| { | |
| "best_metric": 0.47944945096969604, | |
| "best_model_checkpoint": "ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram/checkpoint-1512", | |
| "epoch": 99.99653979238754, | |
| "global_step": 7200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.3086, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.3275, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.3051, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.3072, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.2957, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3e-06, | |
| "loss": 0.2856, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.5000000000000004e-06, | |
| "loss": 0.314, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.4815235435962677, | |
| "eval_runtime": 130.4571, | |
| "eval_samples_per_second": 4.078, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.20768785755608407, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.2981, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.2972, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2892, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 0.3014, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 6e-06, | |
| "loss": 0.3013, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 0.315, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 0.3064, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5082846283912659, | |
| "eval_runtime": 130.0863, | |
| "eval_samples_per_second": 4.09, | |
| "eval_steps_per_second": 0.515, | |
| "eval_wer": 0.2101947676287202, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 7.5e-06, | |
| "loss": 0.3067, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.95e-06, | |
| "loss": 0.304, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 8.45e-06, | |
| "loss": 0.3065, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 8.95e-06, | |
| "loss": 0.3014, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 9.450000000000001e-06, | |
| "loss": 0.2938, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 9.950000000000001e-06, | |
| "loss": 0.3086, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.045e-05, | |
| "loss": 0.2951, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.5146709680557251, | |
| "eval_runtime": 129.1484, | |
| "eval_samples_per_second": 4.119, | |
| "eval_steps_per_second": 0.519, | |
| "eval_wer": 0.2158513852285145, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.095e-05, | |
| "loss": 0.3079, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 1.145e-05, | |
| "loss": 0.2984, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 1.195e-05, | |
| "loss": 0.3067, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 1.2450000000000001e-05, | |
| "loss": 0.3033, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.2950000000000001e-05, | |
| "loss": 0.2912, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.3450000000000002e-05, | |
| "loss": 0.2915, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 1.3950000000000002e-05, | |
| "loss": 0.2835, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.515735387802124, | |
| "eval_runtime": 128.8527, | |
| "eval_samples_per_second": 4.129, | |
| "eval_steps_per_second": 0.52, | |
| "eval_wer": 0.20910201195603265, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 1.4449999999999999e-05, | |
| "loss": 0.3069, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 1.4950000000000001e-05, | |
| "loss": 0.2931, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 1.545e-05, | |
| "loss": 0.2916, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 1.595e-05, | |
| "loss": 0.304, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 1.645e-05, | |
| "loss": 0.301, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 1.6950000000000002e-05, | |
| "loss": 0.3098, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 1.745e-05, | |
| "loss": 0.2935, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1.795e-05, | |
| "loss": 0.3011, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.495644748210907, | |
| "eval_runtime": 129.107, | |
| "eval_samples_per_second": 4.121, | |
| "eval_steps_per_second": 0.519, | |
| "eval_wer": 0.215080028283088, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 1.845e-05, | |
| "loss": 0.302, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 1.895e-05, | |
| "loss": 0.3081, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 1.9450000000000002e-05, | |
| "loss": 0.3041, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "learning_rate": 1.995e-05, | |
| "loss": 0.3061, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 2.045e-05, | |
| "loss": 0.3081, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 2.09e-05, | |
| "loss": 0.2989, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 2.1400000000000002e-05, | |
| "loss": 0.3097, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.5190498232841492, | |
| "eval_runtime": 129.2076, | |
| "eval_samples_per_second": 4.117, | |
| "eval_steps_per_second": 0.519, | |
| "eval_wer": 0.21533714726489683, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 2.19e-05, | |
| "loss": 0.3235, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 2.2400000000000002e-05, | |
| "loss": 0.3015, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 2.29e-05, | |
| "loss": 0.2979, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 2.3400000000000003e-05, | |
| "loss": 0.3303, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 2.39e-05, | |
| "loss": 0.318, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 2.44e-05, | |
| "loss": 0.3111, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 2.4900000000000002e-05, | |
| "loss": 0.2998, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.5349323153495789, | |
| "eval_runtime": 129.2108, | |
| "eval_samples_per_second": 4.117, | |
| "eval_steps_per_second": 0.519, | |
| "eval_wer": 0.22015812817381245, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 2.4970149253731346e-05, | |
| "loss": 0.3216, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 2.493283582089552e-05, | |
| "loss": 0.3147, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 2.4895522388059704e-05, | |
| "loss": 0.3128, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 2.4858208955223883e-05, | |
| "loss": 0.3079, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 2.482089552238806e-05, | |
| "loss": 0.2967, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 2.478358208955224e-05, | |
| "loss": 0.3098, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 2.474626865671642e-05, | |
| "loss": 0.3086, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.5055466890335083, | |
| "eval_runtime": 128.9787, | |
| "eval_samples_per_second": 4.125, | |
| "eval_steps_per_second": 0.519, | |
| "eval_wer": 0.21450151057401812, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 2.4708955223880597e-05, | |
| "loss": 0.3243, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 2.467164179104478e-05, | |
| "loss": 0.3088, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 2.4634328358208955e-05, | |
| "loss": 0.3071, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 2.4597014925373134e-05, | |
| "loss": 0.3094, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 2.4559701492537317e-05, | |
| "loss": 0.3049, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 2.4522388059701492e-05, | |
| "loss": 0.3061, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 2.448507462686567e-05, | |
| "loss": 0.2964, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.5091516971588135, | |
| "eval_runtime": 129.4051, | |
| "eval_samples_per_second": 4.111, | |
| "eval_steps_per_second": 0.518, | |
| "eval_wer": 0.2183582953011506, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 2.4447761194029854e-05, | |
| "loss": 0.3212, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 2.441044776119403e-05, | |
| "loss": 0.302, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 2.437313432835821e-05, | |
| "loss": 0.3103, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 2.433582089552239e-05, | |
| "loss": 0.3102, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 2.4298507462686567e-05, | |
| "loss": 0.3045, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 2.4261194029850746e-05, | |
| "loss": 0.3162, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 2.4223880597014926e-05, | |
| "loss": 0.3186, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 2.4186567164179105e-05, | |
| "loss": 0.3288, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.5076370239257812, | |
| "eval_runtime": 129.7675, | |
| "eval_samples_per_second": 4.1, | |
| "eval_steps_per_second": 0.516, | |
| "eval_wer": 0.2190653725011249, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "learning_rate": 2.4149253731343284e-05, | |
| "loss": 0.3037, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 2.4111940298507463e-05, | |
| "loss": 0.3256, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 2.4074626865671642e-05, | |
| "loss": 0.3209, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 2.403731343283582e-05, | |
| "loss": 0.3259, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 10.69, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.3081, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 2.396268656716418e-05, | |
| "loss": 0.3153, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 2.392537313432836e-05, | |
| "loss": 0.3019, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.5125810503959656, | |
| "eval_runtime": 128.8657, | |
| "eval_samples_per_second": 4.128, | |
| "eval_steps_per_second": 0.52, | |
| "eval_wer": 0.20916629170148487, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 2.3888059701492538e-05, | |
| "loss": 0.3151, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "learning_rate": 2.3850746268656717e-05, | |
| "loss": 0.3154, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 11.39, | |
| "learning_rate": 2.3813432835820896e-05, | |
| "loss": 0.2949, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 11.53, | |
| "learning_rate": 2.3776119402985076e-05, | |
| "loss": 0.3214, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 11.66, | |
| "learning_rate": 2.3738805970149255e-05, | |
| "loss": 0.2946, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 2.3701492537313434e-05, | |
| "loss": 0.3154, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 2.3664179104477613e-05, | |
| "loss": 0.3047, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.5249019861221313, | |
| "eval_runtime": 129.2154, | |
| "eval_samples_per_second": 4.117, | |
| "eval_steps_per_second": 0.519, | |
| "eval_wer": 0.2117374815195732, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 12.08, | |
| "learning_rate": 2.3626865671641792e-05, | |
| "loss": 0.2959, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 12.22, | |
| "learning_rate": 2.358955223880597e-05, | |
| "loss": 0.295, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "learning_rate": 2.355223880597015e-05, | |
| "loss": 0.3122, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 2.351492537313433e-05, | |
| "loss": 0.3028, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 2.347761194029851e-05, | |
| "loss": 0.2777, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 2.3440298507462688e-05, | |
| "loss": 0.3025, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 2.3402985074626867e-05, | |
| "loss": 0.2998, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.531330406665802, | |
| "eval_runtime": 129.1703, | |
| "eval_samples_per_second": 4.119, | |
| "eval_steps_per_second": 0.519, | |
| "eval_wer": 0.21405155235585266, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 2.3365671641791046e-05, | |
| "loss": 0.3192, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 2.3328358208955225e-05, | |
| "loss": 0.2997, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 2.32910447761194e-05, | |
| "loss": 0.3163, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 2.3253731343283584e-05, | |
| "loss": 0.3046, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 2.3216417910447763e-05, | |
| "loss": 0.2924, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 2.317910447761194e-05, | |
| "loss": 0.3161, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 2.314179104477612e-05, | |
| "loss": 0.3043, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.5343348979949951, | |
| "eval_runtime": 129.5843, | |
| "eval_samples_per_second": 4.105, | |
| "eval_steps_per_second": 0.517, | |
| "eval_wer": 0.21861541428295944, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 2.31044776119403e-05, | |
| "loss": 0.3099, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 14.17, | |
| "learning_rate": 2.306716417910448e-05, | |
| "loss": 0.2953, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 2.302985074626866e-05, | |
| "loss": 0.3134, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 2.2992537313432838e-05, | |
| "loss": 0.2917, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 14.58, | |
| "learning_rate": 2.2955223880597017e-05, | |
| "loss": 0.3108, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 2.2917910447761196e-05, | |
| "loss": 0.3085, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "learning_rate": 2.2880597014925372e-05, | |
| "loss": 0.2921, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.2843283582089555e-05, | |
| "loss": 0.3147, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.506893515586853, | |
| "eval_runtime": 129.0401, | |
| "eval_samples_per_second": 4.123, | |
| "eval_steps_per_second": 0.519, | |
| "eval_wer": 0.21713698013755867, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "learning_rate": 2.2805970149253734e-05, | |
| "loss": 0.307, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 15.28, | |
| "learning_rate": 2.276865671641791e-05, | |
| "loss": 0.3152, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 15.42, | |
| "learning_rate": 2.2731343283582092e-05, | |
| "loss": 0.3002, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 15.55, | |
| "learning_rate": 2.269402985074627e-05, | |
| "loss": 0.2992, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 15.69, | |
| "learning_rate": 2.2656716417910447e-05, | |
| "loss": 0.2897, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 15.83, | |
| "learning_rate": 2.261940298507463e-05, | |
| "loss": 0.3069, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 2.258208955223881e-05, | |
| "loss": 0.3049, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.5032855272293091, | |
| "eval_runtime": 129.2941, | |
| "eval_samples_per_second": 4.115, | |
| "eval_steps_per_second": 0.518, | |
| "eval_wer": 0.20736645882882304, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 16.11, | |
| "learning_rate": 2.2544776119402984e-05, | |
| "loss": 0.3014, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "learning_rate": 2.2507462686567167e-05, | |
| "loss": 0.3078, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 16.39, | |
| "learning_rate": 2.2470149253731346e-05, | |
| "loss": 0.2942, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 16.53, | |
| "learning_rate": 2.2432835820895522e-05, | |
| "loss": 0.3168, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 16.66, | |
| "learning_rate": 2.2395522388059704e-05, | |
| "loss": 0.3124, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 2.235820895522388e-05, | |
| "loss": 0.2951, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 16.94, | |
| "learning_rate": 2.232089552238806e-05, | |
| "loss": 0.298, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.5108718276023865, | |
| "eval_runtime": 129.096, | |
| "eval_samples_per_second": 4.121, | |
| "eval_steps_per_second": 0.519, | |
| "eval_wer": 0.20498810824709135, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 17.08, | |
| "learning_rate": 2.2283582089552242e-05, | |
| "loss": 0.3255, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 17.22, | |
| "learning_rate": 2.2246268656716418e-05, | |
| "loss": 0.2867, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 17.36, | |
| "learning_rate": 2.2208955223880597e-05, | |
| "loss": 0.2983, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 2.217164179104478e-05, | |
| "loss": 0.3105, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 17.64, | |
| "learning_rate": 2.2134328358208955e-05, | |
| "loss": 0.2818, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "learning_rate": 2.2097014925373134e-05, | |
| "loss": 0.3107, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 2.2059701492537317e-05, | |
| "loss": 0.2948, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.5252682566642761, | |
| "eval_runtime": 129.1692, | |
| "eval_samples_per_second": 4.119, | |
| "eval_steps_per_second": 0.519, | |
| "eval_wer": 0.20993764864691136, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "learning_rate": 2.2022388059701493e-05, | |
| "loss": 0.316, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "learning_rate": 2.1985074626865672e-05, | |
| "loss": 0.3066, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 18.33, | |
| "learning_rate": 2.194776119402985e-05, | |
| "loss": 0.3031, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 18.47, | |
| "learning_rate": 2.191044776119403e-05, | |
| "loss": 0.3037, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "learning_rate": 2.187313432835821e-05, | |
| "loss": 0.2986, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "learning_rate": 2.183582089552239e-05, | |
| "loss": 0.2955, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 18.89, | |
| "learning_rate": 2.1798507462686568e-05, | |
| "loss": 0.2986, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.4976494014263153, | |
| "eval_runtime": 129.378, | |
| "eval_samples_per_second": 4.112, | |
| "eval_steps_per_second": 0.518, | |
| "eval_wer": 0.20209551970174197, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 2.1761194029850747e-05, | |
| "loss": 0.3021, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 2.1723880597014926e-05, | |
| "loss": 0.2887, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 19.3, | |
| "learning_rate": 2.1686567164179105e-05, | |
| "loss": 0.3059, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 19.44, | |
| "learning_rate": 2.1649253731343284e-05, | |
| "loss": 0.2945, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 19.58, | |
| "learning_rate": 2.1611940298507463e-05, | |
| "loss": 0.3006, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 2.1574626865671643e-05, | |
| "loss": 0.3033, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 19.86, | |
| "learning_rate": 2.153731343283582e-05, | |
| "loss": 0.3002, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.15e-05, | |
| "loss": 0.2958, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.5233781933784485, | |
| "eval_runtime": 129.422, | |
| "eval_samples_per_second": 4.111, | |
| "eval_steps_per_second": 0.518, | |
| "eval_wer": 0.20935913093784148, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 20.14, | |
| "learning_rate": 2.146268656716418e-05, | |
| "loss": 0.2982, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 20.28, | |
| "learning_rate": 2.142537313432836e-05, | |
| "loss": 0.2861, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 20.42, | |
| "learning_rate": 2.1388059701492538e-05, | |
| "loss": 0.293, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 20.55, | |
| "learning_rate": 2.1350746268656717e-05, | |
| "loss": 0.304, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 20.69, | |
| "learning_rate": 2.1313432835820897e-05, | |
| "loss": 0.2926, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 2.1276119402985076e-05, | |
| "loss": 0.3092, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 20.97, | |
| "learning_rate": 2.1238805970149255e-05, | |
| "loss": 0.2931, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.47944945096969604, | |
| "eval_runtime": 130.2981, | |
| "eval_samples_per_second": 4.083, | |
| "eval_steps_per_second": 0.514, | |
| "eval_wer": 0.20595230442887447, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 21.11, | |
| "learning_rate": 2.1201492537313434e-05, | |
| "loss": 0.2956, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 21.25, | |
| "learning_rate": 2.1164179104477613e-05, | |
| "loss": 0.3007, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 21.39, | |
| "learning_rate": 2.1126865671641792e-05, | |
| "loss": 0.3045, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 21.53, | |
| "learning_rate": 2.108955223880597e-05, | |
| "loss": 0.3002, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 21.66, | |
| "learning_rate": 2.105223880597015e-05, | |
| "loss": 0.2848, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 21.8, | |
| "learning_rate": 2.1014925373134326e-05, | |
| "loss": 0.286, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 21.94, | |
| "learning_rate": 2.097761194029851e-05, | |
| "loss": 0.305, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.4916737377643585, | |
| "eval_runtime": 129.0137, | |
| "eval_samples_per_second": 4.124, | |
| "eval_steps_per_second": 0.519, | |
| "eval_wer": 0.20492382850163912, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 2.0940298507462688e-05, | |
| "loss": 0.3092, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 2.0902985074626867e-05, | |
| "loss": 0.2979, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 22.36, | |
| "learning_rate": 2.0865671641791047e-05, | |
| "loss": 0.2921, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "learning_rate": 2.0828358208955226e-05, | |
| "loss": 0.3052, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 22.64, | |
| "learning_rate": 2.0791044776119405e-05, | |
| "loss": 0.2977, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 22.78, | |
| "learning_rate": 2.0753731343283584e-05, | |
| "loss": 0.2938, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 22.91, | |
| "learning_rate": 2.0716417910447763e-05, | |
| "loss": 0.2847, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.5089883804321289, | |
| "eval_runtime": 129.655, | |
| "eval_samples_per_second": 4.103, | |
| "eval_steps_per_second": 0.517, | |
| "eval_wer": 0.21000192839236356, | |
| "step": 1656 | |
| }, | |
| { | |
| "epoch": 23.06, | |
| "learning_rate": 2.0679104477611942e-05, | |
| "loss": 0.2993, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 2.064179104477612e-05, | |
| "loss": 0.3081, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 23.33, | |
| "learning_rate": 2.0604477611940297e-05, | |
| "loss": 0.2998, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 23.47, | |
| "learning_rate": 2.056716417910448e-05, | |
| "loss": 0.3125, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 23.61, | |
| "learning_rate": 2.052985074626866e-05, | |
| "loss": 0.3135, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 23.75, | |
| "learning_rate": 2.0492537313432835e-05, | |
| "loss": 0.3039, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 23.89, | |
| "learning_rate": 2.0455223880597017e-05, | |
| "loss": 0.2869, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.5296673774719238, | |
| "eval_runtime": 132.3841, | |
| "eval_samples_per_second": 4.019, | |
| "eval_steps_per_second": 0.506, | |
| "eval_wer": 0.2101947676287202, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 24.03, | |
| "learning_rate": 2.0417910447761196e-05, | |
| "loss": 0.2958, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 24.17, | |
| "learning_rate": 2.0380597014925372e-05, | |
| "loss": 0.2985, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 24.3, | |
| "learning_rate": 2.0343283582089555e-05, | |
| "loss": 0.2914, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 24.44, | |
| "learning_rate": 2.0305970149253734e-05, | |
| "loss": 0.2975, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 24.58, | |
| "learning_rate": 2.026865671641791e-05, | |
| "loss": 0.3037, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 24.72, | |
| "learning_rate": 2.0231343283582092e-05, | |
| "loss": 0.294, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "learning_rate": 2.0194029850746268e-05, | |
| "loss": 0.3024, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 2.0156716417910447e-05, | |
| "loss": 0.2997, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.5185533165931702, | |
| "eval_runtime": 132.6367, | |
| "eval_samples_per_second": 4.011, | |
| "eval_steps_per_second": 0.505, | |
| "eval_wer": 0.20878061322877162, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 25.14, | |
| "learning_rate": 2.011940298507463e-05, | |
| "loss": 0.3077, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 2.0082089552238805e-05, | |
| "loss": 0.2926, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 25.42, | |
| "learning_rate": 2.0044776119402985e-05, | |
| "loss": 0.2924, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 25.55, | |
| "learning_rate": 2.0007462686567167e-05, | |
| "loss": 0.2969, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 25.69, | |
| "learning_rate": 1.9970149253731343e-05, | |
| "loss": 0.299, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 25.83, | |
| "learning_rate": 1.9932835820895522e-05, | |
| "loss": 0.2963, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 25.97, | |
| "learning_rate": 1.9895522388059705e-05, | |
| "loss": 0.2996, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 0.5218982100486755, | |
| "eval_runtime": 131.3811, | |
| "eval_samples_per_second": 4.049, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.20980908915600693, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 26.11, | |
| "learning_rate": 1.985820895522388e-05, | |
| "loss": 0.2972, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 26.25, | |
| "learning_rate": 1.982089552238806e-05, | |
| "loss": 0.2993, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 26.39, | |
| "learning_rate": 1.9783582089552242e-05, | |
| "loss": 0.2877, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 26.53, | |
| "learning_rate": 1.9746268656716418e-05, | |
| "loss": 0.2864, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 26.66, | |
| "learning_rate": 1.9708955223880597e-05, | |
| "loss": 0.2869, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 26.8, | |
| "learning_rate": 1.9671641791044776e-05, | |
| "loss": 0.3113, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 26.94, | |
| "learning_rate": 1.9634328358208955e-05, | |
| "loss": 0.298, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 0.506175696849823, | |
| "eval_runtime": 132.0981, | |
| "eval_samples_per_second": 4.027, | |
| "eval_steps_per_second": 0.507, | |
| "eval_wer": 0.21077328533779005, | |
| "step": 1944 | |
| }, | |
| { | |
| "epoch": 27.08, | |
| "learning_rate": 1.9597014925373135e-05, | |
| "loss": 0.3057, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 27.22, | |
| "learning_rate": 1.9559701492537314e-05, | |
| "loss": 0.3026, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 1.9522388059701493e-05, | |
| "loss": 0.298, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "learning_rate": 1.9485074626865672e-05, | |
| "loss": 0.3077, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 27.64, | |
| "learning_rate": 1.944776119402985e-05, | |
| "loss": 0.3073, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 27.78, | |
| "learning_rate": 1.941044776119403e-05, | |
| "loss": 0.3163, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "learning_rate": 1.9373134328358213e-05, | |
| "loss": 0.3057, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 0.5299437642097473, | |
| "eval_runtime": 132.6119, | |
| "eval_samples_per_second": 4.012, | |
| "eval_steps_per_second": 0.505, | |
| "eval_wer": 0.21366587388313943, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 28.06, | |
| "learning_rate": 1.933582089552239e-05, | |
| "loss": 0.3058, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 28.19, | |
| "learning_rate": 1.9298507462686568e-05, | |
| "loss": 0.2959, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 28.33, | |
| "learning_rate": 1.9261194029850747e-05, | |
| "loss": 0.3052, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 28.47, | |
| "learning_rate": 1.9223880597014926e-05, | |
| "loss": 0.2961, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 28.61, | |
| "learning_rate": 1.9186567164179105e-05, | |
| "loss": 0.3006, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 28.75, | |
| "learning_rate": 1.9149253731343284e-05, | |
| "loss": 0.3096, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "learning_rate": 1.9111940298507464e-05, | |
| "loss": 0.2937, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 0.5345147848129272, | |
| "eval_runtime": 131.6737, | |
| "eval_samples_per_second": 4.04, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.21540142701034903, | |
| "step": 2088 | |
| }, | |
| { | |
| "epoch": 29.03, | |
| "learning_rate": 1.9074626865671643e-05, | |
| "loss": 0.3, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 29.17, | |
| "learning_rate": 1.9037313432835822e-05, | |
| "loss": 0.2895, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 29.3, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.2907, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 1.896268656716418e-05, | |
| "loss": 0.2975, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 29.58, | |
| "learning_rate": 1.892537313432836e-05, | |
| "loss": 0.2945, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 29.72, | |
| "learning_rate": 1.888805970149254e-05, | |
| "loss": 0.3019, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 29.86, | |
| "learning_rate": 1.8850746268656718e-05, | |
| "loss": 0.2987, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 1.8813432835820897e-05, | |
| "loss": 0.3064, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.5374366044998169, | |
| "eval_runtime": 131.625, | |
| "eval_samples_per_second": 4.042, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.21160892202866877, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 30.14, | |
| "learning_rate": 1.8776119402985076e-05, | |
| "loss": 0.2945, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 30.28, | |
| "learning_rate": 1.8738805970149255e-05, | |
| "loss": 0.2925, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 30.42, | |
| "learning_rate": 1.8701492537313434e-05, | |
| "loss": 0.2875, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 30.55, | |
| "learning_rate": 1.8664179104477613e-05, | |
| "loss": 0.2936, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 30.69, | |
| "learning_rate": 1.8626865671641793e-05, | |
| "loss": 0.2937, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 30.83, | |
| "learning_rate": 1.8589552238805972e-05, | |
| "loss": 0.2952, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 30.97, | |
| "learning_rate": 1.855223880597015e-05, | |
| "loss": 0.2915, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 0.5184913873672485, | |
| "eval_runtime": 131.6654, | |
| "eval_samples_per_second": 4.041, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.20736645882882304, | |
| "step": 2232 | |
| }, | |
| { | |
| "epoch": 31.11, | |
| "learning_rate": 1.851492537313433e-05, | |
| "loss": 0.3009, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 31.25, | |
| "learning_rate": 1.847761194029851e-05, | |
| "loss": 0.3002, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 31.39, | |
| "learning_rate": 1.844029850746269e-05, | |
| "loss": 0.2676, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 31.53, | |
| "learning_rate": 1.8402985074626868e-05, | |
| "loss": 0.2795, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 31.66, | |
| "learning_rate": 1.8365671641791047e-05, | |
| "loss": 0.2855, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 31.8, | |
| "learning_rate": 1.8328358208955223e-05, | |
| "loss": 0.2967, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 31.94, | |
| "learning_rate": 1.8291044776119405e-05, | |
| "loss": 0.2942, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 0.5221661925315857, | |
| "eval_runtime": 131.7358, | |
| "eval_samples_per_second": 4.038, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.20935913093784148, | |
| "step": 2304 | |
| }, | |
| { | |
| "epoch": 32.08, | |
| "learning_rate": 1.8253731343283584e-05, | |
| "loss": 0.3027, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 32.22, | |
| "learning_rate": 1.821641791044776e-05, | |
| "loss": 0.2919, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 32.36, | |
| "learning_rate": 1.8179104477611943e-05, | |
| "loss": 0.2963, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "learning_rate": 1.814179104477612e-05, | |
| "loss": 0.2917, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 32.64, | |
| "learning_rate": 1.8104477611940297e-05, | |
| "loss": 0.2753, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 32.78, | |
| "learning_rate": 1.806716417910448e-05, | |
| "loss": 0.288, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 32.91, | |
| "learning_rate": 1.802985074626866e-05, | |
| "loss": 0.2777, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 0.5229014158248901, | |
| "eval_runtime": 131.9614, | |
| "eval_samples_per_second": 4.031, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.21077328533779005, | |
| "step": 2376 | |
| }, | |
| { | |
| "epoch": 33.06, | |
| "learning_rate": 1.7992537313432835e-05, | |
| "loss": 0.3004, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "learning_rate": 1.7955223880597017e-05, | |
| "loss": 0.2916, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 1.7917910447761193e-05, | |
| "loss": 0.2933, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 33.47, | |
| "learning_rate": 1.7880597014925372e-05, | |
| "loss": 0.296, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 33.61, | |
| "learning_rate": 1.7843283582089555e-05, | |
| "loss": 0.2959, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 33.75, | |
| "learning_rate": 1.780597014925373e-05, | |
| "loss": 0.2846, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 33.89, | |
| "learning_rate": 1.776865671641791e-05, | |
| "loss": 0.2821, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 0.5242453813552856, | |
| "eval_runtime": 132.7946, | |
| "eval_samples_per_second": 4.006, | |
| "eval_steps_per_second": 0.505, | |
| "eval_wer": 0.2101947676287202, | |
| "step": 2448 | |
| }, | |
| { | |
| "epoch": 34.03, | |
| "learning_rate": 1.7731343283582092e-05, | |
| "loss": 0.2997, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 34.17, | |
| "learning_rate": 1.7694029850746268e-05, | |
| "loss": 0.2872, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 34.3, | |
| "learning_rate": 1.7656716417910447e-05, | |
| "loss": 0.2826, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 34.44, | |
| "learning_rate": 1.761940298507463e-05, | |
| "loss": 0.2965, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 34.58, | |
| "learning_rate": 1.7582089552238806e-05, | |
| "loss": 0.2812, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 34.72, | |
| "learning_rate": 1.7548507462686566e-05, | |
| "loss": 0.2893, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 34.86, | |
| "learning_rate": 1.751119402985075e-05, | |
| "loss": 0.2799, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 1.7473880597014928e-05, | |
| "loss": 0.2859, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 0.5292270183563232, | |
| "eval_runtime": 131.3549, | |
| "eval_samples_per_second": 4.05, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.2096162499196503, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 35.14, | |
| "learning_rate": 1.7436567164179103e-05, | |
| "loss": 0.2936, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 35.28, | |
| "learning_rate": 1.7399253731343286e-05, | |
| "loss": 0.2941, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 35.42, | |
| "learning_rate": 1.7361940298507465e-05, | |
| "loss": 0.2887, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 35.55, | |
| "learning_rate": 1.732462686567164e-05, | |
| "loss": 0.296, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 35.69, | |
| "learning_rate": 1.7287313432835823e-05, | |
| "loss": 0.2905, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 35.83, | |
| "learning_rate": 1.725e-05, | |
| "loss": 0.2872, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 35.97, | |
| "learning_rate": 1.721268656716418e-05, | |
| "loss": 0.283, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 0.5041770339012146, | |
| "eval_runtime": 131.4728, | |
| "eval_samples_per_second": 4.046, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.20665938162884875, | |
| "step": 2592 | |
| }, | |
| { | |
| "epoch": 36.11, | |
| "learning_rate": 1.717537313432836e-05, | |
| "loss": 0.2914, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 36.25, | |
| "learning_rate": 1.7138059701492537e-05, | |
| "loss": 0.2829, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 36.39, | |
| "learning_rate": 1.7100746268656716e-05, | |
| "loss": 0.2682, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 36.53, | |
| "learning_rate": 1.70634328358209e-05, | |
| "loss": 0.2989, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 36.66, | |
| "learning_rate": 1.7026119402985074e-05, | |
| "loss": 0.2873, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 36.8, | |
| "learning_rate": 1.6992537313432834e-05, | |
| "loss": 0.29, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 36.94, | |
| "learning_rate": 1.6955223880597017e-05, | |
| "loss": 0.2895, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 0.5222975015640259, | |
| "eval_runtime": 131.841, | |
| "eval_samples_per_second": 4.035, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.2045381500289259, | |
| "step": 2664 | |
| }, | |
| { | |
| "epoch": 37.08, | |
| "learning_rate": 1.6917910447761196e-05, | |
| "loss": 0.2939, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 37.22, | |
| "learning_rate": 1.6880597014925372e-05, | |
| "loss": 0.295, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 37.36, | |
| "learning_rate": 1.6843283582089554e-05, | |
| "loss": 0.2793, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 1.6805970149253734e-05, | |
| "loss": 0.2842, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 37.64, | |
| "learning_rate": 1.676865671641791e-05, | |
| "loss": 0.2678, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 37.78, | |
| "learning_rate": 1.6731343283582092e-05, | |
| "loss": 0.2868, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 37.91, | |
| "learning_rate": 1.669402985074627e-05, | |
| "loss": 0.2822, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 0.5093514919281006, | |
| "eval_runtime": 132.4112, | |
| "eval_samples_per_second": 4.018, | |
| "eval_steps_per_second": 0.506, | |
| "eval_wer": 0.2071093398470142, | |
| "step": 2736 | |
| }, | |
| { | |
| "epoch": 38.06, | |
| "learning_rate": 1.6656716417910447e-05, | |
| "loss": 0.2914, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 38.19, | |
| "learning_rate": 1.661940298507463e-05, | |
| "loss": 0.2828, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 38.33, | |
| "learning_rate": 1.658208955223881e-05, | |
| "loss": 0.2637, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 38.47, | |
| "learning_rate": 1.6544776119402984e-05, | |
| "loss": 0.288, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 38.61, | |
| "learning_rate": 1.6507462686567167e-05, | |
| "loss": 0.2814, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 38.75, | |
| "learning_rate": 1.6470149253731343e-05, | |
| "loss": 0.2902, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 38.89, | |
| "learning_rate": 1.6432835820895522e-05, | |
| "loss": 0.2672, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 0.5250556468963623, | |
| "eval_runtime": 131.822, | |
| "eval_samples_per_second": 4.036, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.20415247155621263, | |
| "step": 2808 | |
| }, | |
| { | |
| "epoch": 39.03, | |
| "learning_rate": 1.6395522388059704e-05, | |
| "loss": 0.2954, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 39.17, | |
| "learning_rate": 1.635820895522388e-05, | |
| "loss": 0.2854, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 39.3, | |
| "learning_rate": 1.632089552238806e-05, | |
| "loss": 0.2874, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 39.44, | |
| "learning_rate": 1.6283582089552242e-05, | |
| "loss": 0.2671, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 39.58, | |
| "learning_rate": 1.6246268656716418e-05, | |
| "loss": 0.2761, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 39.72, | |
| "learning_rate": 1.6208955223880597e-05, | |
| "loss": 0.2904, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 39.86, | |
| "learning_rate": 1.617164179104478e-05, | |
| "loss": 0.2783, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.6134328358208955e-05, | |
| "loss": 0.2925, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 0.5071823000907898, | |
| "eval_runtime": 132.8431, | |
| "eval_samples_per_second": 4.005, | |
| "eval_steps_per_second": 0.504, | |
| "eval_wer": 0.20511666773799575, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 40.14, | |
| "learning_rate": 1.6097014925373134e-05, | |
| "loss": 0.2936, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 40.28, | |
| "learning_rate": 1.6059701492537313e-05, | |
| "loss": 0.2848, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 40.42, | |
| "learning_rate": 1.6022388059701492e-05, | |
| "loss": 0.2866, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 40.55, | |
| "learning_rate": 1.598507462686567e-05, | |
| "loss": 0.289, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 40.69, | |
| "learning_rate": 1.594776119402985e-05, | |
| "loss": 0.2817, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 40.83, | |
| "learning_rate": 1.591044776119403e-05, | |
| "loss": 0.293, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 40.97, | |
| "learning_rate": 1.587313432835821e-05, | |
| "loss": 0.295, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 0.4903075695037842, | |
| "eval_runtime": 131.5707, | |
| "eval_samples_per_second": 4.043, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.2071093398470142, | |
| "step": 2952 | |
| }, | |
| { | |
| "epoch": 41.11, | |
| "learning_rate": 1.5835820895522388e-05, | |
| "loss": 0.2957, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 41.25, | |
| "learning_rate": 1.5798507462686567e-05, | |
| "loss": 0.294, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 41.39, | |
| "learning_rate": 1.5761194029850747e-05, | |
| "loss": 0.2779, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 41.53, | |
| "learning_rate": 1.5723880597014926e-05, | |
| "loss": 0.2808, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 41.66, | |
| "learning_rate": 1.5686567164179105e-05, | |
| "loss": 0.2924, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 41.8, | |
| "learning_rate": 1.5649253731343284e-05, | |
| "loss": 0.2917, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 41.94, | |
| "learning_rate": 1.5611940298507463e-05, | |
| "loss": 0.2725, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 0.49732398986816406, | |
| "eval_runtime": 131.4816, | |
| "eval_samples_per_second": 4.046, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.20485954875618692, | |
| "step": 3024 | |
| }, | |
| { | |
| "epoch": 42.08, | |
| "learning_rate": 1.5574626865671642e-05, | |
| "loss": 0.2972, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 42.22, | |
| "learning_rate": 1.553731343283582e-05, | |
| "loss": 0.2854, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 42.36, | |
| "learning_rate": 1.55e-05, | |
| "loss": 0.2874, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 42.5, | |
| "learning_rate": 1.546268656716418e-05, | |
| "loss": 0.2928, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 42.64, | |
| "learning_rate": 1.542537313432836e-05, | |
| "loss": 0.2773, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 42.78, | |
| "learning_rate": 1.5388059701492538e-05, | |
| "loss": 0.2954, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 42.91, | |
| "learning_rate": 1.5350746268656717e-05, | |
| "loss": 0.2758, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 0.5097233057022095, | |
| "eval_runtime": 131.4822, | |
| "eval_samples_per_second": 4.046, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.2015812817381243, | |
| "step": 3096 | |
| }, | |
| { | |
| "epoch": 43.06, | |
| "learning_rate": 1.5313432835820896e-05, | |
| "loss": 0.2904, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 43.19, | |
| "learning_rate": 1.5276119402985076e-05, | |
| "loss": 0.2831, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 43.33, | |
| "learning_rate": 1.5238805970149256e-05, | |
| "loss": 0.2779, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 43.47, | |
| "learning_rate": 1.5201492537313434e-05, | |
| "loss": 0.2844, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 43.61, | |
| "learning_rate": 1.5164179104477613e-05, | |
| "loss": 0.2842, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 43.75, | |
| "learning_rate": 1.512686567164179e-05, | |
| "loss": 0.2856, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 43.89, | |
| "learning_rate": 1.5089552238805971e-05, | |
| "loss": 0.2809, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 0.49982935190200806, | |
| "eval_runtime": 131.8613, | |
| "eval_samples_per_second": 4.035, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.20280259690171626, | |
| "step": 3168 | |
| }, | |
| { | |
| "epoch": 44.03, | |
| "learning_rate": 1.505223880597015e-05, | |
| "loss": 0.2936, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 44.17, | |
| "learning_rate": 1.5014925373134328e-05, | |
| "loss": 0.285, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 44.3, | |
| "learning_rate": 1.4977611940298509e-05, | |
| "loss": 0.2833, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "learning_rate": 1.4940298507462688e-05, | |
| "loss": 0.282, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 44.58, | |
| "learning_rate": 1.4902985074626866e-05, | |
| "loss": 0.2816, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 44.72, | |
| "learning_rate": 1.4865671641791046e-05, | |
| "loss": 0.2711, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 44.86, | |
| "learning_rate": 1.4828358208955226e-05, | |
| "loss": 0.2702, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 1.4791044776119403e-05, | |
| "loss": 0.2804, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 0.5103247761726379, | |
| "eval_runtime": 131.3748, | |
| "eval_samples_per_second": 4.049, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.20421675130166483, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 45.14, | |
| "learning_rate": 1.4753731343283584e-05, | |
| "loss": 0.2664, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 45.28, | |
| "learning_rate": 1.4716417910447761e-05, | |
| "loss": 0.2755, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 45.42, | |
| "learning_rate": 1.467910447761194e-05, | |
| "loss": 0.2725, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 45.55, | |
| "learning_rate": 1.4641791044776121e-05, | |
| "loss": 0.2878, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 45.69, | |
| "learning_rate": 1.4604477611940299e-05, | |
| "loss": 0.2847, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 45.83, | |
| "learning_rate": 1.4567164179104478e-05, | |
| "loss": 0.2826, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 45.97, | |
| "learning_rate": 1.4529850746268659e-05, | |
| "loss": 0.2842, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 0.48608192801475525, | |
| "eval_runtime": 131.8901, | |
| "eval_samples_per_second": 4.034, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.2021597994471942, | |
| "step": 3312 | |
| }, | |
| { | |
| "epoch": 46.11, | |
| "learning_rate": 1.4492537313432836e-05, | |
| "loss": 0.2921, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 46.25, | |
| "learning_rate": 1.4455223880597015e-05, | |
| "loss": 0.2833, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 46.39, | |
| "learning_rate": 1.4417910447761196e-05, | |
| "loss": 0.2787, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 46.53, | |
| "learning_rate": 1.4380597014925374e-05, | |
| "loss": 0.2772, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 46.66, | |
| "learning_rate": 1.4343283582089553e-05, | |
| "loss": 0.2756, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 46.8, | |
| "learning_rate": 1.430597014925373e-05, | |
| "loss": 0.2745, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 46.94, | |
| "learning_rate": 1.4268656716417911e-05, | |
| "loss": 0.2721, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 0.5053983926773071, | |
| "eval_runtime": 131.5158, | |
| "eval_samples_per_second": 4.045, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.20595230442887447, | |
| "step": 3384 | |
| }, | |
| { | |
| "epoch": 47.08, | |
| "learning_rate": 1.423134328358209e-05, | |
| "loss": 0.2809, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 47.22, | |
| "learning_rate": 1.4194029850746268e-05, | |
| "loss": 0.2767, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 47.36, | |
| "learning_rate": 1.4156716417910449e-05, | |
| "loss": 0.267, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 47.5, | |
| "learning_rate": 1.4119402985074628e-05, | |
| "loss": 0.2758, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 47.64, | |
| "learning_rate": 1.4082089552238805e-05, | |
| "loss": 0.2654, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 47.78, | |
| "learning_rate": 1.4044776119402986e-05, | |
| "loss": 0.2781, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 47.91, | |
| "learning_rate": 1.4007462686567165e-05, | |
| "loss": 0.2673, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 0.5044223070144653, | |
| "eval_runtime": 131.7824, | |
| "eval_samples_per_second": 4.037, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.1999742881018191, | |
| "step": 3456 | |
| }, | |
| { | |
| "epoch": 48.06, | |
| "learning_rate": 1.3970149253731343e-05, | |
| "loss": 0.2927, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 48.19, | |
| "learning_rate": 1.3932835820895524e-05, | |
| "loss": 0.2854, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 48.33, | |
| "learning_rate": 1.3895522388059703e-05, | |
| "loss": 0.284, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 48.47, | |
| "learning_rate": 1.385820895522388e-05, | |
| "loss": 0.2675, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 48.61, | |
| "learning_rate": 1.3820895522388061e-05, | |
| "loss": 0.2719, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 48.75, | |
| "learning_rate": 1.3783582089552239e-05, | |
| "loss": 0.2748, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 48.89, | |
| "learning_rate": 1.3746268656716418e-05, | |
| "loss": 0.2696, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_loss": 0.5187488794326782, | |
| "eval_runtime": 131.1067, | |
| "eval_samples_per_second": 4.058, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.1983030147200617, | |
| "step": 3528 | |
| }, | |
| { | |
| "epoch": 49.03, | |
| "learning_rate": 1.3708955223880599e-05, | |
| "loss": 0.2806, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 49.17, | |
| "learning_rate": 1.3671641791044776e-05, | |
| "loss": 0.2766, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 49.3, | |
| "learning_rate": 1.3634328358208955e-05, | |
| "loss": 0.2821, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 49.44, | |
| "learning_rate": 1.3597014925373136e-05, | |
| "loss": 0.2673, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 49.58, | |
| "learning_rate": 1.3559701492537314e-05, | |
| "loss": 0.2794, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 49.72, | |
| "learning_rate": 1.3522388059701493e-05, | |
| "loss": 0.2745, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 49.86, | |
| "learning_rate": 1.3485074626865674e-05, | |
| "loss": 0.2664, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 1.3447761194029851e-05, | |
| "loss": 0.2724, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 0.5234389901161194, | |
| "eval_runtime": 131.879, | |
| "eval_samples_per_second": 4.034, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.20350967410169055, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 50.14, | |
| "learning_rate": 1.3410447761194032e-05, | |
| "loss": 0.2814, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 50.28, | |
| "learning_rate": 1.3373134328358208e-05, | |
| "loss": 0.267, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 50.42, | |
| "learning_rate": 1.3335820895522388e-05, | |
| "loss": 0.2681, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 50.55, | |
| "learning_rate": 1.329850746268657e-05, | |
| "loss": 0.2812, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 50.69, | |
| "learning_rate": 1.3261194029850745e-05, | |
| "loss": 0.2709, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 50.83, | |
| "learning_rate": 1.3223880597014926e-05, | |
| "loss": 0.2719, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 50.97, | |
| "learning_rate": 1.3186567164179107e-05, | |
| "loss": 0.2736, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_loss": 0.5106495022773743, | |
| "eval_runtime": 131.9308, | |
| "eval_samples_per_second": 4.032, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.2016455614835765, | |
| "step": 3672 | |
| }, | |
| { | |
| "epoch": 51.11, | |
| "learning_rate": 1.3149253731343284e-05, | |
| "loss": 0.2766, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 51.25, | |
| "learning_rate": 1.3111940298507463e-05, | |
| "loss": 0.2771, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 51.39, | |
| "learning_rate": 1.3074626865671644e-05, | |
| "loss": 0.2754, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 51.53, | |
| "learning_rate": 1.3037313432835822e-05, | |
| "loss": 0.2849, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 51.66, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 0.2669, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 51.8, | |
| "learning_rate": 1.2962686567164178e-05, | |
| "loss": 0.2623, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 51.94, | |
| "learning_rate": 1.292537313432836e-05, | |
| "loss": 0.2662, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_loss": 0.5071024298667908, | |
| "eval_runtime": 131.882, | |
| "eval_samples_per_second": 4.034, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.20537378671980458, | |
| "step": 3744 | |
| }, | |
| { | |
| "epoch": 52.08, | |
| "learning_rate": 1.2888059701492538e-05, | |
| "loss": 0.2814, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 52.22, | |
| "learning_rate": 1.2850746268656716e-05, | |
| "loss": 0.2733, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 52.36, | |
| "learning_rate": 1.2813432835820897e-05, | |
| "loss": 0.2679, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 52.5, | |
| "learning_rate": 1.2776119402985076e-05, | |
| "loss": 0.2717, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 52.64, | |
| "learning_rate": 1.2738805970149253e-05, | |
| "loss": 0.2563, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 52.78, | |
| "learning_rate": 1.2701492537313434e-05, | |
| "loss": 0.2791, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 52.91, | |
| "learning_rate": 1.2664179104477613e-05, | |
| "loss": 0.2701, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_loss": 0.5253528356552124, | |
| "eval_runtime": 131.2156, | |
| "eval_samples_per_second": 4.054, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.2016455614835765, | |
| "step": 3816 | |
| }, | |
| { | |
| "epoch": 53.06, | |
| "learning_rate": 1.262686567164179e-05, | |
| "loss": 0.2935, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 53.19, | |
| "learning_rate": 1.2589552238805972e-05, | |
| "loss": 0.2654, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 53.33, | |
| "learning_rate": 1.255223880597015e-05, | |
| "loss": 0.2768, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 53.47, | |
| "learning_rate": 1.2514925373134328e-05, | |
| "loss": 0.2779, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 53.61, | |
| "learning_rate": 1.2477611940298509e-05, | |
| "loss": 0.2743, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 53.75, | |
| "learning_rate": 1.2440298507462687e-05, | |
| "loss": 0.2719, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 53.89, | |
| "learning_rate": 1.2402985074626866e-05, | |
| "loss": 0.261, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_loss": 0.4967404007911682, | |
| "eval_runtime": 131.9132, | |
| "eval_samples_per_second": 4.033, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.19939577039274925, | |
| "step": 3888 | |
| }, | |
| { | |
| "epoch": 54.03, | |
| "learning_rate": 1.2365671641791045e-05, | |
| "loss": 0.2909, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 54.17, | |
| "learning_rate": 1.2328358208955226e-05, | |
| "loss": 0.2642, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 54.3, | |
| "learning_rate": 1.2291044776119403e-05, | |
| "loss": 0.2746, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 54.44, | |
| "learning_rate": 1.2253731343283582e-05, | |
| "loss": 0.2655, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 54.58, | |
| "learning_rate": 1.2216417910447763e-05, | |
| "loss": 0.2722, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 54.72, | |
| "learning_rate": 1.217910447761194e-05, | |
| "loss": 0.2721, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 54.86, | |
| "learning_rate": 1.214179104477612e-05, | |
| "loss": 0.2728, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "learning_rate": 1.2104477611940299e-05, | |
| "loss": 0.2708, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_loss": 0.5263388156890869, | |
| "eval_runtime": 131.5494, | |
| "eval_samples_per_second": 4.044, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.19688886032011313, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 55.14, | |
| "learning_rate": 1.2067164179104478e-05, | |
| "loss": 0.2684, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 55.28, | |
| "learning_rate": 1.2029850746268657e-05, | |
| "loss": 0.2699, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 55.42, | |
| "learning_rate": 1.1992537313432836e-05, | |
| "loss": 0.2796, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 55.55, | |
| "learning_rate": 1.1955223880597016e-05, | |
| "loss": 0.2666, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 55.69, | |
| "learning_rate": 1.1917910447761195e-05, | |
| "loss": 0.2702, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 55.83, | |
| "learning_rate": 1.1880597014925374e-05, | |
| "loss": 0.2711, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 55.97, | |
| "learning_rate": 1.1843283582089553e-05, | |
| "loss": 0.2764, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_loss": 0.5201473236083984, | |
| "eval_runtime": 131.8696, | |
| "eval_samples_per_second": 4.034, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.19676030082920873, | |
| "step": 4032 | |
| }, | |
| { | |
| "epoch": 56.11, | |
| "learning_rate": 1.1805970149253732e-05, | |
| "loss": 0.272, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 56.25, | |
| "learning_rate": 1.1768656716417911e-05, | |
| "loss": 0.2624, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 56.39, | |
| "learning_rate": 1.173134328358209e-05, | |
| "loss": 0.2566, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 56.53, | |
| "learning_rate": 1.1694029850746268e-05, | |
| "loss": 0.2789, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 56.66, | |
| "learning_rate": 1.1656716417910449e-05, | |
| "loss": 0.267, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 56.8, | |
| "learning_rate": 1.1619402985074628e-05, | |
| "loss": 0.2711, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 56.94, | |
| "learning_rate": 1.1582089552238806e-05, | |
| "loss": 0.268, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_loss": 0.5023506879806519, | |
| "eval_runtime": 131.2011, | |
| "eval_samples_per_second": 4.055, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.19785305650189625, | |
| "step": 4104 | |
| }, | |
| { | |
| "epoch": 57.08, | |
| "learning_rate": 1.1544776119402986e-05, | |
| "loss": 0.2639, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 57.22, | |
| "learning_rate": 1.1507462686567166e-05, | |
| "loss": 0.2725, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 57.36, | |
| "learning_rate": 1.1470149253731343e-05, | |
| "loss": 0.271, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 57.5, | |
| "learning_rate": 1.1432835820895522e-05, | |
| "loss": 0.2778, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 57.64, | |
| "learning_rate": 1.1395522388059703e-05, | |
| "loss": 0.2673, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 57.78, | |
| "learning_rate": 1.135820895522388e-05, | |
| "loss": 0.2665, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 57.91, | |
| "learning_rate": 1.132089552238806e-05, | |
| "loss": 0.2536, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_loss": 0.5224213600158691, | |
| "eval_runtime": 131.5544, | |
| "eval_samples_per_second": 4.044, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.19701741981101756, | |
| "step": 4176 | |
| }, | |
| { | |
| "epoch": 58.06, | |
| "learning_rate": 1.1283582089552239e-05, | |
| "loss": 0.2727, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 58.19, | |
| "learning_rate": 1.124626865671642e-05, | |
| "loss": 0.2596, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 58.33, | |
| "learning_rate": 1.1208955223880597e-05, | |
| "loss": 0.2671, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 58.47, | |
| "learning_rate": 1.1171641791044776e-05, | |
| "loss": 0.2667, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 58.61, | |
| "learning_rate": 1.1134328358208957e-05, | |
| "loss": 0.2648, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 58.75, | |
| "learning_rate": 1.1097014925373135e-05, | |
| "loss": 0.2828, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 58.89, | |
| "learning_rate": 1.1059701492537314e-05, | |
| "loss": 0.2625, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_loss": 0.5316326022148132, | |
| "eval_runtime": 131.6958, | |
| "eval_samples_per_second": 4.04, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.1999742881018191, | |
| "step": 4248 | |
| }, | |
| { | |
| "epoch": 59.03, | |
| "learning_rate": 1.1022388059701493e-05, | |
| "loss": 0.2725, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 59.17, | |
| "learning_rate": 1.0985074626865672e-05, | |
| "loss": 0.2541, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 59.3, | |
| "learning_rate": 1.0947761194029851e-05, | |
| "loss": 0.2703, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 59.44, | |
| "learning_rate": 1.091044776119403e-05, | |
| "loss": 0.2725, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 59.58, | |
| "learning_rate": 1.087313432835821e-05, | |
| "loss": 0.273, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 59.72, | |
| "learning_rate": 1.0835820895522389e-05, | |
| "loss": 0.2793, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 59.86, | |
| "learning_rate": 1.0798507462686568e-05, | |
| "loss": 0.257, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 1.0761194029850747e-05, | |
| "loss": 0.2621, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_loss": 0.5173215270042419, | |
| "eval_runtime": 131.579, | |
| "eval_samples_per_second": 4.043, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.19965288937455808, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 60.14, | |
| "learning_rate": 1.0723880597014926e-05, | |
| "loss": 0.272, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 60.28, | |
| "learning_rate": 1.0686567164179105e-05, | |
| "loss": 0.2669, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 60.42, | |
| "learning_rate": 1.0649253731343284e-05, | |
| "loss": 0.2703, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 60.55, | |
| "learning_rate": 1.0611940298507462e-05, | |
| "loss": 0.2633, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 60.69, | |
| "learning_rate": 1.0574626865671643e-05, | |
| "loss": 0.2657, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 60.83, | |
| "learning_rate": 1.0537313432835822e-05, | |
| "loss": 0.2654, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 60.97, | |
| "learning_rate": 1.05e-05, | |
| "loss": 0.2673, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_loss": 0.5116785764694214, | |
| "eval_runtime": 131.1081, | |
| "eval_samples_per_second": 4.058, | |
| "eval_steps_per_second": 0.511, | |
| "eval_wer": 0.20280259690171626, | |
| "step": 4392 | |
| }, | |
| { | |
| "epoch": 61.11, | |
| "learning_rate": 1.046268656716418e-05, | |
| "loss": 0.2678, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 61.25, | |
| "learning_rate": 1.042537313432836e-05, | |
| "loss": 0.2706, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 61.39, | |
| "learning_rate": 1.0388059701492537e-05, | |
| "loss": 0.2641, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 61.53, | |
| "learning_rate": 1.0350746268656716e-05, | |
| "loss": 0.2596, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 61.66, | |
| "learning_rate": 1.0313432835820897e-05, | |
| "loss": 0.2562, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 61.8, | |
| "learning_rate": 1.0276119402985074e-05, | |
| "loss": 0.2802, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 61.94, | |
| "learning_rate": 1.0238805970149254e-05, | |
| "loss": 0.2723, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_loss": 0.5285342335700989, | |
| "eval_runtime": 131.8603, | |
| "eval_samples_per_second": 4.035, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.1999742881018191, | |
| "step": 4464 | |
| }, | |
| { | |
| "epoch": 62.08, | |
| "learning_rate": 1.0201492537313434e-05, | |
| "loss": 0.2846, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 62.22, | |
| "learning_rate": 1.0164179104477614e-05, | |
| "loss": 0.2758, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 62.36, | |
| "learning_rate": 1.0126865671641791e-05, | |
| "loss": 0.277, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 62.5, | |
| "learning_rate": 1.008955223880597e-05, | |
| "loss": 0.2761, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 62.64, | |
| "learning_rate": 1.0052238805970151e-05, | |
| "loss": 0.2684, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 62.78, | |
| "learning_rate": 1.0014925373134328e-05, | |
| "loss": 0.2817, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 62.91, | |
| "learning_rate": 9.977611940298508e-06, | |
| "loss": 0.2691, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_loss": 0.5328835248947144, | |
| "eval_runtime": 131.3705, | |
| "eval_samples_per_second": 4.05, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.19611750337468664, | |
| "step": 4536 | |
| }, | |
| { | |
| "epoch": 63.06, | |
| "learning_rate": 9.940298507462687e-06, | |
| "loss": 0.2824, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 63.19, | |
| "learning_rate": 9.902985074626866e-06, | |
| "loss": 0.2772, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 63.33, | |
| "learning_rate": 9.865671641791045e-06, | |
| "loss": 0.2708, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 63.47, | |
| "learning_rate": 9.828358208955224e-06, | |
| "loss": 0.2679, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 63.61, | |
| "learning_rate": 9.791044776119403e-06, | |
| "loss": 0.268, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 63.75, | |
| "learning_rate": 9.753731343283583e-06, | |
| "loss": 0.2705, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 63.89, | |
| "learning_rate": 9.716417910447762e-06, | |
| "loss": 0.2668, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_loss": 0.5160889625549316, | |
| "eval_runtime": 131.2903, | |
| "eval_samples_per_second": 4.052, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.19643890210194767, | |
| "step": 4608 | |
| }, | |
| { | |
| "epoch": 64.03, | |
| "learning_rate": 9.679104477611941e-06, | |
| "loss": 0.2774, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 64.17, | |
| "learning_rate": 9.64179104477612e-06, | |
| "loss": 0.2688, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 64.3, | |
| "learning_rate": 9.6044776119403e-06, | |
| "loss": 0.2773, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 64.44, | |
| "learning_rate": 9.567164179104478e-06, | |
| "loss": 0.2633, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 64.58, | |
| "learning_rate": 9.529850746268656e-06, | |
| "loss": 0.2735, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 64.72, | |
| "learning_rate": 9.492537313432837e-06, | |
| "loss": 0.2683, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 64.86, | |
| "learning_rate": 9.455223880597016e-06, | |
| "loss": 0.2719, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "learning_rate": 9.417910447761193e-06, | |
| "loss": 0.27, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_loss": 0.5026705861091614, | |
| "eval_runtime": 131.4228, | |
| "eval_samples_per_second": 4.048, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.19695314006556533, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 65.14, | |
| "learning_rate": 9.380597014925374e-06, | |
| "loss": 0.2786, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 65.28, | |
| "learning_rate": 9.343283582089553e-06, | |
| "loss": 0.2731, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 65.42, | |
| "learning_rate": 9.30597014925373e-06, | |
| "loss": 0.2707, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 65.55, | |
| "learning_rate": 9.26865671641791e-06, | |
| "loss": 0.2638, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 65.69, | |
| "learning_rate": 9.23134328358209e-06, | |
| "loss": 0.2605, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 65.83, | |
| "learning_rate": 9.194029850746268e-06, | |
| "loss": 0.2736, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 65.97, | |
| "learning_rate": 9.156716417910447e-06, | |
| "loss": 0.257, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_loss": 0.5016449689865112, | |
| "eval_runtime": 132.0547, | |
| "eval_samples_per_second": 4.029, | |
| "eval_steps_per_second": 0.507, | |
| "eval_wer": 0.19965288937455808, | |
| "step": 4752 | |
| }, | |
| { | |
| "epoch": 66.11, | |
| "learning_rate": 9.119402985074628e-06, | |
| "loss": 0.277, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 66.25, | |
| "learning_rate": 9.082089552238807e-06, | |
| "loss": 0.2734, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 66.39, | |
| "learning_rate": 9.044776119402985e-06, | |
| "loss": 0.2679, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 66.53, | |
| "learning_rate": 9.007462686567164e-06, | |
| "loss": 0.2755, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 66.66, | |
| "learning_rate": 8.970149253731345e-06, | |
| "loss": 0.2686, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 66.8, | |
| "learning_rate": 8.932835820895522e-06, | |
| "loss": 0.2651, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 66.94, | |
| "learning_rate": 8.895522388059702e-06, | |
| "loss": 0.2711, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_loss": 0.5059924721717834, | |
| "eval_runtime": 131.6036, | |
| "eval_samples_per_second": 4.042, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.19714597930192196, | |
| "step": 4824 | |
| }, | |
| { | |
| "epoch": 67.08, | |
| "learning_rate": 8.85820895522388e-06, | |
| "loss": 0.2678, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 67.22, | |
| "learning_rate": 8.82089552238806e-06, | |
| "loss": 0.2676, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 67.36, | |
| "learning_rate": 8.783582089552239e-06, | |
| "loss": 0.2569, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 67.5, | |
| "learning_rate": 8.746268656716418e-06, | |
| "loss": 0.2681, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 67.64, | |
| "learning_rate": 8.708955223880597e-06, | |
| "loss": 0.2664, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 67.78, | |
| "learning_rate": 8.671641791044776e-06, | |
| "loss": 0.2725, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 67.91, | |
| "learning_rate": 8.634328358208956e-06, | |
| "loss": 0.269, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_loss": 0.5219683051109314, | |
| "eval_runtime": 131.9262, | |
| "eval_samples_per_second": 4.033, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.1983030147200617, | |
| "step": 4896 | |
| }, | |
| { | |
| "epoch": 68.06, | |
| "learning_rate": 8.597014925373135e-06, | |
| "loss": 0.2747, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 68.19, | |
| "learning_rate": 8.559701492537314e-06, | |
| "loss": 0.2724, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 68.33, | |
| "learning_rate": 8.522388059701493e-06, | |
| "loss": 0.2773, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 68.47, | |
| "learning_rate": 8.485074626865672e-06, | |
| "loss": 0.282, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 68.61, | |
| "learning_rate": 8.447761194029851e-06, | |
| "loss": 0.2674, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 68.75, | |
| "learning_rate": 8.41044776119403e-06, | |
| "loss": 0.2611, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 68.89, | |
| "learning_rate": 8.37313432835821e-06, | |
| "loss": 0.2659, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_loss": 0.498529314994812, | |
| "eval_runtime": 132.3204, | |
| "eval_samples_per_second": 4.021, | |
| "eval_steps_per_second": 0.506, | |
| "eval_wer": 0.19856013370187053, | |
| "step": 4968 | |
| }, | |
| { | |
| "epoch": 69.03, | |
| "learning_rate": 8.335820895522387e-06, | |
| "loss": 0.2752, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 69.17, | |
| "learning_rate": 8.298507462686568e-06, | |
| "loss": 0.2671, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 69.3, | |
| "learning_rate": 8.261194029850747e-06, | |
| "loss": 0.2704, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 69.44, | |
| "learning_rate": 8.223880597014925e-06, | |
| "loss": 0.265, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 69.58, | |
| "learning_rate": 8.186567164179104e-06, | |
| "loss": 0.2757, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 69.72, | |
| "learning_rate": 8.149253731343285e-06, | |
| "loss": 0.2688, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 69.86, | |
| "learning_rate": 8.111940298507462e-06, | |
| "loss": 0.2666, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 8.074626865671641e-06, | |
| "loss": 0.2669, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_loss": 0.514457643032074, | |
| "eval_runtime": 131.6706, | |
| "eval_samples_per_second": 4.04, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.1958603843928778, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 70.14, | |
| "learning_rate": 8.037313432835822e-06, | |
| "loss": 0.2716, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 70.28, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.2729, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 70.42, | |
| "learning_rate": 7.962686567164179e-06, | |
| "loss": 0.259, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 70.55, | |
| "learning_rate": 7.925373134328358e-06, | |
| "loss": 0.2651, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 70.69, | |
| "learning_rate": 7.888059701492539e-06, | |
| "loss": 0.2657, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 70.83, | |
| "learning_rate": 7.850746268656716e-06, | |
| "loss": 0.2735, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 70.97, | |
| "learning_rate": 7.813432835820895e-06, | |
| "loss": 0.2685, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_loss": 0.5079246163368225, | |
| "eval_runtime": 131.456, | |
| "eval_samples_per_second": 4.047, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.19560326541106898, | |
| "step": 5112 | |
| }, | |
| { | |
| "epoch": 71.11, | |
| "learning_rate": 7.776119402985076e-06, | |
| "loss": 0.2732, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 71.25, | |
| "learning_rate": 7.738805970149254e-06, | |
| "loss": 0.2568, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 71.39, | |
| "learning_rate": 7.701492537313433e-06, | |
| "loss": 0.2552, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 71.53, | |
| "learning_rate": 7.664179104477612e-06, | |
| "loss": 0.2634, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 71.66, | |
| "learning_rate": 7.626865671641792e-06, | |
| "loss": 0.2663, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 71.8, | |
| "learning_rate": 7.58955223880597e-06, | |
| "loss": 0.2679, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 71.94, | |
| "learning_rate": 7.5522388059701495e-06, | |
| "loss": 0.2669, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_loss": 0.49233612418174744, | |
| "eval_runtime": 131.3756, | |
| "eval_samples_per_second": 4.049, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.19361059330205052, | |
| "step": 5184 | |
| }, | |
| { | |
| "epoch": 72.08, | |
| "learning_rate": 7.514925373134328e-06, | |
| "loss": 0.2722, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 72.22, | |
| "learning_rate": 7.477611940298508e-06, | |
| "loss": 0.2698, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 72.36, | |
| "learning_rate": 7.440298507462687e-06, | |
| "loss": 0.2527, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 72.5, | |
| "learning_rate": 7.402985074626865e-06, | |
| "loss": 0.2658, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 72.64, | |
| "learning_rate": 7.365671641791045e-06, | |
| "loss": 0.2623, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 72.78, | |
| "learning_rate": 7.3283582089552245e-06, | |
| "loss": 0.2574, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 72.91, | |
| "learning_rate": 7.291044776119403e-06, | |
| "loss": 0.2586, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_loss": 0.4957040250301361, | |
| "eval_runtime": 131.9056, | |
| "eval_samples_per_second": 4.033, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.19528186668380793, | |
| "step": 5256 | |
| }, | |
| { | |
| "epoch": 73.06, | |
| "learning_rate": 7.253731343283582e-06, | |
| "loss": 0.2703, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 73.19, | |
| "learning_rate": 7.216417910447762e-06, | |
| "loss": 0.2618, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 73.33, | |
| "learning_rate": 7.17910447761194e-06, | |
| "loss": 0.2643, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 73.47, | |
| "learning_rate": 7.1417910447761194e-06, | |
| "loss": 0.2735, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 73.61, | |
| "learning_rate": 7.1044776119402994e-06, | |
| "loss": 0.2562, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 73.75, | |
| "learning_rate": 7.067164179104479e-06, | |
| "loss": 0.2597, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 73.89, | |
| "learning_rate": 7.029850746268657e-06, | |
| "loss": 0.2486, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_loss": 0.4974006712436676, | |
| "eval_runtime": 132.0022, | |
| "eval_samples_per_second": 4.03, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.19316063508388506, | |
| "step": 5328 | |
| }, | |
| { | |
| "epoch": 74.03, | |
| "learning_rate": 6.992537313432835e-06, | |
| "loss": 0.2732, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 74.17, | |
| "learning_rate": 6.955223880597016e-06, | |
| "loss": 0.2455, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 74.3, | |
| "learning_rate": 6.917910447761194e-06, | |
| "loss": 0.2517, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 74.44, | |
| "learning_rate": 6.8805970149253735e-06, | |
| "loss": 0.2618, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 74.58, | |
| "learning_rate": 6.843283582089552e-06, | |
| "loss": 0.2667, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 74.72, | |
| "learning_rate": 6.805970149253732e-06, | |
| "loss": 0.2635, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 74.86, | |
| "learning_rate": 6.768656716417911e-06, | |
| "loss": 0.2667, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 6.731343283582089e-06, | |
| "loss": 0.2611, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_loss": 0.5044746398925781, | |
| "eval_runtime": 131.9706, | |
| "eval_samples_per_second": 4.031, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.1948961882110947, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 75.14, | |
| "learning_rate": 6.694029850746269e-06, | |
| "loss": 0.2813, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 75.28, | |
| "learning_rate": 6.6567164179104485e-06, | |
| "loss": 0.2708, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 75.42, | |
| "learning_rate": 6.619402985074627e-06, | |
| "loss": 0.2558, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 75.55, | |
| "learning_rate": 6.582089552238806e-06, | |
| "loss": 0.2593, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 75.69, | |
| "learning_rate": 6.544776119402986e-06, | |
| "loss": 0.2532, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 75.83, | |
| "learning_rate": 6.507462686567164e-06, | |
| "loss": 0.2601, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 75.97, | |
| "learning_rate": 6.4701492537313434e-06, | |
| "loss": 0.264, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_loss": 0.5025977492332458, | |
| "eval_runtime": 132.0676, | |
| "eval_samples_per_second": 4.028, | |
| "eval_steps_per_second": 0.507, | |
| "eval_wer": 0.1965674615928521, | |
| "step": 5472 | |
| }, | |
| { | |
| "epoch": 76.11, | |
| "learning_rate": 6.4328358208955234e-06, | |
| "loss": 0.256, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 76.25, | |
| "learning_rate": 6.395522388059702e-06, | |
| "loss": 0.2661, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 76.39, | |
| "learning_rate": 6.358208955223881e-06, | |
| "loss": 0.2603, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 76.53, | |
| "learning_rate": 6.320895522388059e-06, | |
| "loss": 0.2574, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 76.66, | |
| "learning_rate": 6.283582089552239e-06, | |
| "loss": 0.2572, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 76.8, | |
| "learning_rate": 6.246268656716418e-06, | |
| "loss": 0.2587, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 76.94, | |
| "learning_rate": 6.208955223880597e-06, | |
| "loss": 0.2653, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_loss": 0.5044174790382385, | |
| "eval_runtime": 133.5324, | |
| "eval_samples_per_second": 3.984, | |
| "eval_steps_per_second": 0.502, | |
| "eval_wer": 0.19361059330205052, | |
| "step": 5544 | |
| }, | |
| { | |
| "epoch": 77.08, | |
| "learning_rate": 6.171641791044777e-06, | |
| "loss": 0.2586, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 77.22, | |
| "learning_rate": 6.134328358208956e-06, | |
| "loss": 0.2628, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 77.36, | |
| "learning_rate": 6.097014925373134e-06, | |
| "loss": 0.2637, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 77.5, | |
| "learning_rate": 6.059701492537314e-06, | |
| "loss": 0.2594, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 77.64, | |
| "learning_rate": 6.0223880597014925e-06, | |
| "loss": 0.2567, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 77.78, | |
| "learning_rate": 5.9850746268656725e-06, | |
| "loss": 0.2684, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 77.91, | |
| "learning_rate": 5.947761194029851e-06, | |
| "loss": 0.2579, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_loss": 0.4963833689689636, | |
| "eval_runtime": 131.9034, | |
| "eval_samples_per_second": 4.033, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.1966960210837565, | |
| "step": 5616 | |
| }, | |
| { | |
| "epoch": 78.06, | |
| "learning_rate": 5.91044776119403e-06, | |
| "loss": 0.2654, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 78.19, | |
| "learning_rate": 5.873134328358209e-06, | |
| "loss": 0.2565, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 78.33, | |
| "learning_rate": 5.835820895522388e-06, | |
| "loss": 0.2647, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 78.47, | |
| "learning_rate": 5.7985074626865674e-06, | |
| "loss": 0.2561, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 78.61, | |
| "learning_rate": 5.761194029850747e-06, | |
| "loss": 0.2495, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 78.75, | |
| "learning_rate": 5.723880597014926e-06, | |
| "loss": 0.2562, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 78.89, | |
| "learning_rate": 5.686567164179105e-06, | |
| "loss": 0.26, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_loss": 0.4918227195739746, | |
| "eval_runtime": 132.2622, | |
| "eval_samples_per_second": 4.022, | |
| "eval_steps_per_second": 0.507, | |
| "eval_wer": 0.19373915279295495, | |
| "step": 5688 | |
| }, | |
| { | |
| "epoch": 79.03, | |
| "learning_rate": 5.649253731343284e-06, | |
| "loss": 0.269, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 79.17, | |
| "learning_rate": 5.611940298507462e-06, | |
| "loss": 0.2585, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 79.3, | |
| "learning_rate": 5.574626865671642e-06, | |
| "loss": 0.2609, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 79.44, | |
| "learning_rate": 5.537313432835821e-06, | |
| "loss": 0.256, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 79.58, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 0.2615, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 79.72, | |
| "learning_rate": 5.46268656716418e-06, | |
| "loss": 0.2626, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 79.86, | |
| "learning_rate": 5.425373134328358e-06, | |
| "loss": 0.2545, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 5.388059701492538e-06, | |
| "loss": 0.2634, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_loss": 0.4841861128807068, | |
| "eval_runtime": 131.8698, | |
| "eval_samples_per_second": 4.034, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.19277495661117183, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 80.14, | |
| "learning_rate": 5.3507462686567165e-06, | |
| "loss": 0.2575, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 80.28, | |
| "learning_rate": 5.313432835820896e-06, | |
| "loss": 0.2567, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 80.42, | |
| "learning_rate": 5.276119402985075e-06, | |
| "loss": 0.2599, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 80.55, | |
| "learning_rate": 5.238805970149254e-06, | |
| "loss": 0.246, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 80.69, | |
| "learning_rate": 5.201492537313433e-06, | |
| "loss": 0.2546, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 80.83, | |
| "learning_rate": 5.164179104477612e-06, | |
| "loss": 0.2675, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 80.97, | |
| "learning_rate": 5.1268656716417914e-06, | |
| "loss": 0.2598, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_loss": 0.5017235279083252, | |
| "eval_runtime": 132.1658, | |
| "eval_samples_per_second": 4.025, | |
| "eval_steps_per_second": 0.507, | |
| "eval_wer": 0.19463906922928584, | |
| "step": 5832 | |
| }, | |
| { | |
| "epoch": 81.11, | |
| "learning_rate": 5.089552238805971e-06, | |
| "loss": 0.2551, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 81.25, | |
| "learning_rate": 5.05223880597015e-06, | |
| "loss": 0.2648, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 81.39, | |
| "learning_rate": 5.014925373134328e-06, | |
| "loss": 0.2447, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 81.53, | |
| "learning_rate": 4.977611940298508e-06, | |
| "loss": 0.2561, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 81.66, | |
| "learning_rate": 4.940298507462686e-06, | |
| "loss": 0.261, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 81.8, | |
| "learning_rate": 4.902985074626866e-06, | |
| "loss": 0.2653, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 81.94, | |
| "learning_rate": 4.865671641791045e-06, | |
| "loss": 0.2571, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_loss": 0.4997570514678955, | |
| "eval_runtime": 131.7552, | |
| "eval_samples_per_second": 4.038, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.1983672944655139, | |
| "step": 5904 | |
| }, | |
| { | |
| "epoch": 82.08, | |
| "learning_rate": 4.828358208955224e-06, | |
| "loss": 0.2628, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 82.22, | |
| "learning_rate": 4.791044776119404e-06, | |
| "loss": 0.2625, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 82.36, | |
| "learning_rate": 4.753731343283582e-06, | |
| "loss": 0.2396, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 82.5, | |
| "learning_rate": 4.716417910447761e-06, | |
| "loss": 0.2698, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 82.64, | |
| "learning_rate": 4.6791044776119405e-06, | |
| "loss": 0.2571, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 82.78, | |
| "learning_rate": 4.64179104477612e-06, | |
| "loss": 0.2592, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 82.91, | |
| "learning_rate": 4.604477611940299e-06, | |
| "loss": 0.2564, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_loss": 0.4961981475353241, | |
| "eval_runtime": 132.3751, | |
| "eval_samples_per_second": 4.019, | |
| "eval_steps_per_second": 0.506, | |
| "eval_wer": 0.19393199202931155, | |
| "step": 5976 | |
| }, | |
| { | |
| "epoch": 83.06, | |
| "learning_rate": 4.567164179104478e-06, | |
| "loss": 0.2661, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 83.19, | |
| "learning_rate": 4.529850746268656e-06, | |
| "loss": 0.2602, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 83.33, | |
| "learning_rate": 4.492537313432836e-06, | |
| "loss": 0.2515, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 83.47, | |
| "learning_rate": 4.4552238805970154e-06, | |
| "loss": 0.2607, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 83.61, | |
| "learning_rate": 4.417910447761195e-06, | |
| "loss": 0.2457, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 83.75, | |
| "learning_rate": 4.380597014925374e-06, | |
| "loss": 0.2613, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 83.89, | |
| "learning_rate": 4.343283582089552e-06, | |
| "loss": 0.2606, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_loss": 0.49531611800193787, | |
| "eval_runtime": 131.4182, | |
| "eval_samples_per_second": 4.048, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.19155364144757986, | |
| "step": 6048 | |
| }, | |
| { | |
| "epoch": 84.03, | |
| "learning_rate": 4.305970149253732e-06, | |
| "loss": 0.2655, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 84.17, | |
| "learning_rate": 4.26865671641791e-06, | |
| "loss": 0.2488, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 84.3, | |
| "learning_rate": 4.2313432835820895e-06, | |
| "loss": 0.258, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 84.44, | |
| "learning_rate": 4.194029850746269e-06, | |
| "loss": 0.2644, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 84.58, | |
| "learning_rate": 4.156716417910448e-06, | |
| "loss": 0.2573, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 84.72, | |
| "learning_rate": 4.119402985074627e-06, | |
| "loss": 0.243, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 84.86, | |
| "learning_rate": 4.082089552238806e-06, | |
| "loss": 0.2581, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "learning_rate": 4.044776119402985e-06, | |
| "loss": 0.2587, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_loss": 0.4982677400112152, | |
| "eval_runtime": 132.0294, | |
| "eval_samples_per_second": 4.029, | |
| "eval_steps_per_second": 0.507, | |
| "eval_wer": 0.19463906922928584, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 85.14, | |
| "learning_rate": 4.0074626865671645e-06, | |
| "loss": 0.2455, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 85.28, | |
| "learning_rate": 3.970149253731344e-06, | |
| "loss": 0.2532, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 85.42, | |
| "learning_rate": 3.932835820895522e-06, | |
| "loss": 0.2608, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 85.55, | |
| "learning_rate": 3.895522388059702e-06, | |
| "loss": 0.2604, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 85.69, | |
| "learning_rate": 3.85820895522388e-06, | |
| "loss": 0.2489, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 85.83, | |
| "learning_rate": 3.82089552238806e-06, | |
| "loss": 0.2594, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 85.97, | |
| "learning_rate": 3.7835820895522394e-06, | |
| "loss": 0.2499, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_loss": 0.5027219653129578, | |
| "eval_runtime": 131.6359, | |
| "eval_samples_per_second": 4.041, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.19534614642926015, | |
| "step": 6192 | |
| }, | |
| { | |
| "epoch": 86.11, | |
| "learning_rate": 3.746268656716418e-06, | |
| "loss": 0.2499, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 86.25, | |
| "learning_rate": 3.7089552238805973e-06, | |
| "loss": 0.2627, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 86.39, | |
| "learning_rate": 3.671641791044776e-06, | |
| "loss": 0.2471, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 86.53, | |
| "learning_rate": 3.6343283582089557e-06, | |
| "loss": 0.2538, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 86.66, | |
| "learning_rate": 3.5970149253731344e-06, | |
| "loss": 0.2432, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 86.8, | |
| "learning_rate": 3.5597014925373135e-06, | |
| "loss": 0.2625, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 86.94, | |
| "learning_rate": 3.5223880597014923e-06, | |
| "loss": 0.253, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_loss": 0.5000377297401428, | |
| "eval_runtime": 132.268, | |
| "eval_samples_per_second": 4.022, | |
| "eval_steps_per_second": 0.507, | |
| "eval_wer": 0.19515330719290352, | |
| "step": 6264 | |
| }, | |
| { | |
| "epoch": 87.08, | |
| "learning_rate": 3.485074626865672e-06, | |
| "loss": 0.2605, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 87.22, | |
| "learning_rate": 3.4477611940298506e-06, | |
| "loss": 0.2625, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 87.36, | |
| "learning_rate": 3.41044776119403e-06, | |
| "loss": 0.2449, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 87.5, | |
| "learning_rate": 3.3731343283582093e-06, | |
| "loss": 0.2529, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 87.64, | |
| "learning_rate": 3.335820895522388e-06, | |
| "loss": 0.2388, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 87.78, | |
| "learning_rate": 3.2985074626865677e-06, | |
| "loss": 0.2504, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 87.91, | |
| "learning_rate": 3.2611940298507464e-06, | |
| "loss": 0.2614, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_loss": 0.4974157512187958, | |
| "eval_runtime": 132.0096, | |
| "eval_samples_per_second": 4.03, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.19354631355659832, | |
| "step": 6336 | |
| }, | |
| { | |
| "epoch": 88.06, | |
| "learning_rate": 3.2238805970149255e-06, | |
| "loss": 0.2682, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 88.19, | |
| "learning_rate": 3.1865671641791043e-06, | |
| "loss": 0.2494, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 88.33, | |
| "learning_rate": 3.149253731343284e-06, | |
| "loss": 0.2554, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 88.47, | |
| "learning_rate": 3.111940298507463e-06, | |
| "loss": 0.2546, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 88.61, | |
| "learning_rate": 3.0746268656716418e-06, | |
| "loss": 0.2447, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 88.75, | |
| "learning_rate": 3.037313432835821e-06, | |
| "loss": 0.257, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 88.89, | |
| "learning_rate": 3e-06, | |
| "loss": 0.2533, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_loss": 0.4969758987426758, | |
| "eval_runtime": 132.51, | |
| "eval_samples_per_second": 4.015, | |
| "eval_steps_per_second": 0.506, | |
| "eval_wer": 0.1948961882110947, | |
| "step": 6408 | |
| }, | |
| { | |
| "epoch": 89.03, | |
| "learning_rate": 2.9626865671641792e-06, | |
| "loss": 0.2591, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 89.17, | |
| "learning_rate": 2.9253731343283584e-06, | |
| "loss": 0.2604, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 89.3, | |
| "learning_rate": 2.8880597014925376e-06, | |
| "loss": 0.2445, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 89.44, | |
| "learning_rate": 2.8507462686567167e-06, | |
| "loss": 0.2494, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 89.58, | |
| "learning_rate": 2.813432835820896e-06, | |
| "loss": 0.255, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 89.72, | |
| "learning_rate": 2.7761194029850746e-06, | |
| "loss": 0.2512, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 89.86, | |
| "learning_rate": 2.7388059701492538e-06, | |
| "loss": 0.253, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 2.701492537313433e-06, | |
| "loss": 0.2553, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_loss": 0.5005418658256531, | |
| "eval_runtime": 131.5872, | |
| "eval_samples_per_second": 4.043, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.19296779584752843, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 90.14, | |
| "learning_rate": 2.664179104477612e-06, | |
| "loss": 0.2521, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 90.28, | |
| "learning_rate": 2.626865671641791e-06, | |
| "loss": 0.2599, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 90.42, | |
| "learning_rate": 2.5895522388059704e-06, | |
| "loss": 0.256, | |
| "step": 6510 | |
| }, | |
| { | |
| "epoch": 90.55, | |
| "learning_rate": 2.5522388059701496e-06, | |
| "loss": 0.2559, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 90.69, | |
| "learning_rate": 2.5149253731343287e-06, | |
| "loss": 0.2507, | |
| "step": 6530 | |
| }, | |
| { | |
| "epoch": 90.83, | |
| "learning_rate": 2.4776119402985074e-06, | |
| "loss": 0.2525, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 90.97, | |
| "learning_rate": 2.4402985074626866e-06, | |
| "loss": 0.2518, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_loss": 0.5009539127349854, | |
| "eval_runtime": 131.4903, | |
| "eval_samples_per_second": 4.046, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.1948961882110947, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 91.11, | |
| "learning_rate": 2.4029850746268658e-06, | |
| "loss": 0.2618, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 91.25, | |
| "learning_rate": 2.365671641791045e-06, | |
| "loss": 0.2592, | |
| "step": 6570 | |
| }, | |
| { | |
| "epoch": 91.39, | |
| "learning_rate": 2.328358208955224e-06, | |
| "loss": 0.2505, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 91.53, | |
| "learning_rate": 2.291044776119403e-06, | |
| "loss": 0.2539, | |
| "step": 6590 | |
| }, | |
| { | |
| "epoch": 91.66, | |
| "learning_rate": 2.2537313432835824e-06, | |
| "loss": 0.249, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 91.8, | |
| "learning_rate": 2.2164179104477616e-06, | |
| "loss": 0.2428, | |
| "step": 6610 | |
| }, | |
| { | |
| "epoch": 91.94, | |
| "learning_rate": 2.1791044776119403e-06, | |
| "loss": 0.2481, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_loss": 0.4958493113517761, | |
| "eval_runtime": 131.9046, | |
| "eval_samples_per_second": 4.033, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.1918107604293887, | |
| "step": 6624 | |
| }, | |
| { | |
| "epoch": 92.08, | |
| "learning_rate": 2.1417910447761194e-06, | |
| "loss": 0.2649, | |
| "step": 6630 | |
| }, | |
| { | |
| "epoch": 92.22, | |
| "learning_rate": 2.1044776119402986e-06, | |
| "loss": 0.2549, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 92.36, | |
| "learning_rate": 2.0671641791044778e-06, | |
| "loss": 0.2425, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 92.5, | |
| "learning_rate": 2.029850746268657e-06, | |
| "loss": 0.2598, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 92.64, | |
| "learning_rate": 1.9925373134328357e-06, | |
| "loss": 0.2429, | |
| "step": 6670 | |
| }, | |
| { | |
| "epoch": 92.78, | |
| "learning_rate": 1.955223880597015e-06, | |
| "loss": 0.2596, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 92.91, | |
| "learning_rate": 1.9179104477611944e-06, | |
| "loss": 0.2491, | |
| "step": 6690 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_loss": 0.4932185709476471, | |
| "eval_runtime": 131.4467, | |
| "eval_samples_per_second": 4.047, | |
| "eval_steps_per_second": 0.51, | |
| "eval_wer": 0.1909108439930578, | |
| "step": 6696 | |
| }, | |
| { | |
| "epoch": 93.06, | |
| "learning_rate": 1.8805970149253733e-06, | |
| "loss": 0.2682, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 93.19, | |
| "learning_rate": 1.8432835820895525e-06, | |
| "loss": 0.2455, | |
| "step": 6710 | |
| }, | |
| { | |
| "epoch": 93.33, | |
| "learning_rate": 1.8059701492537314e-06, | |
| "loss": 0.2456, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 93.47, | |
| "learning_rate": 1.7686567164179106e-06, | |
| "loss": 0.2493, | |
| "step": 6730 | |
| }, | |
| { | |
| "epoch": 93.61, | |
| "learning_rate": 1.7313432835820896e-06, | |
| "loss": 0.2526, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 93.75, | |
| "learning_rate": 1.6940298507462687e-06, | |
| "loss": 0.2599, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 93.89, | |
| "learning_rate": 1.6567164179104477e-06, | |
| "loss": 0.2455, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_loss": 0.493074506521225, | |
| "eval_runtime": 131.6855, | |
| "eval_samples_per_second": 4.04, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.19123224272031883, | |
| "step": 6768 | |
| }, | |
| { | |
| "epoch": 94.03, | |
| "learning_rate": 1.6194029850746268e-06, | |
| "loss": 0.2531, | |
| "step": 6770 | |
| }, | |
| { | |
| "epoch": 94.17, | |
| "learning_rate": 1.5820895522388062e-06, | |
| "loss": 0.2513, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 94.3, | |
| "learning_rate": 1.5447761194029851e-06, | |
| "loss": 0.2534, | |
| "step": 6790 | |
| }, | |
| { | |
| "epoch": 94.44, | |
| "learning_rate": 1.5111940298507464e-06, | |
| "loss": 0.2418, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 94.58, | |
| "learning_rate": 1.4738805970149254e-06, | |
| "loss": 0.2407, | |
| "step": 6810 | |
| }, | |
| { | |
| "epoch": 94.72, | |
| "learning_rate": 1.4365671641791045e-06, | |
| "loss": 0.251, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 94.86, | |
| "learning_rate": 1.3992537313432837e-06, | |
| "loss": 0.2494, | |
| "step": 6830 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "learning_rate": 1.3619402985074628e-06, | |
| "loss": 0.2581, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_loss": 0.49741461873054504, | |
| "eval_runtime": 132.2805, | |
| "eval_samples_per_second": 4.022, | |
| "eval_steps_per_second": 0.506, | |
| "eval_wer": 0.19148936170212766, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 95.14, | |
| "learning_rate": 1.3246268656716418e-06, | |
| "loss": 0.2415, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 95.28, | |
| "learning_rate": 1.287313432835821e-06, | |
| "loss": 0.2474, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 95.42, | |
| "learning_rate": 1.25e-06, | |
| "loss": 0.2488, | |
| "step": 6870 | |
| }, | |
| { | |
| "epoch": 95.55, | |
| "learning_rate": 1.2126865671641793e-06, | |
| "loss": 0.2566, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 95.69, | |
| "learning_rate": 1.1753731343283582e-06, | |
| "loss": 0.2457, | |
| "step": 6890 | |
| }, | |
| { | |
| "epoch": 95.83, | |
| "learning_rate": 1.1380597014925374e-06, | |
| "loss": 0.2489, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 95.97, | |
| "learning_rate": 1.1007462686567163e-06, | |
| "loss": 0.2578, | |
| "step": 6910 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_loss": 0.4990382492542267, | |
| "eval_runtime": 131.6402, | |
| "eval_samples_per_second": 4.041, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.1909108439930578, | |
| "step": 6912 | |
| }, | |
| { | |
| "epoch": 96.11, | |
| "learning_rate": 1.0634328358208957e-06, | |
| "loss": 0.2528, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 96.25, | |
| "learning_rate": 1.0261194029850746e-06, | |
| "loss": 0.2517, | |
| "step": 6930 | |
| }, | |
| { | |
| "epoch": 96.39, | |
| "learning_rate": 9.888059701492538e-07, | |
| "loss": 0.2358, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 96.53, | |
| "learning_rate": 9.514925373134328e-07, | |
| "loss": 0.254, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 96.66, | |
| "learning_rate": 9.141791044776121e-07, | |
| "loss": 0.2491, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 96.8, | |
| "learning_rate": 8.768656716417912e-07, | |
| "loss": 0.2494, | |
| "step": 6970 | |
| }, | |
| { | |
| "epoch": 96.94, | |
| "learning_rate": 8.395522388059702e-07, | |
| "loss": 0.2503, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_loss": 0.4989832937717438, | |
| "eval_runtime": 131.556, | |
| "eval_samples_per_second": 4.044, | |
| "eval_steps_per_second": 0.509, | |
| "eval_wer": 0.19136080221122323, | |
| "step": 6984 | |
| }, | |
| { | |
| "epoch": 97.08, | |
| "learning_rate": 8.022388059701493e-07, | |
| "loss": 0.2468, | |
| "step": 6990 | |
| }, | |
| { | |
| "epoch": 97.22, | |
| "learning_rate": 7.649253731343284e-07, | |
| "loss": 0.2519, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 97.36, | |
| "learning_rate": 7.276119402985075e-07, | |
| "loss": 0.2464, | |
| "step": 7010 | |
| }, | |
| { | |
| "epoch": 97.5, | |
| "learning_rate": 6.902985074626866e-07, | |
| "loss": 0.2423, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 97.64, | |
| "learning_rate": 6.529850746268657e-07, | |
| "loss": 0.2327, | |
| "step": 7030 | |
| }, | |
| { | |
| "epoch": 97.78, | |
| "learning_rate": 6.156716417910448e-07, | |
| "loss": 0.2523, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 97.91, | |
| "learning_rate": 5.783582089552239e-07, | |
| "loss": 0.2544, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_loss": 0.4931636154651642, | |
| "eval_runtime": 132.145, | |
| "eval_samples_per_second": 4.026, | |
| "eval_steps_per_second": 0.507, | |
| "eval_wer": 0.1903323262839879, | |
| "step": 7056 | |
| }, | |
| { | |
| "epoch": 98.06, | |
| "learning_rate": 5.41044776119403e-07, | |
| "loss": 0.2491, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 98.19, | |
| "learning_rate": 5.037313432835821e-07, | |
| "loss": 0.2483, | |
| "step": 7070 | |
| }, | |
| { | |
| "epoch": 98.33, | |
| "learning_rate": 4.6641791044776116e-07, | |
| "loss": 0.2478, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 98.47, | |
| "learning_rate": 4.291044776119403e-07, | |
| "loss": 0.255, | |
| "step": 7090 | |
| }, | |
| { | |
| "epoch": 98.61, | |
| "learning_rate": 3.9179104477611937e-07, | |
| "loss": 0.2429, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 98.75, | |
| "learning_rate": 3.544776119402985e-07, | |
| "loss": 0.2524, | |
| "step": 7110 | |
| }, | |
| { | |
| "epoch": 98.89, | |
| "learning_rate": 3.1716417910447763e-07, | |
| "loss": 0.2391, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_loss": 0.49354514479637146, | |
| "eval_runtime": 131.8773, | |
| "eval_samples_per_second": 4.034, | |
| "eval_steps_per_second": 0.508, | |
| "eval_wer": 0.1903966060294401, | |
| "step": 7128 | |
| }, | |
| { | |
| "epoch": 99.03, | |
| "learning_rate": 2.7985074626865674e-07, | |
| "loss": 0.265, | |
| "step": 7130 | |
| }, | |
| { | |
| "epoch": 99.17, | |
| "learning_rate": 2.4253731343283584e-07, | |
| "loss": 0.2477, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 99.3, | |
| "learning_rate": 2.0522388059701492e-07, | |
| "loss": 0.2497, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 99.44, | |
| "learning_rate": 1.6791044776119403e-07, | |
| "loss": 0.2535, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 99.58, | |
| "learning_rate": 1.3059701492537316e-07, | |
| "loss": 0.2511, | |
| "step": 7170 | |
| }, | |
| { | |
| "epoch": 99.72, | |
| "learning_rate": 9.328358208955224e-08, | |
| "loss": 0.2441, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 99.86, | |
| "learning_rate": 5.597014925373135e-08, | |
| "loss": 0.2413, | |
| "step": 7190 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 1.8656716417910447e-08, | |
| "loss": 0.2498, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_loss": 0.4945172667503357, | |
| "eval_runtime": 132.2872, | |
| "eval_samples_per_second": 4.022, | |
| "eval_steps_per_second": 0.506, | |
| "eval_wer": 0.1909108439930578, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 7200, | |
| "total_flos": 2.7202925310621965e+20, | |
| "train_loss": 0.2786852648191982, | |
| "train_runtime": 194751.2153, | |
| "train_samples_per_second": 2.371, | |
| "train_steps_per_second": 0.037 | |
| } | |
| ], | |
| "max_steps": 7200, | |
| "num_train_epochs": 100, | |
| "total_flos": 2.7202925310621965e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |