| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 112.12090680100755, | |
| "global_step": 22200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0003, | |
| "loss": 6.4459, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 3.1488852500915527, | |
| "eval_runtime": 134.1012, | |
| "eval_samples_per_second": 4.892, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.00029898648648648646, | |
| "loss": 3.0913, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 3.1127500534057617, | |
| "eval_runtime": 138.7081, | |
| "eval_samples_per_second": 4.729, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 0.00029797297297297294, | |
| "loss": 3.0716, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "eval_loss": 3.0870425701141357, | |
| "eval_runtime": 138.315, | |
| "eval_samples_per_second": 4.743, | |
| "eval_wer": 1.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 0.0002969594594594594, | |
| "loss": 3.0298, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "eval_loss": 3.0003437995910645, | |
| "eval_runtime": 134.8731, | |
| "eval_samples_per_second": 4.864, | |
| "eval_wer": 1.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.0002959459459459459, | |
| "loss": 1.728, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_loss": 0.805480420589447, | |
| "eval_runtime": 135.0581, | |
| "eval_samples_per_second": 4.857, | |
| "eval_wer": 0.8985599322321051, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "learning_rate": 0.0002949324324324324, | |
| "loss": 0.6228, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "eval_loss": 0.6153338551521301, | |
| "eval_runtime": 138.3824, | |
| "eval_samples_per_second": 4.74, | |
| "eval_wer": 0.8263447691656078, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 0.0002939189189189189, | |
| "loss": 0.4109, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "eval_loss": 0.5761246085166931, | |
| "eval_runtime": 136.2401, | |
| "eval_samples_per_second": 4.815, | |
| "eval_wer": 0.8009318085556968, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 0.00029290540540540536, | |
| "loss": 0.3384, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "eval_loss": 0.6021555662155151, | |
| "eval_runtime": 135.414, | |
| "eval_samples_per_second": 4.844, | |
| "eval_wer": 0.7981787378229563, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 0.0002918918918918919, | |
| "loss": 0.2676, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "eval_loss": 0.556929349899292, | |
| "eval_runtime": 136.0159, | |
| "eval_samples_per_second": 4.823, | |
| "eval_wer": 0.7505294366793731, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "learning_rate": 0.0002908783783783784, | |
| "loss": 0.2321, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "eval_loss": 0.6468214392662048, | |
| "eval_runtime": 135.5988, | |
| "eval_samples_per_second": 4.838, | |
| "eval_wer": 0.7736128759000424, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 0.00028986486486486487, | |
| "loss": 0.2031, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "eval_loss": 0.6612684726715088, | |
| "eval_runtime": 135.8609, | |
| "eval_samples_per_second": 4.828, | |
| "eval_wer": 0.7884371029224905, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "learning_rate": 0.00028885135135135135, | |
| "loss": 0.1853, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "eval_loss": 0.6352970600128174, | |
| "eval_runtime": 135.9654, | |
| "eval_samples_per_second": 4.825, | |
| "eval_wer": 0.736552308343922, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 13.13, | |
| "learning_rate": 0.0002878378378378378, | |
| "loss": 0.1826, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 13.13, | |
| "eval_loss": 0.6177716851234436, | |
| "eval_runtime": 136.1311, | |
| "eval_samples_per_second": 4.819, | |
| "eval_wer": 0.7238458280389666, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 0.00028682432432432426, | |
| "loss": 0.1627, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "eval_loss": 0.6629394888877869, | |
| "eval_runtime": 135.7236, | |
| "eval_samples_per_second": 4.833, | |
| "eval_wer": 0.734011012282931, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 15.15, | |
| "learning_rate": 0.0002858108108108108, | |
| "loss": 0.1506, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 15.15, | |
| "eval_loss": 0.6606569886207581, | |
| "eval_runtime": 137.5748, | |
| "eval_samples_per_second": 4.768, | |
| "eval_wer": 0.7272342227869547, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 0.0002847972972972973, | |
| "loss": 0.1432, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "eval_loss": 0.6748045086860657, | |
| "eval_runtime": 135.8657, | |
| "eval_samples_per_second": 4.828, | |
| "eval_wer": 0.7335874629394324, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 17.17, | |
| "learning_rate": 0.00028378378378378377, | |
| "loss": 0.1396, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 17.17, | |
| "eval_loss": 0.6931908130645752, | |
| "eval_runtime": 136.0012, | |
| "eval_samples_per_second": 4.823, | |
| "eval_wer": 0.7236340533672173, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "learning_rate": 0.00028277027027027025, | |
| "loss": 0.1397, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "eval_loss": 0.6838018894195557, | |
| "eval_runtime": 135.7614, | |
| "eval_samples_per_second": 4.832, | |
| "eval_wer": 0.7316814908936892, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 19.19, | |
| "learning_rate": 0.00028175675675675674, | |
| "loss": 0.1317, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 19.19, | |
| "eval_loss": 0.689399242401123, | |
| "eval_runtime": 136.2101, | |
| "eval_samples_per_second": 4.816, | |
| "eval_wer": 0.7242693773824651, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 20.2, | |
| "learning_rate": 0.0002807432432432432, | |
| "loss": 0.1225, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 20.2, | |
| "eval_loss": 0.7114871144294739, | |
| "eval_runtime": 135.7901, | |
| "eval_samples_per_second": 4.831, | |
| "eval_wer": 0.745446844557391, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 21.21, | |
| "learning_rate": 0.0002797297297297297, | |
| "loss": 0.121, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 21.21, | |
| "eval_loss": 0.7714667916297913, | |
| "eval_runtime": 144.4676, | |
| "eval_samples_per_second": 4.541, | |
| "eval_wer": 0.7439644218551461, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 0.0002787162162162162, | |
| "loss": 0.1214, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "eval_loss": 0.6892368197441101, | |
| "eval_runtime": 141.5565, | |
| "eval_samples_per_second": 4.634, | |
| "eval_wer": 0.7246929267259635, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 23.23, | |
| "learning_rate": 0.00027770270270270267, | |
| "loss": 0.1201, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 23.23, | |
| "eval_loss": 0.7176805734634399, | |
| "eval_runtime": 136.4081, | |
| "eval_samples_per_second": 4.809, | |
| "eval_wer": 0.7329521389241846, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 24.24, | |
| "learning_rate": 0.00027668918918918916, | |
| "loss": 0.1144, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 24.24, | |
| "eval_loss": 0.7144946455955505, | |
| "eval_runtime": 135.6564, | |
| "eval_samples_per_second": 4.836, | |
| "eval_wer": 0.7143159678102499, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 25.25, | |
| "learning_rate": 0.00027567567567567564, | |
| "loss": 0.1087, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 25.25, | |
| "eval_loss": 0.6824408769607544, | |
| "eval_runtime": 146.0202, | |
| "eval_samples_per_second": 4.493, | |
| "eval_wer": 0.7551884794578568, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 26.26, | |
| "learning_rate": 0.0002746621621621621, | |
| "loss": 0.1088, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 26.26, | |
| "eval_loss": 0.7299026846885681, | |
| "eval_runtime": 136.6707, | |
| "eval_samples_per_second": 4.8, | |
| "eval_wer": 0.7293519695044473, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 27.27, | |
| "learning_rate": 0.0002736486486486486, | |
| "loss": 0.1033, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 27.27, | |
| "eval_loss": 0.7187995910644531, | |
| "eval_runtime": 135.6478, | |
| "eval_samples_per_second": 4.836, | |
| "eval_wer": 0.7187632359169843, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 28.28, | |
| "learning_rate": 0.0002726351351351351, | |
| "loss": 0.1035, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 28.28, | |
| "eval_loss": 0.7574965953826904, | |
| "eval_runtime": 135.5201, | |
| "eval_samples_per_second": 4.841, | |
| "eval_wer": 0.743117323168149, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 29.29, | |
| "learning_rate": 0.0002716216216216216, | |
| "loss": 0.1052, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 29.29, | |
| "eval_loss": 0.7272396683692932, | |
| "eval_runtime": 135.608, | |
| "eval_samples_per_second": 4.837, | |
| "eval_wer": 0.7181279119017365, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 30.3, | |
| "learning_rate": 0.00027060810810810806, | |
| "loss": 0.1074, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 30.3, | |
| "eval_loss": 0.7088936567306519, | |
| "eval_runtime": 135.3489, | |
| "eval_samples_per_second": 4.847, | |
| "eval_wer": 0.7011859381617959, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 31.31, | |
| "learning_rate": 0.0002695945945945946, | |
| "loss": 0.105, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 31.31, | |
| "eval_loss": 0.7318005561828613, | |
| "eval_runtime": 136.2308, | |
| "eval_samples_per_second": 4.815, | |
| "eval_wer": 0.7157983905124947, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 32.32, | |
| "learning_rate": 0.0002685810810810811, | |
| "loss": 0.0937, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 32.32, | |
| "eval_loss": 0.743655264377594, | |
| "eval_runtime": 135.8626, | |
| "eval_samples_per_second": 4.828, | |
| "eval_wer": 0.7115628970775095, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 0.00026756756756756756, | |
| "loss": 0.0976, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "eval_loss": 0.7406659126281738, | |
| "eval_runtime": 136.2332, | |
| "eval_samples_per_second": 4.815, | |
| "eval_wer": 0.7257518000847099, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 34.34, | |
| "learning_rate": 0.00026655405405405405, | |
| "loss": 0.0961, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 34.34, | |
| "eval_loss": 0.7474074959754944, | |
| "eval_runtime": 136.361, | |
| "eval_samples_per_second": 4.811, | |
| "eval_wer": 0.729987293519695, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 35.35, | |
| "learning_rate": 0.0002655405405405405, | |
| "loss": 0.0922, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 35.35, | |
| "eval_loss": 0.7413117289543152, | |
| "eval_runtime": 137.8262, | |
| "eval_samples_per_second": 4.76, | |
| "eval_wer": 0.7399407030919102, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 36.36, | |
| "learning_rate": 0.000264527027027027, | |
| "loss": 0.0897, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 36.36, | |
| "eval_loss": 0.7571277618408203, | |
| "eval_runtime": 135.8962, | |
| "eval_samples_per_second": 4.827, | |
| "eval_wer": 0.7467174925878864, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 37.37, | |
| "learning_rate": 0.0002635135135135135, | |
| "loss": 0.0936, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 37.37, | |
| "eval_loss": 0.7212100028991699, | |
| "eval_runtime": 136.3693, | |
| "eval_samples_per_second": 4.81, | |
| "eval_wer": 0.7162219398559933, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 38.38, | |
| "learning_rate": 0.0002625, | |
| "loss": 0.0898, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 38.38, | |
| "eval_loss": 0.751598060131073, | |
| "eval_runtime": 138.668, | |
| "eval_samples_per_second": 4.731, | |
| "eval_wer": 0.7210927573062261, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 39.39, | |
| "learning_rate": 0.00026148648648648647, | |
| "loss": 0.0902, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 39.39, | |
| "eval_loss": 0.7493733167648315, | |
| "eval_runtime": 136.1591, | |
| "eval_samples_per_second": 4.818, | |
| "eval_wer": 0.7477763659466328, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 40.4, | |
| "learning_rate": 0.00026047297297297295, | |
| "loss": 0.0847, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 40.4, | |
| "eval_loss": 0.6728424429893494, | |
| "eval_runtime": 140.5502, | |
| "eval_samples_per_second": 4.667, | |
| "eval_wer": 0.7306226175349428, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 41.41, | |
| "learning_rate": 0.00025945945945945944, | |
| "loss": 0.0866, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 41.41, | |
| "eval_loss": 0.749858558177948, | |
| "eval_runtime": 146.7628, | |
| "eval_samples_per_second": 4.47, | |
| "eval_wer": 0.7151630664972469, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 42.42, | |
| "learning_rate": 0.0002584459459459459, | |
| "loss": 0.0809, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 42.42, | |
| "eval_loss": 0.7739278078079224, | |
| "eval_runtime": 136.5403, | |
| "eval_samples_per_second": 4.804, | |
| "eval_wer": 0.7429055484963998, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 43.43, | |
| "learning_rate": 0.0002574324324324324, | |
| "loss": 0.0847, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 43.43, | |
| "eval_loss": 0.7759637236595154, | |
| "eval_runtime": 136.7555, | |
| "eval_samples_per_second": 4.797, | |
| "eval_wer": 0.7244811520542143, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "learning_rate": 0.0002564189189189189, | |
| "loss": 0.0852, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "eval_loss": 0.7829259634017944, | |
| "eval_runtime": 139.6603, | |
| "eval_samples_per_second": 4.697, | |
| "eval_wer": 0.7227869546802203, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 45.45, | |
| "learning_rate": 0.00025540540540540537, | |
| "loss": 0.0802, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 45.45, | |
| "eval_loss": 0.7056646347045898, | |
| "eval_runtime": 135.8647, | |
| "eval_samples_per_second": 4.828, | |
| "eval_wer": 0.7100804743752647, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 46.46, | |
| "learning_rate": 0.0002543918918918919, | |
| "loss": 0.0794, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 46.46, | |
| "eval_loss": 0.7538515329360962, | |
| "eval_runtime": 140.8763, | |
| "eval_samples_per_second": 4.657, | |
| "eval_wer": 0.7098686997035154, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 47.47, | |
| "learning_rate": 0.0002533783783783784, | |
| "loss": 0.0827, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 47.47, | |
| "eval_loss": 0.7439035773277283, | |
| "eval_runtime": 143.0424, | |
| "eval_samples_per_second": 4.586, | |
| "eval_wer": 0.7151630664972469, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 48.48, | |
| "learning_rate": 0.0002523648648648648, | |
| "loss": 0.0803, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 48.48, | |
| "eval_loss": 0.7053723335266113, | |
| "eval_runtime": 143.445, | |
| "eval_samples_per_second": 4.573, | |
| "eval_wer": 0.7075391783142736, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 49.49, | |
| "learning_rate": 0.0002513513513513513, | |
| "loss": 0.0781, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 49.49, | |
| "eval_loss": 0.8703842163085938, | |
| "eval_runtime": 143.62, | |
| "eval_samples_per_second": 4.568, | |
| "eval_wer": 0.7630241423125794, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 50.5, | |
| "learning_rate": 0.0002503378378378378, | |
| "loss": 0.0766, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 50.5, | |
| "eval_loss": 0.7902593612670898, | |
| "eval_runtime": 139.0704, | |
| "eval_samples_per_second": 4.717, | |
| "eval_wer": 0.7130453197797544, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 51.51, | |
| "learning_rate": 0.0002493243243243243, | |
| "loss": 0.0771, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 51.51, | |
| "eval_loss": 0.7181321978569031, | |
| "eval_runtime": 138.4984, | |
| "eval_samples_per_second": 4.737, | |
| "eval_wer": 0.7149512918254977, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 52.52, | |
| "learning_rate": 0.0002483108108108108, | |
| "loss": 0.0713, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 52.52, | |
| "eval_loss": 0.7941905856132507, | |
| "eval_runtime": 137.9511, | |
| "eval_samples_per_second": 4.755, | |
| "eval_wer": 0.7164337145277425, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 53.53, | |
| "learning_rate": 0.0002472972972972973, | |
| "loss": 0.0761, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 53.53, | |
| "eval_loss": 0.8347806334495544, | |
| "eval_runtime": 137.6637, | |
| "eval_samples_per_second": 4.765, | |
| "eval_wer": 0.7100804743752647, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 54.54, | |
| "learning_rate": 0.0002462837837837838, | |
| "loss": 0.0721, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 54.54, | |
| "eval_loss": 0.7271831035614014, | |
| "eval_runtime": 137.7418, | |
| "eval_samples_per_second": 4.763, | |
| "eval_wer": 0.7024565861922915, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 55.55, | |
| "learning_rate": 0.00024527027027027026, | |
| "loss": 0.0684, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 55.55, | |
| "eval_loss": 0.7921620011329651, | |
| "eval_runtime": 137.9904, | |
| "eval_samples_per_second": 4.754, | |
| "eval_wer": 0.6977975434138077, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 56.56, | |
| "learning_rate": 0.00024425675675675675, | |
| "loss": 0.0733, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 56.56, | |
| "eval_loss": 0.782407820224762, | |
| "eval_runtime": 138.0874, | |
| "eval_samples_per_second": 4.751, | |
| "eval_wer": 0.7052096569250318, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 57.57, | |
| "learning_rate": 0.00024324324324324323, | |
| "loss": 0.0723, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 57.57, | |
| "eval_loss": 0.7807161211967468, | |
| "eval_runtime": 137.5671, | |
| "eval_samples_per_second": 4.769, | |
| "eval_wer": 0.6994917407878017, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 58.58, | |
| "learning_rate": 0.00024222972972972971, | |
| "loss": 0.0701, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 58.58, | |
| "eval_loss": 0.7515387535095215, | |
| "eval_runtime": 138.0585, | |
| "eval_samples_per_second": 4.752, | |
| "eval_wer": 0.7085980516730199, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 59.59, | |
| "learning_rate": 0.0002412162162162162, | |
| "loss": 0.0687, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 59.59, | |
| "eval_loss": 0.7535402774810791, | |
| "eval_runtime": 137.596, | |
| "eval_samples_per_second": 4.768, | |
| "eval_wer": 0.688267683185091, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 60.6, | |
| "learning_rate": 0.00024020270270270268, | |
| "loss": 0.0676, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 60.6, | |
| "eval_loss": 0.7971649169921875, | |
| "eval_runtime": 138.6186, | |
| "eval_samples_per_second": 4.732, | |
| "eval_wer": 0.7132570944515036, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 61.61, | |
| "learning_rate": 0.00023918918918918917, | |
| "loss": 0.0733, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 61.61, | |
| "eval_loss": 0.7672501802444458, | |
| "eval_runtime": 138.3057, | |
| "eval_samples_per_second": 4.743, | |
| "eval_wer": 0.711139347734011, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 62.62, | |
| "learning_rate": 0.00023817567567567568, | |
| "loss": 0.0661, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 62.62, | |
| "eval_loss": 0.7474766373634338, | |
| "eval_runtime": 138.3209, | |
| "eval_samples_per_second": 4.743, | |
| "eval_wer": 0.6975857687420585, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 63.63, | |
| "learning_rate": 0.00023716216216216216, | |
| "loss": 0.0666, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 63.63, | |
| "eval_loss": 0.7444884181022644, | |
| "eval_runtime": 137.4553, | |
| "eval_samples_per_second": 4.772, | |
| "eval_wer": 0.7083862770012707, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 64.64, | |
| "learning_rate": 0.00023614864864864862, | |
| "loss": 0.0712, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 64.64, | |
| "eval_loss": 0.7816994190216064, | |
| "eval_runtime": 138.1127, | |
| "eval_samples_per_second": 4.75, | |
| "eval_wer": 0.7210927573062261, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 65.65, | |
| "learning_rate": 0.0002351351351351351, | |
| "loss": 0.063, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 65.65, | |
| "eval_loss": 0.8192810416221619, | |
| "eval_runtime": 137.4083, | |
| "eval_samples_per_second": 4.774, | |
| "eval_wer": 0.7092333756882677, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 66.66, | |
| "learning_rate": 0.00023412162162162159, | |
| "loss": 0.0681, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 66.66, | |
| "eval_loss": 0.7333322763442993, | |
| "eval_runtime": 137.9838, | |
| "eval_samples_per_second": 4.754, | |
| "eval_wer": 0.698009318085557, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 67.68, | |
| "learning_rate": 0.00023310810810810807, | |
| "loss": 0.0642, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 67.68, | |
| "eval_loss": 0.7417888045310974, | |
| "eval_runtime": 137.6106, | |
| "eval_samples_per_second": 4.767, | |
| "eval_wer": 0.7083862770012707, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 68.69, | |
| "learning_rate": 0.00023209459459459458, | |
| "loss": 0.0622, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 68.69, | |
| "eval_loss": 0.7969706654548645, | |
| "eval_runtime": 137.6918, | |
| "eval_samples_per_second": 4.764, | |
| "eval_wer": 0.7329521389241846, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 69.7, | |
| "learning_rate": 0.00023108108108108106, | |
| "loss": 0.0639, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 69.7, | |
| "eval_loss": 0.8013876080513, | |
| "eval_runtime": 137.5846, | |
| "eval_samples_per_second": 4.768, | |
| "eval_wer": 0.6988564167725541, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 70.71, | |
| "learning_rate": 0.00023006756756756755, | |
| "loss": 0.065, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 70.71, | |
| "eval_loss": 0.7792071104049683, | |
| "eval_runtime": 137.6266, | |
| "eval_samples_per_second": 4.767, | |
| "eval_wer": 0.7043625582380347, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 71.72, | |
| "learning_rate": 0.00022905405405405403, | |
| "loss": 0.0608, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 71.72, | |
| "eval_loss": 0.7951736450195312, | |
| "eval_runtime": 138.4177, | |
| "eval_samples_per_second": 4.739, | |
| "eval_wer": 0.6944091486658196, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 72.73, | |
| "learning_rate": 0.00022804054054054052, | |
| "loss": 0.0557, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 72.73, | |
| "eval_loss": 0.8266920447349548, | |
| "eval_runtime": 138.5687, | |
| "eval_samples_per_second": 4.734, | |
| "eval_wer": 0.6977975434138077, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 73.74, | |
| "learning_rate": 0.00022702702702702703, | |
| "loss": 0.0592, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 73.74, | |
| "eval_loss": 0.8056704998016357, | |
| "eval_runtime": 137.1892, | |
| "eval_samples_per_second": 4.782, | |
| "eval_wer": 0.7075391783142736, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 74.75, | |
| "learning_rate": 0.0002260135135135135, | |
| "loss": 0.064, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 74.75, | |
| "eval_loss": 0.815148115158081, | |
| "eval_runtime": 137.9946, | |
| "eval_samples_per_second": 4.754, | |
| "eval_wer": 0.7009741634900466, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 75.76, | |
| "learning_rate": 0.000225, | |
| "loss": 0.0603, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 75.76, | |
| "eval_loss": 0.7697699069976807, | |
| "eval_runtime": 138.1754, | |
| "eval_samples_per_second": 4.748, | |
| "eval_wer": 0.7124099957645066, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 76.77, | |
| "learning_rate": 0.00022398648648648645, | |
| "loss": 0.0613, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 76.77, | |
| "eval_loss": 0.7657320499420166, | |
| "eval_runtime": 137.8551, | |
| "eval_samples_per_second": 4.759, | |
| "eval_wer": 0.7170690385429903, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 77.78, | |
| "learning_rate": 0.00022297297297297293, | |
| "loss": 0.0602, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 77.78, | |
| "eval_loss": 0.7715324759483337, | |
| "eval_runtime": 137.9821, | |
| "eval_samples_per_second": 4.754, | |
| "eval_wer": 0.716857263871241, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 78.79, | |
| "learning_rate": 0.00022195945945945945, | |
| "loss": 0.0597, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 78.79, | |
| "eval_loss": 0.7833596467971802, | |
| "eval_runtime": 137.7858, | |
| "eval_samples_per_second": 4.761, | |
| "eval_wer": 0.7132570944515036, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 79.8, | |
| "learning_rate": 0.00022094594594594593, | |
| "loss": 0.0585, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 79.8, | |
| "eval_loss": 0.8398387432098389, | |
| "eval_runtime": 137.7412, | |
| "eval_samples_per_second": 4.763, | |
| "eval_wer": 0.7088098263447692, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 80.81, | |
| "learning_rate": 0.0002199324324324324, | |
| "loss": 0.056, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 80.81, | |
| "eval_loss": 0.8182487487792969, | |
| "eval_runtime": 137.8628, | |
| "eval_samples_per_second": 4.758, | |
| "eval_wer": 0.7128335451080051, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 81.82, | |
| "learning_rate": 0.0002189189189189189, | |
| "loss": 0.06, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 81.82, | |
| "eval_loss": 0.8023802638053894, | |
| "eval_runtime": 137.792, | |
| "eval_samples_per_second": 4.761, | |
| "eval_wer": 0.6918678526048284, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 82.83, | |
| "learning_rate": 0.00021790540540540538, | |
| "loss": 0.0542, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 82.83, | |
| "eval_loss": 0.7613797187805176, | |
| "eval_runtime": 138.0605, | |
| "eval_samples_per_second": 4.752, | |
| "eval_wer": 0.6916560779330791, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 83.84, | |
| "learning_rate": 0.0002168918918918919, | |
| "loss": 0.0565, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 83.84, | |
| "eval_loss": 0.7780935764312744, | |
| "eval_runtime": 138.2761, | |
| "eval_samples_per_second": 4.744, | |
| "eval_wer": 0.7153748411689962, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 84.85, | |
| "learning_rate": 0.00021587837837837838, | |
| "loss": 0.0518, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 84.85, | |
| "eval_loss": 0.8466140031814575, | |
| "eval_runtime": 138.8619, | |
| "eval_samples_per_second": 4.724, | |
| "eval_wer": 0.7475645912748835, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 85.86, | |
| "learning_rate": 0.00021486486486486486, | |
| "loss": 0.0566, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 85.86, | |
| "eval_loss": 0.8004465699195862, | |
| "eval_runtime": 137.4262, | |
| "eval_samples_per_second": 4.773, | |
| "eval_wer": 0.7064803049555273, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 86.87, | |
| "learning_rate": 0.00021385135135135134, | |
| "loss": 0.0535, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 86.87, | |
| "eval_loss": 0.8326082825660706, | |
| "eval_runtime": 137.6615, | |
| "eval_samples_per_second": 4.765, | |
| "eval_wer": 0.7043625582380347, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 87.88, | |
| "learning_rate": 0.0002128378378378378, | |
| "loss": 0.0483, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 87.88, | |
| "eval_loss": 0.7926554083824158, | |
| "eval_runtime": 138.0063, | |
| "eval_samples_per_second": 4.753, | |
| "eval_wer": 0.7251164760694621, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 88.89, | |
| "learning_rate": 0.00021182432432432428, | |
| "loss": 0.0486, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 88.89, | |
| "eval_loss": 0.7882806062698364, | |
| "eval_runtime": 138.7006, | |
| "eval_samples_per_second": 4.73, | |
| "eval_wer": 0.6899618805590851, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 89.9, | |
| "learning_rate": 0.0002108108108108108, | |
| "loss": 0.0504, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 89.9, | |
| "eval_loss": 0.7685484290122986, | |
| "eval_runtime": 138.3804, | |
| "eval_samples_per_second": 4.741, | |
| "eval_wer": 0.6939855993223211, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 90.91, | |
| "learning_rate": 0.00020979729729729728, | |
| "loss": 0.056, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 90.91, | |
| "eval_loss": 0.848064124584198, | |
| "eval_runtime": 137.1191, | |
| "eval_samples_per_second": 4.784, | |
| "eval_wer": 0.7007623888182973, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 91.92, | |
| "learning_rate": 0.00020878378378378376, | |
| "loss": 0.049, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 91.92, | |
| "eval_loss": 0.845516562461853, | |
| "eval_runtime": 137.1172, | |
| "eval_samples_per_second": 4.784, | |
| "eval_wer": 0.7119864464210081, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 92.93, | |
| "learning_rate": 0.00020777027027027025, | |
| "loss": 0.0536, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 92.93, | |
| "eval_loss": 0.7710561752319336, | |
| "eval_runtime": 138.0433, | |
| "eval_samples_per_second": 4.752, | |
| "eval_wer": 0.6925031766200762, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 93.94, | |
| "learning_rate": 0.00020675675675675673, | |
| "loss": 0.0503, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 93.94, | |
| "eval_loss": 0.8255069851875305, | |
| "eval_runtime": 137.6117, | |
| "eval_samples_per_second": 4.767, | |
| "eval_wer": 0.7174925878864887, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 94.95, | |
| "learning_rate": 0.00020574324324324324, | |
| "loss": 0.0488, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 94.95, | |
| "eval_loss": 0.8600437641143799, | |
| "eval_runtime": 137.4326, | |
| "eval_samples_per_second": 4.773, | |
| "eval_wer": 0.7246929267259635, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 95.96, | |
| "learning_rate": 0.00020472972972972972, | |
| "loss": 0.0468, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 95.96, | |
| "eval_loss": 0.7781614661216736, | |
| "eval_runtime": 137.8454, | |
| "eval_samples_per_second": 4.759, | |
| "eval_wer": 0.7001270648030495, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 96.97, | |
| "learning_rate": 0.0002037162162162162, | |
| "loss": 0.0486, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 96.97, | |
| "eval_loss": 0.7687584161758423, | |
| "eval_runtime": 137.2673, | |
| "eval_samples_per_second": 4.779, | |
| "eval_wer": 0.7054214315967811, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 97.98, | |
| "learning_rate": 0.0002027027027027027, | |
| "loss": 0.0523, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 97.98, | |
| "eval_loss": 0.8229833245277405, | |
| "eval_runtime": 137.1013, | |
| "eval_samples_per_second": 4.785, | |
| "eval_wer": 0.7066920796272765, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 98.99, | |
| "learning_rate": 0.00020168918918918915, | |
| "loss": 0.0507, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 98.99, | |
| "eval_loss": 0.761595606803894, | |
| "eval_runtime": 137.3405, | |
| "eval_samples_per_second": 4.776, | |
| "eval_wer": 0.6910207539178315, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 0.00020067567567567566, | |
| "loss": 0.049, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_loss": 0.8465907573699951, | |
| "eval_runtime": 136.8552, | |
| "eval_samples_per_second": 4.793, | |
| "eval_wer": 0.704574332909784, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 101.01, | |
| "learning_rate": 0.00019966216216216214, | |
| "loss": 0.0502, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 101.01, | |
| "eval_loss": 0.8005170226097107, | |
| "eval_runtime": 137.3151, | |
| "eval_samples_per_second": 4.777, | |
| "eval_wer": 0.6925031766200762, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 102.02, | |
| "learning_rate": 0.00019864864864864863, | |
| "loss": 0.0443, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 102.02, | |
| "eval_loss": 0.8749315142631531, | |
| "eval_runtime": 137.9488, | |
| "eval_samples_per_second": 4.755, | |
| "eval_wer": 0.6927149512918255, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 103.03, | |
| "learning_rate": 0.0001976351351351351, | |
| "loss": 0.0486, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 103.03, | |
| "eval_loss": 0.7846581339836121, | |
| "eval_runtime": 136.7448, | |
| "eval_samples_per_second": 4.797, | |
| "eval_wer": 0.7124099957645066, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 104.04, | |
| "learning_rate": 0.0001966216216216216, | |
| "loss": 0.0455, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 104.04, | |
| "eval_loss": 0.842466413974762, | |
| "eval_runtime": 137.1975, | |
| "eval_samples_per_second": 4.781, | |
| "eval_wer": 0.7189750105887336, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 105.05, | |
| "learning_rate": 0.00019560810810810808, | |
| "loss": 0.0435, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 105.05, | |
| "eval_loss": 0.8235080242156982, | |
| "eval_runtime": 137.1509, | |
| "eval_samples_per_second": 4.783, | |
| "eval_wer": 0.6927149512918255, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 106.06, | |
| "learning_rate": 0.0001945945945945946, | |
| "loss": 0.0452, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 106.06, | |
| "eval_loss": 0.7949621677398682, | |
| "eval_runtime": 137.8819, | |
| "eval_samples_per_second": 4.758, | |
| "eval_wer": 0.6891147818720881, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 107.07, | |
| "learning_rate": 0.00019358108108108107, | |
| "loss": 0.0441, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 107.07, | |
| "eval_loss": 0.8163775205612183, | |
| "eval_runtime": 136.9828, | |
| "eval_samples_per_second": 4.789, | |
| "eval_wer": 0.6992799661160525, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 108.08, | |
| "learning_rate": 0.00019256756756756756, | |
| "loss": 0.0433, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 108.08, | |
| "eval_loss": 0.9103622436523438, | |
| "eval_runtime": 138.0294, | |
| "eval_samples_per_second": 4.753, | |
| "eval_wer": 0.7009741634900466, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 109.09, | |
| "learning_rate": 0.00019155405405405404, | |
| "loss": 0.0423, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 109.09, | |
| "eval_loss": 0.8365850448608398, | |
| "eval_runtime": 137.9595, | |
| "eval_samples_per_second": 4.755, | |
| "eval_wer": 0.6954680220245658, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 110.1, | |
| "learning_rate": 0.0001905405405405405, | |
| "loss": 0.0428, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 110.1, | |
| "eval_loss": 0.9046308994293213, | |
| "eval_runtime": 137.2986, | |
| "eval_samples_per_second": 4.778, | |
| "eval_wer": 0.6863617111393477, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 111.11, | |
| "learning_rate": 0.00018952702702702704, | |
| "loss": 0.0389, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 111.11, | |
| "eval_loss": 0.8430789709091187, | |
| "eval_runtime": 137.4909, | |
| "eval_samples_per_second": 4.771, | |
| "eval_wer": 0.6869970351545955, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 112.12, | |
| "learning_rate": 0.0001885135135135135, | |
| "loss": 0.0388, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 112.12, | |
| "eval_loss": 0.8418474793434143, | |
| "eval_runtime": 138.0347, | |
| "eval_samples_per_second": 4.752, | |
| "eval_wer": 0.6990681914443032, | |
| "step": 22200 | |
| } | |
| ], | |
| "max_steps": 59400, | |
| "num_train_epochs": 300, | |
| "total_flos": 3.071129167748675e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |