| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 100.0, | |
| "global_step": 18300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 47.84418869018555, | |
| "eval_runtime": 186.8063, | |
| "eval_samples_per_second": 19.587, | |
| "eval_steps_per_second": 1.226, | |
| "eval_wer": 1.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 6.310945510864258, | |
| "eval_runtime": 163.2985, | |
| "eval_samples_per_second": 22.407, | |
| "eval_steps_per_second": 1.402, | |
| "eval_wer": 1.0, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.00029699999999999996, | |
| "loss": 41.8902, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 6.239192008972168, | |
| "eval_runtime": 163.0201, | |
| "eval_samples_per_second": 22.445, | |
| "eval_steps_per_second": 1.405, | |
| "eval_wer": 1.0, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 5.973925590515137, | |
| "eval_runtime": 163.0214, | |
| "eval_samples_per_second": 22.445, | |
| "eval_steps_per_second": 1.405, | |
| "eval_wer": 1.1123227917121048, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 4.901411056518555, | |
| "eval_runtime": 162.8715, | |
| "eval_samples_per_second": 22.466, | |
| "eval_steps_per_second": 1.406, | |
| "eval_wer": 1.9473827699018538, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 0.00018834586466165413, | |
| "loss": 5.5817, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 3.9892334938049316, | |
| "eval_runtime": 163.2053, | |
| "eval_samples_per_second": 22.42, | |
| "eval_steps_per_second": 1.403, | |
| "eval_wer": 1.0188113413304254, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 3.5080456733703613, | |
| "eval_runtime": 162.7362, | |
| "eval_samples_per_second": 22.484, | |
| "eval_steps_per_second": 1.407, | |
| "eval_wer": 1.0103598691384952, | |
| "step": 1281 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 3.0796852111816406, | |
| "eval_runtime": 164.2666, | |
| "eval_samples_per_second": 22.275, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.9904580152671756, | |
| "step": 1464 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 7.556390977443609e-05, | |
| "loss": 3.5579, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.8110806941986084, | |
| "eval_runtime": 168.541, | |
| "eval_samples_per_second": 21.71, | |
| "eval_steps_per_second": 1.359, | |
| "eval_wer": 0.9836423118865867, | |
| "step": 1647 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.67260479927063, | |
| "eval_runtime": 165.7448, | |
| "eval_samples_per_second": 22.076, | |
| "eval_steps_per_second": 1.382, | |
| "eval_wer": 0.9814612868047983, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 10.93, | |
| "learning_rate": 0.00027480337078651684, | |
| "loss": 2.7771, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 2.7177391052246094, | |
| "eval_runtime": 191.8821, | |
| "eval_samples_per_second": 19.069, | |
| "eval_steps_per_second": 1.193, | |
| "eval_wer": 0.9809160305343512, | |
| "step": 2013 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 2.3581743240356445, | |
| "eval_runtime": 168.9095, | |
| "eval_samples_per_second": 21.662, | |
| "eval_steps_per_second": 1.356, | |
| "eval_wer": 0.9691930207197382, | |
| "step": 2196 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 2.1708498001098633, | |
| "eval_runtime": 167.2979, | |
| "eval_samples_per_second": 21.871, | |
| "eval_steps_per_second": 1.369, | |
| "eval_wer": 0.9757360959651036, | |
| "step": 2379 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 0.000266376404494382, | |
| "loss": 2.3488, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 2.049051284790039, | |
| "eval_runtime": 169.536, | |
| "eval_samples_per_second": 21.582, | |
| "eval_steps_per_second": 1.351, | |
| "eval_wer": 0.9525627044711014, | |
| "step": 2562 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.8517801761627197, | |
| "eval_runtime": 166.9821, | |
| "eval_samples_per_second": 21.913, | |
| "eval_steps_per_second": 1.371, | |
| "eval_wer": 0.9378407851690295, | |
| "step": 2745 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.6844531297683716, | |
| "eval_runtime": 166.3633, | |
| "eval_samples_per_second": 21.994, | |
| "eval_steps_per_second": 1.377, | |
| "eval_wer": 0.9285714285714286, | |
| "step": 2928 | |
| }, | |
| { | |
| "epoch": 16.39, | |
| "learning_rate": 0.00025794943820224716, | |
| "loss": 1.7859, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.641157627105713, | |
| "eval_runtime": 165.2481, | |
| "eval_samples_per_second": 22.142, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.9280261723009815, | |
| "step": 3111 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.5487942695617676, | |
| "eval_runtime": 166.3028, | |
| "eval_samples_per_second": 22.002, | |
| "eval_steps_per_second": 1.377, | |
| "eval_wer": 0.9034896401308615, | |
| "step": 3294 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.4545683860778809, | |
| "eval_runtime": 169.7236, | |
| "eval_samples_per_second": 21.559, | |
| "eval_steps_per_second": 1.349, | |
| "eval_wer": 0.9010359869138496, | |
| "step": 3477 | |
| }, | |
| { | |
| "epoch": 19.13, | |
| "learning_rate": 0.00024952247191011235, | |
| "loss": 1.3898, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.5146596431732178, | |
| "eval_runtime": 170.5824, | |
| "eval_samples_per_second": 21.45, | |
| "eval_steps_per_second": 1.342, | |
| "eval_wer": 0.9201199563794984, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 1.446706771850586, | |
| "eval_runtime": 164.7146, | |
| "eval_samples_per_second": 22.214, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.895856052344602, | |
| "step": 3843 | |
| }, | |
| { | |
| "epoch": 21.86, | |
| "learning_rate": 0.00024111235955056177, | |
| "loss": 1.1291, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 1.474255084991455, | |
| "eval_runtime": 166.7828, | |
| "eval_samples_per_second": 21.939, | |
| "eval_steps_per_second": 1.373, | |
| "eval_wer": 0.9034896401308615, | |
| "step": 4026 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 1.3826948404312134, | |
| "eval_runtime": 165.2382, | |
| "eval_samples_per_second": 22.144, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.876226826608506, | |
| "step": 4209 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 1.3436840772628784, | |
| "eval_runtime": 167.9623, | |
| "eval_samples_per_second": 21.785, | |
| "eval_steps_per_second": 1.363, | |
| "eval_wer": 0.8792257360959651, | |
| "step": 4392 | |
| }, | |
| { | |
| "epoch": 24.59, | |
| "learning_rate": 0.00023268539325842696, | |
| "loss": 0.8993, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 1.2894562482833862, | |
| "eval_runtime": 179.0778, | |
| "eval_samples_per_second": 20.432, | |
| "eval_steps_per_second": 1.279, | |
| "eval_wer": 0.8576881134133042, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 1.2927522659301758, | |
| "eval_runtime": 173.2382, | |
| "eval_samples_per_second": 21.121, | |
| "eval_steps_per_second": 1.322, | |
| "eval_wer": 0.8557797164667393, | |
| "step": 4758 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 1.294653058052063, | |
| "eval_runtime": 166.3679, | |
| "eval_samples_per_second": 21.993, | |
| "eval_steps_per_second": 1.376, | |
| "eval_wer": 0.9163031624863686, | |
| "step": 4941 | |
| }, | |
| { | |
| "epoch": 27.32, | |
| "learning_rate": 0.0002242584269662921, | |
| "loss": 0.6298, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 1.3150520324707031, | |
| "eval_runtime": 164.8819, | |
| "eval_samples_per_second": 22.192, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.873773173391494, | |
| "step": 5124 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 1.2971961498260498, | |
| "eval_runtime": 163.7658, | |
| "eval_samples_per_second": 22.343, | |
| "eval_steps_per_second": 1.398, | |
| "eval_wer": 0.8514176663031625, | |
| "step": 5307 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 1.302983283996582, | |
| "eval_runtime": 162.8739, | |
| "eval_samples_per_second": 22.465, | |
| "eval_steps_per_second": 1.406, | |
| "eval_wer": 0.8432388222464559, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 30.05, | |
| "learning_rate": 0.00021583146067415728, | |
| "loss": 0.4757, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 1.3263603448867798, | |
| "eval_runtime": 163.1422, | |
| "eval_samples_per_second": 22.428, | |
| "eval_steps_per_second": 1.404, | |
| "eval_wer": 0.836423118865867, | |
| "step": 5673 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 1.3130974769592285, | |
| "eval_runtime": 162.7813, | |
| "eval_samples_per_second": 22.478, | |
| "eval_steps_per_second": 1.407, | |
| "eval_wer": 0.8421483097055616, | |
| "step": 5856 | |
| }, | |
| { | |
| "epoch": 32.79, | |
| "learning_rate": 0.00020740449438202247, | |
| "loss": 0.3735, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 1.3457393646240234, | |
| "eval_runtime": 164.771, | |
| "eval_samples_per_second": 22.207, | |
| "eval_steps_per_second": 1.39, | |
| "eval_wer": 0.8587786259541985, | |
| "step": 6039 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 1.3450396060943604, | |
| "eval_runtime": 163.6185, | |
| "eval_samples_per_second": 22.363, | |
| "eval_steps_per_second": 1.4, | |
| "eval_wer": 0.8473282442748091, | |
| "step": 6222 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 1.3451658487319946, | |
| "eval_runtime": 167.7067, | |
| "eval_samples_per_second": 21.818, | |
| "eval_steps_per_second": 1.365, | |
| "eval_wer": 0.9217557251908397, | |
| "step": 6405 | |
| }, | |
| { | |
| "epoch": 35.52, | |
| "learning_rate": 0.0001989775280898876, | |
| "loss": 0.3253, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 1.375409722328186, | |
| "eval_runtime": 164.3009, | |
| "eval_samples_per_second": 22.27, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.8396946564885496, | |
| "step": 6588 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 1.3554260730743408, | |
| "eval_runtime": 163.3464, | |
| "eval_samples_per_second": 22.4, | |
| "eval_steps_per_second": 1.402, | |
| "eval_wer": 0.8353326063249727, | |
| "step": 6771 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 1.353210687637329, | |
| "eval_runtime": 166.4062, | |
| "eval_samples_per_second": 21.988, | |
| "eval_steps_per_second": 1.376, | |
| "eval_wer": 0.8312431842966194, | |
| "step": 6954 | |
| }, | |
| { | |
| "epoch": 38.25, | |
| "learning_rate": 0.0001905505617977528, | |
| "loss": 0.2816, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 1.369396686553955, | |
| "eval_runtime": 165.9264, | |
| "eval_samples_per_second": 22.052, | |
| "eval_steps_per_second": 1.38, | |
| "eval_wer": 0.8345147219193021, | |
| "step": 7137 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 1.395269751548767, | |
| "eval_runtime": 163.891, | |
| "eval_samples_per_second": 22.326, | |
| "eval_steps_per_second": 1.397, | |
| "eval_wer": 0.829607415485278, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 40.98, | |
| "learning_rate": 0.00018212359550561795, | |
| "loss": 0.2397, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 1.385826826095581, | |
| "eval_runtime": 165.4232, | |
| "eval_samples_per_second": 22.119, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.8293347873500545, | |
| "step": 7503 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 1.3958967924118042, | |
| "eval_runtime": 163.1457, | |
| "eval_samples_per_second": 22.428, | |
| "eval_steps_per_second": 1.404, | |
| "eval_wer": 0.8402399127589967, | |
| "step": 7686 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 1.435033917427063, | |
| "eval_runtime": 163.4766, | |
| "eval_samples_per_second": 22.382, | |
| "eval_steps_per_second": 1.401, | |
| "eval_wer": 0.9318429661941112, | |
| "step": 7869 | |
| }, | |
| { | |
| "epoch": 43.72, | |
| "learning_rate": 0.0001737134831460674, | |
| "loss": 0.2084, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 1.4003560543060303, | |
| "eval_runtime": 164.4371, | |
| "eval_samples_per_second": 22.252, | |
| "eval_steps_per_second": 1.393, | |
| "eval_wer": 0.8805888767720829, | |
| "step": 8052 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 1.387134075164795, | |
| "eval_runtime": 164.8129, | |
| "eval_samples_per_second": 22.201, | |
| "eval_steps_per_second": 1.389, | |
| "eval_wer": 0.8255179934569248, | |
| "step": 8235 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 1.4059827327728271, | |
| "eval_runtime": 166.2017, | |
| "eval_samples_per_second": 22.015, | |
| "eval_steps_per_second": 1.378, | |
| "eval_wer": 0.8252453653217012, | |
| "step": 8418 | |
| }, | |
| { | |
| "epoch": 46.45, | |
| "learning_rate": 0.00016528651685393257, | |
| "loss": 0.1853, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 1.3992133140563965, | |
| "eval_runtime": 164.2693, | |
| "eval_samples_per_second": 22.274, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.8500545256270448, | |
| "step": 8601 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 1.4186208248138428, | |
| "eval_runtime": 162.8365, | |
| "eval_samples_per_second": 22.47, | |
| "eval_steps_per_second": 1.406, | |
| "eval_wer": 0.8252453653217012, | |
| "step": 8784 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_loss": 1.4120242595672607, | |
| "eval_runtime": 164.9525, | |
| "eval_samples_per_second": 22.182, | |
| "eval_steps_per_second": 1.388, | |
| "eval_wer": 0.8165212649945475, | |
| "step": 8967 | |
| }, | |
| { | |
| "epoch": 49.18, | |
| "learning_rate": 0.00015685955056179775, | |
| "loss": 0.1671, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 1.4165652990341187, | |
| "eval_runtime": 173.8761, | |
| "eval_samples_per_second": 21.044, | |
| "eval_steps_per_second": 1.317, | |
| "eval_wer": 0.8214285714285714, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_loss": 1.4411484003067017, | |
| "eval_runtime": 165.9975, | |
| "eval_samples_per_second": 22.043, | |
| "eval_steps_per_second": 1.38, | |
| "eval_wer": 0.8500545256270448, | |
| "step": 9333 | |
| }, | |
| { | |
| "epoch": 51.91, | |
| "learning_rate": 0.00014843258426966292, | |
| "loss": 0.1513, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_loss": 1.4692339897155762, | |
| "eval_runtime": 163.251, | |
| "eval_samples_per_second": 22.413, | |
| "eval_steps_per_second": 1.403, | |
| "eval_wer": 0.839422028353326, | |
| "step": 9516 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_loss": 1.4640177488327026, | |
| "eval_runtime": 162.0066, | |
| "eval_samples_per_second": 22.586, | |
| "eval_steps_per_second": 1.414, | |
| "eval_wer": 0.8391494002181025, | |
| "step": 9699 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_loss": 1.450060486793518, | |
| "eval_runtime": 165.9207, | |
| "eval_samples_per_second": 22.053, | |
| "eval_steps_per_second": 1.38, | |
| "eval_wer": 0.8418756815703381, | |
| "step": 9882 | |
| }, | |
| { | |
| "epoch": 54.64, | |
| "learning_rate": 0.00014002247191011234, | |
| "loss": 0.133, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_loss": 1.4133520126342773, | |
| "eval_runtime": 163.1361, | |
| "eval_samples_per_second": 22.429, | |
| "eval_steps_per_second": 1.404, | |
| "eval_wer": 0.8350599781897492, | |
| "step": 10065 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_loss": 1.4592992067337036, | |
| "eval_runtime": 161.8579, | |
| "eval_samples_per_second": 22.606, | |
| "eval_steps_per_second": 1.415, | |
| "eval_wer": 0.8405125408942202, | |
| "step": 10248 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_loss": 1.45597505569458, | |
| "eval_runtime": 161.821, | |
| "eval_samples_per_second": 22.611, | |
| "eval_steps_per_second": 1.415, | |
| "eval_wer": 0.8388767720828789, | |
| "step": 10431 | |
| }, | |
| { | |
| "epoch": 57.38, | |
| "learning_rate": 0.00013159550561797753, | |
| "loss": 0.1198, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_loss": 1.4733554124832153, | |
| "eval_runtime": 162.1949, | |
| "eval_samples_per_second": 22.559, | |
| "eval_steps_per_second": 1.412, | |
| "eval_wer": 0.8334242093784079, | |
| "step": 10614 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_loss": 1.4649208784103394, | |
| "eval_runtime": 162.1709, | |
| "eval_samples_per_second": 22.563, | |
| "eval_steps_per_second": 1.412, | |
| "eval_wer": 0.8317884405670665, | |
| "step": 10797 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_loss": 1.4659123420715332, | |
| "eval_runtime": 163.9506, | |
| "eval_samples_per_second": 22.318, | |
| "eval_steps_per_second": 1.397, | |
| "eval_wer": 0.8099781897491821, | |
| "step": 10980 | |
| }, | |
| { | |
| "epoch": 60.11, | |
| "learning_rate": 0.0001231685393258427, | |
| "loss": 0.1109, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_loss": 1.4783909320831299, | |
| "eval_runtime": 165.1461, | |
| "eval_samples_per_second": 22.156, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.811886586695747, | |
| "step": 11163 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_loss": 1.493830680847168, | |
| "eval_runtime": 164.5944, | |
| "eval_samples_per_second": 22.23, | |
| "eval_steps_per_second": 1.391, | |
| "eval_wer": 0.8148854961832062, | |
| "step": 11346 | |
| }, | |
| { | |
| "epoch": 62.84, | |
| "learning_rate": 0.00011474157303370785, | |
| "loss": 0.1063, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_loss": 1.5050164461135864, | |
| "eval_runtime": 163.3536, | |
| "eval_samples_per_second": 22.399, | |
| "eval_steps_per_second": 1.402, | |
| "eval_wer": 0.8151581243184297, | |
| "step": 11529 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_loss": 1.4773460626602173, | |
| "eval_runtime": 168.4977, | |
| "eval_samples_per_second": 21.715, | |
| "eval_steps_per_second": 1.359, | |
| "eval_wer": 0.8176117775354417, | |
| "step": 11712 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_loss": 1.4835622310638428, | |
| "eval_runtime": 166.8711, | |
| "eval_samples_per_second": 21.927, | |
| "eval_steps_per_second": 1.372, | |
| "eval_wer": 0.8260632497273719, | |
| "step": 11895 | |
| }, | |
| { | |
| "epoch": 65.57, | |
| "learning_rate": 0.00010631460674157301, | |
| "loss": 0.0966, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_loss": 1.4978560209274292, | |
| "eval_runtime": 162.3032, | |
| "eval_samples_per_second": 22.544, | |
| "eval_steps_per_second": 1.411, | |
| "eval_wer": 0.8157033805888768, | |
| "step": 12078 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_loss": 1.4603493213653564, | |
| "eval_runtime": 162.8062, | |
| "eval_samples_per_second": 22.475, | |
| "eval_steps_per_second": 1.407, | |
| "eval_wer": 0.8047982551799345, | |
| "step": 12261 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_loss": 1.4802541732788086, | |
| "eval_runtime": 169.4775, | |
| "eval_samples_per_second": 21.59, | |
| "eval_steps_per_second": 1.351, | |
| "eval_wer": 0.8127044711014176, | |
| "step": 12444 | |
| }, | |
| { | |
| "epoch": 68.31, | |
| "learning_rate": 9.790449438202247e-05, | |
| "loss": 0.0867, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_loss": 1.4973595142364502, | |
| "eval_runtime": 164.1372, | |
| "eval_samples_per_second": 22.292, | |
| "eval_steps_per_second": 1.395, | |
| "eval_wer": 0.8129770992366412, | |
| "step": 12627 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_loss": 1.4721262454986572, | |
| "eval_runtime": 163.536, | |
| "eval_samples_per_second": 22.374, | |
| "eval_steps_per_second": 1.4, | |
| "eval_wer": 0.8077971646673937, | |
| "step": 12810 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_loss": 1.4643745422363281, | |
| "eval_runtime": 166.8819, | |
| "eval_samples_per_second": 21.926, | |
| "eval_steps_per_second": 1.372, | |
| "eval_wer": 0.819247546346783, | |
| "step": 12993 | |
| }, | |
| { | |
| "epoch": 71.04, | |
| "learning_rate": 8.947752808988763e-05, | |
| "loss": 0.0827, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_loss": 1.4834694862365723, | |
| "eval_runtime": 167.6508, | |
| "eval_samples_per_second": 21.825, | |
| "eval_steps_per_second": 1.366, | |
| "eval_wer": 0.8137949836423118, | |
| "step": 13176 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_loss": 1.4933878183364868, | |
| "eval_runtime": 170.3063, | |
| "eval_samples_per_second": 21.485, | |
| "eval_steps_per_second": 1.345, | |
| "eval_wer": 0.8121592148309705, | |
| "step": 13359 | |
| }, | |
| { | |
| "epoch": 73.77, | |
| "learning_rate": 8.10505617977528e-05, | |
| "loss": 0.0734, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_loss": 1.4950696229934692, | |
| "eval_runtime": 175.7645, | |
| "eval_samples_per_second": 20.818, | |
| "eval_steps_per_second": 1.303, | |
| "eval_wer": 0.8061613958560524, | |
| "step": 13542 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_loss": 1.490771770477295, | |
| "eval_runtime": 168.0913, | |
| "eval_samples_per_second": 21.768, | |
| "eval_steps_per_second": 1.362, | |
| "eval_wer": 0.806979280261723, | |
| "step": 13725 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_loss": 1.4876092672348022, | |
| "eval_runtime": 166.128, | |
| "eval_samples_per_second": 22.025, | |
| "eval_steps_per_second": 1.378, | |
| "eval_wer": 0.8124318429661941, | |
| "step": 13908 | |
| }, | |
| { | |
| "epoch": 76.5, | |
| "learning_rate": 7.262359550561797e-05, | |
| "loss": 0.0664, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_loss": 1.493386149406433, | |
| "eval_runtime": 166.8817, | |
| "eval_samples_per_second": 21.926, | |
| "eval_steps_per_second": 1.372, | |
| "eval_wer": 0.8053435114503816, | |
| "step": 14091 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_loss": 1.4603490829467773, | |
| "eval_runtime": 169.3203, | |
| "eval_samples_per_second": 21.61, | |
| "eval_steps_per_second": 1.352, | |
| "eval_wer": 0.8047982551799345, | |
| "step": 14274 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_loss": 1.4732308387756348, | |
| "eval_runtime": 165.2553, | |
| "eval_samples_per_second": 22.142, | |
| "eval_steps_per_second": 1.386, | |
| "eval_wer": 0.8072519083969466, | |
| "step": 14457 | |
| }, | |
| { | |
| "epoch": 79.23, | |
| "learning_rate": 6.42134831460674e-05, | |
| "loss": 0.0602, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_loss": 1.4924767017364502, | |
| "eval_runtime": 166.2646, | |
| "eval_samples_per_second": 22.007, | |
| "eval_steps_per_second": 1.377, | |
| "eval_wer": 0.8077971646673937, | |
| "step": 14640 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_loss": 1.4812291860580444, | |
| "eval_runtime": 166.8878, | |
| "eval_samples_per_second": 21.925, | |
| "eval_steps_per_second": 1.372, | |
| "eval_wer": 0.806434023991276, | |
| "step": 14823 | |
| }, | |
| { | |
| "epoch": 81.97, | |
| "learning_rate": 5.578651685393258e-05, | |
| "loss": 0.057, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_loss": 1.4949839115142822, | |
| "eval_runtime": 166.616, | |
| "eval_samples_per_second": 21.961, | |
| "eval_steps_per_second": 1.374, | |
| "eval_wer": 0.8012540894220284, | |
| "step": 15006 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_loss": 1.4784878492355347, | |
| "eval_runtime": 172.4918, | |
| "eval_samples_per_second": 21.213, | |
| "eval_steps_per_second": 1.328, | |
| "eval_wer": 0.8056161395856052, | |
| "step": 15189 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_loss": 1.485625982284546, | |
| "eval_runtime": 165.5579, | |
| "eval_samples_per_second": 22.101, | |
| "eval_steps_per_second": 1.383, | |
| "eval_wer": 0.7993456924754635, | |
| "step": 15372 | |
| }, | |
| { | |
| "epoch": 84.7, | |
| "learning_rate": 4.735955056179775e-05, | |
| "loss": 0.0517, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_loss": 1.4754849672317505, | |
| "eval_runtime": 168.7909, | |
| "eval_samples_per_second": 21.678, | |
| "eval_steps_per_second": 1.357, | |
| "eval_wer": 0.8034351145038168, | |
| "step": 15555 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_loss": 1.4813350439071655, | |
| "eval_runtime": 168.272, | |
| "eval_samples_per_second": 21.745, | |
| "eval_steps_per_second": 1.361, | |
| "eval_wer": 0.8034351145038168, | |
| "step": 15738 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_loss": 1.4965763092041016, | |
| "eval_runtime": 166.9884, | |
| "eval_samples_per_second": 21.912, | |
| "eval_steps_per_second": 1.371, | |
| "eval_wer": 0.8047982551799345, | |
| "step": 15921 | |
| }, | |
| { | |
| "epoch": 87.43, | |
| "learning_rate": 3.893258426966292e-05, | |
| "loss": 0.0468, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_loss": 1.4883418083190918, | |
| "eval_runtime": 166.1387, | |
| "eval_samples_per_second": 22.024, | |
| "eval_steps_per_second": 1.378, | |
| "eval_wer": 0.8001635768811342, | |
| "step": 16104 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_loss": 1.4746148586273193, | |
| "eval_runtime": 165.9654, | |
| "eval_samples_per_second": 22.047, | |
| "eval_steps_per_second": 1.38, | |
| "eval_wer": 0.8023446019629226, | |
| "step": 16287 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_loss": 1.4697260856628418, | |
| "eval_runtime": 166.9567, | |
| "eval_samples_per_second": 21.916, | |
| "eval_steps_per_second": 1.372, | |
| "eval_wer": 0.7974372955288986, | |
| "step": 16470 | |
| }, | |
| { | |
| "epoch": 90.16, | |
| "learning_rate": 3.0505617977528088e-05, | |
| "loss": 0.0426, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_loss": 1.4775140285491943, | |
| "eval_runtime": 165.779, | |
| "eval_samples_per_second": 22.072, | |
| "eval_steps_per_second": 1.381, | |
| "eval_wer": 0.8004362050163577, | |
| "step": 16653 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_loss": 1.4852207899093628, | |
| "eval_runtime": 173.415, | |
| "eval_samples_per_second": 21.1, | |
| "eval_steps_per_second": 1.321, | |
| "eval_wer": 0.8023446019629226, | |
| "step": 16836 | |
| }, | |
| { | |
| "epoch": 92.9, | |
| "learning_rate": 2.2078651685393255e-05, | |
| "loss": 0.0387, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_loss": 1.4868098497390747, | |
| "eval_runtime": 166.0768, | |
| "eval_samples_per_second": 22.032, | |
| "eval_steps_per_second": 1.379, | |
| "eval_wer": 0.8004362050163577, | |
| "step": 17019 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_loss": 1.47845458984375, | |
| "eval_runtime": 171.2193, | |
| "eval_samples_per_second": 21.37, | |
| "eval_steps_per_second": 1.337, | |
| "eval_wer": 0.802071973827699, | |
| "step": 17202 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_loss": 1.4892385005950928, | |
| "eval_runtime": 165.5064, | |
| "eval_samples_per_second": 22.108, | |
| "eval_steps_per_second": 1.384, | |
| "eval_wer": 0.8015267175572519, | |
| "step": 17385 | |
| }, | |
| { | |
| "epoch": 95.63, | |
| "learning_rate": 1.3668539325842695e-05, | |
| "loss": 0.0359, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_loss": 1.486182451248169, | |
| "eval_runtime": 174.5056, | |
| "eval_samples_per_second": 20.968, | |
| "eval_steps_per_second": 1.312, | |
| "eval_wer": 0.8017993456924755, | |
| "step": 17568 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_loss": 1.4851171970367432, | |
| "eval_runtime": 165.0543, | |
| "eval_samples_per_second": 22.168, | |
| "eval_steps_per_second": 1.387, | |
| "eval_wer": 0.8007088331515813, | |
| "step": 17751 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_loss": 1.48457932472229, | |
| "eval_runtime": 169.1905, | |
| "eval_samples_per_second": 21.627, | |
| "eval_steps_per_second": 1.354, | |
| "eval_wer": 0.7998909487459106, | |
| "step": 17934 | |
| }, | |
| { | |
| "epoch": 98.36, | |
| "learning_rate": 5.241573033707864e-06, | |
| "loss": 0.0347, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_loss": 1.4852174520492554, | |
| "eval_runtime": 168.792, | |
| "eval_samples_per_second": 21.678, | |
| "eval_steps_per_second": 1.357, | |
| "eval_wer": 0.7993456924754635, | |
| "step": 18117 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_loss": 1.484755277633667, | |
| "eval_runtime": 179.7891, | |
| "eval_samples_per_second": 20.352, | |
| "eval_steps_per_second": 1.274, | |
| "eval_wer": 0.8004362050163577, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 18300, | |
| "total_flos": 1.3576650149787481e+20, | |
| "train_loss": 0.34965579027686616, | |
| "train_runtime": 66008.5183, | |
| "train_samples_per_second": 17.704, | |
| "train_steps_per_second": 0.277 | |
| } | |
| ], | |
| "max_steps": 18300, | |
| "num_train_epochs": 100, | |
| "total_flos": 1.3576650149787481e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |