| { | |
| "best_metric": 0.4505438506603241, | |
| "best_model_checkpoint": "ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram/checkpoint-144", | |
| "epoch": 99.99653979238754, | |
| "global_step": 14400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1e-08, | |
| "loss": 0.3265, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2e-08, | |
| "loss": 0.2936, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3e-08, | |
| "loss": 0.3377, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4e-08, | |
| "loss": 0.3115, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.8999999999999995e-08, | |
| "loss": 0.2965, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 5.899999999999999e-08, | |
| "loss": 0.3149, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.9e-08, | |
| "loss": 0.3081, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 7.9e-08, | |
| "loss": 0.3169, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 8.9e-08, | |
| "loss": 0.2917, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.9e-08, | |
| "loss": 0.2992, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 9.993706293706293e-08, | |
| "loss": 0.2906, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.986713286713286e-08, | |
| "loss": 0.2784, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 9.97972027972028e-08, | |
| "loss": 0.2894, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.972727272727273e-08, | |
| "loss": 0.3355, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4505438506603241, | |
| "eval_runtime": 125.645, | |
| "eval_samples_per_second": 4.234, | |
| "eval_steps_per_second": 0.533, | |
| "eval_wer": 0.2119303207559298, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.965734265734266e-08, | |
| "loss": 0.3171, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 9.958741258741257e-08, | |
| "loss": 0.2943, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 9.951748251748252e-08, | |
| "loss": 0.3114, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 9.944755244755244e-08, | |
| "loss": 0.2967, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 9.937762237762237e-08, | |
| "loss": 0.2989, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.93076923076923e-08, | |
| "loss": 0.2854, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 9.923776223776223e-08, | |
| "loss": 0.3102, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.916783216783217e-08, | |
| "loss": 0.3067, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.90979020979021e-08, | |
| "loss": 0.3084, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 9.902797202797203e-08, | |
| "loss": 0.3034, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 9.895804195804194e-08, | |
| "loss": 0.33, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 9.888811188811189e-08, | |
| "loss": 0.3178, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 9.881818181818181e-08, | |
| "loss": 0.3092, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 9.874825174825174e-08, | |
| "loss": 0.3069, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.4508611261844635, | |
| "eval_runtime": 124.4797, | |
| "eval_samples_per_second": 4.274, | |
| "eval_steps_per_second": 0.538, | |
| "eval_wer": 0.21244455871954748, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.867832167832167e-08, | |
| "loss": 0.3261, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.86083916083916e-08, | |
| "loss": 0.2934, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 9.853846153846154e-08, | |
| "loss": 0.2934, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 9.846853146853147e-08, | |
| "loss": 0.3236, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 9.84055944055944e-08, | |
| "loss": 0.3102, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 9.833566433566433e-08, | |
| "loss": 0.3034, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 9.826573426573426e-08, | |
| "loss": 0.3008, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.819580419580419e-08, | |
| "loss": 0.3054, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 9.812587412587412e-08, | |
| "loss": 0.3082, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 9.805594405594405e-08, | |
| "loss": 0.2822, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 9.798601398601398e-08, | |
| "loss": 0.3262, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 9.791608391608392e-08, | |
| "loss": 0.2923, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 9.784615384615385e-08, | |
| "loss": 0.3001, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 9.777622377622378e-08, | |
| "loss": 0.2936, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 9.770629370629369e-08, | |
| "loss": 0.3049, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.45110616087913513, | |
| "eval_runtime": 124.298, | |
| "eval_samples_per_second": 4.28, | |
| "eval_steps_per_second": 0.539, | |
| "eval_wer": 0.2119303207559298, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 9.763636363636363e-08, | |
| "loss": 0.3107, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 9.756643356643356e-08, | |
| "loss": 0.2906, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 9.749650349650349e-08, | |
| "loss": 0.3096, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 9.742657342657342e-08, | |
| "loss": 0.3167, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 9.735664335664336e-08, | |
| "loss": 0.3098, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 9.728671328671329e-08, | |
| "loss": 0.2877, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 9.721678321678322e-08, | |
| "loss": 0.3091, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 9.714685314685315e-08, | |
| "loss": 0.3056, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 9.707692307692307e-08, | |
| "loss": 0.2843, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 9.7006993006993e-08, | |
| "loss": 0.2973, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 9.693706293706293e-08, | |
| "loss": 0.2943, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 9.686713286713286e-08, | |
| "loss": 0.2849, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 9.679720279720279e-08, | |
| "loss": 0.2847, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 9.672727272727273e-08, | |
| "loss": 0.3028, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.45211368799209595, | |
| "eval_runtime": 125.1896, | |
| "eval_samples_per_second": 4.25, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.21141608279231214, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 9.665734265734266e-08, | |
| "loss": 0.318, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 9.658741258741259e-08, | |
| "loss": 0.2967, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 9.651748251748252e-08, | |
| "loss": 0.2939, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 9.644755244755244e-08, | |
| "loss": 0.3009, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 9.637762237762237e-08, | |
| "loss": 0.2922, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 9.63076923076923e-08, | |
| "loss": 0.2946, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 9.623776223776223e-08, | |
| "loss": 0.3112, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 9.616783216783216e-08, | |
| "loss": 0.3101, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 9.60979020979021e-08, | |
| "loss": 0.2973, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 9.602797202797203e-08, | |
| "loss": 0.2952, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 9.595804195804196e-08, | |
| "loss": 0.3323, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 9.588811188811188e-08, | |
| "loss": 0.293, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 9.581818181818181e-08, | |
| "loss": 0.2905, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 9.574825174825174e-08, | |
| "loss": 0.283, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9.567832167832167e-08, | |
| "loss": 0.3092, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.45315271615982056, | |
| "eval_runtime": 124.2517, | |
| "eval_samples_per_second": 4.282, | |
| "eval_steps_per_second": 0.539, | |
| "eval_wer": 0.2111589638105033, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 9.56153846153846e-08, | |
| "loss": 0.3119, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 9.554545454545453e-08, | |
| "loss": 0.2761, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 9.547552447552448e-08, | |
| "loss": 0.3117, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 9.54055944055944e-08, | |
| "loss": 0.31, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 9.533566433566433e-08, | |
| "loss": 0.2987, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 9.526573426573426e-08, | |
| "loss": 0.2952, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 9.519580419580419e-08, | |
| "loss": 0.3025, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 9.512587412587412e-08, | |
| "loss": 0.2963, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 9.505594405594405e-08, | |
| "loss": 0.3028, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 9.498601398601398e-08, | |
| "loss": 0.3098, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 9.49160839160839e-08, | |
| "loss": 0.2962, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 9.484615384615385e-08, | |
| "loss": 0.294, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 9.477622377622377e-08, | |
| "loss": 0.2928, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 9.47062937062937e-08, | |
| "loss": 0.3043, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.45363667607307434, | |
| "eval_runtime": 124.0394, | |
| "eval_samples_per_second": 4.289, | |
| "eval_steps_per_second": 0.54, | |
| "eval_wer": 0.2117374815195732, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 9.463636363636363e-08, | |
| "loss": 0.3254, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 9.456643356643356e-08, | |
| "loss": 0.2964, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 9.449650349650349e-08, | |
| "loss": 0.2846, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 9.442657342657342e-08, | |
| "loss": 0.2963, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 9.435664335664335e-08, | |
| "loss": 0.2863, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 9.428671328671329e-08, | |
| "loss": 0.2902, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 9.421678321678322e-08, | |
| "loss": 0.313, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 9.414685314685314e-08, | |
| "loss": 0.3214, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 9.407692307692307e-08, | |
| "loss": 0.3108, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 9.4006993006993e-08, | |
| "loss": 0.3055, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 9.393706293706293e-08, | |
| "loss": 0.3021, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 9.386713286713286e-08, | |
| "loss": 0.2739, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 9.379720279720279e-08, | |
| "loss": 0.2823, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 9.372727272727272e-08, | |
| "loss": 0.2903, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.45427393913269043, | |
| "eval_runtime": 124.5628, | |
| "eval_samples_per_second": 4.271, | |
| "eval_steps_per_second": 0.538, | |
| "eval_wer": 0.21141608279231214, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 9.365734265734266e-08, | |
| "loss": 0.3251, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 9.358741258741259e-08, | |
| "loss": 0.3057, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 9.351748251748251e-08, | |
| "loss": 0.2984, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 9.344755244755244e-08, | |
| "loss": 0.3178, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 9.337762237762237e-08, | |
| "loss": 0.2961, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 9.33076923076923e-08, | |
| "loss": 0.3056, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 9.323776223776223e-08, | |
| "loss": 0.3043, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 9.316783216783216e-08, | |
| "loss": 0.3135, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 9.309790209790209e-08, | |
| "loss": 0.293, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 9.302797202797203e-08, | |
| "loss": 0.2911, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 9.295804195804196e-08, | |
| "loss": 0.3015, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 9.288811188811188e-08, | |
| "loss": 0.3013, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 9.281818181818181e-08, | |
| "loss": 0.2994, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 9.274825174825175e-08, | |
| "loss": 0.3001, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "learning_rate": 9.267832167832167e-08, | |
| "loss": 0.3124, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.45375916361808777, | |
| "eval_runtime": 125.2241, | |
| "eval_samples_per_second": 4.248, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.2118017612650254, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 9.26083916083916e-08, | |
| "loss": 0.3097, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 9.253846153846153e-08, | |
| "loss": 0.2956, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 9.246853146853147e-08, | |
| "loss": 0.3062, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 9.24055944055944e-08, | |
| "loss": 0.2969, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 9.233566433566433e-08, | |
| "loss": 0.2966, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 9.226573426573426e-08, | |
| "loss": 0.2913, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 9.219580419580419e-08, | |
| "loss": 0.3216, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 9.212587412587413e-08, | |
| "loss": 0.2958, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 9.205594405594406e-08, | |
| "loss": 0.2979, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 9.198601398601398e-08, | |
| "loss": 0.3039, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 9.19160839160839e-08, | |
| "loss": 0.3069, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 9.184615384615385e-08, | |
| "loss": 0.3097, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 9.177622377622377e-08, | |
| "loss": 0.284, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 9.17062937062937e-08, | |
| "loss": 0.3079, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.4540739357471466, | |
| "eval_runtime": 124.6563, | |
| "eval_samples_per_second": 4.268, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.21212315999228643, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 9.163636363636363e-08, | |
| "loss": 0.3217, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 9.156643356643356e-08, | |
| "loss": 0.2947, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 9.14965034965035e-08, | |
| "loss": 0.2962, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 9.142657342657343e-08, | |
| "loss": 0.309, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 9.135664335664335e-08, | |
| "loss": 0.3029, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 9.128671328671327e-08, | |
| "loss": 0.2914, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 9.121678321678322e-08, | |
| "loss": 0.3195, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 9.114685314685314e-08, | |
| "loss": 0.294, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 9.107692307692307e-08, | |
| "loss": 0.2908, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 9.1006993006993e-08, | |
| "loss": 0.2845, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 9.093706293706293e-08, | |
| "loss": 0.3149, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 9.086713286713287e-08, | |
| "loss": 0.2929, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 9.079720279720279e-08, | |
| "loss": 0.3, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 9.072727272727272e-08, | |
| "loss": 0.3184, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 9.065734265734264e-08, | |
| "loss": 0.3093, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.45372533798217773, | |
| "eval_runtime": 124.5898, | |
| "eval_samples_per_second": 4.27, | |
| "eval_steps_per_second": 0.538, | |
| "eval_wer": 0.2117374815195732, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "learning_rate": 9.058741258741259e-08, | |
| "loss": 0.3081, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 9.051748251748251e-08, | |
| "loss": 0.2662, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 10.21, | |
| "learning_rate": 9.044755244755244e-08, | |
| "loss": 0.3141, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 9.037762237762237e-08, | |
| "loss": 0.3076, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 10.35, | |
| "learning_rate": 9.030769230769231e-08, | |
| "loss": 0.3101, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 9.023776223776224e-08, | |
| "loss": 0.3046, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 9.016783216783216e-08, | |
| "loss": 0.3239, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 9.009790209790209e-08, | |
| "loss": 0.3102, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 9.002797202797203e-08, | |
| "loss": 0.2965, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 8.995804195804196e-08, | |
| "loss": 0.3083, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "learning_rate": 8.988811188811188e-08, | |
| "loss": 0.293, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 8.981818181818181e-08, | |
| "loss": 0.3076, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 8.974825174825174e-08, | |
| "loss": 0.2893, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 8.967832167832168e-08, | |
| "loss": 0.3093, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.4544175863265991, | |
| "eval_runtime": 124.7871, | |
| "eval_samples_per_second": 4.263, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.2110946840650511, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 8.960839160839161e-08, | |
| "loss": 0.3053, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 8.953846153846153e-08, | |
| "loss": 0.303, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 11.18, | |
| "learning_rate": 8.946853146853146e-08, | |
| "loss": 0.3016, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "learning_rate": 8.93986013986014e-08, | |
| "loss": 0.3203, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 11.32, | |
| "learning_rate": 8.932867132867133e-08, | |
| "loss": 0.2898, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 11.39, | |
| "learning_rate": 8.925874125874125e-08, | |
| "loss": 0.2814, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 8.918881118881118e-08, | |
| "loss": 0.3191, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 11.53, | |
| "learning_rate": 8.911888111888111e-08, | |
| "loss": 0.3098, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "learning_rate": 8.904895104895105e-08, | |
| "loss": 0.2874, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 11.66, | |
| "learning_rate": 8.897902097902098e-08, | |
| "loss": 0.2959, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 8.89090909090909e-08, | |
| "loss": 0.3104, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 8.883916083916083e-08, | |
| "loss": 0.3159, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "learning_rate": 8.876923076923077e-08, | |
| "loss": 0.2965, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 8.86993006993007e-08, | |
| "loss": 0.3202, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.454854279756546, | |
| "eval_runtime": 123.9841, | |
| "eval_samples_per_second": 4.291, | |
| "eval_steps_per_second": 0.54, | |
| "eval_wer": 0.2110304043195989, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 8.862937062937062e-08, | |
| "loss": 0.2885, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 12.08, | |
| "learning_rate": 8.855944055944055e-08, | |
| "loss": 0.2938, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 8.84895104895105e-08, | |
| "loss": 0.2967, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 12.22, | |
| "learning_rate": 8.841958041958042e-08, | |
| "loss": 0.2927, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 12.29, | |
| "learning_rate": 8.834965034965035e-08, | |
| "loss": 0.3118, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 8.827972027972027e-08, | |
| "loss": 0.3016, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 12.43, | |
| "learning_rate": 8.820979020979021e-08, | |
| "loss": 0.3066, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 8.813986013986014e-08, | |
| "loss": 0.3105, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 12.57, | |
| "learning_rate": 8.806993006993007e-08, | |
| "loss": 0.2786, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 8.8e-08, | |
| "loss": 0.2787, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "learning_rate": 8.793006993006992e-08, | |
| "loss": 0.3091, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 8.786013986013986e-08, | |
| "loss": 0.3016, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "learning_rate": 8.779020979020979e-08, | |
| "loss": 0.2923, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 8.772027972027972e-08, | |
| "loss": 0.2987, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 12.98, | |
| "learning_rate": 8.765034965034964e-08, | |
| "loss": 0.3086, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.45460543036460876, | |
| "eval_runtime": 124.6282, | |
| "eval_samples_per_second": 4.269, | |
| "eval_steps_per_second": 0.538, | |
| "eval_wer": 0.21038760686507682, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 8.758041958041958e-08, | |
| "loss": 0.3237, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 8.751048951048951e-08, | |
| "loss": 0.2848, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 8.744055944055944e-08, | |
| "loss": 0.3026, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 13.26, | |
| "learning_rate": 8.737062937062936e-08, | |
| "loss": 0.307, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 8.730069930069929e-08, | |
| "loss": 0.3074, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 8.723076923076923e-08, | |
| "loss": 0.287, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 8.716083916083916e-08, | |
| "loss": 0.3155, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 13.54, | |
| "learning_rate": 8.709090909090908e-08, | |
| "loss": 0.2844, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 8.7020979020979e-08, | |
| "loss": 0.2906, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 13.68, | |
| "learning_rate": 8.695104895104895e-08, | |
| "loss": 0.3207, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 8.688111888111888e-08, | |
| "loss": 0.3065, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 8.68111888111888e-08, | |
| "loss": 0.2981, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 8.674125874125873e-08, | |
| "loss": 0.3055, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.96, | |
| "learning_rate": 8.667132867132868e-08, | |
| "loss": 0.2947, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.45417994260787964, | |
| "eval_runtime": 125.4546, | |
| "eval_samples_per_second": 4.241, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.2118660410104776, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 8.66013986013986e-08, | |
| "loss": 0.3253, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 8.653146853146853e-08, | |
| "loss": 0.2948, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 14.17, | |
| "learning_rate": 8.646153846153845e-08, | |
| "loss": 0.2984, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 8.639160839160839e-08, | |
| "loss": 0.3073, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 8.632167832167832e-08, | |
| "loss": 0.3093, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 14.37, | |
| "learning_rate": 8.625174825174825e-08, | |
| "loss": 0.2832, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 8.618181818181818e-08, | |
| "loss": 0.2995, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 14.51, | |
| "learning_rate": 8.61118881118881e-08, | |
| "loss": 0.3037, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 14.58, | |
| "learning_rate": 8.604195804195805e-08, | |
| "loss": 0.3084, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 14.65, | |
| "learning_rate": 8.597202797202797e-08, | |
| "loss": 0.3077, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 8.59020979020979e-08, | |
| "loss": 0.3075, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 14.79, | |
| "learning_rate": 8.583216783216782e-08, | |
| "loss": 0.3031, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "learning_rate": 8.576223776223776e-08, | |
| "loss": 0.2753, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 8.569230769230769e-08, | |
| "loss": 0.3041, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 8.562237762237762e-08, | |
| "loss": 0.3145, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.4538927972316742, | |
| "eval_runtime": 124.1864, | |
| "eval_samples_per_second": 4.284, | |
| "eval_steps_per_second": 0.54, | |
| "eval_wer": 0.21148036253776434, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 15.07, | |
| "learning_rate": 8.555244755244754e-08, | |
| "loss": 0.331, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "learning_rate": 8.548251748251747e-08, | |
| "loss": 0.2866, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 15.21, | |
| "learning_rate": 8.541258741258742e-08, | |
| "loss": 0.3192, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 15.28, | |
| "learning_rate": 8.534265734265734e-08, | |
| "loss": 0.315, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 15.35, | |
| "learning_rate": 8.527272727272727e-08, | |
| "loss": 0.2952, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 15.42, | |
| "learning_rate": 8.520279720279719e-08, | |
| "loss": 0.2968, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 15.48, | |
| "learning_rate": 8.513286713286713e-08, | |
| "loss": 0.3148, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 15.55, | |
| "learning_rate": 8.506293706293706e-08, | |
| "loss": 0.2874, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 15.62, | |
| "learning_rate": 8.499300699300699e-08, | |
| "loss": 0.2868, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 15.69, | |
| "learning_rate": 8.492307692307691e-08, | |
| "loss": 0.2961, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 15.76, | |
| "learning_rate": 8.485314685314686e-08, | |
| "loss": 0.3006, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 15.83, | |
| "learning_rate": 8.478321678321679e-08, | |
| "loss": 0.3136, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 8.471328671328671e-08, | |
| "loss": 0.2967, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 8.464335664335664e-08, | |
| "loss": 0.3292, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.45324820280075073, | |
| "eval_runtime": 124.7151, | |
| "eval_samples_per_second": 4.266, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.21148036253776434, | |
| "step": 2304 | |
| }, | |
| { | |
| "epoch": 16.04, | |
| "learning_rate": 8.457342657342657e-08, | |
| "loss": 0.3095, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 16.11, | |
| "learning_rate": 8.45034965034965e-08, | |
| "loss": 0.2971, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 8.443356643356643e-08, | |
| "loss": 0.3044, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "learning_rate": 8.436363636363636e-08, | |
| "loss": 0.3076, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 8.429370629370628e-08, | |
| "loss": 0.2836, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 16.39, | |
| "learning_rate": 8.422377622377623e-08, | |
| "loss": 0.2969, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 16.46, | |
| "learning_rate": 8.415384615384616e-08, | |
| "loss": 0.3067, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 16.53, | |
| "learning_rate": 8.408391608391608e-08, | |
| "loss": 0.32, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 16.6, | |
| "learning_rate": 8.401398601398601e-08, | |
| "loss": 0.3146, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 16.66, | |
| "learning_rate": 8.394405594405594e-08, | |
| "loss": 0.3055, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 16.73, | |
| "learning_rate": 8.387412587412587e-08, | |
| "loss": 0.2949, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 8.38041958041958e-08, | |
| "loss": 0.287, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 16.87, | |
| "learning_rate": 8.373426573426573e-08, | |
| "loss": 0.2937, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 8.366433566433565e-08, | |
| "loss": 0.3049, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.4547367990016937, | |
| "eval_runtime": 124.7967, | |
| "eval_samples_per_second": 4.263, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.21167320177412097, | |
| "step": 2448 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 8.35944055944056e-08, | |
| "loss": 0.3257, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 17.08, | |
| "learning_rate": 8.352447552447552e-08, | |
| "loss": 0.3134, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 17.15, | |
| "learning_rate": 8.345454545454545e-08, | |
| "loss": 0.2877, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 17.22, | |
| "learning_rate": 8.338461538461538e-08, | |
| "loss": 0.2959, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 17.29, | |
| "learning_rate": 8.331468531468531e-08, | |
| "loss": 0.2957, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 17.36, | |
| "learning_rate": 8.324475524475524e-08, | |
| "loss": 0.304, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 17.43, | |
| "learning_rate": 8.317482517482517e-08, | |
| "loss": 0.31, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 8.31048951048951e-08, | |
| "loss": 0.3194, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 17.57, | |
| "learning_rate": 8.303496503496504e-08, | |
| "loss": 0.2908, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "learning_rate": 8.296503496503497e-08, | |
| "loss": 0.2742, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 17.71, | |
| "learning_rate": 8.28951048951049e-08, | |
| "loss": 0.3131, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "learning_rate": 8.282517482517482e-08, | |
| "loss": 0.3145, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 17.84, | |
| "learning_rate": 8.275524475524475e-08, | |
| "loss": 0.2892, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 8.268531468531468e-08, | |
| "loss": 0.3043, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 17.98, | |
| "learning_rate": 8.261538461538461e-08, | |
| "loss": 0.3177, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.4543834626674652, | |
| "eval_runtime": 125.0427, | |
| "eval_samples_per_second": 4.255, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.2110946840650511, | |
| "step": 2592 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "learning_rate": 8.254545454545454e-08, | |
| "loss": 0.3099, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 18.12, | |
| "learning_rate": 8.247552447552447e-08, | |
| "loss": 0.293, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "learning_rate": 8.240559440559441e-08, | |
| "loss": 0.3213, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 18.26, | |
| "learning_rate": 8.233566433566434e-08, | |
| "loss": 0.3018, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 18.33, | |
| "learning_rate": 8.226573426573426e-08, | |
| "loss": 0.3029, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 8.219580419580419e-08, | |
| "loss": 0.2866, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 18.47, | |
| "learning_rate": 8.212587412587412e-08, | |
| "loss": 0.3231, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 18.54, | |
| "learning_rate": 8.205594405594405e-08, | |
| "loss": 0.2897, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "learning_rate": 8.198601398601398e-08, | |
| "loss": 0.3032, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 18.68, | |
| "learning_rate": 8.191608391608391e-08, | |
| "loss": 0.2892, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 8.184615384615385e-08, | |
| "loss": 0.3076, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 18.82, | |
| "learning_rate": 8.177622377622378e-08, | |
| "loss": 0.3015, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 18.89, | |
| "learning_rate": 8.17062937062937e-08, | |
| "loss": 0.2942, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 18.96, | |
| "learning_rate": 8.163636363636363e-08, | |
| "loss": 0.3108, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.45473238825798035, | |
| "eval_runtime": 125.1963, | |
| "eval_samples_per_second": 4.249, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.21135180304685994, | |
| "step": 2736 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 8.156643356643356e-08, | |
| "loss": 0.3028, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 19.1, | |
| "learning_rate": 8.149650349650349e-08, | |
| "loss": 0.2919, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 8.142657342657342e-08, | |
| "loss": 0.2932, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 19.24, | |
| "learning_rate": 8.135664335664335e-08, | |
| "loss": 0.3195, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 19.3, | |
| "learning_rate": 8.128671328671328e-08, | |
| "loss": 0.3012, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 19.37, | |
| "learning_rate": 8.121678321678322e-08, | |
| "loss": 0.2927, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 19.44, | |
| "learning_rate": 8.114685314685315e-08, | |
| "loss": 0.2934, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 19.51, | |
| "learning_rate": 8.107692307692308e-08, | |
| "loss": 0.2991, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 19.58, | |
| "learning_rate": 8.1006993006993e-08, | |
| "loss": 0.3037, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 19.65, | |
| "learning_rate": 8.093706293706293e-08, | |
| "loss": 0.2956, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 8.086713286713286e-08, | |
| "loss": 0.3235, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 19.79, | |
| "learning_rate": 8.079720279720279e-08, | |
| "loss": 0.3024, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 8.072727272727272e-08, | |
| "loss": 0.2904, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 19.93, | |
| "learning_rate": 8.065734265734265e-08, | |
| "loss": 0.3023, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 8.058741258741259e-08, | |
| "loss": 0.2944, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.45603910088539124, | |
| "eval_runtime": 124.5301, | |
| "eval_samples_per_second": 4.272, | |
| "eval_steps_per_second": 0.538, | |
| "eval_wer": 0.21051616635598122, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 20.07, | |
| "learning_rate": 8.051748251748252e-08, | |
| "loss": 0.3124, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 20.14, | |
| "learning_rate": 8.044755244755245e-08, | |
| "loss": 0.2925, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 20.21, | |
| "learning_rate": 8.037762237762237e-08, | |
| "loss": 0.2936, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 20.28, | |
| "learning_rate": 8.03076923076923e-08, | |
| "loss": 0.2922, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 20.35, | |
| "learning_rate": 8.023776223776223e-08, | |
| "loss": 0.286, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 20.42, | |
| "learning_rate": 8.016783216783216e-08, | |
| "loss": 0.2994, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 8.009790209790209e-08, | |
| "loss": 0.3175, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 20.55, | |
| "learning_rate": 8.002797202797203e-08, | |
| "loss": 0.2909, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 20.62, | |
| "learning_rate": 7.995804195804196e-08, | |
| "loss": 0.2971, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 20.69, | |
| "learning_rate": 7.988811188811189e-08, | |
| "loss": 0.2992, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 20.76, | |
| "learning_rate": 7.981818181818182e-08, | |
| "loss": 0.3092, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 7.974825174825174e-08, | |
| "loss": 0.3097, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 20.9, | |
| "learning_rate": 7.967832167832167e-08, | |
| "loss": 0.289, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 20.97, | |
| "learning_rate": 7.96083916083916e-08, | |
| "loss": 0.3232, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.4560084044933319, | |
| "eval_runtime": 125.1707, | |
| "eval_samples_per_second": 4.25, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.21128752330140774, | |
| "step": 3024 | |
| }, | |
| { | |
| "epoch": 21.04, | |
| "learning_rate": 7.953846153846153e-08, | |
| "loss": 0.3218, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 21.11, | |
| "learning_rate": 7.946853146853146e-08, | |
| "loss": 0.2953, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 21.18, | |
| "learning_rate": 7.93986013986014e-08, | |
| "loss": 0.3195, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 21.25, | |
| "learning_rate": 7.932867132867133e-08, | |
| "loss": 0.3144, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 21.32, | |
| "learning_rate": 7.925874125874126e-08, | |
| "loss": 0.3106, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 21.39, | |
| "learning_rate": 7.918881118881119e-08, | |
| "loss": 0.3161, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 21.46, | |
| "learning_rate": 7.911888111888111e-08, | |
| "loss": 0.3224, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 21.53, | |
| "learning_rate": 7.904895104895104e-08, | |
| "loss": 0.298, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 7.897902097902097e-08, | |
| "loss": 0.3036, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 21.66, | |
| "learning_rate": 7.89090909090909e-08, | |
| "loss": 0.2758, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 21.73, | |
| "learning_rate": 7.883916083916083e-08, | |
| "loss": 0.2993, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 21.8, | |
| "learning_rate": 7.876923076923077e-08, | |
| "loss": 0.2969, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 21.87, | |
| "learning_rate": 7.86993006993007e-08, | |
| "loss": 0.31, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 21.94, | |
| "learning_rate": 7.862937062937063e-08, | |
| "loss": 0.3196, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.4558967351913452, | |
| "eval_runtime": 124.6818, | |
| "eval_samples_per_second": 4.267, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.21070900559233785, | |
| "step": 3168 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 7.855944055944056e-08, | |
| "loss": 0.3253, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 7.84895104895105e-08, | |
| "loss": 0.3071, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 22.15, | |
| "learning_rate": 7.841958041958041e-08, | |
| "loss": 0.2848, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 7.834965034965034e-08, | |
| "loss": 0.3256, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 22.29, | |
| "learning_rate": 7.827972027972027e-08, | |
| "loss": 0.2954, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 22.36, | |
| "learning_rate": 7.820979020979021e-08, | |
| "loss": 0.3098, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 22.43, | |
| "learning_rate": 7.813986013986014e-08, | |
| "loss": 0.3216, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "learning_rate": 7.806993006993007e-08, | |
| "loss": 0.3203, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 22.57, | |
| "learning_rate": 7.8e-08, | |
| "loss": 0.3222, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 22.64, | |
| "learning_rate": 7.793006993006993e-08, | |
| "loss": 0.2984, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 22.71, | |
| "learning_rate": 7.786013986013987e-08, | |
| "loss": 0.2926, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 22.78, | |
| "learning_rate": 7.779020979020978e-08, | |
| "loss": 0.3074, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 22.84, | |
| "learning_rate": 7.772027972027971e-08, | |
| "loss": 0.2961, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 22.91, | |
| "learning_rate": 7.765034965034964e-08, | |
| "loss": 0.2952, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 22.98, | |
| "learning_rate": 7.758041958041958e-08, | |
| "loss": 0.3207, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.4562700688838959, | |
| "eval_runtime": 124.7048, | |
| "eval_samples_per_second": 4.266, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.21058044610143345, | |
| "step": 3312 | |
| }, | |
| { | |
| "epoch": 23.06, | |
| "learning_rate": 7.751048951048951e-08, | |
| "loss": 0.3096, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 23.12, | |
| "learning_rate": 7.744055944055944e-08, | |
| "loss": 0.3169, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 7.737062937062937e-08, | |
| "loss": 0.317, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 23.26, | |
| "learning_rate": 7.73006993006993e-08, | |
| "loss": 0.3145, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 23.33, | |
| "learning_rate": 7.723076923076924e-08, | |
| "loss": 0.3007, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 23.4, | |
| "learning_rate": 7.716083916083915e-08, | |
| "loss": 0.3124, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 23.47, | |
| "learning_rate": 7.709090909090908e-08, | |
| "loss": 0.3297, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 23.54, | |
| "learning_rate": 7.702097902097901e-08, | |
| "loss": 0.3184, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 23.61, | |
| "learning_rate": 7.695104895104895e-08, | |
| "loss": 0.3127, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 7.688111888111888e-08, | |
| "loss": 0.3025, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 23.75, | |
| "learning_rate": 7.681118881118881e-08, | |
| "loss": 0.3127, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 23.82, | |
| "learning_rate": 7.674125874125874e-08, | |
| "loss": 0.3018, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 23.89, | |
| "learning_rate": 7.667132867132868e-08, | |
| "loss": 0.2825, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 23.96, | |
| "learning_rate": 7.66013986013986e-08, | |
| "loss": 0.3039, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.4554515779018402, | |
| "eval_runtime": 124.6511, | |
| "eval_samples_per_second": 4.268, | |
| "eval_steps_per_second": 0.538, | |
| "eval_wer": 0.2110304043195989, | |
| "step": 3456 | |
| }, | |
| { | |
| "epoch": 24.03, | |
| "learning_rate": 7.653146853146852e-08, | |
| "loss": 0.3051, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 24.1, | |
| "learning_rate": 7.646153846153845e-08, | |
| "loss": 0.3098, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 24.17, | |
| "learning_rate": 7.639160839160839e-08, | |
| "loss": 0.3121, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 24.24, | |
| "learning_rate": 7.632167832167832e-08, | |
| "loss": 0.324, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 24.3, | |
| "learning_rate": 7.625174825174825e-08, | |
| "loss": 0.2895, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 24.37, | |
| "learning_rate": 7.618181818181818e-08, | |
| "loss": 0.2959, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 24.44, | |
| "learning_rate": 7.611188811188811e-08, | |
| "loss": 0.3209, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 24.51, | |
| "learning_rate": 7.604195804195805e-08, | |
| "loss": 0.3189, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 24.58, | |
| "learning_rate": 7.597202797202796e-08, | |
| "loss": 0.3101, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 24.65, | |
| "learning_rate": 7.590209790209789e-08, | |
| "loss": 0.3033, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 24.72, | |
| "learning_rate": 7.583216783216782e-08, | |
| "loss": 0.3091, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 24.79, | |
| "learning_rate": 7.576223776223776e-08, | |
| "loss": 0.3175, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "learning_rate": 7.569230769230769e-08, | |
| "loss": 0.3065, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 24.93, | |
| "learning_rate": 7.562237762237762e-08, | |
| "loss": 0.2913, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 7.555244755244755e-08, | |
| "loss": 0.3157, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.4560137987136841, | |
| "eval_runtime": 124.3166, | |
| "eval_samples_per_second": 4.279, | |
| "eval_steps_per_second": 0.539, | |
| "eval_wer": 0.21167320177412097, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 25.07, | |
| "learning_rate": 7.548251748251748e-08, | |
| "loss": 0.3334, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 25.14, | |
| "learning_rate": 7.541258741258742e-08, | |
| "loss": 0.3007, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 25.21, | |
| "learning_rate": 7.534265734265733e-08, | |
| "loss": 0.3095, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 7.527272727272726e-08, | |
| "loss": 0.3006, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 25.35, | |
| "learning_rate": 7.520279720279719e-08, | |
| "loss": 0.2973, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 25.42, | |
| "learning_rate": 7.513286713286713e-08, | |
| "loss": 0.3137, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 25.48, | |
| "learning_rate": 7.506293706293706e-08, | |
| "loss": 0.3177, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 25.55, | |
| "learning_rate": 7.499300699300699e-08, | |
| "loss": 0.2962, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 25.62, | |
| "learning_rate": 7.492307692307692e-08, | |
| "loss": 0.3091, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 25.69, | |
| "learning_rate": 7.485314685314686e-08, | |
| "loss": 0.3141, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 25.76, | |
| "learning_rate": 7.478321678321679e-08, | |
| "loss": 0.2974, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 25.83, | |
| "learning_rate": 7.47132867132867e-08, | |
| "loss": 0.3144, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 25.9, | |
| "learning_rate": 7.464335664335663e-08, | |
| "loss": 0.2906, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 25.97, | |
| "learning_rate": 7.457342657342657e-08, | |
| "loss": 0.3285, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.4560698866844177, | |
| "eval_runtime": 124.7729, | |
| "eval_samples_per_second": 4.264, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.2101947676287202, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 26.04, | |
| "learning_rate": 7.45034965034965e-08, | |
| "loss": 0.3154, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 26.11, | |
| "learning_rate": 7.443356643356643e-08, | |
| "loss": 0.2981, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 26.18, | |
| "learning_rate": 7.436363636363636e-08, | |
| "loss": 0.3087, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 26.25, | |
| "learning_rate": 7.429370629370629e-08, | |
| "loss": 0.3152, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 26.32, | |
| "learning_rate": 7.422377622377623e-08, | |
| "loss": 0.2943, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 26.39, | |
| "learning_rate": 7.415384615384616e-08, | |
| "loss": 0.3023, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 26.46, | |
| "learning_rate": 7.408391608391607e-08, | |
| "loss": 0.3037, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 26.53, | |
| "learning_rate": 7.4013986013986e-08, | |
| "loss": 0.3052, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 26.6, | |
| "learning_rate": 7.394405594405594e-08, | |
| "loss": 0.2984, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 26.66, | |
| "learning_rate": 7.387412587412587e-08, | |
| "loss": 0.2993, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 26.73, | |
| "learning_rate": 7.38041958041958e-08, | |
| "loss": 0.314, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 26.8, | |
| "learning_rate": 7.373426573426573e-08, | |
| "loss": 0.3059, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 26.87, | |
| "learning_rate": 7.366433566433566e-08, | |
| "loss": 0.2876, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 26.94, | |
| "learning_rate": 7.35944055944056e-08, | |
| "loss": 0.3125, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.45533081889152527, | |
| "eval_runtime": 125.1519, | |
| "eval_samples_per_second": 4.251, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.21070900559233785, | |
| "step": 3888 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 7.352447552447553e-08, | |
| "loss": 0.3291, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 27.08, | |
| "learning_rate": 7.345454545454544e-08, | |
| "loss": 0.2982, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 27.15, | |
| "learning_rate": 7.338461538461537e-08, | |
| "loss": 0.2939, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 27.22, | |
| "learning_rate": 7.331468531468531e-08, | |
| "loss": 0.3167, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 27.29, | |
| "learning_rate": 7.324475524475524e-08, | |
| "loss": 0.3061, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 7.317482517482517e-08, | |
| "loss": 0.2938, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 27.43, | |
| "learning_rate": 7.31048951048951e-08, | |
| "loss": 0.3175, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "learning_rate": 7.303496503496504e-08, | |
| "loss": 0.295, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 27.57, | |
| "learning_rate": 7.296503496503497e-08, | |
| "loss": 0.303, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 27.64, | |
| "learning_rate": 7.289510489510488e-08, | |
| "loss": 0.2899, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 27.71, | |
| "learning_rate": 7.282517482517481e-08, | |
| "loss": 0.3212, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 27.78, | |
| "learning_rate": 7.275524475524475e-08, | |
| "loss": 0.3078, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 7.268531468531468e-08, | |
| "loss": 0.3001, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "learning_rate": 7.261538461538461e-08, | |
| "loss": 0.3144, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 27.98, | |
| "learning_rate": 7.254545454545454e-08, | |
| "loss": 0.3051, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.45601600408554077, | |
| "eval_runtime": 124.7218, | |
| "eval_samples_per_second": 4.265, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.21032332711962462, | |
| "step": 4032 | |
| }, | |
| { | |
| "epoch": 28.06, | |
| "learning_rate": 7.247552447552447e-08, | |
| "loss": 0.3215, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 28.12, | |
| "learning_rate": 7.240559440559441e-08, | |
| "loss": 0.3026, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 28.19, | |
| "learning_rate": 7.233566433566434e-08, | |
| "loss": 0.3129, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 28.26, | |
| "learning_rate": 7.226573426573425e-08, | |
| "loss": 0.3273, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 28.33, | |
| "learning_rate": 7.219580419580418e-08, | |
| "loss": 0.3012, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 28.4, | |
| "learning_rate": 7.212587412587412e-08, | |
| "loss": 0.3052, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 28.47, | |
| "learning_rate": 7.205594405594405e-08, | |
| "loss": 0.3036, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 28.54, | |
| "learning_rate": 7.198601398601398e-08, | |
| "loss": 0.3165, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 28.61, | |
| "learning_rate": 7.191608391608391e-08, | |
| "loss": 0.3035, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 28.68, | |
| "learning_rate": 7.184615384615384e-08, | |
| "loss": 0.3126, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 28.75, | |
| "learning_rate": 7.177622377622378e-08, | |
| "loss": 0.3221, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 28.82, | |
| "learning_rate": 7.170629370629371e-08, | |
| "loss": 0.3043, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "learning_rate": 7.163636363636362e-08, | |
| "loss": 0.2889, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 7.156643356643355e-08, | |
| "loss": 0.3166, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.45603635907173157, | |
| "eval_runtime": 125.2848, | |
| "eval_samples_per_second": 4.246, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.2102590473741724, | |
| "step": 4176 | |
| }, | |
| { | |
| "epoch": 29.03, | |
| "learning_rate": 7.15034965034965e-08, | |
| "loss": 0.2922, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 29.1, | |
| "learning_rate": 7.143356643356643e-08, | |
| "loss": 0.3043, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 29.17, | |
| "learning_rate": 7.136363636363636e-08, | |
| "loss": 0.2948, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 29.24, | |
| "learning_rate": 7.129370629370629e-08, | |
| "loss": 0.31, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 29.3, | |
| "learning_rate": 7.122377622377622e-08, | |
| "loss": 0.3016, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 29.37, | |
| "learning_rate": 7.115384615384616e-08, | |
| "loss": 0.3072, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 7.108391608391609e-08, | |
| "loss": 0.3162, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 29.51, | |
| "learning_rate": 7.101398601398601e-08, | |
| "loss": 0.309, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 29.58, | |
| "learning_rate": 7.094405594405593e-08, | |
| "loss": 0.3018, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 29.65, | |
| "learning_rate": 7.087412587412587e-08, | |
| "loss": 0.2995, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 29.72, | |
| "learning_rate": 7.08041958041958e-08, | |
| "loss": 0.3232, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 29.79, | |
| "learning_rate": 7.073426573426573e-08, | |
| "loss": 0.3087, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 29.86, | |
| "learning_rate": 7.066433566433566e-08, | |
| "loss": 0.3053, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 29.93, | |
| "learning_rate": 7.05944055944056e-08, | |
| "loss": 0.3152, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 7.052447552447553e-08, | |
| "loss": 0.321, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.45514750480651855, | |
| "eval_runtime": 125.524, | |
| "eval_samples_per_second": 4.238, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.21006620813781576, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 30.07, | |
| "learning_rate": 7.045454545454546e-08, | |
| "loss": 0.3198, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 30.14, | |
| "learning_rate": 7.038461538461538e-08, | |
| "loss": 0.2989, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 30.21, | |
| "learning_rate": 7.031468531468531e-08, | |
| "loss": 0.3201, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 30.28, | |
| "learning_rate": 7.024475524475524e-08, | |
| "loss": 0.3106, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 30.35, | |
| "learning_rate": 7.017482517482517e-08, | |
| "loss": 0.3052, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 30.42, | |
| "learning_rate": 7.01048951048951e-08, | |
| "loss": 0.2948, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 30.48, | |
| "learning_rate": 7.003496503496503e-08, | |
| "loss": 0.3185, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 30.55, | |
| "learning_rate": 6.996503496503497e-08, | |
| "loss": 0.3055, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 30.62, | |
| "learning_rate": 6.98951048951049e-08, | |
| "loss": 0.2938, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 30.69, | |
| "learning_rate": 6.982517482517483e-08, | |
| "loss": 0.3115, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 30.76, | |
| "learning_rate": 6.975524475524475e-08, | |
| "loss": 0.3253, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 30.83, | |
| "learning_rate": 6.968531468531468e-08, | |
| "loss": 0.2925, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 30.9, | |
| "learning_rate": 6.961538461538461e-08, | |
| "loss": 0.3013, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 30.97, | |
| "learning_rate": 6.954545454545454e-08, | |
| "loss": 0.3146, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 0.45516493916511536, | |
| "eval_runtime": 124.7588, | |
| "eval_samples_per_second": 4.264, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.21000192839236356, | |
| "step": 4464 | |
| }, | |
| { | |
| "epoch": 31.04, | |
| "learning_rate": 6.947552447552447e-08, | |
| "loss": 0.3219, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 31.11, | |
| "learning_rate": 6.94055944055944e-08, | |
| "loss": 0.3089, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 31.18, | |
| "learning_rate": 6.933566433566434e-08, | |
| "loss": 0.3014, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 31.25, | |
| "learning_rate": 6.926573426573427e-08, | |
| "loss": 0.3128, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 31.32, | |
| "learning_rate": 6.91958041958042e-08, | |
| "loss": 0.2938, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 31.39, | |
| "learning_rate": 6.912587412587411e-08, | |
| "loss": 0.2748, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 31.46, | |
| "learning_rate": 6.905594405594405e-08, | |
| "loss": 0.3006, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 31.53, | |
| "learning_rate": 6.898601398601398e-08, | |
| "loss": 0.2995, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 31.6, | |
| "learning_rate": 6.891608391608391e-08, | |
| "loss": 0.3053, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 31.66, | |
| "learning_rate": 6.884615384615384e-08, | |
| "loss": 0.2982, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 31.73, | |
| "learning_rate": 6.877622377622378e-08, | |
| "loss": 0.3137, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 31.8, | |
| "learning_rate": 6.870629370629371e-08, | |
| "loss": 0.3082, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 31.87, | |
| "learning_rate": 6.863636363636364e-08, | |
| "loss": 0.2906, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 31.94, | |
| "learning_rate": 6.856643356643357e-08, | |
| "loss": 0.323, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 0.455118864774704, | |
| "eval_runtime": 124.8626, | |
| "eval_samples_per_second": 4.261, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.21045188661052902, | |
| "step": 4608 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 6.84965034965035e-08, | |
| "loss": 0.3277, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 32.08, | |
| "learning_rate": 6.842657342657342e-08, | |
| "loss": 0.3165, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 32.15, | |
| "learning_rate": 6.835664335664335e-08, | |
| "loss": 0.2931, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 32.22, | |
| "learning_rate": 6.828671328671328e-08, | |
| "loss": 0.3201, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 32.29, | |
| "learning_rate": 6.821678321678321e-08, | |
| "loss": 0.3135, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 32.36, | |
| "learning_rate": 6.814685314685315e-08, | |
| "loss": 0.3095, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 32.43, | |
| "learning_rate": 6.807692307692308e-08, | |
| "loss": 0.3221, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "learning_rate": 6.800699300699301e-08, | |
| "loss": 0.2995, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 32.57, | |
| "learning_rate": 6.793706293706294e-08, | |
| "loss": 0.2911, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 32.64, | |
| "learning_rate": 6.786713286713286e-08, | |
| "loss": 0.2947, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 32.71, | |
| "learning_rate": 6.779720279720279e-08, | |
| "loss": 0.3102, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 32.78, | |
| "learning_rate": 6.772727272727272e-08, | |
| "loss": 0.3051, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 32.84, | |
| "learning_rate": 6.765734265734265e-08, | |
| "loss": 0.2989, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 32.91, | |
| "learning_rate": 6.758741258741258e-08, | |
| "loss": 0.2823, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 32.98, | |
| "learning_rate": 6.751748251748252e-08, | |
| "loss": 0.3223, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 0.4553714394569397, | |
| "eval_runtime": 124.7302, | |
| "eval_samples_per_second": 4.265, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.21006620813781576, | |
| "step": 4752 | |
| }, | |
| { | |
| "epoch": 33.06, | |
| "learning_rate": 6.744755244755245e-08, | |
| "loss": 0.3246, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 33.12, | |
| "learning_rate": 6.737762237762238e-08, | |
| "loss": 0.292, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "learning_rate": 6.73076923076923e-08, | |
| "loss": 0.3096, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 33.26, | |
| "learning_rate": 6.723776223776223e-08, | |
| "loss": 0.3122, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 6.716783216783216e-08, | |
| "loss": 0.3033, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 33.4, | |
| "learning_rate": 6.709790209790209e-08, | |
| "loss": 0.3089, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 33.47, | |
| "learning_rate": 6.702797202797202e-08, | |
| "loss": 0.3257, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 33.54, | |
| "learning_rate": 6.695804195804196e-08, | |
| "loss": 0.3204, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 33.61, | |
| "learning_rate": 6.688811188811189e-08, | |
| "loss": 0.3, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 33.68, | |
| "learning_rate": 6.681818181818182e-08, | |
| "loss": 0.2929, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 33.75, | |
| "learning_rate": 6.674825174825175e-08, | |
| "loss": 0.3148, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 33.82, | |
| "learning_rate": 6.667832167832168e-08, | |
| "loss": 0.2944, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 33.89, | |
| "learning_rate": 6.66083916083916e-08, | |
| "loss": 0.2877, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 33.96, | |
| "learning_rate": 6.653846153846153e-08, | |
| "loss": 0.3105, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 0.45485761761665344, | |
| "eval_runtime": 125.0143, | |
| "eval_samples_per_second": 4.256, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.2101947676287202, | |
| "step": 4896 | |
| }, | |
| { | |
| "epoch": 34.03, | |
| "learning_rate": 6.646853146853146e-08, | |
| "loss": 0.3325, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 34.1, | |
| "learning_rate": 6.639860139860139e-08, | |
| "loss": 0.3061, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 34.17, | |
| "learning_rate": 6.632867132867133e-08, | |
| "loss": 0.2963, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 34.24, | |
| "learning_rate": 6.625874125874126e-08, | |
| "loss": 0.3217, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 34.3, | |
| "learning_rate": 6.618881118881119e-08, | |
| "loss": 0.2963, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 34.37, | |
| "learning_rate": 6.611888111888112e-08, | |
| "loss": 0.2936, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 34.44, | |
| "learning_rate": 6.604895104895105e-08, | |
| "loss": 0.3294, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 34.51, | |
| "learning_rate": 6.597902097902097e-08, | |
| "loss": 0.2936, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 34.58, | |
| "learning_rate": 6.59090909090909e-08, | |
| "loss": 0.2964, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 34.65, | |
| "learning_rate": 6.583916083916083e-08, | |
| "loss": 0.287, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 34.72, | |
| "learning_rate": 6.576923076923076e-08, | |
| "loss": 0.333, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 34.79, | |
| "learning_rate": 6.56993006993007e-08, | |
| "loss": 0.3139, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 34.86, | |
| "learning_rate": 6.562937062937063e-08, | |
| "loss": 0.2905, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 34.93, | |
| "learning_rate": 6.555944055944056e-08, | |
| "loss": 0.2926, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 6.548951048951049e-08, | |
| "loss": 0.3134, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 0.455160528421402, | |
| "eval_runtime": 124.7318, | |
| "eval_samples_per_second": 4.265, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.210130487883268, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 35.07, | |
| "learning_rate": 6.541958041958042e-08, | |
| "loss": 0.326, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 35.14, | |
| "learning_rate": 6.534965034965034e-08, | |
| "loss": 0.2994, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 35.21, | |
| "learning_rate": 6.527972027972027e-08, | |
| "loss": 0.3064, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 35.28, | |
| "learning_rate": 6.52097902097902e-08, | |
| "loss": 0.3143, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 35.35, | |
| "learning_rate": 6.513986013986014e-08, | |
| "loss": 0.3084, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 35.42, | |
| "learning_rate": 6.506993006993007e-08, | |
| "loss": 0.3019, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 35.48, | |
| "learning_rate": 6.5e-08, | |
| "loss": 0.3311, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 35.55, | |
| "learning_rate": 6.493006993006993e-08, | |
| "loss": 0.2954, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 35.62, | |
| "learning_rate": 6.486013986013986e-08, | |
| "loss": 0.2935, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 35.69, | |
| "learning_rate": 6.479020979020979e-08, | |
| "loss": 0.313, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 35.76, | |
| "learning_rate": 6.472027972027971e-08, | |
| "loss": 0.3091, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 35.83, | |
| "learning_rate": 6.465034965034964e-08, | |
| "loss": 0.3088, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 35.9, | |
| "learning_rate": 6.458041958041957e-08, | |
| "loss": 0.3053, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 35.97, | |
| "learning_rate": 6.451048951048951e-08, | |
| "loss": 0.3054, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 0.45497918128967285, | |
| "eval_runtime": 125.1007, | |
| "eval_samples_per_second": 4.253, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.2102590473741724, | |
| "step": 5184 | |
| }, | |
| { | |
| "epoch": 36.04, | |
| "learning_rate": 6.444055944055944e-08, | |
| "loss": 0.3189, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 36.11, | |
| "learning_rate": 6.437062937062937e-08, | |
| "loss": 0.305, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 36.18, | |
| "learning_rate": 6.43006993006993e-08, | |
| "loss": 0.3042, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 36.25, | |
| "learning_rate": 6.423076923076923e-08, | |
| "loss": 0.3064, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 36.32, | |
| "learning_rate": 6.416083916083916e-08, | |
| "loss": 0.3035, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 36.39, | |
| "learning_rate": 6.409090909090908e-08, | |
| "loss": 0.2824, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 36.46, | |
| "learning_rate": 6.402097902097901e-08, | |
| "loss": 0.3349, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 36.53, | |
| "learning_rate": 6.395104895104894e-08, | |
| "loss": 0.3118, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 36.6, | |
| "learning_rate": 6.388111888111888e-08, | |
| "loss": 0.2959, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 36.66, | |
| "learning_rate": 6.381118881118881e-08, | |
| "loss": 0.3248, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 36.73, | |
| "learning_rate": 6.374125874125874e-08, | |
| "loss": 0.3058, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 36.8, | |
| "learning_rate": 6.367132867132867e-08, | |
| "loss": 0.3024, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 36.87, | |
| "learning_rate": 6.360139860139861e-08, | |
| "loss": 0.3061, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 36.94, | |
| "learning_rate": 6.353146853146853e-08, | |
| "loss": 0.3162, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 0.45536696910858154, | |
| "eval_runtime": 124.8299, | |
| "eval_samples_per_second": 4.262, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.21064472584688565, | |
| "step": 5328 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 6.346153846153845e-08, | |
| "loss": 0.3289, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 37.08, | |
| "learning_rate": 6.339160839160838e-08, | |
| "loss": 0.3126, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 37.15, | |
| "learning_rate": 6.332167832167832e-08, | |
| "loss": 0.3065, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 37.22, | |
| "learning_rate": 6.325174825174825e-08, | |
| "loss": 0.3321, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 37.29, | |
| "learning_rate": 6.318181818181818e-08, | |
| "loss": 0.2904, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 37.36, | |
| "learning_rate": 6.311188811188811e-08, | |
| "loss": 0.3142, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 37.43, | |
| "learning_rate": 6.304195804195804e-08, | |
| "loss": 0.3071, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 6.297202797202798e-08, | |
| "loss": 0.3065, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 37.57, | |
| "learning_rate": 6.29020979020979e-08, | |
| "loss": 0.2882, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 37.64, | |
| "learning_rate": 6.283216783216782e-08, | |
| "loss": 0.2924, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 37.71, | |
| "learning_rate": 6.276223776223775e-08, | |
| "loss": 0.308, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 37.78, | |
| "learning_rate": 6.26923076923077e-08, | |
| "loss": 0.3204, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 37.84, | |
| "learning_rate": 6.262237762237762e-08, | |
| "loss": 0.2947, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 37.91, | |
| "learning_rate": 6.255244755244755e-08, | |
| "loss": 0.3001, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 37.98, | |
| "learning_rate": 6.248251748251748e-08, | |
| "loss": 0.3094, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 0.45511770248413086, | |
| "eval_runtime": 124.8613, | |
| "eval_samples_per_second": 4.261, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.20987336890145916, | |
| "step": 5472 | |
| }, | |
| { | |
| "epoch": 38.06, | |
| "learning_rate": 6.241258741258741e-08, | |
| "loss": 0.3229, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 38.12, | |
| "learning_rate": 6.234265734265734e-08, | |
| "loss": 0.3057, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 38.19, | |
| "learning_rate": 6.227272727272726e-08, | |
| "loss": 0.311, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 38.26, | |
| "learning_rate": 6.220279720279719e-08, | |
| "loss": 0.2936, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 38.33, | |
| "learning_rate": 6.213286713286712e-08, | |
| "loss": 0.289, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 38.4, | |
| "learning_rate": 6.206293706293706e-08, | |
| "loss": 0.3014, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 38.47, | |
| "learning_rate": 6.199300699300699e-08, | |
| "loss": 0.3114, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 38.54, | |
| "learning_rate": 6.192307692307692e-08, | |
| "loss": 0.2931, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 38.61, | |
| "learning_rate": 6.185314685314685e-08, | |
| "loss": 0.3096, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 38.68, | |
| "learning_rate": 6.178321678321679e-08, | |
| "loss": 0.3113, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 38.75, | |
| "learning_rate": 6.17132867132867e-08, | |
| "loss": 0.3197, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 38.82, | |
| "learning_rate": 6.164335664335663e-08, | |
| "loss": 0.3017, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 38.89, | |
| "learning_rate": 6.157342657342656e-08, | |
| "loss": 0.282, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 38.96, | |
| "learning_rate": 6.15034965034965e-08, | |
| "loss": 0.3174, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 0.4552527070045471, | |
| "eval_runtime": 125.1162, | |
| "eval_samples_per_second": 4.252, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.21051616635598122, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 39.03, | |
| "learning_rate": 6.143356643356643e-08, | |
| "loss": 0.3242, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 39.1, | |
| "learning_rate": 6.136363636363636e-08, | |
| "loss": 0.3017, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 39.17, | |
| "learning_rate": 6.129370629370629e-08, | |
| "loss": 0.3194, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 39.24, | |
| "learning_rate": 6.122377622377622e-08, | |
| "loss": 0.3173, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 39.3, | |
| "learning_rate": 6.115384615384616e-08, | |
| "loss": 0.301, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 39.37, | |
| "learning_rate": 6.108391608391608e-08, | |
| "loss": 0.286, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 39.44, | |
| "learning_rate": 6.1013986013986e-08, | |
| "loss": 0.3003, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 39.51, | |
| "learning_rate": 6.094405594405593e-08, | |
| "loss": 0.3198, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 39.58, | |
| "learning_rate": 6.087412587412587e-08, | |
| "loss": 0.2933, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 39.65, | |
| "learning_rate": 6.08041958041958e-08, | |
| "loss": 0.3132, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 39.72, | |
| "learning_rate": 6.073426573426573e-08, | |
| "loss": 0.3093, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 39.79, | |
| "learning_rate": 6.066433566433566e-08, | |
| "loss": 0.2969, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 39.86, | |
| "learning_rate": 6.059440559440559e-08, | |
| "loss": 0.2997, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 39.93, | |
| "learning_rate": 6.052447552447553e-08, | |
| "loss": 0.309, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 6.045454545454545e-08, | |
| "loss": 0.3218, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 0.45527562499046326, | |
| "eval_runtime": 124.7062, | |
| "eval_samples_per_second": 4.266, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.21064472584688565, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 40.07, | |
| "learning_rate": 6.038461538461537e-08, | |
| "loss": 0.3171, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 40.14, | |
| "learning_rate": 6.03146853146853e-08, | |
| "loss": 0.3063, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 40.21, | |
| "learning_rate": 6.024475524475524e-08, | |
| "loss": 0.3026, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 40.28, | |
| "learning_rate": 6.017482517482517e-08, | |
| "loss": 0.3062, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 40.35, | |
| "learning_rate": 6.01048951048951e-08, | |
| "loss": 0.3005, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 40.42, | |
| "learning_rate": 6.003496503496503e-08, | |
| "loss": 0.2984, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 40.48, | |
| "learning_rate": 5.996503496503497e-08, | |
| "loss": 0.3114, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 40.55, | |
| "learning_rate": 5.98951048951049e-08, | |
| "loss": 0.2973, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 40.62, | |
| "learning_rate": 5.982517482517482e-08, | |
| "loss": 0.2944, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 40.69, | |
| "learning_rate": 5.975524475524474e-08, | |
| "loss": 0.3022, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 40.76, | |
| "learning_rate": 5.968531468531469e-08, | |
| "loss": 0.3308, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 40.83, | |
| "learning_rate": 5.961538461538461e-08, | |
| "loss": 0.303, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 40.9, | |
| "learning_rate": 5.954545454545454e-08, | |
| "loss": 0.3076, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 40.97, | |
| "learning_rate": 5.947552447552447e-08, | |
| "loss": 0.3134, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 0.4552476704120636, | |
| "eval_runtime": 125.4458, | |
| "eval_samples_per_second": 4.241, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.210130487883268, | |
| "step": 5904 | |
| }, | |
| { | |
| "epoch": 41.04, | |
| "learning_rate": 5.940559440559441e-08, | |
| "loss": 0.3269, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 41.11, | |
| "learning_rate": 5.9335664335664335e-08, | |
| "loss": 0.3187, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 41.18, | |
| "learning_rate": 5.926573426573427e-08, | |
| "loss": 0.3081, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 41.25, | |
| "learning_rate": 5.9195804195804186e-08, | |
| "loss": 0.3103, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 41.32, | |
| "learning_rate": 5.912587412587412e-08, | |
| "loss": 0.3, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 41.39, | |
| "learning_rate": 5.905594405594405e-08, | |
| "loss": 0.2945, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 41.46, | |
| "learning_rate": 5.8986013986013985e-08, | |
| "loss": 0.2946, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 41.53, | |
| "learning_rate": 5.891608391608391e-08, | |
| "loss": 0.3034, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 41.6, | |
| "learning_rate": 5.884615384615385e-08, | |
| "loss": 0.3125, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 41.66, | |
| "learning_rate": 5.877622377622378e-08, | |
| "loss": 0.3103, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 41.73, | |
| "learning_rate": 5.8706293706293705e-08, | |
| "loss": 0.3194, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 41.8, | |
| "learning_rate": 5.863636363636363e-08, | |
| "loss": 0.3034, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 41.87, | |
| "learning_rate": 5.856643356643356e-08, | |
| "loss": 0.2802, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 41.94, | |
| "learning_rate": 5.849650349650349e-08, | |
| "loss": 0.3019, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 0.45515522360801697, | |
| "eval_runtime": 124.7476, | |
| "eval_samples_per_second": 4.265, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.210130487883268, | |
| "step": 6048 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 5.842657342657342e-08, | |
| "loss": 0.3301, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 42.08, | |
| "learning_rate": 5.8356643356643355e-08, | |
| "loss": 0.3072, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 42.15, | |
| "learning_rate": 5.828671328671328e-08, | |
| "loss": 0.2945, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 42.22, | |
| "learning_rate": 5.821678321678322e-08, | |
| "loss": 0.3046, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 42.29, | |
| "learning_rate": 5.814685314685315e-08, | |
| "loss": 0.3039, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 42.36, | |
| "learning_rate": 5.807692307692308e-08, | |
| "loss": 0.3063, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 42.43, | |
| "learning_rate": 5.8006993006993e-08, | |
| "loss": 0.3227, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 42.5, | |
| "learning_rate": 5.793706293706293e-08, | |
| "loss": 0.3166, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 42.57, | |
| "learning_rate": 5.786713286713286e-08, | |
| "loss": 0.2964, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 42.64, | |
| "learning_rate": 5.7797202797202796e-08, | |
| "loss": 0.291, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 42.71, | |
| "learning_rate": 5.7727272727272724e-08, | |
| "loss": 0.3238, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 42.78, | |
| "learning_rate": 5.765734265734265e-08, | |
| "loss": 0.3122, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 42.84, | |
| "learning_rate": 5.758741258741259e-08, | |
| "loss": 0.3016, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 42.91, | |
| "learning_rate": 5.7517482517482517e-08, | |
| "loss": 0.3022, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 42.98, | |
| "learning_rate": 5.744755244755245e-08, | |
| "loss": 0.3169, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 0.45521482825279236, | |
| "eval_runtime": 124.9253, | |
| "eval_samples_per_second": 4.259, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.2094876904287459, | |
| "step": 6192 | |
| }, | |
| { | |
| "epoch": 43.06, | |
| "learning_rate": 5.737762237762237e-08, | |
| "loss": 0.3154, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 43.12, | |
| "learning_rate": 5.73076923076923e-08, | |
| "loss": 0.2931, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 43.19, | |
| "learning_rate": 5.723776223776223e-08, | |
| "loss": 0.3138, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 43.26, | |
| "learning_rate": 5.7167832167832166e-08, | |
| "loss": 0.3008, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 43.33, | |
| "learning_rate": 5.7097902097902094e-08, | |
| "loss": 0.307, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 43.4, | |
| "learning_rate": 5.702797202797203e-08, | |
| "loss": 0.29, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 43.47, | |
| "learning_rate": 5.695804195804196e-08, | |
| "loss": 0.318, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 43.54, | |
| "learning_rate": 5.6888111888111886e-08, | |
| "loss": 0.3169, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 43.61, | |
| "learning_rate": 5.681818181818182e-08, | |
| "loss": 0.2977, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 43.68, | |
| "learning_rate": 5.6748251748251744e-08, | |
| "loss": 0.2999, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 43.75, | |
| "learning_rate": 5.667832167832167e-08, | |
| "loss": 0.306, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 43.82, | |
| "learning_rate": 5.66083916083916e-08, | |
| "loss": 0.297, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 43.89, | |
| "learning_rate": 5.6538461538461536e-08, | |
| "loss": 0.3025, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 43.96, | |
| "learning_rate": 5.6468531468531464e-08, | |
| "loss": 0.3209, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 0.455024391412735, | |
| "eval_runtime": 125.1171, | |
| "eval_samples_per_second": 4.252, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.20903773221058045, | |
| "step": 6336 | |
| }, | |
| { | |
| "epoch": 44.03, | |
| "learning_rate": 5.63986013986014e-08, | |
| "loss": 0.3088, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 44.1, | |
| "learning_rate": 5.632867132867133e-08, | |
| "loss": 0.3, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 44.17, | |
| "learning_rate": 5.625874125874126e-08, | |
| "loss": 0.311, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 44.24, | |
| "learning_rate": 5.618881118881119e-08, | |
| "loss": 0.3261, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 44.3, | |
| "learning_rate": 5.6118881118881113e-08, | |
| "loss": 0.2959, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 44.37, | |
| "learning_rate": 5.604895104895104e-08, | |
| "loss": 0.2956, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "learning_rate": 5.597902097902098e-08, | |
| "loss": 0.3096, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 44.51, | |
| "learning_rate": 5.5909090909090906e-08, | |
| "loss": 0.3158, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 44.58, | |
| "learning_rate": 5.5839160839160834e-08, | |
| "loss": 0.2997, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 44.65, | |
| "learning_rate": 5.576923076923077e-08, | |
| "loss": 0.2955, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 44.72, | |
| "learning_rate": 5.56993006993007e-08, | |
| "loss": 0.2991, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 44.79, | |
| "learning_rate": 5.562937062937063e-08, | |
| "loss": 0.3, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 44.86, | |
| "learning_rate": 5.555944055944056e-08, | |
| "loss": 0.2895, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 44.93, | |
| "learning_rate": 5.5489510489510483e-08, | |
| "loss": 0.3117, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 5.541958041958041e-08, | |
| "loss": 0.3035, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 0.4550085663795471, | |
| "eval_runtime": 124.8581, | |
| "eval_samples_per_second": 4.261, | |
| "eval_steps_per_second": 0.537, | |
| "eval_wer": 0.21000192839236356, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 45.07, | |
| "learning_rate": 5.534965034965035e-08, | |
| "loss": 0.3058, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 45.14, | |
| "learning_rate": 5.5279720279720275e-08, | |
| "loss": 0.2872, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 45.21, | |
| "learning_rate": 5.520979020979021e-08, | |
| "loss": 0.3062, | |
| "step": 6510 | |
| }, | |
| { | |
| "epoch": 45.28, | |
| "learning_rate": 5.513986013986014e-08, | |
| "loss": 0.3075, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 45.35, | |
| "learning_rate": 5.506993006993007e-08, | |
| "loss": 0.3009, | |
| "step": 6530 | |
| }, | |
| { | |
| "epoch": 45.42, | |
| "learning_rate": 5.5e-08, | |
| "loss": 0.3048, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 45.48, | |
| "learning_rate": 5.4930069930069925e-08, | |
| "loss": 0.3214, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 45.55, | |
| "learning_rate": 5.486013986013985e-08, | |
| "loss": 0.3041, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 45.62, | |
| "learning_rate": 5.479020979020978e-08, | |
| "loss": 0.302, | |
| "step": 6570 | |
| }, | |
| { | |
| "epoch": 45.69, | |
| "learning_rate": 5.472027972027972e-08, | |
| "loss": 0.318, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 45.76, | |
| "learning_rate": 5.4650349650349645e-08, | |
| "loss": 0.3125, | |
| "step": 6590 | |
| }, | |
| { | |
| "epoch": 45.83, | |
| "learning_rate": 5.458041958041958e-08, | |
| "loss": 0.3042, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 45.9, | |
| "learning_rate": 5.451048951048951e-08, | |
| "loss": 0.3026, | |
| "step": 6610 | |
| }, | |
| { | |
| "epoch": 45.97, | |
| "learning_rate": 5.4440559440559444e-08, | |
| "loss": 0.3181, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 0.4549944996833801, | |
| "eval_runtime": 126.527, | |
| "eval_samples_per_second": 4.205, | |
| "eval_steps_per_second": 0.53, | |
| "eval_wer": 0.21038760686507682, | |
| "step": 6624 | |
| }, | |
| { | |
| "epoch": 46.04, | |
| "learning_rate": 5.437062937062937e-08, | |
| "loss": 0.3249, | |
| "step": 6630 | |
| }, | |
| { | |
| "epoch": 46.11, | |
| "learning_rate": 5.4300699300699295e-08, | |
| "loss": 0.3154, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 46.18, | |
| "learning_rate": 5.423076923076922e-08, | |
| "loss": 0.3056, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 46.25, | |
| "learning_rate": 5.416083916083916e-08, | |
| "loss": 0.3066, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 46.32, | |
| "learning_rate": 5.409090909090909e-08, | |
| "loss": 0.3126, | |
| "step": 6670 | |
| }, | |
| { | |
| "epoch": 46.39, | |
| "learning_rate": 5.4020979020979015e-08, | |
| "loss": 0.296, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 46.46, | |
| "learning_rate": 5.395104895104895e-08, | |
| "loss": 0.3179, | |
| "step": 6690 | |
| }, | |
| { | |
| "epoch": 46.53, | |
| "learning_rate": 5.388111888111888e-08, | |
| "loss": 0.2977, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 46.6, | |
| "learning_rate": 5.3811188811188814e-08, | |
| "loss": 0.2954, | |
| "step": 6710 | |
| }, | |
| { | |
| "epoch": 46.66, | |
| "learning_rate": 5.374125874125874e-08, | |
| "loss": 0.3088, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 46.73, | |
| "learning_rate": 5.3671328671328665e-08, | |
| "loss": 0.3116, | |
| "step": 6730 | |
| }, | |
| { | |
| "epoch": 46.8, | |
| "learning_rate": 5.360139860139859e-08, | |
| "loss": 0.3034, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 46.87, | |
| "learning_rate": 5.353146853146853e-08, | |
| "loss": 0.2882, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 46.94, | |
| "learning_rate": 5.3461538461538457e-08, | |
| "loss": 0.3133, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 0.4546278417110443, | |
| "eval_runtime": 126.0526, | |
| "eval_samples_per_second": 4.22, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.2096162499196503, | |
| "step": 6768 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 5.339160839160839e-08, | |
| "loss": 0.3183, | |
| "step": 6770 | |
| }, | |
| { | |
| "epoch": 47.08, | |
| "learning_rate": 5.332167832167832e-08, | |
| "loss": 0.3128, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 47.15, | |
| "learning_rate": 5.325174825174825e-08, | |
| "loss": 0.2944, | |
| "step": 6790 | |
| }, | |
| { | |
| "epoch": 47.22, | |
| "learning_rate": 5.3181818181818184e-08, | |
| "loss": 0.3211, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 47.29, | |
| "learning_rate": 5.311188811188811e-08, | |
| "loss": 0.2992, | |
| "step": 6810 | |
| }, | |
| { | |
| "epoch": 47.36, | |
| "learning_rate": 5.3041958041958034e-08, | |
| "loss": 0.293, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 47.43, | |
| "learning_rate": 5.297202797202796e-08, | |
| "loss": 0.3071, | |
| "step": 6830 | |
| }, | |
| { | |
| "epoch": 47.5, | |
| "learning_rate": 5.29020979020979e-08, | |
| "loss": 0.3085, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 47.57, | |
| "learning_rate": 5.2832167832167827e-08, | |
| "loss": 0.304, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 47.64, | |
| "learning_rate": 5.276223776223776e-08, | |
| "loss": 0.2849, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 47.71, | |
| "learning_rate": 5.269230769230769e-08, | |
| "loss": 0.3098, | |
| "step": 6870 | |
| }, | |
| { | |
| "epoch": 47.78, | |
| "learning_rate": 5.2622377622377625e-08, | |
| "loss": 0.3013, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 47.84, | |
| "learning_rate": 5.2552447552447554e-08, | |
| "loss": 0.299, | |
| "step": 6890 | |
| }, | |
| { | |
| "epoch": 47.91, | |
| "learning_rate": 5.248251748251748e-08, | |
| "loss": 0.2936, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 47.98, | |
| "learning_rate": 5.2412587412587404e-08, | |
| "loss": 0.3173, | |
| "step": 6910 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 0.4555531144142151, | |
| "eval_runtime": 125.1457, | |
| "eval_samples_per_second": 4.251, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.20987336890145916, | |
| "step": 6912 | |
| }, | |
| { | |
| "epoch": 48.06, | |
| "learning_rate": 5.234265734265734e-08, | |
| "loss": 0.3205, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 48.12, | |
| "learning_rate": 5.227272727272727e-08, | |
| "loss": 0.3143, | |
| "step": 6930 | |
| }, | |
| { | |
| "epoch": 48.19, | |
| "learning_rate": 5.2202797202797196e-08, | |
| "loss": 0.3174, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 48.26, | |
| "learning_rate": 5.213286713286713e-08, | |
| "loss": 0.319, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 48.33, | |
| "learning_rate": 5.206293706293706e-08, | |
| "loss": 0.3122, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 48.4, | |
| "learning_rate": 5.1993006993006995e-08, | |
| "loss": 0.2946, | |
| "step": 6970 | |
| }, | |
| { | |
| "epoch": 48.47, | |
| "learning_rate": 5.1923076923076924e-08, | |
| "loss": 0.3057, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 48.54, | |
| "learning_rate": 5.185314685314686e-08, | |
| "loss": 0.3136, | |
| "step": 6990 | |
| }, | |
| { | |
| "epoch": 48.61, | |
| "learning_rate": 5.1783216783216774e-08, | |
| "loss": 0.2954, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 48.68, | |
| "learning_rate": 5.171328671328671e-08, | |
| "loss": 0.3105, | |
| "step": 7010 | |
| }, | |
| { | |
| "epoch": 48.75, | |
| "learning_rate": 5.164335664335664e-08, | |
| "loss": 0.3031, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 48.82, | |
| "learning_rate": 5.157342657342657e-08, | |
| "loss": 0.2934, | |
| "step": 7030 | |
| }, | |
| { | |
| "epoch": 48.89, | |
| "learning_rate": 5.15034965034965e-08, | |
| "loss": 0.2922, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 48.96, | |
| "learning_rate": 5.143356643356643e-08, | |
| "loss": 0.3174, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_loss": 0.4552439749240875, | |
| "eval_runtime": 125.064, | |
| "eval_samples_per_second": 4.254, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.210130487883268, | |
| "step": 7056 | |
| }, | |
| { | |
| "epoch": 49.03, | |
| "learning_rate": 5.1363636363636365e-08, | |
| "loss": 0.3092, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 49.1, | |
| "learning_rate": 5.1293706293706294e-08, | |
| "loss": 0.3072, | |
| "step": 7070 | |
| }, | |
| { | |
| "epoch": 49.17, | |
| "learning_rate": 5.1223776223776216e-08, | |
| "loss": 0.3093, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 49.24, | |
| "learning_rate": 5.115384615384615e-08, | |
| "loss": 0.313, | |
| "step": 7090 | |
| }, | |
| { | |
| "epoch": 49.3, | |
| "learning_rate": 5.108391608391608e-08, | |
| "loss": 0.3116, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 49.37, | |
| "learning_rate": 5.101398601398601e-08, | |
| "loss": 0.2941, | |
| "step": 7110 | |
| }, | |
| { | |
| "epoch": 49.44, | |
| "learning_rate": 5.094405594405594e-08, | |
| "loss": 0.2958, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 49.51, | |
| "learning_rate": 5.087412587412587e-08, | |
| "loss": 0.3077, | |
| "step": 7130 | |
| }, | |
| { | |
| "epoch": 49.58, | |
| "learning_rate": 5.0804195804195807e-08, | |
| "loss": 0.311, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 49.65, | |
| "learning_rate": 5.0734265734265735e-08, | |
| "loss": 0.2952, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 49.72, | |
| "learning_rate": 5.0664335664335664e-08, | |
| "loss": 0.3214, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 49.79, | |
| "learning_rate": 5.0594405594405585e-08, | |
| "loss": 0.3078, | |
| "step": 7170 | |
| }, | |
| { | |
| "epoch": 49.86, | |
| "learning_rate": 5.052447552447552e-08, | |
| "loss": 0.2949, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 49.93, | |
| "learning_rate": 5.045454545454545e-08, | |
| "loss": 0.3014, | |
| "step": 7190 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 5.0384615384615384e-08, | |
| "loss": 0.313, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 0.45530128479003906, | |
| "eval_runtime": 125.0255, | |
| "eval_samples_per_second": 4.255, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.21000192839236356, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 50.07, | |
| "learning_rate": 5.031468531468531e-08, | |
| "loss": 0.3193, | |
| "step": 7210 | |
| }, | |
| { | |
| "epoch": 50.14, | |
| "learning_rate": 5.024475524475524e-08, | |
| "loss": 0.2949, | |
| "step": 7220 | |
| }, | |
| { | |
| "epoch": 50.21, | |
| "learning_rate": 5.0174825174825176e-08, | |
| "loss": 0.3012, | |
| "step": 7230 | |
| }, | |
| { | |
| "epoch": 50.28, | |
| "learning_rate": 5.0104895104895105e-08, | |
| "loss": 0.2952, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 50.35, | |
| "learning_rate": 5.003496503496504e-08, | |
| "loss": 0.2993, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 50.42, | |
| "learning_rate": 4.996503496503496e-08, | |
| "loss": 0.2985, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 50.48, | |
| "learning_rate": 4.98951048951049e-08, | |
| "loss": 0.3212, | |
| "step": 7270 | |
| }, | |
| { | |
| "epoch": 50.55, | |
| "learning_rate": 4.982517482517482e-08, | |
| "loss": 0.3026, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 50.62, | |
| "learning_rate": 4.9755244755244754e-08, | |
| "loss": 0.2887, | |
| "step": 7290 | |
| }, | |
| { | |
| "epoch": 50.69, | |
| "learning_rate": 4.968531468531468e-08, | |
| "loss": 0.3185, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 50.76, | |
| "learning_rate": 4.961538461538461e-08, | |
| "loss": 0.3111, | |
| "step": 7310 | |
| }, | |
| { | |
| "epoch": 50.83, | |
| "learning_rate": 4.9545454545454546e-08, | |
| "loss": 0.2992, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 50.9, | |
| "learning_rate": 4.9475524475524475e-08, | |
| "loss": 0.2989, | |
| "step": 7330 | |
| }, | |
| { | |
| "epoch": 50.97, | |
| "learning_rate": 4.9405594405594403e-08, | |
| "loss": 0.3139, | |
| "step": 7340 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_loss": 0.4555349051952362, | |
| "eval_runtime": 125.0505, | |
| "eval_samples_per_second": 4.254, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.210130487883268, | |
| "step": 7344 | |
| }, | |
| { | |
| "epoch": 51.04, | |
| "learning_rate": 4.933566433566433e-08, | |
| "loss": 0.3188, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 51.11, | |
| "learning_rate": 4.926573426573427e-08, | |
| "loss": 0.2961, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 51.18, | |
| "learning_rate": 4.919580419580419e-08, | |
| "loss": 0.3107, | |
| "step": 7370 | |
| }, | |
| { | |
| "epoch": 51.25, | |
| "learning_rate": 4.9125874125874124e-08, | |
| "loss": 0.3127, | |
| "step": 7380 | |
| }, | |
| { | |
| "epoch": 51.32, | |
| "learning_rate": 4.905594405594405e-08, | |
| "loss": 0.3161, | |
| "step": 7390 | |
| }, | |
| { | |
| "epoch": 51.39, | |
| "learning_rate": 4.898601398601399e-08, | |
| "loss": 0.3014, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 51.46, | |
| "learning_rate": 4.891608391608391e-08, | |
| "loss": 0.3248, | |
| "step": 7410 | |
| }, | |
| { | |
| "epoch": 51.53, | |
| "learning_rate": 4.8846153846153845e-08, | |
| "loss": 0.3022, | |
| "step": 7420 | |
| }, | |
| { | |
| "epoch": 51.6, | |
| "learning_rate": 4.877622377622377e-08, | |
| "loss": 0.2863, | |
| "step": 7430 | |
| }, | |
| { | |
| "epoch": 51.66, | |
| "learning_rate": 4.870629370629371e-08, | |
| "loss": 0.2961, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 51.73, | |
| "learning_rate": 4.863636363636364e-08, | |
| "loss": 0.2994, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 51.8, | |
| "learning_rate": 4.8566433566433565e-08, | |
| "loss": 0.2939, | |
| "step": 7460 | |
| }, | |
| { | |
| "epoch": 51.87, | |
| "learning_rate": 4.8496503496503494e-08, | |
| "loss": 0.2891, | |
| "step": 7470 | |
| }, | |
| { | |
| "epoch": 51.94, | |
| "learning_rate": 4.842657342657342e-08, | |
| "loss": 0.3054, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_loss": 0.4554886221885681, | |
| "eval_runtime": 125.0885, | |
| "eval_samples_per_second": 4.253, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.21000192839236356, | |
| "step": 7488 | |
| }, | |
| { | |
| "epoch": 52.01, | |
| "learning_rate": 4.835664335664336e-08, | |
| "loss": 0.3241, | |
| "step": 7490 | |
| }, | |
| { | |
| "epoch": 52.08, | |
| "learning_rate": 4.828671328671328e-08, | |
| "loss": 0.2958, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 52.15, | |
| "learning_rate": 4.8216783216783215e-08, | |
| "loss": 0.2988, | |
| "step": 7510 | |
| }, | |
| { | |
| "epoch": 52.22, | |
| "learning_rate": 4.814685314685314e-08, | |
| "loss": 0.3128, | |
| "step": 7520 | |
| }, | |
| { | |
| "epoch": 52.29, | |
| "learning_rate": 4.807692307692308e-08, | |
| "loss": 0.3047, | |
| "step": 7530 | |
| }, | |
| { | |
| "epoch": 52.36, | |
| "learning_rate": 4.800699300699301e-08, | |
| "loss": 0.3053, | |
| "step": 7540 | |
| }, | |
| { | |
| "epoch": 52.43, | |
| "learning_rate": 4.7937062937062935e-08, | |
| "loss": 0.3022, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 52.5, | |
| "learning_rate": 4.7867132867132864e-08, | |
| "loss": 0.3066, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 52.57, | |
| "learning_rate": 4.77972027972028e-08, | |
| "loss": 0.2962, | |
| "step": 7570 | |
| }, | |
| { | |
| "epoch": 52.64, | |
| "learning_rate": 4.772727272727273e-08, | |
| "loss": 0.2781, | |
| "step": 7580 | |
| }, | |
| { | |
| "epoch": 52.71, | |
| "learning_rate": 4.7657342657342656e-08, | |
| "loss": 0.3196, | |
| "step": 7590 | |
| }, | |
| { | |
| "epoch": 52.78, | |
| "learning_rate": 4.7587412587412585e-08, | |
| "loss": 0.2967, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 52.84, | |
| "learning_rate": 4.751748251748251e-08, | |
| "loss": 0.3097, | |
| "step": 7610 | |
| }, | |
| { | |
| "epoch": 52.91, | |
| "learning_rate": 4.744755244755245e-08, | |
| "loss": 0.2951, | |
| "step": 7620 | |
| }, | |
| { | |
| "epoch": 52.98, | |
| "learning_rate": 4.737762237762238e-08, | |
| "loss": 0.3212, | |
| "step": 7630 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_loss": 0.45544198155403137, | |
| "eval_runtime": 125.0646, | |
| "eval_samples_per_second": 4.254, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.20968052966510253, | |
| "step": 7632 | |
| }, | |
| { | |
| "epoch": 53.06, | |
| "learning_rate": 4.7307692307692305e-08, | |
| "loss": 0.3205, | |
| "step": 7640 | |
| }, | |
| { | |
| "epoch": 53.12, | |
| "learning_rate": 4.7237762237762234e-08, | |
| "loss": 0.2896, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 53.19, | |
| "learning_rate": 4.716783216783217e-08, | |
| "loss": 0.3089, | |
| "step": 7660 | |
| }, | |
| { | |
| "epoch": 53.26, | |
| "learning_rate": 4.70979020979021e-08, | |
| "loss": 0.3156, | |
| "step": 7670 | |
| }, | |
| { | |
| "epoch": 53.33, | |
| "learning_rate": 4.7027972027972026e-08, | |
| "loss": 0.2994, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 53.4, | |
| "learning_rate": 4.6958041958041954e-08, | |
| "loss": 0.295, | |
| "step": 7690 | |
| }, | |
| { | |
| "epoch": 53.47, | |
| "learning_rate": 4.688811188811189e-08, | |
| "loss": 0.3193, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 53.54, | |
| "learning_rate": 4.681818181818182e-08, | |
| "loss": 0.3006, | |
| "step": 7710 | |
| }, | |
| { | |
| "epoch": 53.61, | |
| "learning_rate": 4.6748251748251747e-08, | |
| "loss": 0.3087, | |
| "step": 7720 | |
| }, | |
| { | |
| "epoch": 53.68, | |
| "learning_rate": 4.6678321678321675e-08, | |
| "loss": 0.3041, | |
| "step": 7730 | |
| }, | |
| { | |
| "epoch": 53.75, | |
| "learning_rate": 4.6608391608391604e-08, | |
| "loss": 0.3001, | |
| "step": 7740 | |
| }, | |
| { | |
| "epoch": 53.82, | |
| "learning_rate": 4.653846153846154e-08, | |
| "loss": 0.2971, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 53.89, | |
| "learning_rate": 4.646853146853147e-08, | |
| "loss": 0.2862, | |
| "step": 7760 | |
| }, | |
| { | |
| "epoch": 53.96, | |
| "learning_rate": 4.6398601398601396e-08, | |
| "loss": 0.3252, | |
| "step": 7770 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_loss": 0.4552533030509949, | |
| "eval_runtime": 124.9702, | |
| "eval_samples_per_second": 4.257, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.20968052966510253, | |
| "step": 7776 | |
| }, | |
| { | |
| "epoch": 54.03, | |
| "learning_rate": 4.6328671328671324e-08, | |
| "loss": 0.3264, | |
| "step": 7780 | |
| }, | |
| { | |
| "epoch": 54.1, | |
| "learning_rate": 4.625874125874126e-08, | |
| "loss": 0.2853, | |
| "step": 7790 | |
| }, | |
| { | |
| "epoch": 54.17, | |
| "learning_rate": 4.618881118881119e-08, | |
| "loss": 0.3041, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 54.24, | |
| "learning_rate": 4.6118881118881117e-08, | |
| "loss": 0.3258, | |
| "step": 7810 | |
| }, | |
| { | |
| "epoch": 54.3, | |
| "learning_rate": 4.6048951048951045e-08, | |
| "loss": 0.2932, | |
| "step": 7820 | |
| }, | |
| { | |
| "epoch": 54.37, | |
| "learning_rate": 4.597902097902098e-08, | |
| "loss": 0.2867, | |
| "step": 7830 | |
| }, | |
| { | |
| "epoch": 54.44, | |
| "learning_rate": 4.590909090909091e-08, | |
| "loss": 0.3054, | |
| "step": 7840 | |
| }, | |
| { | |
| "epoch": 54.51, | |
| "learning_rate": 4.583916083916084e-08, | |
| "loss": 0.3145, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 54.58, | |
| "learning_rate": 4.5769230769230766e-08, | |
| "loss": 0.2996, | |
| "step": 7860 | |
| }, | |
| { | |
| "epoch": 54.65, | |
| "learning_rate": 4.5699300699300694e-08, | |
| "loss": 0.281, | |
| "step": 7870 | |
| }, | |
| { | |
| "epoch": 54.72, | |
| "learning_rate": 4.562937062937063e-08, | |
| "loss": 0.329, | |
| "step": 7880 | |
| }, | |
| { | |
| "epoch": 54.79, | |
| "learning_rate": 4.555944055944056e-08, | |
| "loss": 0.2992, | |
| "step": 7890 | |
| }, | |
| { | |
| "epoch": 54.86, | |
| "learning_rate": 4.5489510489510486e-08, | |
| "loss": 0.3127, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 54.93, | |
| "learning_rate": 4.5419580419580415e-08, | |
| "loss": 0.3077, | |
| "step": 7910 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 4.534965034965035e-08, | |
| "loss": 0.3063, | |
| "step": 7920 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_loss": 0.455412358045578, | |
| "eval_runtime": 125.4434, | |
| "eval_samples_per_second": 4.241, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.21058044610143345, | |
| "step": 7920 | |
| }, | |
| { | |
| "epoch": 55.07, | |
| "learning_rate": 4.527972027972028e-08, | |
| "loss": 0.3244, | |
| "step": 7930 | |
| }, | |
| { | |
| "epoch": 55.14, | |
| "learning_rate": 4.520979020979021e-08, | |
| "loss": 0.2888, | |
| "step": 7940 | |
| }, | |
| { | |
| "epoch": 55.21, | |
| "learning_rate": 4.5139860139860136e-08, | |
| "loss": 0.3097, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 55.28, | |
| "learning_rate": 4.506993006993007e-08, | |
| "loss": 0.308, | |
| "step": 7960 | |
| }, | |
| { | |
| "epoch": 55.35, | |
| "learning_rate": 4.5e-08, | |
| "loss": 0.3119, | |
| "step": 7970 | |
| }, | |
| { | |
| "epoch": 55.42, | |
| "learning_rate": 4.493006993006993e-08, | |
| "loss": 0.3181, | |
| "step": 7980 | |
| }, | |
| { | |
| "epoch": 55.48, | |
| "learning_rate": 4.4860139860139856e-08, | |
| "loss": 0.3095, | |
| "step": 7990 | |
| }, | |
| { | |
| "epoch": 55.55, | |
| "learning_rate": 4.4790209790209785e-08, | |
| "loss": 0.2983, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 55.62, | |
| "learning_rate": 4.472027972027972e-08, | |
| "loss": 0.294, | |
| "step": 8010 | |
| }, | |
| { | |
| "epoch": 55.69, | |
| "learning_rate": 4.465034965034965e-08, | |
| "loss": 0.3136, | |
| "step": 8020 | |
| }, | |
| { | |
| "epoch": 55.76, | |
| "learning_rate": 4.458041958041958e-08, | |
| "loss": 0.3047, | |
| "step": 8030 | |
| }, | |
| { | |
| "epoch": 55.83, | |
| "learning_rate": 4.4510489510489506e-08, | |
| "loss": 0.303, | |
| "step": 8040 | |
| }, | |
| { | |
| "epoch": 55.9, | |
| "learning_rate": 4.444055944055944e-08, | |
| "loss": 0.3001, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 55.97, | |
| "learning_rate": 4.437062937062937e-08, | |
| "loss": 0.3206, | |
| "step": 8060 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_loss": 0.45509257912635803, | |
| "eval_runtime": 125.3357, | |
| "eval_samples_per_second": 4.245, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.20974480941055473, | |
| "step": 8064 | |
| }, | |
| { | |
| "epoch": 56.04, | |
| "learning_rate": 4.4300699300699304e-08, | |
| "loss": 0.3179, | |
| "step": 8070 | |
| }, | |
| { | |
| "epoch": 56.11, | |
| "learning_rate": 4.4230769230769226e-08, | |
| "loss": 0.2984, | |
| "step": 8080 | |
| }, | |
| { | |
| "epoch": 56.18, | |
| "learning_rate": 4.416083916083916e-08, | |
| "loss": 0.3053, | |
| "step": 8090 | |
| }, | |
| { | |
| "epoch": 56.25, | |
| "learning_rate": 4.409090909090909e-08, | |
| "loss": 0.3024, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 56.32, | |
| "learning_rate": 4.402097902097902e-08, | |
| "loss": 0.3024, | |
| "step": 8110 | |
| }, | |
| { | |
| "epoch": 56.39, | |
| "learning_rate": 4.395104895104895e-08, | |
| "loss": 0.2716, | |
| "step": 8120 | |
| }, | |
| { | |
| "epoch": 56.46, | |
| "learning_rate": 4.3881118881118875e-08, | |
| "loss": 0.3257, | |
| "step": 8130 | |
| }, | |
| { | |
| "epoch": 56.53, | |
| "learning_rate": 4.381118881118881e-08, | |
| "loss": 0.3121, | |
| "step": 8140 | |
| }, | |
| { | |
| "epoch": 56.6, | |
| "learning_rate": 4.374125874125874e-08, | |
| "loss": 0.3129, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 56.66, | |
| "learning_rate": 4.367132867132867e-08, | |
| "loss": 0.2992, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 56.73, | |
| "learning_rate": 4.3601398601398596e-08, | |
| "loss": 0.3202, | |
| "step": 8170 | |
| }, | |
| { | |
| "epoch": 56.8, | |
| "learning_rate": 4.353146853146853e-08, | |
| "loss": 0.3048, | |
| "step": 8180 | |
| }, | |
| { | |
| "epoch": 56.87, | |
| "learning_rate": 4.346153846153846e-08, | |
| "loss": 0.2948, | |
| "step": 8190 | |
| }, | |
| { | |
| "epoch": 56.94, | |
| "learning_rate": 4.3391608391608395e-08, | |
| "loss": 0.3176, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_loss": 0.45521798729896545, | |
| "eval_runtime": 124.9847, | |
| "eval_samples_per_second": 4.257, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.210130487883268, | |
| "step": 8208 | |
| }, | |
| { | |
| "epoch": 57.01, | |
| "learning_rate": 4.332167832167832e-08, | |
| "loss": 0.3074, | |
| "step": 8210 | |
| }, | |
| { | |
| "epoch": 57.08, | |
| "learning_rate": 4.325174825174825e-08, | |
| "loss": 0.2965, | |
| "step": 8220 | |
| }, | |
| { | |
| "epoch": 57.15, | |
| "learning_rate": 4.318181818181818e-08, | |
| "loss": 0.3028, | |
| "step": 8230 | |
| }, | |
| { | |
| "epoch": 57.22, | |
| "learning_rate": 4.311188811188811e-08, | |
| "loss": 0.3185, | |
| "step": 8240 | |
| }, | |
| { | |
| "epoch": 57.29, | |
| "learning_rate": 4.304195804195804e-08, | |
| "loss": 0.3108, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 57.36, | |
| "learning_rate": 4.2972027972027966e-08, | |
| "loss": 0.3111, | |
| "step": 8260 | |
| }, | |
| { | |
| "epoch": 57.43, | |
| "learning_rate": 4.29020979020979e-08, | |
| "loss": 0.3211, | |
| "step": 8270 | |
| }, | |
| { | |
| "epoch": 57.5, | |
| "learning_rate": 4.283216783216783e-08, | |
| "loss": 0.3162, | |
| "step": 8280 | |
| }, | |
| { | |
| "epoch": 57.57, | |
| "learning_rate": 4.2762237762237765e-08, | |
| "loss": 0.3081, | |
| "step": 8290 | |
| }, | |
| { | |
| "epoch": 57.64, | |
| "learning_rate": 4.269230769230769e-08, | |
| "loss": 0.3021, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 57.71, | |
| "learning_rate": 4.262237762237762e-08, | |
| "loss": 0.3041, | |
| "step": 8310 | |
| }, | |
| { | |
| "epoch": 57.78, | |
| "learning_rate": 4.255244755244755e-08, | |
| "loss": 0.3036, | |
| "step": 8320 | |
| }, | |
| { | |
| "epoch": 57.84, | |
| "learning_rate": 4.2482517482517486e-08, | |
| "loss": 0.2954, | |
| "step": 8330 | |
| }, | |
| { | |
| "epoch": 57.91, | |
| "learning_rate": 4.241258741258741e-08, | |
| "loss": 0.2984, | |
| "step": 8340 | |
| }, | |
| { | |
| "epoch": 57.98, | |
| "learning_rate": 4.234265734265734e-08, | |
| "loss": 0.3179, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_loss": 0.4553627073764801, | |
| "eval_runtime": 125.6572, | |
| "eval_samples_per_second": 4.234, | |
| "eval_steps_per_second": 0.533, | |
| "eval_wer": 0.20987336890145916, | |
| "step": 8352 | |
| }, | |
| { | |
| "epoch": 58.06, | |
| "learning_rate": 4.227272727272727e-08, | |
| "loss": 0.3152, | |
| "step": 8360 | |
| }, | |
| { | |
| "epoch": 58.12, | |
| "learning_rate": 4.22027972027972e-08, | |
| "loss": 0.2867, | |
| "step": 8370 | |
| }, | |
| { | |
| "epoch": 58.19, | |
| "learning_rate": 4.2132867132867135e-08, | |
| "loss": 0.3128, | |
| "step": 8380 | |
| }, | |
| { | |
| "epoch": 58.26, | |
| "learning_rate": 4.2062937062937057e-08, | |
| "loss": 0.3094, | |
| "step": 8390 | |
| }, | |
| { | |
| "epoch": 58.33, | |
| "learning_rate": 4.199300699300699e-08, | |
| "loss": 0.314, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 58.4, | |
| "learning_rate": 4.192307692307692e-08, | |
| "loss": 0.2887, | |
| "step": 8410 | |
| }, | |
| { | |
| "epoch": 58.47, | |
| "learning_rate": 4.1853146853146855e-08, | |
| "loss": 0.3179, | |
| "step": 8420 | |
| }, | |
| { | |
| "epoch": 58.54, | |
| "learning_rate": 4.178321678321678e-08, | |
| "loss": 0.2969, | |
| "step": 8430 | |
| }, | |
| { | |
| "epoch": 58.61, | |
| "learning_rate": 4.171328671328671e-08, | |
| "loss": 0.292, | |
| "step": 8440 | |
| }, | |
| { | |
| "epoch": 58.68, | |
| "learning_rate": 4.164335664335664e-08, | |
| "loss": 0.3117, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 58.75, | |
| "learning_rate": 4.1573426573426576e-08, | |
| "loss": 0.3323, | |
| "step": 8460 | |
| }, | |
| { | |
| "epoch": 58.82, | |
| "learning_rate": 4.15034965034965e-08, | |
| "loss": 0.3086, | |
| "step": 8470 | |
| }, | |
| { | |
| "epoch": 58.89, | |
| "learning_rate": 4.143356643356643e-08, | |
| "loss": 0.2893, | |
| "step": 8480 | |
| }, | |
| { | |
| "epoch": 58.96, | |
| "learning_rate": 4.136363636363636e-08, | |
| "loss": 0.3064, | |
| "step": 8490 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_loss": 0.4559072256088257, | |
| "eval_runtime": 125.7617, | |
| "eval_samples_per_second": 4.23, | |
| "eval_steps_per_second": 0.533, | |
| "eval_wer": 0.20923057144693707, | |
| "step": 8496 | |
| }, | |
| { | |
| "epoch": 59.03, | |
| "learning_rate": 4.129370629370629e-08, | |
| "loss": 0.3209, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 59.1, | |
| "learning_rate": 4.1223776223776225e-08, | |
| "loss": 0.2766, | |
| "step": 8510 | |
| }, | |
| { | |
| "epoch": 59.17, | |
| "learning_rate": 4.115384615384615e-08, | |
| "loss": 0.305, | |
| "step": 8520 | |
| }, | |
| { | |
| "epoch": 59.24, | |
| "learning_rate": 4.108391608391608e-08, | |
| "loss": 0.3124, | |
| "step": 8530 | |
| }, | |
| { | |
| "epoch": 59.3, | |
| "learning_rate": 4.101398601398601e-08, | |
| "loss": 0.3096, | |
| "step": 8540 | |
| }, | |
| { | |
| "epoch": 59.37, | |
| "learning_rate": 4.0944055944055946e-08, | |
| "loss": 0.3051, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 59.44, | |
| "learning_rate": 4.087412587412587e-08, | |
| "loss": 0.3216, | |
| "step": 8560 | |
| }, | |
| { | |
| "epoch": 59.51, | |
| "learning_rate": 4.08041958041958e-08, | |
| "loss": 0.3129, | |
| "step": 8570 | |
| }, | |
| { | |
| "epoch": 59.58, | |
| "learning_rate": 4.073426573426573e-08, | |
| "loss": 0.2994, | |
| "step": 8580 | |
| }, | |
| { | |
| "epoch": 59.65, | |
| "learning_rate": 4.0664335664335667e-08, | |
| "loss": 0.307, | |
| "step": 8590 | |
| }, | |
| { | |
| "epoch": 59.72, | |
| "learning_rate": 4.0594405594405595e-08, | |
| "loss": 0.3325, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 59.79, | |
| "learning_rate": 4.0524475524475524e-08, | |
| "loss": 0.2928, | |
| "step": 8610 | |
| }, | |
| { | |
| "epoch": 59.86, | |
| "learning_rate": 4.045454545454545e-08, | |
| "loss": 0.2867, | |
| "step": 8620 | |
| }, | |
| { | |
| "epoch": 59.93, | |
| "learning_rate": 4.038461538461538e-08, | |
| "loss": 0.2962, | |
| "step": 8630 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 4.0314685314685316e-08, | |
| "loss": 0.301, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_loss": 0.45589613914489746, | |
| "eval_runtime": 125.3843, | |
| "eval_samples_per_second": 4.243, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.21032332711962462, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 60.07, | |
| "learning_rate": 4.024475524475524e-08, | |
| "loss": 0.3324, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 60.14, | |
| "learning_rate": 4.017482517482517e-08, | |
| "loss": 0.29, | |
| "step": 8660 | |
| }, | |
| { | |
| "epoch": 60.21, | |
| "learning_rate": 4.01048951048951e-08, | |
| "loss": 0.2998, | |
| "step": 8670 | |
| }, | |
| { | |
| "epoch": 60.28, | |
| "learning_rate": 4.0034965034965037e-08, | |
| "loss": 0.3053, | |
| "step": 8680 | |
| }, | |
| { | |
| "epoch": 60.35, | |
| "learning_rate": 3.996503496503496e-08, | |
| "loss": 0.3057, | |
| "step": 8690 | |
| }, | |
| { | |
| "epoch": 60.42, | |
| "learning_rate": 3.9895104895104894e-08, | |
| "loss": 0.303, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 60.48, | |
| "learning_rate": 3.982517482517482e-08, | |
| "loss": 0.3109, | |
| "step": 8710 | |
| }, | |
| { | |
| "epoch": 60.55, | |
| "learning_rate": 3.975524475524476e-08, | |
| "loss": 0.2955, | |
| "step": 8720 | |
| }, | |
| { | |
| "epoch": 60.62, | |
| "learning_rate": 3.9685314685314686e-08, | |
| "loss": 0.2938, | |
| "step": 8730 | |
| }, | |
| { | |
| "epoch": 60.69, | |
| "learning_rate": 3.9615384615384614e-08, | |
| "loss": 0.3215, | |
| "step": 8740 | |
| }, | |
| { | |
| "epoch": 60.76, | |
| "learning_rate": 3.954545454545454e-08, | |
| "loss": 0.3143, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 60.83, | |
| "learning_rate": 3.947552447552447e-08, | |
| "loss": 0.2907, | |
| "step": 8760 | |
| }, | |
| { | |
| "epoch": 60.9, | |
| "learning_rate": 3.9405594405594406e-08, | |
| "loss": 0.3067, | |
| "step": 8770 | |
| }, | |
| { | |
| "epoch": 60.97, | |
| "learning_rate": 3.933566433566433e-08, | |
| "loss": 0.3103, | |
| "step": 8780 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_loss": 0.4558674693107605, | |
| "eval_runtime": 125.3426, | |
| "eval_samples_per_second": 4.244, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.2101947676287202, | |
| "step": 8784 | |
| }, | |
| { | |
| "epoch": 61.04, | |
| "learning_rate": 3.9265734265734264e-08, | |
| "loss": 0.3305, | |
| "step": 8790 | |
| }, | |
| { | |
| "epoch": 61.11, | |
| "learning_rate": 3.919580419580419e-08, | |
| "loss": 0.2908, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 61.18, | |
| "learning_rate": 3.912587412587413e-08, | |
| "loss": 0.3138, | |
| "step": 8810 | |
| }, | |
| { | |
| "epoch": 61.25, | |
| "learning_rate": 3.9055944055944056e-08, | |
| "loss": 0.3161, | |
| "step": 8820 | |
| }, | |
| { | |
| "epoch": 61.32, | |
| "learning_rate": 3.8986013986013984e-08, | |
| "loss": 0.3112, | |
| "step": 8830 | |
| }, | |
| { | |
| "epoch": 61.39, | |
| "learning_rate": 3.891608391608391e-08, | |
| "loss": 0.2869, | |
| "step": 8840 | |
| }, | |
| { | |
| "epoch": 61.46, | |
| "learning_rate": 3.884615384615385e-08, | |
| "loss": 0.315, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 61.53, | |
| "learning_rate": 3.8776223776223776e-08, | |
| "loss": 0.2908, | |
| "step": 8860 | |
| }, | |
| { | |
| "epoch": 61.6, | |
| "learning_rate": 3.8706293706293705e-08, | |
| "loss": 0.2936, | |
| "step": 8870 | |
| }, | |
| { | |
| "epoch": 61.66, | |
| "learning_rate": 3.8636363636363633e-08, | |
| "loss": 0.2904, | |
| "step": 8880 | |
| }, | |
| { | |
| "epoch": 61.73, | |
| "learning_rate": 3.856643356643356e-08, | |
| "loss": 0.3259, | |
| "step": 8890 | |
| }, | |
| { | |
| "epoch": 61.8, | |
| "learning_rate": 3.84965034965035e-08, | |
| "loss": 0.3074, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 61.87, | |
| "learning_rate": 3.8426573426573426e-08, | |
| "loss": 0.3044, | |
| "step": 8910 | |
| }, | |
| { | |
| "epoch": 61.94, | |
| "learning_rate": 3.8356643356643354e-08, | |
| "loss": 0.3169, | |
| "step": 8920 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_loss": 0.45593470335006714, | |
| "eval_runtime": 125.5894, | |
| "eval_samples_per_second": 4.236, | |
| "eval_steps_per_second": 0.533, | |
| "eval_wer": 0.21032332711962462, | |
| "step": 8928 | |
| }, | |
| { | |
| "epoch": 62.01, | |
| "learning_rate": 3.828671328671328e-08, | |
| "loss": 0.3404, | |
| "step": 8930 | |
| }, | |
| { | |
| "epoch": 62.08, | |
| "learning_rate": 3.821678321678322e-08, | |
| "loss": 0.3022, | |
| "step": 8940 | |
| }, | |
| { | |
| "epoch": 62.15, | |
| "learning_rate": 3.8146853146853146e-08, | |
| "loss": 0.3024, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 62.22, | |
| "learning_rate": 3.8076923076923075e-08, | |
| "loss": 0.3229, | |
| "step": 8960 | |
| }, | |
| { | |
| "epoch": 62.29, | |
| "learning_rate": 3.8006993006993003e-08, | |
| "loss": 0.3132, | |
| "step": 8970 | |
| }, | |
| { | |
| "epoch": 62.36, | |
| "learning_rate": 3.793706293706294e-08, | |
| "loss": 0.3151, | |
| "step": 8980 | |
| }, | |
| { | |
| "epoch": 62.43, | |
| "learning_rate": 3.786713286713287e-08, | |
| "loss": 0.3118, | |
| "step": 8990 | |
| }, | |
| { | |
| "epoch": 62.5, | |
| "learning_rate": 3.7797202797202795e-08, | |
| "loss": 0.3097, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 62.57, | |
| "learning_rate": 3.7727272727272724e-08, | |
| "loss": 0.3033, | |
| "step": 9010 | |
| }, | |
| { | |
| "epoch": 62.64, | |
| "learning_rate": 3.765734265734265e-08, | |
| "loss": 0.3012, | |
| "step": 9020 | |
| }, | |
| { | |
| "epoch": 62.71, | |
| "learning_rate": 3.758741258741259e-08, | |
| "loss": 0.3244, | |
| "step": 9030 | |
| }, | |
| { | |
| "epoch": 62.78, | |
| "learning_rate": 3.7517482517482516e-08, | |
| "loss": 0.3148, | |
| "step": 9040 | |
| }, | |
| { | |
| "epoch": 62.84, | |
| "learning_rate": 3.7447552447552445e-08, | |
| "loss": 0.3054, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 62.91, | |
| "learning_rate": 3.737762237762237e-08, | |
| "loss": 0.3046, | |
| "step": 9060 | |
| }, | |
| { | |
| "epoch": 62.98, | |
| "learning_rate": 3.730769230769231e-08, | |
| "loss": 0.3081, | |
| "step": 9070 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_loss": 0.4559272825717926, | |
| "eval_runtime": 125.1414, | |
| "eval_samples_per_second": 4.251, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.210130487883268, | |
| "step": 9072 | |
| }, | |
| { | |
| "epoch": 63.06, | |
| "learning_rate": 3.723776223776224e-08, | |
| "loss": 0.3332, | |
| "step": 9080 | |
| }, | |
| { | |
| "epoch": 63.12, | |
| "learning_rate": 3.7167832167832165e-08, | |
| "loss": 0.2969, | |
| "step": 9090 | |
| }, | |
| { | |
| "epoch": 63.19, | |
| "learning_rate": 3.7097902097902094e-08, | |
| "loss": 0.3179, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 63.26, | |
| "learning_rate": 3.702797202797203e-08, | |
| "loss": 0.3178, | |
| "step": 9110 | |
| }, | |
| { | |
| "epoch": 63.33, | |
| "learning_rate": 3.695804195804196e-08, | |
| "loss": 0.2994, | |
| "step": 9120 | |
| }, | |
| { | |
| "epoch": 63.4, | |
| "learning_rate": 3.6888111888111886e-08, | |
| "loss": 0.3025, | |
| "step": 9130 | |
| }, | |
| { | |
| "epoch": 63.47, | |
| "learning_rate": 3.6818181818181815e-08, | |
| "loss": 0.3187, | |
| "step": 9140 | |
| }, | |
| { | |
| "epoch": 63.54, | |
| "learning_rate": 3.674825174825174e-08, | |
| "loss": 0.3004, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 63.61, | |
| "learning_rate": 3.667832167832168e-08, | |
| "loss": 0.3125, | |
| "step": 9160 | |
| }, | |
| { | |
| "epoch": 63.68, | |
| "learning_rate": 3.660839160839161e-08, | |
| "loss": 0.3081, | |
| "step": 9170 | |
| }, | |
| { | |
| "epoch": 63.75, | |
| "learning_rate": 3.6538461538461535e-08, | |
| "loss": 0.3163, | |
| "step": 9180 | |
| }, | |
| { | |
| "epoch": 63.82, | |
| "learning_rate": 3.6468531468531464e-08, | |
| "loss": 0.3121, | |
| "step": 9190 | |
| }, | |
| { | |
| "epoch": 63.89, | |
| "learning_rate": 3.63986013986014e-08, | |
| "loss": 0.294, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 63.96, | |
| "learning_rate": 3.632867132867133e-08, | |
| "loss": 0.3249, | |
| "step": 9210 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_loss": 0.45550307631492615, | |
| "eval_runtime": 125.0173, | |
| "eval_samples_per_second": 4.255, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.21064472584688565, | |
| "step": 9216 | |
| }, | |
| { | |
| "epoch": 64.03, | |
| "learning_rate": 3.6258741258741256e-08, | |
| "loss": 0.3182, | |
| "step": 9220 | |
| }, | |
| { | |
| "epoch": 64.1, | |
| "learning_rate": 3.6188811188811184e-08, | |
| "loss": 0.3036, | |
| "step": 9230 | |
| }, | |
| { | |
| "epoch": 64.17, | |
| "learning_rate": 3.611888111888112e-08, | |
| "loss": 0.3065, | |
| "step": 9240 | |
| }, | |
| { | |
| "epoch": 64.24, | |
| "learning_rate": 3.604895104895105e-08, | |
| "loss": 0.3194, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 64.3, | |
| "learning_rate": 3.5979020979020977e-08, | |
| "loss": 0.3207, | |
| "step": 9260 | |
| }, | |
| { | |
| "epoch": 64.37, | |
| "learning_rate": 3.5909090909090905e-08, | |
| "loss": 0.2943, | |
| "step": 9270 | |
| }, | |
| { | |
| "epoch": 64.44, | |
| "learning_rate": 3.5839160839160834e-08, | |
| "loss": 0.3085, | |
| "step": 9280 | |
| }, | |
| { | |
| "epoch": 64.51, | |
| "learning_rate": 3.576923076923077e-08, | |
| "loss": 0.3139, | |
| "step": 9290 | |
| }, | |
| { | |
| "epoch": 64.58, | |
| "learning_rate": 3.56993006993007e-08, | |
| "loss": 0.3221, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 64.65, | |
| "learning_rate": 3.5629370629370626e-08, | |
| "loss": 0.3086, | |
| "step": 9310 | |
| }, | |
| { | |
| "epoch": 64.72, | |
| "learning_rate": 3.5559440559440554e-08, | |
| "loss": 0.3098, | |
| "step": 9320 | |
| }, | |
| { | |
| "epoch": 64.79, | |
| "learning_rate": 3.548951048951049e-08, | |
| "loss": 0.3145, | |
| "step": 9330 | |
| }, | |
| { | |
| "epoch": 64.86, | |
| "learning_rate": 3.541958041958042e-08, | |
| "loss": 0.3143, | |
| "step": 9340 | |
| }, | |
| { | |
| "epoch": 64.93, | |
| "learning_rate": 3.534965034965035e-08, | |
| "loss": 0.3161, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 3.5279720279720275e-08, | |
| "loss": 0.3031, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_loss": 0.45534220337867737, | |
| "eval_runtime": 125.0701, | |
| "eval_samples_per_second": 4.254, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.21045188661052902, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 65.07, | |
| "learning_rate": 3.520979020979021e-08, | |
| "loss": 0.3233, | |
| "step": 9370 | |
| }, | |
| { | |
| "epoch": 65.14, | |
| "learning_rate": 3.513986013986014e-08, | |
| "loss": 0.3066, | |
| "step": 9380 | |
| }, | |
| { | |
| "epoch": 65.21, | |
| "learning_rate": 3.506993006993007e-08, | |
| "loss": 0.3262, | |
| "step": 9390 | |
| }, | |
| { | |
| "epoch": 65.28, | |
| "learning_rate": 3.4999999999999996e-08, | |
| "loss": 0.3179, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 65.35, | |
| "learning_rate": 3.4930069930069924e-08, | |
| "loss": 0.2949, | |
| "step": 9410 | |
| }, | |
| { | |
| "epoch": 65.42, | |
| "learning_rate": 3.486013986013986e-08, | |
| "loss": 0.3241, | |
| "step": 9420 | |
| }, | |
| { | |
| "epoch": 65.48, | |
| "learning_rate": 3.479020979020979e-08, | |
| "loss": 0.3158, | |
| "step": 9430 | |
| }, | |
| { | |
| "epoch": 65.55, | |
| "learning_rate": 3.4720279720279716e-08, | |
| "loss": 0.2958, | |
| "step": 9440 | |
| }, | |
| { | |
| "epoch": 65.62, | |
| "learning_rate": 3.4650349650349645e-08, | |
| "loss": 0.2867, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 65.69, | |
| "learning_rate": 3.458041958041958e-08, | |
| "loss": 0.3191, | |
| "step": 9460 | |
| }, | |
| { | |
| "epoch": 65.76, | |
| "learning_rate": 3.451048951048951e-08, | |
| "loss": 0.3061, | |
| "step": 9470 | |
| }, | |
| { | |
| "epoch": 65.83, | |
| "learning_rate": 3.4440559440559444e-08, | |
| "loss": 0.3195, | |
| "step": 9480 | |
| }, | |
| { | |
| "epoch": 65.9, | |
| "learning_rate": 3.4370629370629366e-08, | |
| "loss": 0.2849, | |
| "step": 9490 | |
| }, | |
| { | |
| "epoch": 65.97, | |
| "learning_rate": 3.43006993006993e-08, | |
| "loss": 0.3017, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_loss": 0.4556381106376648, | |
| "eval_runtime": 125.4869, | |
| "eval_samples_per_second": 4.239, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.21051616635598122, | |
| "step": 9504 | |
| }, | |
| { | |
| "epoch": 66.04, | |
| "learning_rate": 3.423076923076923e-08, | |
| "loss": 0.332, | |
| "step": 9510 | |
| }, | |
| { | |
| "epoch": 66.11, | |
| "learning_rate": 3.416083916083916e-08, | |
| "loss": 0.3132, | |
| "step": 9520 | |
| }, | |
| { | |
| "epoch": 66.18, | |
| "learning_rate": 3.4090909090909086e-08, | |
| "loss": 0.2992, | |
| "step": 9530 | |
| }, | |
| { | |
| "epoch": 66.25, | |
| "learning_rate": 3.4020979020979015e-08, | |
| "loss": 0.3254, | |
| "step": 9540 | |
| }, | |
| { | |
| "epoch": 66.32, | |
| "learning_rate": 3.395104895104895e-08, | |
| "loss": 0.3037, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 66.39, | |
| "learning_rate": 3.388111888111888e-08, | |
| "loss": 0.3048, | |
| "step": 9560 | |
| }, | |
| { | |
| "epoch": 66.46, | |
| "learning_rate": 3.3811188811188814e-08, | |
| "loss": 0.3139, | |
| "step": 9570 | |
| }, | |
| { | |
| "epoch": 66.53, | |
| "learning_rate": 3.3741258741258736e-08, | |
| "loss": 0.3183, | |
| "step": 9580 | |
| }, | |
| { | |
| "epoch": 66.6, | |
| "learning_rate": 3.367132867132867e-08, | |
| "loss": 0.31, | |
| "step": 9590 | |
| }, | |
| { | |
| "epoch": 66.66, | |
| "learning_rate": 3.36013986013986e-08, | |
| "loss": 0.308, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 66.73, | |
| "learning_rate": 3.3531468531468534e-08, | |
| "loss": 0.31, | |
| "step": 9610 | |
| }, | |
| { | |
| "epoch": 66.8, | |
| "learning_rate": 3.3461538461538456e-08, | |
| "loss": 0.3064, | |
| "step": 9620 | |
| }, | |
| { | |
| "epoch": 66.87, | |
| "learning_rate": 3.339160839160839e-08, | |
| "loss": 0.2958, | |
| "step": 9630 | |
| }, | |
| { | |
| "epoch": 66.94, | |
| "learning_rate": 3.332167832167832e-08, | |
| "loss": 0.3261, | |
| "step": 9640 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_loss": 0.4551018178462982, | |
| "eval_runtime": 125.502, | |
| "eval_samples_per_second": 4.239, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.21000192839236356, | |
| "step": 9648 | |
| }, | |
| { | |
| "epoch": 67.01, | |
| "learning_rate": 3.325174825174825e-08, | |
| "loss": 0.3242, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 67.08, | |
| "learning_rate": 3.3181818181818184e-08, | |
| "loss": 0.2939, | |
| "step": 9660 | |
| }, | |
| { | |
| "epoch": 67.15, | |
| "learning_rate": 3.311188811188811e-08, | |
| "loss": 0.293, | |
| "step": 9670 | |
| }, | |
| { | |
| "epoch": 67.22, | |
| "learning_rate": 3.304195804195804e-08, | |
| "loss": 0.3406, | |
| "step": 9680 | |
| }, | |
| { | |
| "epoch": 67.29, | |
| "learning_rate": 3.297202797202797e-08, | |
| "loss": 0.3026, | |
| "step": 9690 | |
| }, | |
| { | |
| "epoch": 67.36, | |
| "learning_rate": 3.2902097902097904e-08, | |
| "loss": 0.2868, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 67.43, | |
| "learning_rate": 3.2832167832167826e-08, | |
| "loss": 0.3032, | |
| "step": 9710 | |
| }, | |
| { | |
| "epoch": 67.5, | |
| "learning_rate": 3.276223776223776e-08, | |
| "loss": 0.3139, | |
| "step": 9720 | |
| }, | |
| { | |
| "epoch": 67.57, | |
| "learning_rate": 3.269230769230769e-08, | |
| "loss": 0.3106, | |
| "step": 9730 | |
| }, | |
| { | |
| "epoch": 67.64, | |
| "learning_rate": 3.2622377622377625e-08, | |
| "loss": 0.2955, | |
| "step": 9740 | |
| }, | |
| { | |
| "epoch": 67.71, | |
| "learning_rate": 3.255244755244755e-08, | |
| "loss": 0.3185, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 67.78, | |
| "learning_rate": 3.248251748251748e-08, | |
| "loss": 0.3171, | |
| "step": 9760 | |
| }, | |
| { | |
| "epoch": 67.84, | |
| "learning_rate": 3.241258741258741e-08, | |
| "loss": 0.3127, | |
| "step": 9770 | |
| }, | |
| { | |
| "epoch": 67.91, | |
| "learning_rate": 3.2342657342657346e-08, | |
| "loss": 0.3023, | |
| "step": 9780 | |
| }, | |
| { | |
| "epoch": 67.98, | |
| "learning_rate": 3.2272727272727274e-08, | |
| "loss": 0.3196, | |
| "step": 9790 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_loss": 0.45527660846710205, | |
| "eval_runtime": 125.2245, | |
| "eval_samples_per_second": 4.248, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.2096162499196503, | |
| "step": 9792 | |
| }, | |
| { | |
| "epoch": 68.06, | |
| "learning_rate": 3.22027972027972e-08, | |
| "loss": 0.3124, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 68.12, | |
| "learning_rate": 3.213286713286713e-08, | |
| "loss": 0.2973, | |
| "step": 9810 | |
| }, | |
| { | |
| "epoch": 68.19, | |
| "learning_rate": 3.206293706293706e-08, | |
| "loss": 0.3224, | |
| "step": 9820 | |
| }, | |
| { | |
| "epoch": 68.26, | |
| "learning_rate": 3.1993006993006995e-08, | |
| "loss": 0.317, | |
| "step": 9830 | |
| }, | |
| { | |
| "epoch": 68.33, | |
| "learning_rate": 3.192307692307692e-08, | |
| "loss": 0.3155, | |
| "step": 9840 | |
| }, | |
| { | |
| "epoch": 68.4, | |
| "learning_rate": 3.185314685314685e-08, | |
| "loss": 0.3053, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 68.47, | |
| "learning_rate": 3.178321678321678e-08, | |
| "loss": 0.327, | |
| "step": 9860 | |
| }, | |
| { | |
| "epoch": 68.54, | |
| "learning_rate": 3.1713286713286716e-08, | |
| "loss": 0.3167, | |
| "step": 9870 | |
| }, | |
| { | |
| "epoch": 68.61, | |
| "learning_rate": 3.1643356643356644e-08, | |
| "loss": 0.2909, | |
| "step": 9880 | |
| }, | |
| { | |
| "epoch": 68.68, | |
| "learning_rate": 3.157342657342657e-08, | |
| "loss": 0.3022, | |
| "step": 9890 | |
| }, | |
| { | |
| "epoch": 68.75, | |
| "learning_rate": 3.15034965034965e-08, | |
| "loss": 0.2986, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 68.82, | |
| "learning_rate": 3.1433566433566436e-08, | |
| "loss": 0.3103, | |
| "step": 9910 | |
| }, | |
| { | |
| "epoch": 68.89, | |
| "learning_rate": 3.1363636363636365e-08, | |
| "loss": 0.2973, | |
| "step": 9920 | |
| }, | |
| { | |
| "epoch": 68.96, | |
| "learning_rate": 3.129370629370629e-08, | |
| "loss": 0.3085, | |
| "step": 9930 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_loss": 0.4554106891155243, | |
| "eval_runtime": 125.0091, | |
| "eval_samples_per_second": 4.256, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.2094876904287459, | |
| "step": 9936 | |
| }, | |
| { | |
| "epoch": 69.03, | |
| "learning_rate": 3.122377622377622e-08, | |
| "loss": 0.3269, | |
| "step": 9940 | |
| }, | |
| { | |
| "epoch": 69.1, | |
| "learning_rate": 3.115384615384615e-08, | |
| "loss": 0.3163, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 69.17, | |
| "learning_rate": 3.1083916083916085e-08, | |
| "loss": 0.2952, | |
| "step": 9960 | |
| }, | |
| { | |
| "epoch": 69.24, | |
| "learning_rate": 3.101398601398601e-08, | |
| "loss": 0.3219, | |
| "step": 9970 | |
| }, | |
| { | |
| "epoch": 69.3, | |
| "learning_rate": 3.094405594405594e-08, | |
| "loss": 0.3036, | |
| "step": 9980 | |
| }, | |
| { | |
| "epoch": 69.37, | |
| "learning_rate": 3.087412587412587e-08, | |
| "loss": 0.2988, | |
| "step": 9990 | |
| }, | |
| { | |
| "epoch": 69.44, | |
| "learning_rate": 3.0804195804195806e-08, | |
| "loss": 0.3147, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 69.51, | |
| "learning_rate": 3.0734265734265735e-08, | |
| "loss": 0.3197, | |
| "step": 10010 | |
| }, | |
| { | |
| "epoch": 69.58, | |
| "learning_rate": 3.066433566433566e-08, | |
| "loss": 0.3128, | |
| "step": 10020 | |
| }, | |
| { | |
| "epoch": 69.65, | |
| "learning_rate": 3.059440559440559e-08, | |
| "loss": 0.3008, | |
| "step": 10030 | |
| }, | |
| { | |
| "epoch": 69.72, | |
| "learning_rate": 3.052447552447553e-08, | |
| "loss": 0.3187, | |
| "step": 10040 | |
| }, | |
| { | |
| "epoch": 69.79, | |
| "learning_rate": 3.0454545454545455e-08, | |
| "loss": 0.3086, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 69.86, | |
| "learning_rate": 3.0384615384615384e-08, | |
| "loss": 0.3116, | |
| "step": 10060 | |
| }, | |
| { | |
| "epoch": 69.93, | |
| "learning_rate": 3.031468531468531e-08, | |
| "loss": 0.3029, | |
| "step": 10070 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 3.024475524475524e-08, | |
| "loss": 0.3235, | |
| "step": 10080 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_loss": 0.45517316460609436, | |
| "eval_runtime": 125.5853, | |
| "eval_samples_per_second": 4.236, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.2096162499196503, | |
| "step": 10080 | |
| }, | |
| { | |
| "epoch": 70.07, | |
| "learning_rate": 3.0174825174825176e-08, | |
| "loss": 0.32, | |
| "step": 10090 | |
| }, | |
| { | |
| "epoch": 70.14, | |
| "learning_rate": 3.0104895104895105e-08, | |
| "loss": 0.2995, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 70.21, | |
| "learning_rate": 3.003496503496503e-08, | |
| "loss": 0.306, | |
| "step": 10110 | |
| }, | |
| { | |
| "epoch": 70.28, | |
| "learning_rate": 2.996503496503496e-08, | |
| "loss": 0.3245, | |
| "step": 10120 | |
| }, | |
| { | |
| "epoch": 70.35, | |
| "learning_rate": 2.98951048951049e-08, | |
| "loss": 0.31, | |
| "step": 10130 | |
| }, | |
| { | |
| "epoch": 70.42, | |
| "learning_rate": 2.9825174825174825e-08, | |
| "loss": 0.2895, | |
| "step": 10140 | |
| }, | |
| { | |
| "epoch": 70.48, | |
| "learning_rate": 2.975524475524475e-08, | |
| "loss": 0.317, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 70.55, | |
| "learning_rate": 2.9685314685314682e-08, | |
| "loss": 0.297, | |
| "step": 10160 | |
| }, | |
| { | |
| "epoch": 70.62, | |
| "learning_rate": 2.962237762237762e-08, | |
| "loss": 0.2909, | |
| "step": 10170 | |
| }, | |
| { | |
| "epoch": 70.69, | |
| "learning_rate": 2.955244755244755e-08, | |
| "loss": 0.3232, | |
| "step": 10180 | |
| }, | |
| { | |
| "epoch": 70.76, | |
| "learning_rate": 2.948251748251748e-08, | |
| "loss": 0.3204, | |
| "step": 10190 | |
| }, | |
| { | |
| "epoch": 70.83, | |
| "learning_rate": 2.941258741258741e-08, | |
| "loss": 0.3187, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 70.9, | |
| "learning_rate": 2.934265734265734e-08, | |
| "loss": 0.3042, | |
| "step": 10210 | |
| }, | |
| { | |
| "epoch": 70.97, | |
| "learning_rate": 2.927272727272727e-08, | |
| "loss": 0.3194, | |
| "step": 10220 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_loss": 0.45503440499305725, | |
| "eval_runtime": 125.1192, | |
| "eval_samples_per_second": 4.252, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.2101947676287202, | |
| "step": 10224 | |
| }, | |
| { | |
| "epoch": 71.04, | |
| "learning_rate": 2.9202797202797202e-08, | |
| "loss": 0.3339, | |
| "step": 10230 | |
| }, | |
| { | |
| "epoch": 71.11, | |
| "learning_rate": 2.9132867132867134e-08, | |
| "loss": 0.3077, | |
| "step": 10240 | |
| }, | |
| { | |
| "epoch": 71.18, | |
| "learning_rate": 2.906293706293706e-08, | |
| "loss": 0.2999, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 71.25, | |
| "learning_rate": 2.899300699300699e-08, | |
| "loss": 0.3106, | |
| "step": 10260 | |
| }, | |
| { | |
| "epoch": 71.32, | |
| "learning_rate": 2.8923076923076923e-08, | |
| "loss": 0.3087, | |
| "step": 10270 | |
| }, | |
| { | |
| "epoch": 71.39, | |
| "learning_rate": 2.8853146853146855e-08, | |
| "loss": 0.2891, | |
| "step": 10280 | |
| }, | |
| { | |
| "epoch": 71.46, | |
| "learning_rate": 2.878321678321678e-08, | |
| "loss": 0.32, | |
| "step": 10290 | |
| }, | |
| { | |
| "epoch": 71.53, | |
| "learning_rate": 2.8713286713286712e-08, | |
| "loss": 0.3107, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 71.6, | |
| "learning_rate": 2.8643356643356644e-08, | |
| "loss": 0.3198, | |
| "step": 10310 | |
| }, | |
| { | |
| "epoch": 71.66, | |
| "learning_rate": 2.8573426573426572e-08, | |
| "loss": 0.3005, | |
| "step": 10320 | |
| }, | |
| { | |
| "epoch": 71.73, | |
| "learning_rate": 2.8503496503496504e-08, | |
| "loss": 0.3258, | |
| "step": 10330 | |
| }, | |
| { | |
| "epoch": 71.8, | |
| "learning_rate": 2.843356643356643e-08, | |
| "loss": 0.2996, | |
| "step": 10340 | |
| }, | |
| { | |
| "epoch": 71.87, | |
| "learning_rate": 2.836363636363636e-08, | |
| "loss": 0.2963, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 71.94, | |
| "learning_rate": 2.8293706293706293e-08, | |
| "loss": 0.3243, | |
| "step": 10360 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_loss": 0.4545748829841614, | |
| "eval_runtime": 124.9622, | |
| "eval_samples_per_second": 4.257, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.20980908915600693, | |
| "step": 10368 | |
| }, | |
| { | |
| "epoch": 72.01, | |
| "learning_rate": 2.8223776223776225e-08, | |
| "loss": 0.3357, | |
| "step": 10370 | |
| }, | |
| { | |
| "epoch": 72.08, | |
| "learning_rate": 2.815384615384615e-08, | |
| "loss": 0.316, | |
| "step": 10380 | |
| }, | |
| { | |
| "epoch": 72.15, | |
| "learning_rate": 2.8083916083916082e-08, | |
| "loss": 0.3039, | |
| "step": 10390 | |
| }, | |
| { | |
| "epoch": 72.22, | |
| "learning_rate": 2.8013986013986014e-08, | |
| "loss": 0.3315, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 72.29, | |
| "learning_rate": 2.7944055944055945e-08, | |
| "loss": 0.2956, | |
| "step": 10410 | |
| }, | |
| { | |
| "epoch": 72.36, | |
| "learning_rate": 2.7874125874125877e-08, | |
| "loss": 0.3018, | |
| "step": 10420 | |
| }, | |
| { | |
| "epoch": 72.43, | |
| "learning_rate": 2.7804195804195802e-08, | |
| "loss": 0.3175, | |
| "step": 10430 | |
| }, | |
| { | |
| "epoch": 72.5, | |
| "learning_rate": 2.7734265734265734e-08, | |
| "loss": 0.3145, | |
| "step": 10440 | |
| }, | |
| { | |
| "epoch": 72.57, | |
| "learning_rate": 2.7664335664335663e-08, | |
| "loss": 0.3025, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 72.64, | |
| "learning_rate": 2.7594405594405595e-08, | |
| "loss": 0.3027, | |
| "step": 10460 | |
| }, | |
| { | |
| "epoch": 72.71, | |
| "learning_rate": 2.752447552447552e-08, | |
| "loss": 0.3218, | |
| "step": 10470 | |
| }, | |
| { | |
| "epoch": 72.78, | |
| "learning_rate": 2.745454545454545e-08, | |
| "loss": 0.3009, | |
| "step": 10480 | |
| }, | |
| { | |
| "epoch": 72.84, | |
| "learning_rate": 2.7384615384615383e-08, | |
| "loss": 0.3027, | |
| "step": 10490 | |
| }, | |
| { | |
| "epoch": 72.91, | |
| "learning_rate": 2.7314685314685315e-08, | |
| "loss": 0.2969, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 72.98, | |
| "learning_rate": 2.724475524475524e-08, | |
| "loss": 0.3115, | |
| "step": 10510 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_loss": 0.45424580574035645, | |
| "eval_runtime": 125.1479, | |
| "eval_samples_per_second": 4.251, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.21006620813781576, | |
| "step": 10512 | |
| }, | |
| { | |
| "epoch": 73.06, | |
| "learning_rate": 2.7174825174825172e-08, | |
| "loss": 0.3237, | |
| "step": 10520 | |
| }, | |
| { | |
| "epoch": 73.12, | |
| "learning_rate": 2.7104895104895104e-08, | |
| "loss": 0.2872, | |
| "step": 10530 | |
| }, | |
| { | |
| "epoch": 73.19, | |
| "learning_rate": 2.7034965034965036e-08, | |
| "loss": 0.3233, | |
| "step": 10540 | |
| }, | |
| { | |
| "epoch": 73.26, | |
| "learning_rate": 2.6965034965034968e-08, | |
| "loss": 0.3032, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 73.33, | |
| "learning_rate": 2.6895104895104893e-08, | |
| "loss": 0.3071, | |
| "step": 10560 | |
| }, | |
| { | |
| "epoch": 73.4, | |
| "learning_rate": 2.6825174825174825e-08, | |
| "loss": 0.3264, | |
| "step": 10570 | |
| }, | |
| { | |
| "epoch": 73.47, | |
| "learning_rate": 2.6755244755244753e-08, | |
| "loss": 0.306, | |
| "step": 10580 | |
| }, | |
| { | |
| "epoch": 73.54, | |
| "learning_rate": 2.6685314685314685e-08, | |
| "loss": 0.3005, | |
| "step": 10590 | |
| }, | |
| { | |
| "epoch": 73.61, | |
| "learning_rate": 2.661538461538461e-08, | |
| "loss": 0.304, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 73.68, | |
| "learning_rate": 2.6545454545454542e-08, | |
| "loss": 0.3003, | |
| "step": 10610 | |
| }, | |
| { | |
| "epoch": 73.75, | |
| "learning_rate": 2.6475524475524474e-08, | |
| "loss": 0.313, | |
| "step": 10620 | |
| }, | |
| { | |
| "epoch": 73.82, | |
| "learning_rate": 2.6405594405594406e-08, | |
| "loss": 0.2897, | |
| "step": 10630 | |
| }, | |
| { | |
| "epoch": 73.89, | |
| "learning_rate": 2.6335664335664338e-08, | |
| "loss": 0.2949, | |
| "step": 10640 | |
| }, | |
| { | |
| "epoch": 73.96, | |
| "learning_rate": 2.6265734265734263e-08, | |
| "loss": 0.3307, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_loss": 0.4544503092765808, | |
| "eval_runtime": 125.095, | |
| "eval_samples_per_second": 4.253, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.21000192839236356, | |
| "step": 10656 | |
| }, | |
| { | |
| "epoch": 74.03, | |
| "learning_rate": 2.6195804195804195e-08, | |
| "loss": 0.3164, | |
| "step": 10660 | |
| }, | |
| { | |
| "epoch": 74.1, | |
| "learning_rate": 2.6125874125874127e-08, | |
| "loss": 0.2833, | |
| "step": 10670 | |
| }, | |
| { | |
| "epoch": 74.17, | |
| "learning_rate": 2.605594405594406e-08, | |
| "loss": 0.2871, | |
| "step": 10680 | |
| }, | |
| { | |
| "epoch": 74.24, | |
| "learning_rate": 2.5986013986013984e-08, | |
| "loss": 0.3177, | |
| "step": 10690 | |
| }, | |
| { | |
| "epoch": 74.3, | |
| "learning_rate": 2.5916083916083915e-08, | |
| "loss": 0.2972, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 74.37, | |
| "learning_rate": 2.5846153846153844e-08, | |
| "loss": 0.2965, | |
| "step": 10710 | |
| }, | |
| { | |
| "epoch": 74.44, | |
| "learning_rate": 2.5776223776223776e-08, | |
| "loss": 0.3167, | |
| "step": 10720 | |
| }, | |
| { | |
| "epoch": 74.51, | |
| "learning_rate": 2.57062937062937e-08, | |
| "loss": 0.3104, | |
| "step": 10730 | |
| }, | |
| { | |
| "epoch": 74.58, | |
| "learning_rate": 2.5636363636363633e-08, | |
| "loss": 0.312, | |
| "step": 10740 | |
| }, | |
| { | |
| "epoch": 74.65, | |
| "learning_rate": 2.5566433566433565e-08, | |
| "loss": 0.3036, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 74.72, | |
| "learning_rate": 2.5496503496503496e-08, | |
| "loss": 0.3224, | |
| "step": 10760 | |
| }, | |
| { | |
| "epoch": 74.79, | |
| "learning_rate": 2.5426573426573428e-08, | |
| "loss": 0.3229, | |
| "step": 10770 | |
| }, | |
| { | |
| "epoch": 74.86, | |
| "learning_rate": 2.5356643356643353e-08, | |
| "loss": 0.3112, | |
| "step": 10780 | |
| }, | |
| { | |
| "epoch": 74.93, | |
| "learning_rate": 2.5286713286713285e-08, | |
| "loss": 0.317, | |
| "step": 10790 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 2.5216783216783217e-08, | |
| "loss": 0.3072, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_loss": 0.45469069480895996, | |
| "eval_runtime": 125.8275, | |
| "eval_samples_per_second": 4.228, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.21000192839236356, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 75.07, | |
| "learning_rate": 2.514685314685315e-08, | |
| "loss": 0.3389, | |
| "step": 10810 | |
| }, | |
| { | |
| "epoch": 75.14, | |
| "learning_rate": 2.5076923076923074e-08, | |
| "loss": 0.3117, | |
| "step": 10820 | |
| }, | |
| { | |
| "epoch": 75.21, | |
| "learning_rate": 2.5006993006993006e-08, | |
| "loss": 0.3341, | |
| "step": 10830 | |
| }, | |
| { | |
| "epoch": 75.28, | |
| "learning_rate": 2.4937062937062935e-08, | |
| "loss": 0.3071, | |
| "step": 10840 | |
| }, | |
| { | |
| "epoch": 75.35, | |
| "learning_rate": 2.4867132867132866e-08, | |
| "loss": 0.305, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 75.42, | |
| "learning_rate": 2.4797202797202795e-08, | |
| "loss": 0.3047, | |
| "step": 10860 | |
| }, | |
| { | |
| "epoch": 75.48, | |
| "learning_rate": 2.4727272727272727e-08, | |
| "loss": 0.3316, | |
| "step": 10870 | |
| }, | |
| { | |
| "epoch": 75.55, | |
| "learning_rate": 2.4657342657342655e-08, | |
| "loss": 0.2943, | |
| "step": 10880 | |
| }, | |
| { | |
| "epoch": 75.62, | |
| "learning_rate": 2.4587412587412587e-08, | |
| "loss": 0.302, | |
| "step": 10890 | |
| }, | |
| { | |
| "epoch": 75.69, | |
| "learning_rate": 2.4517482517482516e-08, | |
| "loss": 0.2991, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 75.76, | |
| "learning_rate": 2.4447552447552447e-08, | |
| "loss": 0.3293, | |
| "step": 10910 | |
| }, | |
| { | |
| "epoch": 75.83, | |
| "learning_rate": 2.4377622377622376e-08, | |
| "loss": 0.2859, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 75.9, | |
| "learning_rate": 2.4307692307692308e-08, | |
| "loss": 0.3076, | |
| "step": 10930 | |
| }, | |
| { | |
| "epoch": 75.97, | |
| "learning_rate": 2.4237762237762236e-08, | |
| "loss": 0.3218, | |
| "step": 10940 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_loss": 0.454466313123703, | |
| "eval_runtime": 125.1774, | |
| "eval_samples_per_second": 4.25, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.2101947676287202, | |
| "step": 10944 | |
| }, | |
| { | |
| "epoch": 76.04, | |
| "learning_rate": 2.4167832167832168e-08, | |
| "loss": 0.3128, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 76.11, | |
| "learning_rate": 2.4097902097902097e-08, | |
| "loss": 0.3071, | |
| "step": 10960 | |
| }, | |
| { | |
| "epoch": 76.18, | |
| "learning_rate": 2.4027972027972025e-08, | |
| "loss": 0.3023, | |
| "step": 10970 | |
| }, | |
| { | |
| "epoch": 76.25, | |
| "learning_rate": 2.3958041958041957e-08, | |
| "loss": 0.3387, | |
| "step": 10980 | |
| }, | |
| { | |
| "epoch": 76.32, | |
| "learning_rate": 2.3888111888111885e-08, | |
| "loss": 0.3221, | |
| "step": 10990 | |
| }, | |
| { | |
| "epoch": 76.39, | |
| "learning_rate": 2.3818181818181817e-08, | |
| "loss": 0.2908, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 76.46, | |
| "learning_rate": 2.3748251748251746e-08, | |
| "loss": 0.3087, | |
| "step": 11010 | |
| }, | |
| { | |
| "epoch": 76.53, | |
| "learning_rate": 2.3678321678321678e-08, | |
| "loss": 0.3095, | |
| "step": 11020 | |
| }, | |
| { | |
| "epoch": 76.6, | |
| "learning_rate": 2.3608391608391606e-08, | |
| "loss": 0.313, | |
| "step": 11030 | |
| }, | |
| { | |
| "epoch": 76.66, | |
| "learning_rate": 2.3538461538461538e-08, | |
| "loss": 0.2948, | |
| "step": 11040 | |
| }, | |
| { | |
| "epoch": 76.73, | |
| "learning_rate": 2.3468531468531467e-08, | |
| "loss": 0.3019, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 76.8, | |
| "learning_rate": 2.3398601398601398e-08, | |
| "loss": 0.3104, | |
| "step": 11060 | |
| }, | |
| { | |
| "epoch": 76.87, | |
| "learning_rate": 2.332867132867133e-08, | |
| "loss": 0.3173, | |
| "step": 11070 | |
| }, | |
| { | |
| "epoch": 76.94, | |
| "learning_rate": 2.325874125874126e-08, | |
| "loss": 0.3116, | |
| "step": 11080 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_loss": 0.4539944529533386, | |
| "eval_runtime": 125.3785, | |
| "eval_samples_per_second": 4.243, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.2102590473741724, | |
| "step": 11088 | |
| }, | |
| { | |
| "epoch": 77.01, | |
| "learning_rate": 2.3188811188811187e-08, | |
| "loss": 0.3204, | |
| "step": 11090 | |
| }, | |
| { | |
| "epoch": 77.08, | |
| "learning_rate": 2.3118881118881116e-08, | |
| "loss": 0.2901, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 77.15, | |
| "learning_rate": 2.3048951048951048e-08, | |
| "loss": 0.3055, | |
| "step": 11110 | |
| }, | |
| { | |
| "epoch": 77.22, | |
| "learning_rate": 2.2979020979020976e-08, | |
| "loss": 0.3151, | |
| "step": 11120 | |
| }, | |
| { | |
| "epoch": 77.29, | |
| "learning_rate": 2.2909090909090908e-08, | |
| "loss": 0.3136, | |
| "step": 11130 | |
| }, | |
| { | |
| "epoch": 77.36, | |
| "learning_rate": 2.2839160839160836e-08, | |
| "loss": 0.3122, | |
| "step": 11140 | |
| }, | |
| { | |
| "epoch": 77.43, | |
| "learning_rate": 2.2769230769230768e-08, | |
| "loss": 0.3097, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 77.5, | |
| "learning_rate": 2.2699300699300697e-08, | |
| "loss": 0.3166, | |
| "step": 11160 | |
| }, | |
| { | |
| "epoch": 77.57, | |
| "learning_rate": 2.262937062937063e-08, | |
| "loss": 0.3137, | |
| "step": 11170 | |
| }, | |
| { | |
| "epoch": 77.64, | |
| "learning_rate": 2.255944055944056e-08, | |
| "loss": 0.3082, | |
| "step": 11180 | |
| }, | |
| { | |
| "epoch": 77.71, | |
| "learning_rate": 2.248951048951049e-08, | |
| "loss": 0.3219, | |
| "step": 11190 | |
| }, | |
| { | |
| "epoch": 77.78, | |
| "learning_rate": 2.241958041958042e-08, | |
| "loss": 0.319, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 77.84, | |
| "learning_rate": 2.234965034965035e-08, | |
| "loss": 0.3054, | |
| "step": 11210 | |
| }, | |
| { | |
| "epoch": 77.91, | |
| "learning_rate": 2.2279720279720278e-08, | |
| "loss": 0.3028, | |
| "step": 11220 | |
| }, | |
| { | |
| "epoch": 77.98, | |
| "learning_rate": 2.2209790209790206e-08, | |
| "loss": 0.3021, | |
| "step": 11230 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_loss": 0.4541701078414917, | |
| "eval_runtime": 125.4496, | |
| "eval_samples_per_second": 4.241, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.210130487883268, | |
| "step": 11232 | |
| }, | |
| { | |
| "epoch": 78.06, | |
| "learning_rate": 2.2139860139860138e-08, | |
| "loss": 0.3217, | |
| "step": 11240 | |
| }, | |
| { | |
| "epoch": 78.12, | |
| "learning_rate": 2.2069930069930067e-08, | |
| "loss": 0.3032, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 78.19, | |
| "learning_rate": 2.2e-08, | |
| "loss": 0.3094, | |
| "step": 11260 | |
| }, | |
| { | |
| "epoch": 78.26, | |
| "learning_rate": 2.193006993006993e-08, | |
| "loss": 0.3147, | |
| "step": 11270 | |
| }, | |
| { | |
| "epoch": 78.33, | |
| "learning_rate": 2.186013986013986e-08, | |
| "loss": 0.3154, | |
| "step": 11280 | |
| }, | |
| { | |
| "epoch": 78.4, | |
| "learning_rate": 2.179020979020979e-08, | |
| "loss": 0.2897, | |
| "step": 11290 | |
| }, | |
| { | |
| "epoch": 78.47, | |
| "learning_rate": 2.172027972027972e-08, | |
| "loss": 0.33, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 78.54, | |
| "learning_rate": 2.165034965034965e-08, | |
| "loss": 0.2966, | |
| "step": 11310 | |
| }, | |
| { | |
| "epoch": 78.61, | |
| "learning_rate": 2.158041958041958e-08, | |
| "loss": 0.3068, | |
| "step": 11320 | |
| }, | |
| { | |
| "epoch": 78.68, | |
| "learning_rate": 2.151048951048951e-08, | |
| "loss": 0.3104, | |
| "step": 11330 | |
| }, | |
| { | |
| "epoch": 78.75, | |
| "learning_rate": 2.144055944055944e-08, | |
| "loss": 0.2974, | |
| "step": 11340 | |
| }, | |
| { | |
| "epoch": 78.82, | |
| "learning_rate": 2.137062937062937e-08, | |
| "loss": 0.3165, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 78.89, | |
| "learning_rate": 2.1300699300699297e-08, | |
| "loss": 0.3095, | |
| "step": 11360 | |
| }, | |
| { | |
| "epoch": 78.96, | |
| "learning_rate": 2.123076923076923e-08, | |
| "loss": 0.3165, | |
| "step": 11370 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_loss": 0.4538624584674835, | |
| "eval_runtime": 125.0487, | |
| "eval_samples_per_second": 4.254, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.21090184482869448, | |
| "step": 11376 | |
| }, | |
| { | |
| "epoch": 79.03, | |
| "learning_rate": 2.116083916083916e-08, | |
| "loss": 0.3241, | |
| "step": 11380 | |
| }, | |
| { | |
| "epoch": 79.1, | |
| "learning_rate": 2.109090909090909e-08, | |
| "loss": 0.3085, | |
| "step": 11390 | |
| }, | |
| { | |
| "epoch": 79.17, | |
| "learning_rate": 2.102097902097902e-08, | |
| "loss": 0.2972, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 79.24, | |
| "learning_rate": 2.095104895104895e-08, | |
| "loss": 0.3229, | |
| "step": 11410 | |
| }, | |
| { | |
| "epoch": 79.3, | |
| "learning_rate": 2.088111888111888e-08, | |
| "loss": 0.3059, | |
| "step": 11420 | |
| }, | |
| { | |
| "epoch": 79.37, | |
| "learning_rate": 2.081118881118881e-08, | |
| "loss": 0.2946, | |
| "step": 11430 | |
| }, | |
| { | |
| "epoch": 79.44, | |
| "learning_rate": 2.074125874125874e-08, | |
| "loss": 0.3148, | |
| "step": 11440 | |
| }, | |
| { | |
| "epoch": 79.51, | |
| "learning_rate": 2.067132867132867e-08, | |
| "loss": 0.3165, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 79.58, | |
| "learning_rate": 2.0601398601398602e-08, | |
| "loss": 0.3061, | |
| "step": 11460 | |
| }, | |
| { | |
| "epoch": 79.65, | |
| "learning_rate": 2.053146853146853e-08, | |
| "loss": 0.2927, | |
| "step": 11470 | |
| }, | |
| { | |
| "epoch": 79.72, | |
| "learning_rate": 2.0461538461538462e-08, | |
| "loss": 0.3274, | |
| "step": 11480 | |
| }, | |
| { | |
| "epoch": 79.79, | |
| "learning_rate": 2.039160839160839e-08, | |
| "loss": 0.3029, | |
| "step": 11490 | |
| }, | |
| { | |
| "epoch": 79.86, | |
| "learning_rate": 2.032167832167832e-08, | |
| "loss": 0.3121, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 79.93, | |
| "learning_rate": 2.025174825174825e-08, | |
| "loss": 0.3109, | |
| "step": 11510 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 2.018181818181818e-08, | |
| "loss": 0.327, | |
| "step": 11520 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_loss": 0.4538904130458832, | |
| "eval_runtime": 125.177, | |
| "eval_samples_per_second": 4.25, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.20897345246512825, | |
| "step": 11520 | |
| }, | |
| { | |
| "epoch": 80.07, | |
| "learning_rate": 2.011188811188811e-08, | |
| "loss": 0.3161, | |
| "step": 11530 | |
| }, | |
| { | |
| "epoch": 80.14, | |
| "learning_rate": 2.004195804195804e-08, | |
| "loss": 0.2999, | |
| "step": 11540 | |
| }, | |
| { | |
| "epoch": 80.21, | |
| "learning_rate": 1.9972027972027972e-08, | |
| "loss": 0.3113, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 80.28, | |
| "learning_rate": 1.99020979020979e-08, | |
| "loss": 0.3083, | |
| "step": 11560 | |
| }, | |
| { | |
| "epoch": 80.35, | |
| "learning_rate": 1.9832167832167832e-08, | |
| "loss": 0.3045, | |
| "step": 11570 | |
| }, | |
| { | |
| "epoch": 80.42, | |
| "learning_rate": 1.976223776223776e-08, | |
| "loss": 0.3173, | |
| "step": 11580 | |
| }, | |
| { | |
| "epoch": 80.48, | |
| "learning_rate": 1.9692307692307693e-08, | |
| "loss": 0.3103, | |
| "step": 11590 | |
| }, | |
| { | |
| "epoch": 80.55, | |
| "learning_rate": 1.9622377622377624e-08, | |
| "loss": 0.2861, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 80.62, | |
| "learning_rate": 1.9552447552447553e-08, | |
| "loss": 0.3106, | |
| "step": 11610 | |
| }, | |
| { | |
| "epoch": 80.69, | |
| "learning_rate": 1.948251748251748e-08, | |
| "loss": 0.3117, | |
| "step": 11620 | |
| }, | |
| { | |
| "epoch": 80.76, | |
| "learning_rate": 1.941258741258741e-08, | |
| "loss": 0.3121, | |
| "step": 11630 | |
| }, | |
| { | |
| "epoch": 80.83, | |
| "learning_rate": 1.9342657342657342e-08, | |
| "loss": 0.3197, | |
| "step": 11640 | |
| }, | |
| { | |
| "epoch": 80.9, | |
| "learning_rate": 1.927272727272727e-08, | |
| "loss": 0.2996, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 80.97, | |
| "learning_rate": 1.9202797202797202e-08, | |
| "loss": 0.3268, | |
| "step": 11660 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_loss": 0.4539640545845032, | |
| "eval_runtime": 125.0375, | |
| "eval_samples_per_second": 4.255, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.2110304043195989, | |
| "step": 11664 | |
| }, | |
| { | |
| "epoch": 81.04, | |
| "learning_rate": 1.913286713286713e-08, | |
| "loss": 0.3115, | |
| "step": 11670 | |
| }, | |
| { | |
| "epoch": 81.11, | |
| "learning_rate": 1.9062937062937062e-08, | |
| "loss": 0.3076, | |
| "step": 11680 | |
| }, | |
| { | |
| "epoch": 81.18, | |
| "learning_rate": 1.899300699300699e-08, | |
| "loss": 0.3072, | |
| "step": 11690 | |
| }, | |
| { | |
| "epoch": 81.25, | |
| "learning_rate": 1.8923076923076923e-08, | |
| "loss": 0.3199, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 81.32, | |
| "learning_rate": 1.8853146853146855e-08, | |
| "loss": 0.297, | |
| "step": 11710 | |
| }, | |
| { | |
| "epoch": 81.39, | |
| "learning_rate": 1.8783216783216783e-08, | |
| "loss": 0.2805, | |
| "step": 11720 | |
| }, | |
| { | |
| "epoch": 81.46, | |
| "learning_rate": 1.8713286713286715e-08, | |
| "loss": 0.3012, | |
| "step": 11730 | |
| }, | |
| { | |
| "epoch": 81.53, | |
| "learning_rate": 1.8643356643356643e-08, | |
| "loss": 0.312, | |
| "step": 11740 | |
| }, | |
| { | |
| "epoch": 81.6, | |
| "learning_rate": 1.8573426573426572e-08, | |
| "loss": 0.3134, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 81.66, | |
| "learning_rate": 1.85034965034965e-08, | |
| "loss": 0.3089, | |
| "step": 11760 | |
| }, | |
| { | |
| "epoch": 81.73, | |
| "learning_rate": 1.8433566433566432e-08, | |
| "loss": 0.3262, | |
| "step": 11770 | |
| }, | |
| { | |
| "epoch": 81.8, | |
| "learning_rate": 1.836363636363636e-08, | |
| "loss": 0.3062, | |
| "step": 11780 | |
| }, | |
| { | |
| "epoch": 81.87, | |
| "learning_rate": 1.8293706293706293e-08, | |
| "loss": 0.3041, | |
| "step": 11790 | |
| }, | |
| { | |
| "epoch": 81.94, | |
| "learning_rate": 1.822377622377622e-08, | |
| "loss": 0.304, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_loss": 0.4536815583705902, | |
| "eval_runtime": 125.0215, | |
| "eval_samples_per_second": 4.255, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.20974480941055473, | |
| "step": 11808 | |
| }, | |
| { | |
| "epoch": 82.01, | |
| "learning_rate": 1.8153846153846153e-08, | |
| "loss": 0.3284, | |
| "step": 11810 | |
| }, | |
| { | |
| "epoch": 82.08, | |
| "learning_rate": 1.8083916083916085e-08, | |
| "loss": 0.3081, | |
| "step": 11820 | |
| }, | |
| { | |
| "epoch": 82.15, | |
| "learning_rate": 1.8013986013986013e-08, | |
| "loss": 0.2987, | |
| "step": 11830 | |
| }, | |
| { | |
| "epoch": 82.22, | |
| "learning_rate": 1.7944055944055945e-08, | |
| "loss": 0.33, | |
| "step": 11840 | |
| }, | |
| { | |
| "epoch": 82.29, | |
| "learning_rate": 1.7874125874125874e-08, | |
| "loss": 0.2905, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 82.36, | |
| "learning_rate": 1.7804195804195806e-08, | |
| "loss": 0.293, | |
| "step": 11860 | |
| }, | |
| { | |
| "epoch": 82.43, | |
| "learning_rate": 1.7734265734265734e-08, | |
| "loss": 0.3306, | |
| "step": 11870 | |
| }, | |
| { | |
| "epoch": 82.5, | |
| "learning_rate": 1.7664335664335663e-08, | |
| "loss": 0.3168, | |
| "step": 11880 | |
| }, | |
| { | |
| "epoch": 82.57, | |
| "learning_rate": 1.759440559440559e-08, | |
| "loss": 0.3243, | |
| "step": 11890 | |
| }, | |
| { | |
| "epoch": 82.64, | |
| "learning_rate": 1.7524475524475523e-08, | |
| "loss": 0.2946, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 82.71, | |
| "learning_rate": 1.7454545454545455e-08, | |
| "loss": 0.3041, | |
| "step": 11910 | |
| }, | |
| { | |
| "epoch": 82.78, | |
| "learning_rate": 1.7384615384615383e-08, | |
| "loss": 0.3225, | |
| "step": 11920 | |
| }, | |
| { | |
| "epoch": 82.84, | |
| "learning_rate": 1.7314685314685315e-08, | |
| "loss": 0.3177, | |
| "step": 11930 | |
| }, | |
| { | |
| "epoch": 82.91, | |
| "learning_rate": 1.7244755244755244e-08, | |
| "loss": 0.2915, | |
| "step": 11940 | |
| }, | |
| { | |
| "epoch": 82.98, | |
| "learning_rate": 1.7174825174825175e-08, | |
| "loss": 0.3256, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_loss": 0.4536934792995453, | |
| "eval_runtime": 124.9968, | |
| "eval_samples_per_second": 4.256, | |
| "eval_steps_per_second": 0.536, | |
| "eval_wer": 0.2101947676287202, | |
| "step": 11952 | |
| }, | |
| { | |
| "epoch": 83.06, | |
| "learning_rate": 1.7104895104895104e-08, | |
| "loss": 0.3175, | |
| "step": 11960 | |
| }, | |
| { | |
| "epoch": 83.12, | |
| "learning_rate": 1.7034965034965036e-08, | |
| "loss": 0.3103, | |
| "step": 11970 | |
| }, | |
| { | |
| "epoch": 83.19, | |
| "learning_rate": 1.6965034965034964e-08, | |
| "loss": 0.3086, | |
| "step": 11980 | |
| }, | |
| { | |
| "epoch": 83.26, | |
| "learning_rate": 1.6895104895104896e-08, | |
| "loss": 0.3108, | |
| "step": 11990 | |
| }, | |
| { | |
| "epoch": 83.33, | |
| "learning_rate": 1.6825174825174825e-08, | |
| "loss": 0.3006, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 83.4, | |
| "learning_rate": 1.6755244755244753e-08, | |
| "loss": 0.2951, | |
| "step": 12010 | |
| }, | |
| { | |
| "epoch": 83.47, | |
| "learning_rate": 1.6685314685314685e-08, | |
| "loss": 0.321, | |
| "step": 12020 | |
| }, | |
| { | |
| "epoch": 83.54, | |
| "learning_rate": 1.6615384615384613e-08, | |
| "loss": 0.2959, | |
| "step": 12030 | |
| }, | |
| { | |
| "epoch": 83.61, | |
| "learning_rate": 1.6545454545454545e-08, | |
| "loss": 0.2939, | |
| "step": 12040 | |
| }, | |
| { | |
| "epoch": 83.68, | |
| "learning_rate": 1.6475524475524474e-08, | |
| "loss": 0.3139, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 83.75, | |
| "learning_rate": 1.6405594405594406e-08, | |
| "loss": 0.2986, | |
| "step": 12060 | |
| }, | |
| { | |
| "epoch": 83.82, | |
| "learning_rate": 1.6335664335664334e-08, | |
| "loss": 0.3116, | |
| "step": 12070 | |
| }, | |
| { | |
| "epoch": 83.89, | |
| "learning_rate": 1.6265734265734266e-08, | |
| "loss": 0.3053, | |
| "step": 12080 | |
| }, | |
| { | |
| "epoch": 83.96, | |
| "learning_rate": 1.6195804195804195e-08, | |
| "loss": 0.3208, | |
| "step": 12090 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_loss": 0.4543744921684265, | |
| "eval_runtime": 125.7177, | |
| "eval_samples_per_second": 4.232, | |
| "eval_steps_per_second": 0.533, | |
| "eval_wer": 0.210130487883268, | |
| "step": 12096 | |
| }, | |
| { | |
| "epoch": 84.03, | |
| "learning_rate": 1.6125874125874126e-08, | |
| "loss": 0.3352, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 84.1, | |
| "learning_rate": 1.6055944055944055e-08, | |
| "loss": 0.2983, | |
| "step": 12110 | |
| }, | |
| { | |
| "epoch": 84.17, | |
| "learning_rate": 1.5986013986013987e-08, | |
| "loss": 0.3034, | |
| "step": 12120 | |
| }, | |
| { | |
| "epoch": 84.24, | |
| "learning_rate": 1.5916083916083915e-08, | |
| "loss": 0.3217, | |
| "step": 12130 | |
| }, | |
| { | |
| "epoch": 84.3, | |
| "learning_rate": 1.5846153846153844e-08, | |
| "loss": 0.3052, | |
| "step": 12140 | |
| }, | |
| { | |
| "epoch": 84.37, | |
| "learning_rate": 1.5776223776223776e-08, | |
| "loss": 0.3119, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 84.44, | |
| "learning_rate": 1.5706293706293704e-08, | |
| "loss": 0.3191, | |
| "step": 12160 | |
| }, | |
| { | |
| "epoch": 84.51, | |
| "learning_rate": 1.5636363636363636e-08, | |
| "loss": 0.3147, | |
| "step": 12170 | |
| }, | |
| { | |
| "epoch": 84.58, | |
| "learning_rate": 1.5566433566433564e-08, | |
| "loss": 0.2984, | |
| "step": 12180 | |
| }, | |
| { | |
| "epoch": 84.65, | |
| "learning_rate": 1.5496503496503496e-08, | |
| "loss": 0.2774, | |
| "step": 12190 | |
| }, | |
| { | |
| "epoch": 84.72, | |
| "learning_rate": 1.5426573426573425e-08, | |
| "loss": 0.3162, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 84.79, | |
| "learning_rate": 1.5356643356643357e-08, | |
| "loss": 0.3142, | |
| "step": 12210 | |
| }, | |
| { | |
| "epoch": 84.86, | |
| "learning_rate": 1.5286713286713285e-08, | |
| "loss": 0.3118, | |
| "step": 12220 | |
| }, | |
| { | |
| "epoch": 84.93, | |
| "learning_rate": 1.5216783216783217e-08, | |
| "loss": 0.3114, | |
| "step": 12230 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "learning_rate": 1.514685314685315e-08, | |
| "loss": 0.3199, | |
| "step": 12240 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_loss": 0.45406830310821533, | |
| "eval_runtime": 125.3217, | |
| "eval_samples_per_second": 4.245, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.2094234106832937, | |
| "step": 12240 | |
| }, | |
| { | |
| "epoch": 85.07, | |
| "learning_rate": 1.5076923076923077e-08, | |
| "loss": 0.3013, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 85.14, | |
| "learning_rate": 1.5006993006993006e-08, | |
| "loss": 0.3025, | |
| "step": 12260 | |
| }, | |
| { | |
| "epoch": 85.21, | |
| "learning_rate": 1.4937062937062934e-08, | |
| "loss": 0.3165, | |
| "step": 12270 | |
| }, | |
| { | |
| "epoch": 85.28, | |
| "learning_rate": 1.4867132867132868e-08, | |
| "loss": 0.2998, | |
| "step": 12280 | |
| }, | |
| { | |
| "epoch": 85.35, | |
| "learning_rate": 1.4797202797202796e-08, | |
| "loss": 0.3161, | |
| "step": 12290 | |
| }, | |
| { | |
| "epoch": 85.42, | |
| "learning_rate": 1.4727272727272726e-08, | |
| "loss": 0.3217, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 85.48, | |
| "learning_rate": 1.4657342657342655e-08, | |
| "loss": 0.3216, | |
| "step": 12310 | |
| }, | |
| { | |
| "epoch": 85.55, | |
| "learning_rate": 1.4587412587412587e-08, | |
| "loss": 0.298, | |
| "step": 12320 | |
| }, | |
| { | |
| "epoch": 85.62, | |
| "learning_rate": 1.4517482517482515e-08, | |
| "loss": 0.3017, | |
| "step": 12330 | |
| }, | |
| { | |
| "epoch": 85.69, | |
| "learning_rate": 1.4447552447552447e-08, | |
| "loss": 0.3087, | |
| "step": 12340 | |
| }, | |
| { | |
| "epoch": 85.76, | |
| "learning_rate": 1.4377622377622377e-08, | |
| "loss": 0.3147, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 85.83, | |
| "learning_rate": 1.4307692307692308e-08, | |
| "loss": 0.323, | |
| "step": 12360 | |
| }, | |
| { | |
| "epoch": 85.9, | |
| "learning_rate": 1.4237762237762238e-08, | |
| "loss": 0.2913, | |
| "step": 12370 | |
| }, | |
| { | |
| "epoch": 85.97, | |
| "learning_rate": 1.4167832167832166e-08, | |
| "loss": 0.3104, | |
| "step": 12380 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_loss": 0.45433667302131653, | |
| "eval_runtime": 125.47, | |
| "eval_samples_per_second": 4.24, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.20974480941055473, | |
| "step": 12384 | |
| }, | |
| { | |
| "epoch": 86.04, | |
| "learning_rate": 1.4097902097902098e-08, | |
| "loss": 0.3144, | |
| "step": 12390 | |
| }, | |
| { | |
| "epoch": 86.11, | |
| "learning_rate": 1.4027972027972027e-08, | |
| "loss": 0.3041, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 86.18, | |
| "learning_rate": 1.3958041958041958e-08, | |
| "loss": 0.3133, | |
| "step": 12410 | |
| }, | |
| { | |
| "epoch": 86.25, | |
| "learning_rate": 1.3888111888111887e-08, | |
| "loss": 0.3254, | |
| "step": 12420 | |
| }, | |
| { | |
| "epoch": 86.32, | |
| "learning_rate": 1.3818181818181817e-08, | |
| "loss": 0.3126, | |
| "step": 12430 | |
| }, | |
| { | |
| "epoch": 86.39, | |
| "learning_rate": 1.3748251748251746e-08, | |
| "loss": 0.2937, | |
| "step": 12440 | |
| }, | |
| { | |
| "epoch": 86.46, | |
| "learning_rate": 1.3678321678321677e-08, | |
| "loss": 0.313, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 86.53, | |
| "learning_rate": 1.360839160839161e-08, | |
| "loss": 0.3112, | |
| "step": 12460 | |
| }, | |
| { | |
| "epoch": 86.6, | |
| "learning_rate": 1.3538461538461538e-08, | |
| "loss": 0.292, | |
| "step": 12470 | |
| }, | |
| { | |
| "epoch": 86.66, | |
| "learning_rate": 1.346853146853147e-08, | |
| "loss": 0.2992, | |
| "step": 12480 | |
| }, | |
| { | |
| "epoch": 86.73, | |
| "learning_rate": 1.3398601398601398e-08, | |
| "loss": 0.3185, | |
| "step": 12490 | |
| }, | |
| { | |
| "epoch": 86.8, | |
| "learning_rate": 1.3328671328671328e-08, | |
| "loss": 0.3193, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 86.87, | |
| "learning_rate": 1.3258741258741257e-08, | |
| "loss": 0.2991, | |
| "step": 12510 | |
| }, | |
| { | |
| "epoch": 86.94, | |
| "learning_rate": 1.3188811188811189e-08, | |
| "loss": 0.3218, | |
| "step": 12520 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_loss": 0.4541882574558258, | |
| "eval_runtime": 125.8296, | |
| "eval_samples_per_second": 4.228, | |
| "eval_steps_per_second": 0.532, | |
| "eval_wer": 0.21058044610143345, | |
| "step": 12528 | |
| }, | |
| { | |
| "epoch": 87.01, | |
| "learning_rate": 1.3118881118881117e-08, | |
| "loss": 0.3246, | |
| "step": 12530 | |
| }, | |
| { | |
| "epoch": 87.08, | |
| "learning_rate": 1.3048951048951049e-08, | |
| "loss": 0.3153, | |
| "step": 12540 | |
| }, | |
| { | |
| "epoch": 87.15, | |
| "learning_rate": 1.2979020979020979e-08, | |
| "loss": 0.3133, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 87.22, | |
| "learning_rate": 1.2909090909090908e-08, | |
| "loss": 0.3234, | |
| "step": 12560 | |
| }, | |
| { | |
| "epoch": 87.29, | |
| "learning_rate": 1.283916083916084e-08, | |
| "loss": 0.301, | |
| "step": 12570 | |
| }, | |
| { | |
| "epoch": 87.36, | |
| "learning_rate": 1.2769230769230768e-08, | |
| "loss": 0.3026, | |
| "step": 12580 | |
| }, | |
| { | |
| "epoch": 87.43, | |
| "learning_rate": 1.26993006993007e-08, | |
| "loss": 0.3131, | |
| "step": 12590 | |
| }, | |
| { | |
| "epoch": 87.5, | |
| "learning_rate": 1.2629370629370628e-08, | |
| "loss": 0.3139, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 87.57, | |
| "learning_rate": 1.255944055944056e-08, | |
| "loss": 0.3038, | |
| "step": 12610 | |
| }, | |
| { | |
| "epoch": 87.64, | |
| "learning_rate": 1.2489510489510489e-08, | |
| "loss": 0.284, | |
| "step": 12620 | |
| }, | |
| { | |
| "epoch": 87.71, | |
| "learning_rate": 1.2419580419580419e-08, | |
| "loss": 0.3025, | |
| "step": 12630 | |
| }, | |
| { | |
| "epoch": 87.78, | |
| "learning_rate": 1.2349650349650349e-08, | |
| "loss": 0.3152, | |
| "step": 12640 | |
| }, | |
| { | |
| "epoch": 87.84, | |
| "learning_rate": 1.227972027972028e-08, | |
| "loss": 0.325, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 87.91, | |
| "learning_rate": 1.220979020979021e-08, | |
| "loss": 0.304, | |
| "step": 12660 | |
| }, | |
| { | |
| "epoch": 87.98, | |
| "learning_rate": 1.213986013986014e-08, | |
| "loss": 0.3301, | |
| "step": 12670 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_loss": 0.45383813977241516, | |
| "eval_runtime": 125.2566, | |
| "eval_samples_per_second": 4.247, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.20980908915600693, | |
| "step": 12672 | |
| }, | |
| { | |
| "epoch": 88.06, | |
| "learning_rate": 1.206993006993007e-08, | |
| "loss": 0.3259, | |
| "step": 12680 | |
| }, | |
| { | |
| "epoch": 88.12, | |
| "learning_rate": 1.1999999999999998e-08, | |
| "loss": 0.2943, | |
| "step": 12690 | |
| }, | |
| { | |
| "epoch": 88.19, | |
| "learning_rate": 1.1930069930069928e-08, | |
| "loss": 0.3096, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 88.26, | |
| "learning_rate": 1.186013986013986e-08, | |
| "loss": 0.3033, | |
| "step": 12710 | |
| }, | |
| { | |
| "epoch": 88.33, | |
| "learning_rate": 1.179020979020979e-08, | |
| "loss": 0.3228, | |
| "step": 12720 | |
| }, | |
| { | |
| "epoch": 88.4, | |
| "learning_rate": 1.172027972027972e-08, | |
| "loss": 0.3097, | |
| "step": 12730 | |
| }, | |
| { | |
| "epoch": 88.47, | |
| "learning_rate": 1.165034965034965e-08, | |
| "loss": 0.3138, | |
| "step": 12740 | |
| }, | |
| { | |
| "epoch": 88.54, | |
| "learning_rate": 1.158041958041958e-08, | |
| "loss": 0.3004, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 88.61, | |
| "learning_rate": 1.151048951048951e-08, | |
| "loss": 0.3026, | |
| "step": 12760 | |
| }, | |
| { | |
| "epoch": 88.68, | |
| "learning_rate": 1.144055944055944e-08, | |
| "loss": 0.3096, | |
| "step": 12770 | |
| }, | |
| { | |
| "epoch": 88.75, | |
| "learning_rate": 1.137062937062937e-08, | |
| "loss": 0.3197, | |
| "step": 12780 | |
| }, | |
| { | |
| "epoch": 88.82, | |
| "learning_rate": 1.13006993006993e-08, | |
| "loss": 0.2987, | |
| "step": 12790 | |
| }, | |
| { | |
| "epoch": 88.89, | |
| "learning_rate": 1.123076923076923e-08, | |
| "loss": 0.3051, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 88.96, | |
| "learning_rate": 1.1167832167832167e-08, | |
| "loss": 0.3055, | |
| "step": 12810 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_loss": 0.4539641737937927, | |
| "eval_runtime": 125.3986, | |
| "eval_samples_per_second": 4.242, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.210130487883268, | |
| "step": 12816 | |
| }, | |
| { | |
| "epoch": 89.03, | |
| "learning_rate": 1.1097902097902096e-08, | |
| "loss": 0.3231, | |
| "step": 12820 | |
| }, | |
| { | |
| "epoch": 89.1, | |
| "learning_rate": 1.1027972027972028e-08, | |
| "loss": 0.3217, | |
| "step": 12830 | |
| }, | |
| { | |
| "epoch": 89.17, | |
| "learning_rate": 1.0958041958041958e-08, | |
| "loss": 0.3108, | |
| "step": 12840 | |
| }, | |
| { | |
| "epoch": 89.24, | |
| "learning_rate": 1.0888111888111888e-08, | |
| "loss": 0.3086, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 89.3, | |
| "learning_rate": 1.0818181818181818e-08, | |
| "loss": 0.3004, | |
| "step": 12860 | |
| }, | |
| { | |
| "epoch": 89.37, | |
| "learning_rate": 1.0748251748251749e-08, | |
| "loss": 0.3031, | |
| "step": 12870 | |
| }, | |
| { | |
| "epoch": 89.44, | |
| "learning_rate": 1.0678321678321677e-08, | |
| "loss": 0.3182, | |
| "step": 12880 | |
| }, | |
| { | |
| "epoch": 89.51, | |
| "learning_rate": 1.0608391608391607e-08, | |
| "loss": 0.3205, | |
| "step": 12890 | |
| }, | |
| { | |
| "epoch": 89.58, | |
| "learning_rate": 1.0538461538461537e-08, | |
| "loss": 0.2955, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 89.65, | |
| "learning_rate": 1.0468531468531468e-08, | |
| "loss": 0.2986, | |
| "step": 12910 | |
| }, | |
| { | |
| "epoch": 89.72, | |
| "learning_rate": 1.0398601398601398e-08, | |
| "loss": 0.3204, | |
| "step": 12920 | |
| }, | |
| { | |
| "epoch": 89.79, | |
| "learning_rate": 1.0328671328671328e-08, | |
| "loss": 0.3094, | |
| "step": 12930 | |
| }, | |
| { | |
| "epoch": 89.86, | |
| "learning_rate": 1.0258741258741258e-08, | |
| "loss": 0.3017, | |
| "step": 12940 | |
| }, | |
| { | |
| "epoch": 89.93, | |
| "learning_rate": 1.0188811188811188e-08, | |
| "loss": 0.321, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 1.0118881118881118e-08, | |
| "loss": 0.3154, | |
| "step": 12960 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_loss": 0.45329418778419495, | |
| "eval_runtime": 125.389, | |
| "eval_samples_per_second": 4.243, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.20980908915600693, | |
| "step": 12960 | |
| }, | |
| { | |
| "epoch": 90.07, | |
| "learning_rate": 1.0048951048951049e-08, | |
| "loss": 0.3172, | |
| "step": 12970 | |
| }, | |
| { | |
| "epoch": 90.14, | |
| "learning_rate": 9.979020979020979e-09, | |
| "loss": 0.3008, | |
| "step": 12980 | |
| }, | |
| { | |
| "epoch": 90.21, | |
| "learning_rate": 9.909090909090909e-09, | |
| "loss": 0.3223, | |
| "step": 12990 | |
| }, | |
| { | |
| "epoch": 90.28, | |
| "learning_rate": 9.839160839160839e-09, | |
| "loss": 0.3082, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 90.35, | |
| "learning_rate": 9.76923076923077e-09, | |
| "loss": 0.311, | |
| "step": 13010 | |
| }, | |
| { | |
| "epoch": 90.42, | |
| "learning_rate": 9.699300699300698e-09, | |
| "loss": 0.3057, | |
| "step": 13020 | |
| }, | |
| { | |
| "epoch": 90.48, | |
| "learning_rate": 9.629370629370628e-09, | |
| "loss": 0.3228, | |
| "step": 13030 | |
| }, | |
| { | |
| "epoch": 90.55, | |
| "learning_rate": 9.559440559440558e-09, | |
| "loss": 0.305, | |
| "step": 13040 | |
| }, | |
| { | |
| "epoch": 90.62, | |
| "learning_rate": 9.48951048951049e-09, | |
| "loss": 0.3048, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 90.69, | |
| "learning_rate": 9.41958041958042e-09, | |
| "loss": 0.3081, | |
| "step": 13060 | |
| }, | |
| { | |
| "epoch": 90.76, | |
| "learning_rate": 9.34965034965035e-09, | |
| "loss": 0.3098, | |
| "step": 13070 | |
| }, | |
| { | |
| "epoch": 90.83, | |
| "learning_rate": 9.279720279720279e-09, | |
| "loss": 0.3071, | |
| "step": 13080 | |
| }, | |
| { | |
| "epoch": 90.9, | |
| "learning_rate": 9.209790209790209e-09, | |
| "loss": 0.3002, | |
| "step": 13090 | |
| }, | |
| { | |
| "epoch": 90.97, | |
| "learning_rate": 9.13986013986014e-09, | |
| "loss": 0.3169, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_loss": 0.4542999267578125, | |
| "eval_runtime": 125.4969, | |
| "eval_samples_per_second": 4.239, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.20980908915600693, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 91.04, | |
| "learning_rate": 9.06993006993007e-09, | |
| "loss": 0.3298, | |
| "step": 13110 | |
| }, | |
| { | |
| "epoch": 91.11, | |
| "learning_rate": 9e-09, | |
| "loss": 0.3077, | |
| "step": 13120 | |
| }, | |
| { | |
| "epoch": 91.18, | |
| "learning_rate": 8.93006993006993e-09, | |
| "loss": 0.318, | |
| "step": 13130 | |
| }, | |
| { | |
| "epoch": 91.25, | |
| "learning_rate": 8.86013986013986e-09, | |
| "loss": 0.3136, | |
| "step": 13140 | |
| }, | |
| { | |
| "epoch": 91.32, | |
| "learning_rate": 8.79020979020979e-09, | |
| "loss": 0.3114, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 91.39, | |
| "learning_rate": 8.72027972027972e-09, | |
| "loss": 0.2947, | |
| "step": 13160 | |
| }, | |
| { | |
| "epoch": 91.46, | |
| "learning_rate": 8.65034965034965e-09, | |
| "loss": 0.3132, | |
| "step": 13170 | |
| }, | |
| { | |
| "epoch": 91.53, | |
| "learning_rate": 8.58041958041958e-09, | |
| "loss": 0.3038, | |
| "step": 13180 | |
| }, | |
| { | |
| "epoch": 91.6, | |
| "learning_rate": 8.51048951048951e-09, | |
| "loss": 0.2969, | |
| "step": 13190 | |
| }, | |
| { | |
| "epoch": 91.66, | |
| "learning_rate": 8.440559440559441e-09, | |
| "loss": 0.3057, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 91.73, | |
| "learning_rate": 8.37062937062937e-09, | |
| "loss": 0.2982, | |
| "step": 13210 | |
| }, | |
| { | |
| "epoch": 91.8, | |
| "learning_rate": 8.3006993006993e-09, | |
| "loss": 0.309, | |
| "step": 13220 | |
| }, | |
| { | |
| "epoch": 91.87, | |
| "learning_rate": 8.23076923076923e-09, | |
| "loss": 0.295, | |
| "step": 13230 | |
| }, | |
| { | |
| "epoch": 91.94, | |
| "learning_rate": 8.16083916083916e-09, | |
| "loss": 0.3122, | |
| "step": 13240 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_loss": 0.45405980944633484, | |
| "eval_runtime": 125.596, | |
| "eval_samples_per_second": 4.236, | |
| "eval_steps_per_second": 0.533, | |
| "eval_wer": 0.20980908915600693, | |
| "step": 13248 | |
| }, | |
| { | |
| "epoch": 92.01, | |
| "learning_rate": 8.09090909090909e-09, | |
| "loss": 0.3446, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 92.08, | |
| "learning_rate": 8.020979020979022e-09, | |
| "loss": 0.301, | |
| "step": 13260 | |
| }, | |
| { | |
| "epoch": 92.15, | |
| "learning_rate": 7.95104895104895e-09, | |
| "loss": 0.3062, | |
| "step": 13270 | |
| }, | |
| { | |
| "epoch": 92.22, | |
| "learning_rate": 7.88111888111888e-09, | |
| "loss": 0.3143, | |
| "step": 13280 | |
| }, | |
| { | |
| "epoch": 92.29, | |
| "learning_rate": 7.81118881118881e-09, | |
| "loss": 0.2994, | |
| "step": 13290 | |
| }, | |
| { | |
| "epoch": 92.36, | |
| "learning_rate": 7.741258741258741e-09, | |
| "loss": 0.3051, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 92.43, | |
| "learning_rate": 7.671328671328671e-09, | |
| "loss": 0.3166, | |
| "step": 13310 | |
| }, | |
| { | |
| "epoch": 92.5, | |
| "learning_rate": 7.601398601398601e-09, | |
| "loss": 0.3144, | |
| "step": 13320 | |
| }, | |
| { | |
| "epoch": 92.57, | |
| "learning_rate": 7.531468531468531e-09, | |
| "loss": 0.2983, | |
| "step": 13330 | |
| }, | |
| { | |
| "epoch": 92.64, | |
| "learning_rate": 7.46153846153846e-09, | |
| "loss": 0.3026, | |
| "step": 13340 | |
| }, | |
| { | |
| "epoch": 92.71, | |
| "learning_rate": 7.391608391608391e-09, | |
| "loss": 0.3201, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 92.78, | |
| "learning_rate": 7.32167832167832e-09, | |
| "loss": 0.3201, | |
| "step": 13360 | |
| }, | |
| { | |
| "epoch": 92.84, | |
| "learning_rate": 7.251748251748252e-09, | |
| "loss": 0.3066, | |
| "step": 13370 | |
| }, | |
| { | |
| "epoch": 92.91, | |
| "learning_rate": 7.1818181818181815e-09, | |
| "loss": 0.3031, | |
| "step": 13380 | |
| }, | |
| { | |
| "epoch": 92.98, | |
| "learning_rate": 7.111888111888112e-09, | |
| "loss": 0.319, | |
| "step": 13390 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_loss": 0.4535905122756958, | |
| "eval_runtime": 125.6083, | |
| "eval_samples_per_second": 4.235, | |
| "eval_steps_per_second": 0.533, | |
| "eval_wer": 0.2094234106832937, | |
| "step": 13392 | |
| }, | |
| { | |
| "epoch": 93.06, | |
| "learning_rate": 7.041958041958042e-09, | |
| "loss": 0.3347, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 93.12, | |
| "learning_rate": 6.972027972027972e-09, | |
| "loss": 0.2921, | |
| "step": 13410 | |
| }, | |
| { | |
| "epoch": 93.19, | |
| "learning_rate": 6.902097902097901e-09, | |
| "loss": 0.3056, | |
| "step": 13420 | |
| }, | |
| { | |
| "epoch": 93.26, | |
| "learning_rate": 6.8321678321678316e-09, | |
| "loss": 0.2975, | |
| "step": 13430 | |
| }, | |
| { | |
| "epoch": 93.33, | |
| "learning_rate": 6.762237762237762e-09, | |
| "loss": 0.3154, | |
| "step": 13440 | |
| }, | |
| { | |
| "epoch": 93.4, | |
| "learning_rate": 6.692307692307692e-09, | |
| "loss": 0.2949, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 93.47, | |
| "learning_rate": 6.622377622377621e-09, | |
| "loss": 0.3141, | |
| "step": 13460 | |
| }, | |
| { | |
| "epoch": 93.54, | |
| "learning_rate": 6.552447552447553e-09, | |
| "loss": 0.3119, | |
| "step": 13470 | |
| }, | |
| { | |
| "epoch": 93.61, | |
| "learning_rate": 6.4825174825174824e-09, | |
| "loss": 0.3084, | |
| "step": 13480 | |
| }, | |
| { | |
| "epoch": 93.68, | |
| "learning_rate": 6.412587412587413e-09, | |
| "loss": 0.3118, | |
| "step": 13490 | |
| }, | |
| { | |
| "epoch": 93.75, | |
| "learning_rate": 6.342657342657343e-09, | |
| "loss": 0.3323, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 93.82, | |
| "learning_rate": 6.272727272727273e-09, | |
| "loss": 0.3019, | |
| "step": 13510 | |
| }, | |
| { | |
| "epoch": 93.89, | |
| "learning_rate": 6.202797202797202e-09, | |
| "loss": 0.2973, | |
| "step": 13520 | |
| }, | |
| { | |
| "epoch": 93.96, | |
| "learning_rate": 6.1328671328671325e-09, | |
| "loss": 0.307, | |
| "step": 13530 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_loss": 0.4537724554538727, | |
| "eval_runtime": 125.4254, | |
| "eval_samples_per_second": 4.242, | |
| "eval_steps_per_second": 0.534, | |
| "eval_wer": 0.20923057144693707, | |
| "step": 13536 | |
| }, | |
| { | |
| "epoch": 94.03, | |
| "learning_rate": 6.062937062937063e-09, | |
| "loss": 0.3367, | |
| "step": 13540 | |
| }, | |
| { | |
| "epoch": 94.1, | |
| "learning_rate": 5.993006993006993e-09, | |
| "loss": 0.305, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 94.17, | |
| "learning_rate": 5.923076923076923e-09, | |
| "loss": 0.301, | |
| "step": 13560 | |
| }, | |
| { | |
| "epoch": 94.24, | |
| "learning_rate": 5.853146853146853e-09, | |
| "loss": 0.3187, | |
| "step": 13570 | |
| }, | |
| { | |
| "epoch": 94.3, | |
| "learning_rate": 5.7832167832167825e-09, | |
| "loss": 0.304, | |
| "step": 13580 | |
| }, | |
| { | |
| "epoch": 94.37, | |
| "learning_rate": 5.713286713286713e-09, | |
| "loss": 0.2854, | |
| "step": 13590 | |
| }, | |
| { | |
| "epoch": 94.44, | |
| "learning_rate": 5.643356643356643e-09, | |
| "loss": 0.3187, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 94.51, | |
| "learning_rate": 5.573426573426573e-09, | |
| "loss": 0.2967, | |
| "step": 13610 | |
| }, | |
| { | |
| "epoch": 94.58, | |
| "learning_rate": 5.503496503496503e-09, | |
| "loss": 0.2986, | |
| "step": 13620 | |
| }, | |
| { | |
| "epoch": 94.65, | |
| "learning_rate": 5.433566433566433e-09, | |
| "loss": 0.2974, | |
| "step": 13630 | |
| }, | |
| { | |
| "epoch": 94.72, | |
| "learning_rate": 5.3636363636363635e-09, | |
| "loss": 0.3209, | |
| "step": 13640 | |
| }, | |
| { | |
| "epoch": 94.79, | |
| "learning_rate": 5.293706293706293e-09, | |
| "loss": 0.3098, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 94.86, | |
| "learning_rate": 5.223776223776224e-09, | |
| "loss": 0.312, | |
| "step": 13660 | |
| }, | |
| { | |
| "epoch": 94.93, | |
| "learning_rate": 5.153846153846154e-09, | |
| "loss": 0.3136, | |
| "step": 13670 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "learning_rate": 5.083916083916083e-09, | |
| "loss": 0.3132, | |
| "step": 13680 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_loss": 0.45404911041259766, | |
| "eval_runtime": 125.2585, | |
| "eval_samples_per_second": 4.247, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.20935913093784148, | |
| "step": 13680 | |
| }, | |
| { | |
| "epoch": 95.07, | |
| "learning_rate": 5.0139860139860136e-09, | |
| "loss": 0.3104, | |
| "step": 13690 | |
| }, | |
| { | |
| "epoch": 95.14, | |
| "learning_rate": 4.944055944055944e-09, | |
| "loss": 0.2924, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 95.21, | |
| "learning_rate": 4.874125874125874e-09, | |
| "loss": 0.3132, | |
| "step": 13710 | |
| }, | |
| { | |
| "epoch": 95.28, | |
| "learning_rate": 4.804195804195804e-09, | |
| "loss": 0.3062, | |
| "step": 13720 | |
| }, | |
| { | |
| "epoch": 95.35, | |
| "learning_rate": 4.734265734265734e-09, | |
| "loss": 0.3062, | |
| "step": 13730 | |
| }, | |
| { | |
| "epoch": 95.42, | |
| "learning_rate": 4.6643356643356644e-09, | |
| "loss": 0.307, | |
| "step": 13740 | |
| }, | |
| { | |
| "epoch": 95.48, | |
| "learning_rate": 4.594405594405594e-09, | |
| "loss": 0.3172, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 95.55, | |
| "learning_rate": 4.524475524475524e-09, | |
| "loss": 0.3167, | |
| "step": 13760 | |
| }, | |
| { | |
| "epoch": 95.62, | |
| "learning_rate": 4.454545454545455e-09, | |
| "loss": 0.2872, | |
| "step": 13770 | |
| }, | |
| { | |
| "epoch": 95.69, | |
| "learning_rate": 4.384615384615384e-09, | |
| "loss": 0.3208, | |
| "step": 13780 | |
| }, | |
| { | |
| "epoch": 95.76, | |
| "learning_rate": 4.3146853146853145e-09, | |
| "loss": 0.3121, | |
| "step": 13790 | |
| }, | |
| { | |
| "epoch": 95.83, | |
| "learning_rate": 4.244755244755245e-09, | |
| "loss": 0.3134, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 95.9, | |
| "learning_rate": 4.174825174825174e-09, | |
| "loss": 0.3175, | |
| "step": 13810 | |
| }, | |
| { | |
| "epoch": 95.97, | |
| "learning_rate": 4.104895104895105e-09, | |
| "loss": 0.3185, | |
| "step": 13820 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_loss": 0.45364418625831604, | |
| "eval_runtime": 125.6956, | |
| "eval_samples_per_second": 4.232, | |
| "eval_steps_per_second": 0.533, | |
| "eval_wer": 0.20993764864691136, | |
| "step": 13824 | |
| }, | |
| { | |
| "epoch": 96.04, | |
| "learning_rate": 4.034965034965035e-09, | |
| "loss": 0.318, | |
| "step": 13830 | |
| }, | |
| { | |
| "epoch": 96.11, | |
| "learning_rate": 3.9650349650349645e-09, | |
| "loss": 0.3072, | |
| "step": 13840 | |
| }, | |
| { | |
| "epoch": 96.18, | |
| "learning_rate": 3.895104895104895e-09, | |
| "loss": 0.3078, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 96.25, | |
| "learning_rate": 3.825174825174825e-09, | |
| "loss": 0.3271, | |
| "step": 13860 | |
| }, | |
| { | |
| "epoch": 96.32, | |
| "learning_rate": 3.755244755244755e-09, | |
| "loss": 0.2994, | |
| "step": 13870 | |
| }, | |
| { | |
| "epoch": 96.39, | |
| "learning_rate": 3.685314685314685e-09, | |
| "loss": 0.2849, | |
| "step": 13880 | |
| }, | |
| { | |
| "epoch": 96.46, | |
| "learning_rate": 3.6153846153846154e-09, | |
| "loss": 0.3289, | |
| "step": 13890 | |
| }, | |
| { | |
| "epoch": 96.53, | |
| "learning_rate": 3.545454545454545e-09, | |
| "loss": 0.3095, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 96.6, | |
| "learning_rate": 3.4755244755244753e-09, | |
| "loss": 0.3095, | |
| "step": 13910 | |
| }, | |
| { | |
| "epoch": 96.66, | |
| "learning_rate": 3.405594405594405e-09, | |
| "loss": 0.2978, | |
| "step": 13920 | |
| }, | |
| { | |
| "epoch": 96.73, | |
| "learning_rate": 3.3356643356643356e-09, | |
| "loss": 0.3164, | |
| "step": 13930 | |
| }, | |
| { | |
| "epoch": 96.8, | |
| "learning_rate": 3.265734265734266e-09, | |
| "loss": 0.311, | |
| "step": 13940 | |
| }, | |
| { | |
| "epoch": 96.87, | |
| "learning_rate": 3.1958041958041956e-09, | |
| "loss": 0.3112, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 96.94, | |
| "learning_rate": 3.1258741258741258e-09, | |
| "loss": 0.2996, | |
| "step": 13960 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_loss": 0.4540862441062927, | |
| "eval_runtime": 125.3259, | |
| "eval_samples_per_second": 4.245, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.21000192839236356, | |
| "step": 13968 | |
| }, | |
| { | |
| "epoch": 97.01, | |
| "learning_rate": 3.055944055944056e-09, | |
| "loss": 0.3015, | |
| "step": 13970 | |
| }, | |
| { | |
| "epoch": 97.08, | |
| "learning_rate": 2.9860139860139857e-09, | |
| "loss": 0.318, | |
| "step": 13980 | |
| }, | |
| { | |
| "epoch": 97.15, | |
| "learning_rate": 2.9160839160839163e-09, | |
| "loss": 0.3107, | |
| "step": 13990 | |
| }, | |
| { | |
| "epoch": 97.22, | |
| "learning_rate": 2.846153846153846e-09, | |
| "loss": 0.3218, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 97.29, | |
| "learning_rate": 2.7762237762237758e-09, | |
| "loss": 0.3143, | |
| "step": 14010 | |
| }, | |
| { | |
| "epoch": 97.36, | |
| "learning_rate": 2.7062937062937064e-09, | |
| "loss": 0.286, | |
| "step": 14020 | |
| }, | |
| { | |
| "epoch": 97.43, | |
| "learning_rate": 2.636363636363636e-09, | |
| "loss": 0.3067, | |
| "step": 14030 | |
| }, | |
| { | |
| "epoch": 97.5, | |
| "learning_rate": 2.5664335664335663e-09, | |
| "loss": 0.3043, | |
| "step": 14040 | |
| }, | |
| { | |
| "epoch": 97.57, | |
| "learning_rate": 2.4965034965034965e-09, | |
| "loss": 0.2933, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 97.64, | |
| "learning_rate": 2.4265734265734262e-09, | |
| "loss": 0.2863, | |
| "step": 14060 | |
| }, | |
| { | |
| "epoch": 97.71, | |
| "learning_rate": 2.356643356643357e-09, | |
| "loss": 0.3126, | |
| "step": 14070 | |
| }, | |
| { | |
| "epoch": 97.78, | |
| "learning_rate": 2.2867132867132866e-09, | |
| "loss": 0.3093, | |
| "step": 14080 | |
| }, | |
| { | |
| "epoch": 97.84, | |
| "learning_rate": 2.2167832167832168e-09, | |
| "loss": 0.3239, | |
| "step": 14090 | |
| }, | |
| { | |
| "epoch": 97.91, | |
| "learning_rate": 2.146853146853147e-09, | |
| "loss": 0.3085, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 97.98, | |
| "learning_rate": 2.0769230769230767e-09, | |
| "loss": 0.3193, | |
| "step": 14110 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_loss": 0.4538502097129822, | |
| "eval_runtime": 125.3144, | |
| "eval_samples_per_second": 4.245, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.20916629170148487, | |
| "step": 14112 | |
| }, | |
| { | |
| "epoch": 98.06, | |
| "learning_rate": 2.006993006993007e-09, | |
| "loss": 0.3141, | |
| "step": 14120 | |
| }, | |
| { | |
| "epoch": 98.12, | |
| "learning_rate": 1.937062937062937e-09, | |
| "loss": 0.2964, | |
| "step": 14130 | |
| }, | |
| { | |
| "epoch": 98.19, | |
| "learning_rate": 1.8671328671328668e-09, | |
| "loss": 0.3302, | |
| "step": 14140 | |
| }, | |
| { | |
| "epoch": 98.26, | |
| "learning_rate": 1.7972027972027972e-09, | |
| "loss": 0.3052, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 98.33, | |
| "learning_rate": 1.7272727272727271e-09, | |
| "loss": 0.3109, | |
| "step": 14160 | |
| }, | |
| { | |
| "epoch": 98.4, | |
| "learning_rate": 1.657342657342657e-09, | |
| "loss": 0.3068, | |
| "step": 14170 | |
| }, | |
| { | |
| "epoch": 98.47, | |
| "learning_rate": 1.5874125874125875e-09, | |
| "loss": 0.3238, | |
| "step": 14180 | |
| }, | |
| { | |
| "epoch": 98.54, | |
| "learning_rate": 1.5174825174825174e-09, | |
| "loss": 0.2989, | |
| "step": 14190 | |
| }, | |
| { | |
| "epoch": 98.61, | |
| "learning_rate": 1.4475524475524474e-09, | |
| "loss": 0.3063, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 98.68, | |
| "learning_rate": 1.3776223776223776e-09, | |
| "loss": 0.3078, | |
| "step": 14210 | |
| }, | |
| { | |
| "epoch": 98.75, | |
| "learning_rate": 1.3076923076923076e-09, | |
| "loss": 0.3171, | |
| "step": 14220 | |
| }, | |
| { | |
| "epoch": 98.82, | |
| "learning_rate": 1.2377622377622377e-09, | |
| "loss": 0.3033, | |
| "step": 14230 | |
| }, | |
| { | |
| "epoch": 98.89, | |
| "learning_rate": 1.1678321678321679e-09, | |
| "loss": 0.2913, | |
| "step": 14240 | |
| }, | |
| { | |
| "epoch": 98.96, | |
| "learning_rate": 1.0979020979020979e-09, | |
| "loss": 0.3091, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_loss": 0.4538028836250305, | |
| "eval_runtime": 125.1474, | |
| "eval_samples_per_second": 4.251, | |
| "eval_steps_per_second": 0.535, | |
| "eval_wer": 0.2095519701741981, | |
| "step": 14256 | |
| }, | |
| { | |
| "epoch": 99.03, | |
| "learning_rate": 1.0279720279720278e-09, | |
| "loss": 0.3498, | |
| "step": 14260 | |
| }, | |
| { | |
| "epoch": 99.1, | |
| "learning_rate": 9.58041958041958e-10, | |
| "loss": 0.3194, | |
| "step": 14270 | |
| }, | |
| { | |
| "epoch": 99.17, | |
| "learning_rate": 8.881118881118881e-10, | |
| "loss": 0.2934, | |
| "step": 14280 | |
| }, | |
| { | |
| "epoch": 99.24, | |
| "learning_rate": 8.181818181818182e-10, | |
| "loss": 0.3098, | |
| "step": 14290 | |
| }, | |
| { | |
| "epoch": 99.3, | |
| "learning_rate": 7.482517482517482e-10, | |
| "loss": 0.3036, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 99.37, | |
| "learning_rate": 6.783216783216783e-10, | |
| "loss": 0.3185, | |
| "step": 14310 | |
| }, | |
| { | |
| "epoch": 99.44, | |
| "learning_rate": 6.083916083916083e-10, | |
| "loss": 0.3153, | |
| "step": 14320 | |
| }, | |
| { | |
| "epoch": 99.51, | |
| "learning_rate": 5.384615384615384e-10, | |
| "loss": 0.3154, | |
| "step": 14330 | |
| }, | |
| { | |
| "epoch": 99.58, | |
| "learning_rate": 4.685314685314685e-10, | |
| "loss": 0.3033, | |
| "step": 14340 | |
| }, | |
| { | |
| "epoch": 99.65, | |
| "learning_rate": 3.9860139860139855e-10, | |
| "loss": 0.2982, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 99.72, | |
| "learning_rate": 3.286713286713287e-10, | |
| "loss": 0.3102, | |
| "step": 14360 | |
| }, | |
| { | |
| "epoch": 99.79, | |
| "learning_rate": 2.5874125874125874e-10, | |
| "loss": 0.2979, | |
| "step": 14370 | |
| }, | |
| { | |
| "epoch": 99.86, | |
| "learning_rate": 1.8881118881118881e-10, | |
| "loss": 0.2985, | |
| "step": 14380 | |
| }, | |
| { | |
| "epoch": 99.93, | |
| "learning_rate": 1.1888111888111888e-10, | |
| "loss": 0.3199, | |
| "step": 14390 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 4.895104895104895e-11, | |
| "loss": 0.315, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_loss": 0.4544455111026764, | |
| "eval_runtime": 125.7987, | |
| "eval_samples_per_second": 4.229, | |
| "eval_steps_per_second": 0.533, | |
| "eval_wer": 0.21000192839236356, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 14400, | |
| "total_flos": 2.720292531062204e+20, | |
| "train_loss": 0.30696306536595025, | |
| "train_runtime": 189946.9018, | |
| "train_samples_per_second": 2.431, | |
| "train_steps_per_second": 0.076 | |
| } | |
| ], | |
| "max_steps": 14400, | |
| "num_train_epochs": 100, | |
| "total_flos": 2.720292531062204e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |