 6.305439330543933e-05, |
| "loss": 0.0569, |
| "step": 2770 |
| }, |
| { |
| "epoch": 9.62, |
| "learning_rate": 6.284518828451883e-05, |
| "loss": 0.0634, |
| "step": 2780 |
| }, |
| { |
| "epoch": 9.65, |
| "learning_rate": 6.263598326359834e-05, |
| "loss": 0.0629, |
| "step": 2790 |
| }, |
| { |
| "epoch": 9.69, |
| "learning_rate": 6.242677824267784e-05, |
| "loss": 0.1319, |
| "step": 2800 |
| }, |
| { |
| "epoch": 9.69, |
| "eval_loss": 0.35791799426078796, |
| "eval_runtime": 65.5678, |
| "eval_samples_per_second": 25.622, |
| "eval_steps_per_second": 25.622, |
| "eval_wer": 0.23940458962166633, |
| "step": 2800 |
| }, |
| { |
| "epoch": 9.72, |
| "learning_rate": 6.221757322175734e-05, |
| "loss": 0.1019, |
| "step": 2810 |
| }, |
| { |
| "epoch": 9.76, |
| "learning_rate": 6.200836820083682e-05, |
| "loss": 0.0641, |
| "step": 2820 |
| }, |
| { |
| "epoch": 9.79, |
| "learning_rate": 6.179916317991633e-05, |
| "loss": 0.0452, |
| "step": 2830 |
| }, |
| { |
| "epoch": 9.83, |
| "learning_rate": 6.158995815899583e-05, |
| "loss": 0.0668, |
| "step": 2840 |
| }, |
| { |
| "epoch": 9.86, |
| "learning_rate": 6.138075313807531e-05, |
| "loss": 0.1516, |
| "step": 2850 |
| }, |
| { |
| "epoch": 9.9, |
| "learning_rate": 6.117154811715481e-05, |
| "loss": 0.09, |
| "step": 2860 |
| }, |
| { |
| "epoch": 9.93, |
| "learning_rate": 6.096234309623431e-05, |
| "loss": 0.0594, |
| "step": 2870 |
| }, |
| { |
| "epoch": 9.97, |
| "learning_rate": 6.075313807531381e-05, |
| "loss": 0.076, |
| "step": 2880 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 6.054393305439331e-05, |
| "loss": 0.1389, |
| "step": 2890 |
| }, |
| { |
| "epoch": 10.03, |
| "learning_rate": 6.033472803347281e-05, |
| "loss": 0.0518, |
| "step": 2900 |
| }, |
| { |
| "epoch": 10.03, |
| "eval_loss": 0.3705912232398987, |
| "eval_runtime": 66.27, |
| "eval_samples_per_second": 25.351, |
| "eval_steps_per_second": 25.351, |
| "eval_wer": 0.23182413341602923, |
| "step": 2900 |
| }, |
| { |
| "epoch": 10.07, |
| "learning_rate": 6.012552301255231e-05, |
| "loss": 0.0591, |
| "step": 2910 |
| }, |
| { |
| "epoch": 10.1, |
| "learning_rate": 5.99163179916318e-05, |
| "loss": 0.0628, |
| "step": 2920 |
| }, |
| { |
| "epoch": 10.14, |
| "learning_rate": 5.97071129707113e-05, |
| "loss": 0.0614, |
| "step": 2930 |
| }, |
| { |
| "epoch": 10.17, |
| "learning_rate": 5.94979079497908e-05, |
| "loss": 0.1627, |
| "step": 2940 |
| }, |
| { |
| "epoch": 10.21, |
| "learning_rate": 5.92887029288703e-05, |
| "loss": 0.0647, |
| "step": 2950 |
| }, |
| { |
| "epoch": 10.24, |
| "learning_rate": 5.9079497907949796e-05, |
| "loss": 0.0567, |
| "step": 2960 |
| }, |
| { |
| "epoch": 10.28, |
| "learning_rate": 5.887029288702929e-05, |
| "loss": 0.0595, |
| "step": 2970 |
| }, |
| { |
| "epoch": 10.31, |
| "learning_rate": 5.866108786610879e-05, |
| "loss": 0.0628, |
| "step": 2980 |
| }, |
| { |
| "epoch": 10.35, |
| "learning_rate": 5.8451882845188285e-05, |
| "loss": 0.104, |
| "step": 2990 |
| }, |
| { |
| "epoch": 10.38, |
| "learning_rate": 5.8242677824267786e-05, |
| "loss": 0.0665, |
| "step": 3000 |
| }, |
| { |
| "epoch": 10.38, |
| "eval_loss": 0.3515700697898865, |
| "eval_runtime": 66.8947, |
| "eval_samples_per_second": 25.114, |
| "eval_steps_per_second": 25.114, |
| "eval_wer": 0.2349941423747502, |
| "step": 3000 |
| }, |
| { |
| "epoch": 10.42, |
| "learning_rate": 5.803347280334729e-05, |
| "loss": 0.0377, |
| "step": 3010 |
| }, |
| { |
| "epoch": 10.45, |
| "learning_rate": 5.782426778242678e-05, |
| "loss": 0.0491, |
| "step": 3020 |
| }, |
| { |
| "epoch": 10.48, |
| "learning_rate": 5.7615062761506275e-05, |
| "loss": 0.0489, |
| "step": 3030 |
| }, |
| { |
| "epoch": 10.52, |
| "learning_rate": 5.7405857740585776e-05, |
| "loss": 0.16, |
| "step": 3040 |
| }, |
| { |
| "epoch": 10.55, |
| "learning_rate": 5.719665271966528e-05, |
| "loss": 0.0735, |
| "step": 3050 |
| }, |
| { |
| "epoch": 10.59, |
| "learning_rate": 5.698744769874478e-05, |
| "loss": 0.052, |
| "step": 3060 |
| }, |
| { |
| "epoch": 10.62, |
| "learning_rate": 5.6778242677824265e-05, |
| "loss": 0.0503, |
| "step": 3070 |
| }, |
| { |
| "epoch": 10.66, |
| "learning_rate": 5.6569037656903766e-05, |
| "loss": 0.0454, |
| "step": 3080 |
| }, |
| { |
| "epoch": 10.69, |
| "learning_rate": 5.6359832635983267e-05, |
| "loss": 0.1437, |
| "step": 3090 |
| }, |
| { |
| "epoch": 10.73, |
| "learning_rate": 5.615062761506277e-05, |
| "loss": 0.0832, |
| "step": 3100 |
| }, |
| { |
| "epoch": 10.73, |
| "eval_loss": 0.33939608931541443, |
| "eval_runtime": 66.9082, |
| "eval_samples_per_second": 25.109, |
| "eval_steps_per_second": 25.109, |
| "eval_wer": 0.2308593480807663, |
| "step": 3100 |
| }, |
| { |
| "epoch": 10.76, |
| "learning_rate": 5.594142259414227e-05, |
| "loss": 0.0444, |
| "step": 3110 |
| }, |
| { |
| "epoch": 10.8, |
| "learning_rate": 5.5732217573221756e-05, |
| "loss": 0.0579, |
| "step": 3120 |
| }, |
| { |
| "epoch": 10.83, |
| "learning_rate": 5.5523012552301257e-05, |
| "loss": 0.0613, |
| "step": 3130 |
| }, |
| { |
| "epoch": 10.87, |
| "learning_rate": 5.531380753138076e-05, |
| "loss": 0.1206, |
| "step": 3140 |
| }, |
| { |
| "epoch": 10.9, |
| "learning_rate": 5.510460251046026e-05, |
| "loss": 0.0729, |
| "step": 3150 |
| }, |
| { |
| "epoch": 10.93, |
| "learning_rate": 5.4895397489539746e-05, |
| "loss": 0.0564, |
| "step": 3160 |
| }, |
| { |
| "epoch": 10.97, |
| "learning_rate": 5.4686192468619246e-05, |
| "loss": 0.0816, |
| "step": 3170 |
| }, |
| { |
| "epoch": 11.0, |
| "learning_rate": 5.447698744769875e-05, |
| "loss": 0.1221, |
| "step": 3180 |
| }, |
| { |
| "epoch": 11.04, |
| "learning_rate": 5.426778242677825e-05, |
| "loss": 0.0503, |
| "step": 3190 |
| }, |
| { |
| "epoch": 11.07, |
| "learning_rate": 5.405857740585775e-05, |
| "loss": 0.0403, |
| "step": 3200 |
| }, |
| { |
| "epoch": 11.07, |
| "eval_loss": 0.36069467663764954, |
| "eval_runtime": 66.1131, |
| "eval_samples_per_second": 25.411, |
| "eval_steps_per_second": 25.411, |
| "eval_wer": 0.23258217903659292, |
| "step": 3200 |
| }, |
| { |
| "epoch": 11.11, |
| "learning_rate": 5.3849372384937236e-05, |
| "loss": 0.0467, |
| "step": 3210 |
| }, |
| { |
| "epoch": 11.14, |
| "learning_rate": 5.364016736401674e-05, |
| "loss": 0.0723, |
| "step": 3220 |
| }, |
| { |
| "epoch": 11.18, |
| "learning_rate": 5.343096234309624e-05, |
| "loss": 0.0922, |
| "step": 3230 |
| }, |
| { |
| "epoch": 11.21, |
| "learning_rate": 5.322175732217574e-05, |
| "loss": 0.0442, |
| "step": 3240 |
| }, |
| { |
| "epoch": 11.25, |
| "learning_rate": 5.301255230125523e-05, |
| "loss": 0.0407, |
| "step": 3250 |
| }, |
| { |
| "epoch": 11.28, |
| "learning_rate": 5.280334728033473e-05, |
| "loss": 0.0387, |
| "step": 3260 |
| }, |
| { |
| "epoch": 11.31, |
| "learning_rate": 5.259414225941423e-05, |
| "loss": 0.0576, |
| "step": 3270 |
| }, |
| { |
| "epoch": 11.35, |
| "learning_rate": 5.238493723849372e-05, |
| "loss": 0.1078, |
| "step": 3280 |
| }, |
| { |
| "epoch": 11.38, |
| "learning_rate": 5.217573221757322e-05, |
| "loss": 0.051, |
| "step": 3290 |
| }, |
| { |
| "epoch": 11.42, |
| "learning_rate": 5.1966527196652724e-05, |
| "loss": 0.0309, |
| "step": 3300 |
| }, |
| { |
| "epoch": 11.42, |
| "eval_loss": 0.35881075263023376, |
| "eval_runtime": 65.6303, |
| "eval_samples_per_second": 25.598, |
| "eval_steps_per_second": 25.598, |
| "eval_wer": 0.2296878230308042, |
| "step": 3300 |
| }, |
| { |
| "epoch": 11.45, |
| "learning_rate": 5.175732217573221e-05, |
| "loss": 0.061, |
| "step": 3310 |
| }, |
| { |
| "epoch": 11.49, |
| "learning_rate": 5.154811715481171e-05, |
| "loss": 0.0559, |
| "step": 3320 |
| }, |
| { |
| "epoch": 11.52, |
| "learning_rate": 5.133891213389121e-05, |
| "loss": 0.114, |
| "step": 3330 |
| }, |
| { |
| "epoch": 11.56, |
| "learning_rate": 5.1129707112970714e-05, |
| "loss": 0.0556, |
| "step": 3340 |
| }, |
| { |
| "epoch": 11.59, |
| "learning_rate": 5.0920502092050215e-05, |
| "loss": 0.0312, |
| "step": 3350 |
| }, |
| { |
| "epoch": 11.63, |
| "learning_rate": 5.07112970711297e-05, |
| "loss": 0.0494, |
| "step": 3360 |
| }, |
| { |
| "epoch": 11.66, |
| "learning_rate": 5.05020920502092e-05, |
| "loss": 0.0718, |
| "step": 3370 |
| }, |
| { |
| "epoch": 11.7, |
| "learning_rate": 5.0292887029288704e-05, |
| "loss": 0.1242, |
| "step": 3380 |
| }, |
| { |
| "epoch": 11.73, |
| "learning_rate": 5.0083682008368205e-05, |
| "loss": 0.0579, |
| "step": 3390 |
| }, |
| { |
| "epoch": 11.76, |
| "learning_rate": 4.98744769874477e-05, |
| "loss": 0.0462, |
| "step": 3400 |
| }, |
| { |
| "epoch": 11.76, |
| "eval_loss": 0.36503496766090393, |
| "eval_runtime": 65.8233, |
| "eval_samples_per_second": 25.523, |
| "eval_steps_per_second": 25.523, |
| "eval_wer": 0.2252773757838881, |
| "step": 3400 |
| }, |
| { |
| "epoch": 11.8, |
| "learning_rate": 4.96652719665272e-05, |
| "loss": 0.0473, |
| "step": 3410 |
| }, |
| { |
| "epoch": 11.83, |
| "learning_rate": 4.94560669456067e-05, |
| "loss": 0.0591, |
| "step": 3420 |
| }, |
| { |
| "epoch": 11.87, |
| "learning_rate": 4.9246861924686195e-05, |
| "loss": 0.1507, |
| "step": 3430 |
| }, |
| { |
| "epoch": 11.9, |
| "learning_rate": 4.9037656903765696e-05, |
| "loss": 0.049, |
| "step": 3440 |
| }, |
| { |
| "epoch": 11.94, |
| "learning_rate": 4.882845188284519e-05, |
| "loss": 0.0521, |
| "step": 3450 |
| }, |
| { |
| "epoch": 11.97, |
| "learning_rate": 4.861924686192469e-05, |
| "loss": 0.0606, |
| "step": 3460 |
| }, |
| { |
| "epoch": 12.01, |
| "learning_rate": 4.841004184100419e-05, |
| "loss": 0.1045, |
| "step": 3470 |
| }, |
| { |
| "epoch": 12.04, |
| "learning_rate": 4.8200836820083686e-05, |
| "loss": 0.0561, |
| "step": 3480 |
| }, |
| { |
| "epoch": 12.08, |
| "learning_rate": 4.7991631799163186e-05, |
| "loss": 0.0405, |
| "step": 3490 |
| }, |
| { |
| "epoch": 12.11, |
| "learning_rate": 4.778242677824268e-05, |
| "loss": 0.0505, |
| "step": 3500 |
| }, |
| { |
| "epoch": 12.11, |
| "eval_loss": 0.3625409007072449, |
| "eval_runtime": 65.617, |
| "eval_samples_per_second": 25.603, |
| "eval_steps_per_second": 25.603, |
| "eval_wer": 0.23423609675418647, |
| "step": 3500 |
| }, |
| { |
| "epoch": 12.15, |
| "learning_rate": 4.757322175732218e-05, |
| "loss": 0.0567, |
| "step": 3510 |
| }, |
| { |
| "epoch": 12.18, |
| "learning_rate": 4.7364016736401675e-05, |
| "loss": 0.0897, |
| "step": 3520 |
| }, |
| { |
| "epoch": 12.21, |
| "learning_rate": 4.7154811715481176e-05, |
| "loss": 0.0485, |
| "step": 3530 |
| }, |
| { |
| "epoch": 12.25, |
| "learning_rate": 4.694560669456067e-05, |
| "loss": 0.0408, |
| "step": 3540 |
| }, |
| { |
| "epoch": 12.28, |
| "learning_rate": 4.6736401673640165e-05, |
| "loss": 0.0356, |
| "step": 3550 |
| }, |
| { |
| "epoch": 12.32, |
| "learning_rate": 4.6527196652719665e-05, |
| "loss": 0.0584, |
| "step": 3560 |
| }, |
| { |
| "epoch": 12.35, |
| "learning_rate": 4.6317991631799166e-05, |
| "loss": 0.1004, |
| "step": 3570 |
| }, |
| { |
| "epoch": 12.39, |
| "learning_rate": 4.610878661087866e-05, |
| "loss": 0.0464, |
| "step": 3580 |
| }, |
| { |
| "epoch": 12.42, |
| "learning_rate": 4.589958158995816e-05, |
| "loss": 0.0325, |
| "step": 3590 |
| }, |
| { |
| "epoch": 12.46, |
| "learning_rate": 4.5690376569037655e-05, |
| "loss": 0.0397, |
| "step": 3600 |
| }, |
| { |
| "epoch": 12.46, |
| "eval_loss": 0.3711862564086914, |
| "eval_runtime": 65.5446, |
| "eval_samples_per_second": 25.631, |
| "eval_steps_per_second": 25.631, |
| "eval_wer": 0.22589759492798567, |
| "step": 3600 |
| }, |
| { |
| "epoch": 12.49, |
| "learning_rate": 4.5481171548117156e-05, |
| "loss": 0.0633, |
| "step": 3610 |
| }, |
| { |
| "epoch": 12.53, |
| "learning_rate": 4.527196652719666e-05, |
| "loss": 0.1063, |
| "step": 3620 |
| }, |
| { |
| "epoch": 12.56, |
| "learning_rate": 4.506276150627615e-05, |
| "loss": 0.0521, |
| "step": 3630 |
| }, |
| { |
| "epoch": 12.6, |
| "learning_rate": 4.485355648535565e-05, |
| "loss": 0.0267, |
| "step": 3640 |
| }, |
| { |
| "epoch": 12.63, |
| "learning_rate": 4.4644351464435146e-05, |
| "loss": 0.0284, |
| "step": 3650 |
| }, |
| { |
| "epoch": 12.66, |
| "learning_rate": 4.443514644351465e-05, |
| "loss": 0.0435, |
| "step": 3660 |
| }, |
| { |
| "epoch": 12.7, |
| "learning_rate": 4.422594142259415e-05, |
| "loss": 0.1056, |
| "step": 3670 |
| }, |
| { |
| "epoch": 12.73, |
| "learning_rate": 4.401673640167364e-05, |
| "loss": 0.0504, |
| "step": 3680 |
| }, |
| { |
| "epoch": 12.77, |
| "learning_rate": 4.380753138075314e-05, |
| "loss": 0.0207, |
| "step": 3690 |
| }, |
| { |
| "epoch": 12.8, |
| "learning_rate": 4.359832635983264e-05, |
| "loss": 0.0383, |
| "step": 3700 |
| }, |
| { |
| "epoch": 12.8, |
| "eval_loss": 0.354831337928772, |
| "eval_runtime": 65.7436, |
| "eval_samples_per_second": 25.554, |
| "eval_steps_per_second": 25.554, |
| "eval_wer": 0.22396802425745985, |
| "step": 3700 |
| }, |
| { |
| "epoch": 12.84, |
| "learning_rate": 4.338912133891214e-05, |
| "loss": 0.0404, |
| "step": 3710 |
| }, |
| { |
| "epoch": 12.87, |
| "learning_rate": 4.317991631799164e-05, |
| "loss": 0.0826, |
| "step": 3720 |
| }, |
| { |
| "epoch": 12.91, |
| "learning_rate": 4.297071129707113e-05, |
| "loss": 0.0547, |
| "step": 3730 |
| }, |
| { |
| "epoch": 12.94, |
| "learning_rate": 4.2761506276150634e-05, |
| "loss": 0.0513, |
| "step": 3740 |
| }, |
| { |
| "epoch": 12.98, |
| "learning_rate": 4.255230125523013e-05, |
| "loss": 0.0445, |
| "step": 3750 |
| }, |
| { |
| "epoch": 13.01, |
| "learning_rate": 4.234309623430963e-05, |
| "loss": 0.0905, |
| "step": 3760 |
| }, |
| { |
| "epoch": 13.04, |
| "learning_rate": 4.213389121338912e-05, |
| "loss": 0.0462, |
| "step": 3770 |
| }, |
| { |
| "epoch": 13.08, |
| "learning_rate": 4.1924686192468624e-05, |
| "loss": 0.0275, |
| "step": 3780 |
| }, |
| { |
| "epoch": 13.11, |
| "learning_rate": 4.171548117154812e-05, |
| "loss": 0.0429, |
| "step": 3790 |
| }, |
| { |
| "epoch": 13.15, |
| "learning_rate": 4.150627615062762e-05, |
| "loss": 0.0465, |
| "step": 3800 |
| }, |
| { |
| "epoch": 13.15, |
| "eval_loss": 0.3689797520637512, |
| "eval_runtime": 66.5499, |
| "eval_samples_per_second": 25.244, |
| "eval_steps_per_second": 25.244, |
| "eval_wer": 0.22148714768106953, |
| "step": 3800 |
| }, |
| { |
| "epoch": 13.18, |
| "learning_rate": 4.129707112970711e-05, |
| "loss": 0.0932, |
| "step": 3810 |
| }, |
| { |
| "epoch": 13.22, |
| "learning_rate": 4.108786610878661e-05, |
| "loss": 0.0494, |
| "step": 3820 |
| }, |
| { |
| "epoch": 13.25, |
| "learning_rate": 4.087866108786611e-05, |
| "loss": 0.0251, |
| "step": 3830 |
| }, |
| { |
| "epoch": 13.29, |
| "learning_rate": 4.066945606694561e-05, |
| "loss": 0.0304, |
| "step": 3840 |
| }, |
| { |
| "epoch": 13.32, |
| "learning_rate": 4.04602510460251e-05, |
| "loss": 0.0593, |
| "step": 3850 |
| }, |
| { |
| "epoch": 13.36, |
| "learning_rate": 4.0251046025104604e-05, |
| "loss": 0.0663, |
| "step": 3860 |
| }, |
| { |
| "epoch": 13.39, |
| "learning_rate": 4.00418410041841e-05, |
| "loss": 0.0304, |
| "step": 3870 |
| }, |
| { |
| "epoch": 13.43, |
| "learning_rate": 3.98326359832636e-05, |
| "loss": 0.0245, |
| "step": 3880 |
| }, |
| { |
| "epoch": 13.46, |
| "learning_rate": 3.96234309623431e-05, |
| "loss": 0.0255, |
| "step": 3890 |
| }, |
| { |
| "epoch": 13.49, |
| "learning_rate": 3.9414225941422594e-05, |
| "loss": 0.0571, |
| "step": 3900 |
| }, |
| { |
| "epoch": 13.49, |
| "eval_loss": 0.3834233283996582, |
| "eval_runtime": 65.438, |
| "eval_samples_per_second": 25.673, |
| "eval_steps_per_second": 25.673, |
| "eval_wer": 0.22637998759561712, |
| "step": 3900 |
| }, |
| { |
| "epoch": 13.53, |
| "learning_rate": 3.9205020920502094e-05, |
| "loss": 0.0981, |
| "step": 3910 |
| }, |
| { |
| "epoch": 13.56, |
| "learning_rate": 3.899581589958159e-05, |
| "loss": 0.0369, |
| "step": 3920 |
| }, |
| { |
| "epoch": 13.6, |
| "learning_rate": 3.878661087866109e-05, |
| "loss": 0.0301, |
| "step": 3930 |
| }, |
| { |
| "epoch": 13.63, |
| "learning_rate": 3.857740585774059e-05, |
| "loss": 0.0522, |
| "step": 3940 |
| }, |
| { |
| "epoch": 13.67, |
| "learning_rate": 3.8368200836820084e-05, |
| "loss": 0.0523, |
| "step": 3950 |
| }, |
| { |
| "epoch": 13.7, |
| "learning_rate": 3.8158995815899585e-05, |
| "loss": 0.0768, |
| "step": 3960 |
| }, |
| { |
| "epoch": 13.74, |
| "learning_rate": 3.794979079497908e-05, |
| "loss": 0.045, |
| "step": 3970 |
| }, |
| { |
| "epoch": 13.77, |
| "learning_rate": 3.774058577405858e-05, |
| "loss": 0.0218, |
| "step": 3980 |
| }, |
| { |
| "epoch": 13.81, |
| "learning_rate": 3.753138075313808e-05, |
| "loss": 0.0381, |
| "step": 3990 |
| }, |
| { |
| "epoch": 13.84, |
| "learning_rate": 3.7322175732217575e-05, |
| "loss": 0.0537, |
| "step": 4000 |
| }, |
| { |
| "epoch": 13.84, |
| "eval_loss": 0.36312898993492126, |
| "eval_runtime": 64.9041, |
| "eval_samples_per_second": 25.884, |
| "eval_steps_per_second": 25.884, |
| "eval_wer": 0.2258286816897526, |
| "step": 4000 |
| }, |
| { |
| "epoch": 13.88, |
| "learning_rate": 3.7112970711297076e-05, |
| "loss": 0.1029, |
| "step": 4010 |
| }, |
| { |
| "epoch": 13.91, |
| "learning_rate": 3.690376569037657e-05, |
| "loss": 0.0357, |
| "step": 4020 |
| }, |
| { |
| "epoch": 13.94, |
| "learning_rate": 3.669456066945607e-05, |
| "loss": 0.0374, |
| "step": 4030 |
| }, |
| { |
| "epoch": 13.98, |
| "learning_rate": 3.648535564853557e-05, |
| "loss": 0.0431, |
| "step": 4040 |
| }, |
| { |
| "epoch": 14.01, |
| "learning_rate": 3.6276150627615066e-05, |
| "loss": 0.0625, |
| "step": 4050 |
| }, |
| { |
| "epoch": 14.05, |
| "learning_rate": 3.606694560669456e-05, |
| "loss": 0.0399, |
| "step": 4060 |
| }, |
| { |
| "epoch": 14.08, |
| "learning_rate": 3.585774058577406e-05, |
| "loss": 0.0325, |
| "step": 4070 |
| }, |
| { |
| "epoch": 14.12, |
| "learning_rate": 3.5648535564853555e-05, |
| "loss": 0.0371, |
| "step": 4080 |
| }, |
| { |
| "epoch": 14.15, |
| "learning_rate": 3.5439330543933056e-05, |
| "loss": 0.0332, |
| "step": 4090 |
| }, |
| { |
| "epoch": 14.19, |
| "learning_rate": 3.523012552301255e-05, |
| "loss": 0.0814, |
| "step": 4100 |
| }, |
| { |
| "epoch": 14.19, |
| "eval_loss": 0.3693317174911499, |
| "eval_runtime": 65.8647, |
| "eval_samples_per_second": 25.507, |
| "eval_steps_per_second": 25.507, |
| "eval_wer": 0.2201777961546413, |
| "step": 4100 |
| }, |
| { |
| "epoch": 14.22, |
| "learning_rate": 3.502092050209205e-05, |
| "loss": 0.0313, |
| "step": 4110 |
| }, |
| { |
| "epoch": 14.26, |
| "learning_rate": 3.4811715481171545e-05, |
| "loss": 0.0345, |
| "step": 4120 |
| }, |
| { |
| "epoch": 14.29, |
| "learning_rate": 3.4602510460251046e-05, |
| "loss": 0.035, |
| "step": 4130 |
| }, |
| { |
| "epoch": 14.33, |
| "learning_rate": 3.439330543933055e-05, |
| "loss": 0.0584, |
| "step": 4140 |
| }, |
| { |
| "epoch": 14.36, |
| "learning_rate": 3.418410041841004e-05, |
| "loss": 0.0727, |
| "step": 4150 |
| }, |
| { |
| "epoch": 14.39, |
| "learning_rate": 3.397489539748954e-05, |
| "loss": 0.0308, |
| "step": 4160 |
| }, |
| { |
| "epoch": 14.43, |
| "learning_rate": 3.3765690376569036e-05, |
| "loss": 0.0246, |
| "step": 4170 |
| }, |
| { |
| "epoch": 14.46, |
| "learning_rate": 3.355648535564854e-05, |
| "loss": 0.0419, |
| "step": 4180 |
| }, |
| { |
| "epoch": 14.5, |
| "learning_rate": 3.334728033472804e-05, |
| "loss": 0.0344, |
| "step": 4190 |
| }, |
| { |
| "epoch": 14.53, |
| "learning_rate": 3.313807531380753e-05, |
| "loss": 0.0878, |
| "step": 4200 |
| }, |
| { |
| "epoch": 14.53, |
| "eval_loss": 0.35174939036369324, |
| "eval_runtime": 65.3965, |
| "eval_samples_per_second": 25.689, |
| "eval_steps_per_second": 25.689, |
| "eval_wer": 0.21659430776652194, |
| "step": 4200 |
| }, |
| { |
| "epoch": 14.57, |
| "learning_rate": 3.292887029288703e-05, |
| "loss": 0.0292, |
| "step": 4210 |
| }, |
| { |
| "epoch": 14.6, |
| "learning_rate": 3.271966527196653e-05, |
| "loss": 0.0462, |
| "step": 4220 |
| }, |
| { |
| "epoch": 14.64, |
| "learning_rate": 3.251046025104603e-05, |
| "loss": 0.0402, |
| "step": 4230 |
| }, |
| { |
| "epoch": 14.67, |
| "learning_rate": 3.230125523012553e-05, |
| "loss": 0.0442, |
| "step": 4240 |
| }, |
| { |
| "epoch": 14.71, |
| "learning_rate": 3.209205020920502e-05, |
| "loss": 0.0997, |
| "step": 4250 |
| }, |
| { |
| "epoch": 14.74, |
| "learning_rate": 3.188284518828452e-05, |
| "loss": 0.0376, |
| "step": 4260 |
| }, |
| { |
| "epoch": 14.78, |
| "learning_rate": 3.167364016736402e-05, |
| "loss": 0.0246, |
| "step": 4270 |
| }, |
| { |
| "epoch": 14.81, |
| "learning_rate": 3.146443514644352e-05, |
| "loss": 0.0345, |
| "step": 4280 |
| }, |
| { |
| "epoch": 14.84, |
| "learning_rate": 3.125523012552302e-05, |
| "loss": 0.0375, |
| "step": 4290 |
| }, |
| { |
| "epoch": 14.88, |
| "learning_rate": 3.104602510460251e-05, |
| "loss": 0.0762, |
| "step": 4300 |
| }, |
| { |
| "epoch": 14.88, |
| "eval_loss": 0.36594539880752563, |
| "eval_runtime": 66.4208, |
| "eval_samples_per_second": 25.293, |
| "eval_steps_per_second": 25.293, |
| "eval_wer": 0.224105850733926, |
| "step": 4300 |
| }, |
| { |
| "epoch": 14.91, |
| "learning_rate": 3.0836820083682014e-05, |
| "loss": 0.0338, |
| "step": 4310 |
| }, |
| { |
| "epoch": 14.95, |
| "learning_rate": 3.062761506276151e-05, |
| "loss": 0.0332, |
| "step": 4320 |
| }, |
| { |
| "epoch": 14.98, |
| "learning_rate": 3.0418410041841006e-05, |
| "loss": 0.0406, |
| "step": 4330 |
| }, |
| { |
| "epoch": 15.02, |
| "learning_rate": 3.0209205020920507e-05, |
| "loss": 0.0865, |
| "step": 4340 |
| }, |
| { |
| "epoch": 15.05, |
| "learning_rate": 3e-05, |
| "loss": 0.0289, |
| "step": 4350 |
| }, |
| { |
| "epoch": 15.09, |
| "learning_rate": 2.97907949790795e-05, |
| "loss": 0.0211, |
| "step": 4360 |
| }, |
| { |
| "epoch": 15.12, |
| "learning_rate": 2.9581589958158996e-05, |
| "loss": 0.0233, |
| "step": 4370 |
| }, |
| { |
| "epoch": 15.16, |
| "learning_rate": 2.9372384937238497e-05, |
| "loss": 0.0563, |
| "step": 4380 |
| }, |
| { |
| "epoch": 15.19, |
| "learning_rate": 2.9163179916317994e-05, |
| "loss": 0.057, |
| "step": 4390 |
| }, |
| { |
| "epoch": 15.22, |
| "learning_rate": 2.8953974895397488e-05, |
| "loss": 0.0344, |
| "step": 4400 |
| }, |
| { |
| "epoch": 15.22, |
| "eval_loss": 0.36706846952438354, |
| "eval_runtime": 66.3909, |
| "eval_samples_per_second": 25.305, |
| "eval_steps_per_second": 25.305, |
| "eval_wer": 0.21790365929295016, |
| "step": 4400 |
| }, |
| { |
| "epoch": 15.26, |
| "learning_rate": 2.874476987447699e-05, |
| "loss": 0.0329, |
| "step": 4410 |
| }, |
| { |
| "epoch": 15.29, |
| "learning_rate": 2.8535564853556483e-05, |
| "loss": 0.0322, |
| "step": 4420 |
| }, |
| { |
| "epoch": 15.33, |
| "learning_rate": 2.8326359832635984e-05, |
| "loss": 0.0346, |
| "step": 4430 |
| }, |
| { |
| "epoch": 15.36, |
| "learning_rate": 2.8117154811715485e-05, |
| "loss": 0.0614, |
| "step": 4440 |
| }, |
| { |
| "epoch": 15.4, |
| "learning_rate": 2.790794979079498e-05, |
| "loss": 0.0221, |
| "step": 4450 |
| }, |
| { |
| "epoch": 15.43, |
| "learning_rate": 2.769874476987448e-05, |
| "loss": 0.0334, |
| "step": 4460 |
| }, |
| { |
| "epoch": 15.47, |
| "learning_rate": 2.7489539748953974e-05, |
| "loss": 0.03, |
| "step": 4470 |
| }, |
| { |
| "epoch": 15.5, |
| "learning_rate": 2.7280334728033475e-05, |
| "loss": 0.0343, |
| "step": 4480 |
| }, |
| { |
| "epoch": 15.54, |
| "learning_rate": 2.7071129707112976e-05, |
| "loss": 0.0483, |
| "step": 4490 |
| }, |
| { |
| "epoch": 15.57, |
| "learning_rate": 2.686192468619247e-05, |
| "loss": 0.0248, |
| "step": 4500 |
| }, |
| { |
| "epoch": 15.57, |
| "eval_loss": 0.3676240146160126, |
| "eval_runtime": 65.7176, |
| "eval_samples_per_second": 25.564, |
| "eval_steps_per_second": 25.564, |
| "eval_wer": 0.2172834401488526, |
| "step": 4500 |
| }, |
| { |
| "epoch": 15.61, |
| "learning_rate": 2.665271966527197e-05, |
| "loss": 0.0275, |
| "step": 4510 |
| }, |
| { |
| "epoch": 15.64, |
| "learning_rate": 2.6443514644351465e-05, |
| "loss": 0.0306, |
| "step": 4520 |
| }, |
| { |
| "epoch": 15.67, |
| "learning_rate": 2.6234309623430962e-05, |
| "loss": 0.0508, |
| "step": 4530 |
| }, |
| { |
| "epoch": 15.71, |
| "learning_rate": 2.6025104602510463e-05, |
| "loss": 0.0675, |
| "step": 4540 |
| }, |
| { |
| "epoch": 15.74, |
| "learning_rate": 2.5815899581589957e-05, |
| "loss": 0.0366, |
| "step": 4550 |
| }, |
| { |
| "epoch": 15.78, |
| "learning_rate": 2.5606694560669458e-05, |
| "loss": 0.0282, |
| "step": 4560 |
| }, |
| { |
| "epoch": 15.81, |
| "learning_rate": 2.5397489539748952e-05, |
| "loss": 0.0262, |
| "step": 4570 |
| }, |
| { |
| "epoch": 15.85, |
| "learning_rate": 2.5188284518828453e-05, |
| "loss": 0.0474, |
| "step": 4580 |
| }, |
| { |
| "epoch": 15.88, |
| "learning_rate": 2.497907949790795e-05, |
| "loss": 0.0578, |
| "step": 4590 |
| }, |
| { |
| "epoch": 15.92, |
| "learning_rate": 2.4769874476987448e-05, |
| "loss": 0.0354, |
| "step": 4600 |
| }, |
| { |
| "epoch": 15.92, |
| "eval_loss": 0.34497252106666565, |
| "eval_runtime": 67.066, |
| "eval_samples_per_second": 25.05, |
| "eval_steps_per_second": 25.05, |
| "eval_wer": 0.21700778719592034, |
| "step": 4600 |
| }, |
| { |
| "epoch": 15.95, |
| "learning_rate": 2.456066945606695e-05, |
| "loss": 0.0177, |
| "step": 4610 |
| }, |
| { |
| "epoch": 15.99, |
| "learning_rate": 2.4351464435146446e-05, |
| "loss": 0.0361, |
| "step": 4620 |
| }, |
| { |
| "epoch": 16.02, |
| "learning_rate": 2.4142259414225944e-05, |
| "loss": 0.0594, |
| "step": 4630 |
| }, |
| { |
| "epoch": 16.06, |
| "learning_rate": 2.393305439330544e-05, |
| "loss": 0.0287, |
| "step": 4640 |
| }, |
| { |
| "epoch": 16.09, |
| "learning_rate": 2.372384937238494e-05, |
| "loss": 0.0176, |
| "step": 4650 |
| }, |
| { |
| "epoch": 16.12, |
| "learning_rate": 2.3514644351464436e-05, |
| "loss": 0.0301, |
| "step": 4660 |
| }, |
| { |
| "epoch": 16.16, |
| "learning_rate": 2.3305439330543934e-05, |
| "loss": 0.0614, |
| "step": 4670 |
| }, |
| { |
| "epoch": 16.19, |
| "learning_rate": 2.309623430962343e-05, |
| "loss": 0.0513, |
| "step": 4680 |
| }, |
| { |
| "epoch": 16.23, |
| "learning_rate": 2.288702928870293e-05, |
| "loss": 0.0263, |
| "step": 4690 |
| }, |
| { |
| "epoch": 16.26, |
| "learning_rate": 2.2677824267782426e-05, |
| "loss": 0.0268, |
| "step": 4700 |
| }, |
| { |
| "epoch": 16.26, |
| "eval_loss": 0.3634060025215149, |
| "eval_runtime": 66.0371, |
| "eval_samples_per_second": 25.44, |
| "eval_steps_per_second": 25.44, |
| "eval_wer": 0.21659430776652194, |
| "step": 4700 |
| }, |
| { |
| "epoch": 16.3, |
| "learning_rate": 2.2468619246861924e-05, |
| "loss": 0.0263, |
| "step": 4710 |
| }, |
| { |
| "epoch": 16.33, |
| "learning_rate": 2.2259414225941425e-05, |
| "loss": 0.0419, |
| "step": 4720 |
| }, |
| { |
| "epoch": 16.37, |
| "learning_rate": 2.2050209205020922e-05, |
| "loss": 0.0582, |
| "step": 4730 |
| }, |
| { |
| "epoch": 16.4, |
| "learning_rate": 2.184100418410042e-05, |
| "loss": 0.0335, |
| "step": 4740 |
| }, |
| { |
| "epoch": 16.44, |
| "learning_rate": 2.1652719665271968e-05, |
| "loss": 0.0349, |
| "step": 4750 |
| }, |
| { |
| "epoch": 16.47, |
| "learning_rate": 2.1443514644351465e-05, |
| "loss": 0.0371, |
| "step": 4760 |
| }, |
| { |
| "epoch": 16.51, |
| "learning_rate": 2.1234309623430966e-05, |
| "loss": 0.0346, |
| "step": 4770 |
| }, |
| { |
| "epoch": 16.54, |
| "learning_rate": 2.1025104602510464e-05, |
| "loss": 0.0528, |
| "step": 4780 |
| }, |
| { |
| "epoch": 16.57, |
| "learning_rate": 2.0815899581589958e-05, |
| "loss": 0.0252, |
| "step": 4790 |
| }, |
| { |
| "epoch": 16.61, |
| "learning_rate": 2.0606694560669455e-05, |
| "loss": 0.0184, |
| "step": 4800 |
| }, |
| { |
| "epoch": 16.61, |
| "eval_loss": 0.3609733283519745, |
| "eval_runtime": 66.6564, |
| "eval_samples_per_second": 25.204, |
| "eval_steps_per_second": 25.204, |
| "eval_wer": 0.21624974157535662, |
| "step": 4800 |
| }, |
| { |
| "epoch": 16.64, |
| "learning_rate": 2.0397489539748953e-05, |
| "loss": 0.0263, |
| "step": 4810 |
| }, |
| { |
| "epoch": 16.68, |
| "learning_rate": 2.0188284518828454e-05, |
| "loss": 0.0277, |
| "step": 4820 |
| }, |
| { |
| "epoch": 16.71, |
| "learning_rate": 1.997907949790795e-05, |
| "loss": 0.0473, |
| "step": 4830 |
| }, |
| { |
| "epoch": 16.75, |
| "learning_rate": 1.976987447698745e-05, |
| "loss": 0.0254, |
| "step": 4840 |
| }, |
| { |
| "epoch": 16.78, |
| "learning_rate": 1.9560669456066946e-05, |
| "loss": 0.0254, |
| "step": 4850 |
| }, |
| { |
| "epoch": 16.82, |
| "learning_rate": 1.9351464435146444e-05, |
| "loss": 0.0423, |
| "step": 4860 |
| }, |
| { |
| "epoch": 16.85, |
| "learning_rate": 1.9142259414225944e-05, |
| "loss": 0.0469, |
| "step": 4870 |
| }, |
| { |
| "epoch": 16.89, |
| "learning_rate": 1.8933054393305442e-05, |
| "loss": 0.0628, |
| "step": 4880 |
| }, |
| { |
| "epoch": 16.92, |
| "learning_rate": 1.872384937238494e-05, |
| "loss": 0.0275, |
| "step": 4890 |
| }, |
| { |
| "epoch": 16.96, |
| "learning_rate": 1.8514644351464437e-05, |
| "loss": 0.0268, |
| "step": 4900 |
| }, |
| { |
| "epoch": 16.96, |
| "eval_loss": 0.3481186628341675, |
| "eval_runtime": 66.5216, |
| "eval_samples_per_second": 25.255, |
| "eval_steps_per_second": 25.255, |
| "eval_wer": 0.21500930328716147, |
| "step": 4900 |
| }, |
| { |
| "epoch": 16.99, |
| "learning_rate": 1.8305439330543934e-05, |
| "loss": 0.0413, |
| "step": 4910 |
| }, |
| { |
| "epoch": 17.02, |
| "learning_rate": 1.8096234309623432e-05, |
| "loss": 0.0517, |
| "step": 4920 |
| }, |
| { |
| "epoch": 17.06, |
| "learning_rate": 1.788702928870293e-05, |
| "loss": 0.0208, |
| "step": 4930 |
| }, |
| { |
| "epoch": 17.09, |
| "learning_rate": 1.7677824267782427e-05, |
| "loss": 0.0183, |
| "step": 4940 |
| }, |
| { |
| "epoch": 17.13, |
| "learning_rate": 1.7468619246861924e-05, |
| "loss": 0.0282, |
| "step": 4950 |
| }, |
| { |
| "epoch": 17.16, |
| "learning_rate": 1.7259414225941422e-05, |
| "loss": 0.0411, |
| "step": 4960 |
| }, |
| { |
| "epoch": 17.2, |
| "learning_rate": 1.705020920502092e-05, |
| "loss": 0.062, |
| "step": 4970 |
| }, |
| { |
| "epoch": 17.23, |
| "learning_rate": 1.684100418410042e-05, |
| "loss": 0.0232, |
| "step": 4980 |
| }, |
| { |
| "epoch": 17.27, |
| "learning_rate": 1.6631799163179918e-05, |
| "loss": 0.0198, |
| "step": 4990 |
| }, |
| { |
| "epoch": 17.3, |
| "learning_rate": 1.6422594142259415e-05, |
| "loss": 0.0291, |
| "step": 5000 |
| }, |
| { |
| "epoch": 17.3, |
| "eval_loss": 0.3561110496520996, |
| "eval_runtime": 66.3088, |
| "eval_samples_per_second": 25.336, |
| "eval_steps_per_second": 25.336, |
| "eval_wer": 0.2128040796637034, |
| "step": 5000 |
| }, |
| { |
| "epoch": 17.34, |
| "learning_rate": 1.6213389121338913e-05, |
| "loss": 0.0356, |
| "step": 5010 |
| }, |
| { |
| "epoch": 17.37, |
| "learning_rate": 1.600418410041841e-05, |
| "loss": 0.0326, |
| "step": 5020 |
| }, |
| { |
| "epoch": 17.4, |
| "learning_rate": 1.579497907949791e-05, |
| "loss": 0.0182, |
| "step": 5030 |
| }, |
| { |
| "epoch": 17.44, |
| "learning_rate": 1.558577405857741e-05, |
| "loss": 0.0196, |
| "step": 5040 |
| }, |
| { |
| "epoch": 17.47, |
| "learning_rate": 1.5376569037656906e-05, |
| "loss": 0.0272, |
| "step": 5050 |
| }, |
| { |
| "epoch": 17.51, |
| "learning_rate": 1.5167364016736402e-05, |
| "loss": 0.0553, |
| "step": 5060 |
| }, |
| { |
| "epoch": 17.54, |
| "learning_rate": 1.49581589958159e-05, |
| "loss": 0.0745, |
| "step": 5070 |
| }, |
| { |
| "epoch": 17.58, |
| "learning_rate": 1.4748953974895398e-05, |
| "loss": 0.0188, |
| "step": 5080 |
| }, |
| { |
| "epoch": 17.61, |
| "learning_rate": 1.4539748953974896e-05, |
| "loss": 0.0232, |
| "step": 5090 |
| }, |
| { |
| "epoch": 17.65, |
| "learning_rate": 1.4330543933054393e-05, |
| "loss": 0.0239, |
| "step": 5100 |
| }, |
| { |
| "epoch": 17.65, |
| "eval_loss": 0.33433279395103455, |
| "eval_runtime": 67.1079, |
| "eval_samples_per_second": 25.034, |
| "eval_steps_per_second": 25.034, |
| "eval_wer": 0.20860037213148647, |
| "step": 5100 |
| }, |
| { |
| "epoch": 17.68, |
| "learning_rate": 1.412133891213389e-05, |
| "loss": 0.0479, |
| "step": 5110 |
| }, |
| { |
| "epoch": 17.72, |
| "learning_rate": 1.3912133891213388e-05, |
| "loss": 0.0657, |
| "step": 5120 |
| }, |
| { |
| "epoch": 17.75, |
| "learning_rate": 1.370292887029289e-05, |
| "loss": 0.022, |
| "step": 5130 |
| }, |
| { |
| "epoch": 17.79, |
| "learning_rate": 1.3493723849372387e-05, |
| "loss": 0.0307, |
| "step": 5140 |
| }, |
| { |
| "epoch": 17.82, |
| "learning_rate": 1.3284518828451884e-05, |
| "loss": 0.0273, |
| "step": 5150 |
| }, |
| { |
| "epoch": 17.85, |
| "learning_rate": 1.307531380753138e-05, |
| "loss": 0.0628, |
| "step": 5160 |
| }, |
| { |
| "epoch": 17.89, |
| "learning_rate": 1.2866108786610877e-05, |
| "loss": 0.0288, |
| "step": 5170 |
| }, |
| { |
| "epoch": 17.92, |
| "learning_rate": 1.2656903765690378e-05, |
| "loss": 0.0188, |
| "step": 5180 |
| }, |
| { |
| "epoch": 17.96, |
| "learning_rate": 1.2447698744769876e-05, |
| "loss": 0.0185, |
| "step": 5190 |
| }, |
| { |
| "epoch": 17.99, |
| "learning_rate": 1.2238493723849373e-05, |
| "loss": 0.0429, |
| "step": 5200 |
| }, |
| { |
| "epoch": 17.99, |
| "eval_loss": 0.3415924906730652, |
| "eval_runtime": 66.0534, |
| "eval_samples_per_second": 25.434, |
| "eval_steps_per_second": 25.434, |
| "eval_wer": 0.2094962442285163, |
| "step": 5200 |
| }, |
| { |
| "epoch": 18.03, |
| "learning_rate": 1.202928870292887e-05, |
| "loss": 0.039, |
| "step": 5210 |
| }, |
| { |
| "epoch": 18.06, |
| "learning_rate": 1.1820083682008368e-05, |
| "loss": 0.0234, |
| "step": 5220 |
| }, |
| { |
| "epoch": 18.1, |
| "learning_rate": 1.1610878661087866e-05, |
| "loss": 0.0312, |
| "step": 5230 |
| }, |
| { |
| "epoch": 18.13, |
| "learning_rate": 1.1401673640167365e-05, |
| "loss": 0.0277, |
| "step": 5240 |
| }, |
| { |
| "epoch": 18.17, |
| "learning_rate": 1.1192468619246862e-05, |
| "loss": 0.0466, |
| "step": 5250 |
| }, |
| { |
| "epoch": 18.2, |
| "learning_rate": 1.098326359832636e-05, |
| "loss": 0.0438, |
| "step": 5260 |
| }, |
| { |
| "epoch": 18.24, |
| "learning_rate": 1.0774058577405859e-05, |
| "loss": 0.0254, |
| "step": 5270 |
| }, |
| { |
| "epoch": 18.27, |
| "learning_rate": 1.0564853556485357e-05, |
| "loss": 0.0154, |
| "step": 5280 |
| }, |
| { |
| "epoch": 18.3, |
| "learning_rate": 1.0355648535564854e-05, |
| "loss": 0.021, |
| "step": 5290 |
| }, |
| { |
| "epoch": 18.34, |
| "learning_rate": 1.0146443514644352e-05, |
| "loss": 0.0482, |
| "step": 5300 |
| }, |
| { |
| "epoch": 18.34, |
| "eval_loss": 0.3452380895614624, |
| "eval_runtime": 66.2035, |
| "eval_samples_per_second": 25.376, |
| "eval_steps_per_second": 25.376, |
| "eval_wer": 0.21108124870787678, |
| "step": 5300 |
| }, |
| { |
| "epoch": 18.37, |
| "learning_rate": 9.937238493723849e-06, |
| "loss": 0.046, |
| "step": 5310 |
| }, |
| { |
| "epoch": 18.41, |
| "learning_rate": 9.728033472803348e-06, |
| "loss": 0.0245, |
| "step": 5320 |
| }, |
| { |
| "epoch": 18.44, |
| "learning_rate": 9.518828451882846e-06, |
| "loss": 0.0176, |
| "step": 5330 |
| }, |
| { |
| "epoch": 18.48, |
| "learning_rate": 9.309623430962343e-06, |
| "loss": 0.0294, |
| "step": 5340 |
| }, |
| { |
| "epoch": 18.51, |
| "learning_rate": 9.100418410041842e-06, |
| "loss": 0.0508, |
| "step": 5350 |
| }, |
| { |
| "epoch": 18.55, |
| "learning_rate": 8.891213389121338e-06, |
| "loss": 0.0488, |
| "step": 5360 |
| }, |
| { |
| "epoch": 18.58, |
| "learning_rate": 8.682008368200837e-06, |
| "loss": 0.017, |
| "step": 5370 |
| }, |
| { |
| "epoch": 18.62, |
| "learning_rate": 8.472803347280335e-06, |
| "loss": 0.0227, |
| "step": 5380 |
| }, |
| { |
| "epoch": 18.65, |
| "learning_rate": 8.263598326359832e-06, |
| "loss": 0.0224, |
| "step": 5390 |
| }, |
| { |
| "epoch": 18.69, |
| "learning_rate": 8.054393305439332e-06, |
| "loss": 0.0393, |
| "step": 5400 |
| }, |
| { |
| "epoch": 18.69, |
| "eval_loss": 0.3376636207103729, |
| "eval_runtime": 68.3549, |
| "eval_samples_per_second": 24.578, |
| "eval_steps_per_second": 24.578, |
| "eval_wer": 0.20846254565502034, |
| "step": 5400 |
| }, |
| { |
| "epoch": 18.72, |
| "learning_rate": 7.845188284518829e-06, |
| "loss": 0.0325, |
| "step": 5410 |
| }, |
| { |
| "epoch": 18.75, |
| "learning_rate": 7.635983263598326e-06, |
| "loss": 0.0148, |
| "step": 5420 |
| }, |
| { |
| "epoch": 18.79, |
| "learning_rate": 7.426778242677825e-06, |
| "loss": 0.0325, |
| "step": 5430 |
| }, |
| { |
| "epoch": 18.82, |
| "learning_rate": 7.217573221757322e-06, |
| "loss": 0.0178, |
| "step": 5440 |
| }, |
| { |
| "epoch": 18.86, |
| "learning_rate": 7.008368200836821e-06, |
| "loss": 0.0235, |
| "step": 5450 |
| }, |
| { |
| "epoch": 18.89, |
| "learning_rate": 6.799163179916318e-06, |
| "loss": 0.036, |
| "step": 5460 |
| }, |
| { |
| "epoch": 18.93, |
| "learning_rate": 6.5899581589958165e-06, |
| "loss": 0.0128, |
| "step": 5470 |
| }, |
| { |
| "epoch": 18.96, |
| "learning_rate": 6.380753138075314e-06, |
| "loss": 0.0214, |
| "step": 5480 |
| }, |
| { |
| "epoch": 19.0, |
| "learning_rate": 6.171548117154812e-06, |
| "loss": 0.0371, |
| "step": 5490 |
| }, |
| { |
| "epoch": 19.03, |
| "learning_rate": 5.962343096234311e-06, |
| "loss": 0.0483, |
| "step": 5500 |
| }, |
| { |
| "epoch": 19.03, |
| "eval_loss": 0.3440646529197693, |
| "eval_runtime": 74.2605, |
| "eval_samples_per_second": 22.623, |
| "eval_steps_per_second": 22.623, |
| "eval_wer": 0.2077734132726897, |
| "step": 5500 |
| }, |
| { |
| "epoch": 19.07, |
| "learning_rate": 5.753138075313807e-06, |
| "loss": 0.0124, |
| "step": 5510 |
| }, |
| { |
| "epoch": 19.1, |
| "learning_rate": 5.543933054393306e-06, |
| "loss": 0.0109, |
| "step": 5520 |
| }, |
| { |
| "epoch": 19.13, |
| "learning_rate": 5.334728033472804e-06, |
| "loss": 0.0227, |
| "step": 5530 |
| }, |
| { |
| "epoch": 19.17, |
| "learning_rate": 5.125523012552301e-06, |
| "loss": 0.0488, |
| "step": 5540 |
| }, |
| { |
| "epoch": 19.2, |
| "learning_rate": 4.9163179916318e-06, |
| "loss": 0.0356, |
| "step": 5550 |
| }, |
| { |
| "epoch": 19.24, |
| "learning_rate": 4.707112970711297e-06, |
| "loss": 0.0168, |
| "step": 5560 |
| }, |
| { |
| "epoch": 19.27, |
| "learning_rate": 4.497907949790795e-06, |
| "loss": 0.015, |
| "step": 5570 |
| }, |
| { |
| "epoch": 19.31, |
| "learning_rate": 4.288702928870293e-06, |
| "loss": 0.0164, |
| "step": 5580 |
| }, |
| { |
| "epoch": 19.34, |
| "learning_rate": 4.079497907949791e-06, |
| "loss": 0.0661, |
| "step": 5590 |
| }, |
| { |
| "epoch": 19.38, |
| "learning_rate": 3.870292887029289e-06, |
| "loss": 0.0318, |
| "step": 5600 |
| }, |
| { |
| "epoch": 19.38, |
| "eval_loss": 0.3439980149269104, |
| "eval_runtime": 67.418, |
| "eval_samples_per_second": 24.919, |
| "eval_steps_per_second": 24.919, |
| "eval_wer": 0.20694645441389292, |
| "step": 5600 |
| }, |
| { |
| "epoch": 19.41, |
| "learning_rate": 3.6610878661087868e-06, |
| "loss": 0.025, |
| "step": 5610 |
| }, |
| { |
| "epoch": 19.45, |
| "learning_rate": 3.4518828451882847e-06, |
| "loss": 0.0217, |
| "step": 5620 |
| }, |
| { |
| "epoch": 19.48, |
| "learning_rate": 3.2426778242677826e-06, |
| "loss": 0.016, |
| "step": 5630 |
| }, |
| { |
| "epoch": 19.52, |
| "learning_rate": 3.0334728033472805e-06, |
| "loss": 0.0397, |
| "step": 5640 |
| }, |
| { |
| "epoch": 19.55, |
| "learning_rate": 2.8242677824267784e-06, |
| "loss": 0.0299, |
| "step": 5650 |
| }, |
| { |
| "epoch": 19.58, |
| "learning_rate": 2.6150627615062763e-06, |
| "loss": 0.0167, |
| "step": 5660 |
| }, |
| { |
| "epoch": 19.62, |
| "learning_rate": 2.4058577405857742e-06, |
| "loss": 0.0242, |
| "step": 5670 |
| }, |
| { |
| "epoch": 19.65, |
| "learning_rate": 2.1966527196652717e-06, |
| "loss": 0.0148, |
| "step": 5680 |
| }, |
| { |
| "epoch": 19.69, |
| "learning_rate": 1.98744769874477e-06, |
| "loss": 0.0287, |
| "step": 5690 |
| }, |
| { |
| "epoch": 19.72, |
| "learning_rate": 1.778242677824268e-06, |
| "loss": 0.0494, |
| "step": 5700 |
| }, |
| { |
| "epoch": 19.72, |
| "eval_loss": 0.34927651286125183, |
| "eval_runtime": 67.5383, |
| "eval_samples_per_second": 24.875, |
| "eval_steps_per_second": 24.875, |
| "eval_wer": 0.2057749293639308, |
| "step": 5700 |
| }, |
| { |
| "epoch": 19.76, |
| "learning_rate": 1.5690376569037657e-06, |
| "loss": 0.0113, |
| "step": 5710 |
| }, |
| { |
| "epoch": 19.79, |
| "learning_rate": 1.3598326359832638e-06, |
| "loss": 0.0136, |
| "step": 5720 |
| }, |
| { |
| "epoch": 19.83, |
| "learning_rate": 1.1506276150627617e-06, |
| "loss": 0.0234, |
| "step": 5730 |
| }, |
| { |
| "epoch": 19.86, |
| "learning_rate": 9.414225941422595e-07, |
| "loss": 0.0538, |
| "step": 5740 |
| }, |
| { |
| "epoch": 19.9, |
| "learning_rate": 7.322175732217573e-07, |
| "loss": 0.0275, |
| "step": 5750 |
| }, |
| { |
| "epoch": 19.93, |
| "learning_rate": 5.230125523012552e-07, |
| "loss": 0.0167, |
| "step": 5760 |
| }, |
| { |
| "epoch": 19.97, |
| "learning_rate": 3.1380753138075313e-07, |
| "loss": 0.0159, |
| "step": 5770 |
| }, |
| { |
| "epoch": 20.0, |
| "learning_rate": 1.0460251046025104e-07, |
| "loss": 0.0394, |
| "step": 5780 |
| }, |
| { |
| "epoch": 20.0, |
| "step": 5780, |
| "total_flos": 2.627333556202978e+18, |
| "train_loss": 0.40589111629345015, |
| "train_runtime": 8283.4672, |
| "train_samples_per_second": 11.155, |
| "train_steps_per_second": 0.698 |
| } |
| ], |
| "max_steps": 5780, |
| "num_train_epochs": 20, |
| "total_flos": 2.627333556202978e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
