| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7531219980787704, | |
| "global_step": 98, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5e-06, | |
| "loss": 0.1444, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 0.27758705615997314, | |
| "eval_runtime": 210.178, | |
| "eval_samples_per_second": 17.666, | |
| "eval_steps_per_second": 2.212, | |
| "eval_wer": 0.22257840465886627, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1768, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 0.27495622634887695, | |
| "eval_runtime": 143.6977, | |
| "eval_samples_per_second": 25.839, | |
| "eval_steps_per_second": 3.236, | |
| "eval_wer": 0.22263183202436287, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.1344, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 0.26992350816726685, | |
| "eval_runtime": 145.0666, | |
| "eval_samples_per_second": 25.595, | |
| "eval_steps_per_second": 3.205, | |
| "eval_wer": 0.22097558369396805, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1347, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 0.2631027102470398, | |
| "eval_runtime": 144.3292, | |
| "eval_samples_per_second": 25.726, | |
| "eval_steps_per_second": 3.222, | |
| "eval_wer": 0.2198001816530427, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.1401, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 0.2548554539680481, | |
| "eval_runtime": 145.5653, | |
| "eval_samples_per_second": 25.507, | |
| "eval_steps_per_second": 3.194, | |
| "eval_wer": 0.21825078805364106, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3e-05, | |
| "loss": 0.122, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 0.24481205642223358, | |
| "eval_runtime": 146.1904, | |
| "eval_samples_per_second": 25.398, | |
| "eval_steps_per_second": 3.181, | |
| "eval_wer": 0.21627397553026662, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.1098, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 0.23431816697120667, | |
| "eval_runtime": 143.3943, | |
| "eval_samples_per_second": 25.894, | |
| "eval_steps_per_second": 3.243, | |
| "eval_wer": 0.21317518833146337, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0777, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.2239282727241516, | |
| "eval_runtime": 144.1351, | |
| "eval_samples_per_second": 25.761, | |
| "eval_steps_per_second": 3.226, | |
| "eval_wer": 0.21002297376716353, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0987, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 0.2142292559146881, | |
| "eval_runtime": 142.2093, | |
| "eval_samples_per_second": 26.109, | |
| "eval_steps_per_second": 3.27, | |
| "eval_wer": 0.20703104129935354, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0827, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 0.2058483362197876, | |
| "eval_runtime": 139.25, | |
| "eval_samples_per_second": 26.664, | |
| "eval_steps_per_second": 3.339, | |
| "eval_wer": 0.20409253619704013, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0657, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 0.19945959746837616, | |
| "eval_runtime": 143.6254, | |
| "eval_samples_per_second": 25.852, | |
| "eval_steps_per_second": 3.238, | |
| "eval_wer": 0.2003526206122776, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0464, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 0.19494406878948212, | |
| "eval_runtime": 145.864, | |
| "eval_samples_per_second": 25.455, | |
| "eval_steps_per_second": 3.188, | |
| "eval_wer": 0.19869637228188278, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.0465, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.19232189655303955, | |
| "eval_runtime": 145.6174, | |
| "eval_samples_per_second": 25.498, | |
| "eval_steps_per_second": 3.193, | |
| "eval_wer": 0.19917721857135226, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0577, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 0.19074703752994537, | |
| "eval_runtime": 145.4558, | |
| "eval_samples_per_second": 25.527, | |
| "eval_steps_per_second": 3.197, | |
| "eval_wer": 0.19987177432280814, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0343, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.1901196986436844, | |
| "eval_runtime": 145.104, | |
| "eval_samples_per_second": 25.589, | |
| "eval_steps_per_second": 3.205, | |
| "eval_wer": 0.1995512101298285, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0496, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.19008365273475647, | |
| "eval_runtime": 145.5007, | |
| "eval_samples_per_second": 25.519, | |
| "eval_steps_per_second": 3.196, | |
| "eval_wer": 0.19992520168830474, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.0394, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 0.19069527089595795, | |
| "eval_runtime": 145.1656, | |
| "eval_samples_per_second": 25.578, | |
| "eval_steps_per_second": 3.203, | |
| "eval_wer": 0.19976491959181492, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0389, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 0.19175583124160767, | |
| "eval_runtime": 144.0309, | |
| "eval_samples_per_second": 25.779, | |
| "eval_steps_per_second": 3.228, | |
| "eval_wer": 0.19864294491638618, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.0375, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.1929420530796051, | |
| "eval_runtime": 155.5361, | |
| "eval_samples_per_second": 23.872, | |
| "eval_steps_per_second": 2.99, | |
| "eval_wer": 0.19869637228188278, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0416, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.19433951377868652, | |
| "eval_runtime": 145.7557, | |
| "eval_samples_per_second": 25.474, | |
| "eval_steps_per_second": 3.19, | |
| "eval_wer": 0.19842923545439975, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.909090909090911e-05, | |
| "loss": 0.049, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.19554230570793152, | |
| "eval_runtime": 144.8351, | |
| "eval_samples_per_second": 25.636, | |
| "eval_steps_per_second": 3.211, | |
| "eval_wer": 0.19687984185499813, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.818181818181818e-05, | |
| "loss": 0.0312, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.1970851719379425, | |
| "eval_runtime": 142.3937, | |
| "eval_samples_per_second": 26.076, | |
| "eval_steps_per_second": 3.266, | |
| "eval_wer": 0.19479617460063045, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.727272727272728e-05, | |
| "loss": 0.0455, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.19858291745185852, | |
| "eval_runtime": 140.2626, | |
| "eval_samples_per_second": 26.472, | |
| "eval_steps_per_second": 3.315, | |
| "eval_wer": 0.19330020836672543, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.636363636363637e-05, | |
| "loss": 0.0532, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.19979843497276306, | |
| "eval_runtime": 140.2969, | |
| "eval_samples_per_second": 26.465, | |
| "eval_steps_per_second": 3.314, | |
| "eval_wer": 0.19105625901586792, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 9.545454545454546e-05, | |
| "loss": 0.0442, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 0.20092029869556427, | |
| "eval_runtime": 143.5469, | |
| "eval_samples_per_second": 25.866, | |
| "eval_steps_per_second": 3.239, | |
| "eval_wer": 0.19052198536090184, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.454545454545455e-05, | |
| "loss": 0.0339, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.2023477554321289, | |
| "eval_runtime": 152.7348, | |
| "eval_samples_per_second": 24.31, | |
| "eval_steps_per_second": 3.044, | |
| "eval_wer": 0.1893465833199765, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 9.363636363636364e-05, | |
| "loss": 0.0346, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 0.20320531725883484, | |
| "eval_runtime": 147.0625, | |
| "eval_samples_per_second": 25.248, | |
| "eval_steps_per_second": 3.162, | |
| "eval_wer": 0.18907944649249345, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.272727272727273e-05, | |
| "loss": 0.0405, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 0.20423929393291473, | |
| "eval_runtime": 147.2712, | |
| "eval_samples_per_second": 25.212, | |
| "eval_steps_per_second": 3.157, | |
| "eval_wer": 0.18875888229951382, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 9.181818181818183e-05, | |
| "loss": 0.0273, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 0.20516164600849152, | |
| "eval_runtime": 147.0321, | |
| "eval_samples_per_second": 25.253, | |
| "eval_steps_per_second": 3.163, | |
| "eval_wer": 0.18811775391355454, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 0.0303, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 0.20583093166351318, | |
| "eval_runtime": 147.1797, | |
| "eval_samples_per_second": 25.228, | |
| "eval_steps_per_second": 3.159, | |
| "eval_wer": 0.18843831810653416, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0433, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.2059250921010971, | |
| "eval_runtime": 149.5581, | |
| "eval_samples_per_second": 24.826, | |
| "eval_steps_per_second": 3.109, | |
| "eval_wer": 0.1880108991825613, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.90909090909091e-05, | |
| "loss": 0.0172, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.20622014999389648, | |
| "eval_runtime": 147.3034, | |
| "eval_samples_per_second": 25.206, | |
| "eval_steps_per_second": 3.157, | |
| "eval_wer": 0.18774376235507828, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.818181818181818e-05, | |
| "loss": 0.0417, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.20588700473308563, | |
| "eval_runtime": 147.9347, | |
| "eval_samples_per_second": 25.099, | |
| "eval_steps_per_second": 3.143, | |
| "eval_wer": 0.18710263396911897, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 8.727272727272727e-05, | |
| "loss": 0.0305, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 0.2053101509809494, | |
| "eval_runtime": 147.604, | |
| "eval_samples_per_second": 25.155, | |
| "eval_steps_per_second": 3.15, | |
| "eval_wer": 0.18624779612117326, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 8.636363636363637e-05, | |
| "loss": 0.0294, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 0.2048512101173401, | |
| "eval_runtime": 149.6988, | |
| "eval_samples_per_second": 24.803, | |
| "eval_steps_per_second": 3.106, | |
| "eval_wer": 0.18624779612117326, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.545454545454545e-05, | |
| "loss": 0.0344, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.20456022024154663, | |
| "eval_runtime": 150.2353, | |
| "eval_samples_per_second": 24.715, | |
| "eval_steps_per_second": 3.095, | |
| "eval_wer": 0.1863546508521665, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.454545454545455e-05, | |
| "loss": 0.0352, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.20410528779029846, | |
| "eval_runtime": 147.7984, | |
| "eval_samples_per_second": 25.122, | |
| "eval_steps_per_second": 3.146, | |
| "eval_wer": 0.18539295827322755, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 8.363636363636364e-05, | |
| "loss": 0.0379, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 0.2038663774728775, | |
| "eval_runtime": 147.8438, | |
| "eval_samples_per_second": 25.114, | |
| "eval_steps_per_second": 3.145, | |
| "eval_wer": 0.1857135224662072, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.272727272727273e-05, | |
| "loss": 0.0413, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.20388050377368927, | |
| "eval_runtime": 147.3701, | |
| "eval_samples_per_second": 25.195, | |
| "eval_steps_per_second": 3.155, | |
| "eval_wer": 0.18427098359779878, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 8.181818181818183e-05, | |
| "loss": 0.0317, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 0.20368847250938416, | |
| "eval_runtime": 147.9612, | |
| "eval_samples_per_second": 25.094, | |
| "eval_steps_per_second": 3.143, | |
| "eval_wer": 0.18384356467382593, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8.090909090909092e-05, | |
| "loss": 0.0406, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.20367969572544098, | |
| "eval_runtime": 148.8012, | |
| "eval_samples_per_second": 24.953, | |
| "eval_steps_per_second": 3.125, | |
| "eval_wer": 0.18330929101885987, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 8e-05, | |
| "loss": 0.039, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.20352540910243988, | |
| "eval_runtime": 148.6131, | |
| "eval_samples_per_second": 24.984, | |
| "eval_steps_per_second": 3.129, | |
| "eval_wer": 0.18256130790190736, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 7.90909090909091e-05, | |
| "loss": 0.0418, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.20341253280639648, | |
| "eval_runtime": 148.4125, | |
| "eval_samples_per_second": 25.018, | |
| "eval_steps_per_second": 3.133, | |
| "eval_wer": 0.18229417107442433, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 7.818181818181818e-05, | |
| "loss": 0.0424, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.20320875942707062, | |
| "eval_runtime": 148.7795, | |
| "eval_samples_per_second": 24.956, | |
| "eval_steps_per_second": 3.125, | |
| "eval_wer": 0.18202703424694128, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.727272727272727e-05, | |
| "loss": 0.0262, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.20320919156074524, | |
| "eval_runtime": 149.2065, | |
| "eval_samples_per_second": 24.885, | |
| "eval_steps_per_second": 3.116, | |
| "eval_wer": 0.18170647005396165, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.636363636363637e-05, | |
| "loss": 0.0333, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.20314393937587738, | |
| "eval_runtime": 148.5201, | |
| "eval_samples_per_second": 25.0, | |
| "eval_steps_per_second": 3.131, | |
| "eval_wer": 0.18181332478495485, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.545454545454545e-05, | |
| "loss": 0.0217, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 0.20316116511821747, | |
| "eval_runtime": 149.0026, | |
| "eval_samples_per_second": 24.919, | |
| "eval_steps_per_second": 3.121, | |
| "eval_wer": 0.18186675215045145, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.454545454545455e-05, | |
| "loss": 0.0324, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 0.20341037213802338, | |
| "eval_runtime": 151.4038, | |
| "eval_samples_per_second": 24.524, | |
| "eval_steps_per_second": 3.071, | |
| "eval_wer": 0.18175989741945825, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.363636363636364e-05, | |
| "loss": 0.0438, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.20362479984760284, | |
| "eval_runtime": 147.9041, | |
| "eval_samples_per_second": 25.104, | |
| "eval_steps_per_second": 3.144, | |
| "eval_wer": 0.18154618795747182, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 0.0435, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.20351320505142212, | |
| "eval_runtime": 150.6257, | |
| "eval_samples_per_second": 24.651, | |
| "eval_steps_per_second": 3.087, | |
| "eval_wer": 0.18192017951594808, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.181818181818182e-05, | |
| "loss": 0.0386, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 0.20342397689819336, | |
| "eval_runtime": 149.3494, | |
| "eval_samples_per_second": 24.861, | |
| "eval_steps_per_second": 3.114, | |
| "eval_wer": 0.18202703424694128, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 7.090909090909092e-05, | |
| "loss": 0.034, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.20335783064365387, | |
| "eval_runtime": 148.8221, | |
| "eval_samples_per_second": 24.949, | |
| "eval_steps_per_second": 3.125, | |
| "eval_wer": 0.18245445317091413, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0308, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 0.20360249280929565, | |
| "eval_runtime": 148.86, | |
| "eval_samples_per_second": 24.943, | |
| "eval_steps_per_second": 3.124, | |
| "eval_wer": 0.18250788053641076, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.90909090909091e-05, | |
| "loss": 0.0334, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 0.2034262865781784, | |
| "eval_runtime": 149.0445, | |
| "eval_samples_per_second": 24.912, | |
| "eval_steps_per_second": 3.12, | |
| "eval_wer": 0.1828284447293904, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.818181818181818e-05, | |
| "loss": 0.0334, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.20335279405117035, | |
| "eval_runtime": 149.9535, | |
| "eval_samples_per_second": 24.761, | |
| "eval_steps_per_second": 3.101, | |
| "eval_wer": 0.18240102580541753, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 6.727272727272727e-05, | |
| "loss": 0.0502, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 0.20316840708255768, | |
| "eval_runtime": 150.4496, | |
| "eval_samples_per_second": 24.679, | |
| "eval_steps_per_second": 3.091, | |
| "eval_wer": 0.18256130790190736, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 6.636363636363638e-05, | |
| "loss": 0.0341, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.20272959768772125, | |
| "eval_runtime": 149.4094, | |
| "eval_samples_per_second": 24.851, | |
| "eval_steps_per_second": 3.112, | |
| "eval_wer": 0.1821873163434311, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.545454545454546e-05, | |
| "loss": 0.0595, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 0.20200660824775696, | |
| "eval_runtime": 150.4398, | |
| "eval_samples_per_second": 24.681, | |
| "eval_steps_per_second": 3.091, | |
| "eval_wer": 0.18245445317091413, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.454545454545455e-05, | |
| "loss": 0.0337, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 0.2010081559419632, | |
| "eval_runtime": 149.7401, | |
| "eval_samples_per_second": 24.796, | |
| "eval_steps_per_second": 3.105, | |
| "eval_wer": 0.18304215419137682, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 6.363636363636364e-05, | |
| "loss": 0.0504, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 0.20022302865982056, | |
| "eval_runtime": 150.2278, | |
| "eval_samples_per_second": 24.716, | |
| "eval_steps_per_second": 3.095, | |
| "eval_wer": 0.18341614574985307, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 6.272727272727273e-05, | |
| "loss": 0.0298, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.19969654083251953, | |
| "eval_runtime": 149.9979, | |
| "eval_samples_per_second": 24.754, | |
| "eval_steps_per_second": 3.1, | |
| "eval_wer": 0.18336271838435647, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.181818181818182e-05, | |
| "loss": 0.0216, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.19924180209636688, | |
| "eval_runtime": 149.7227, | |
| "eval_samples_per_second": 24.799, | |
| "eval_steps_per_second": 3.106, | |
| "eval_wer": 0.18411070150130898, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 6.090909090909091e-05, | |
| "loss": 0.0262, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.19875453412532806, | |
| "eval_runtime": 151.0436, | |
| "eval_samples_per_second": 24.582, | |
| "eval_steps_per_second": 3.079, | |
| "eval_wer": 0.18464497515627504, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6e-05, | |
| "loss": 0.012, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 0.19849465787410736, | |
| "eval_runtime": 150.8245, | |
| "eval_samples_per_second": 24.618, | |
| "eval_steps_per_second": 3.083, | |
| "eval_wer": 0.18528610354223432, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5.90909090909091e-05, | |
| "loss": 0.026, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.19816958904266357, | |
| "eval_runtime": 152.5115, | |
| "eval_samples_per_second": 24.346, | |
| "eval_steps_per_second": 3.049, | |
| "eval_wer": 0.185873804562697, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.818181818181818e-05, | |
| "loss": 0.0382, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.19807423651218414, | |
| "eval_runtime": 154.494, | |
| "eval_samples_per_second": 24.033, | |
| "eval_steps_per_second": 3.01, | |
| "eval_wer": 0.18528610354223432, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 5.727272727272728e-05, | |
| "loss": 0.0284, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.1981343924999237, | |
| "eval_runtime": 151.1093, | |
| "eval_samples_per_second": 24.572, | |
| "eval_steps_per_second": 3.077, | |
| "eval_wer": 0.1849121119837581, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 5.636363636363636e-05, | |
| "loss": 0.0273, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 0.19824360311031342, | |
| "eval_runtime": 151.8867, | |
| "eval_samples_per_second": 24.446, | |
| "eval_steps_per_second": 3.061, | |
| "eval_wer": 0.18421755623230218, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.545454545454546e-05, | |
| "loss": 0.0248, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 0.19854041934013367, | |
| "eval_runtime": 150.4994, | |
| "eval_samples_per_second": 24.671, | |
| "eval_steps_per_second": 3.09, | |
| "eval_wer": 0.1844312656942886, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 0.0315, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 0.19896994531154633, | |
| "eval_runtime": 150.9218, | |
| "eval_samples_per_second": 24.602, | |
| "eval_steps_per_second": 3.081, | |
| "eval_wer": 0.18405727413581235, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.363636363636364e-05, | |
| "loss": 0.0443, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.1993587613105774, | |
| "eval_runtime": 151.464, | |
| "eval_samples_per_second": 24.514, | |
| "eval_steps_per_second": 3.07, | |
| "eval_wer": 0.1835764278463429, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.272727272727272e-05, | |
| "loss": 0.0473, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.1994282454252243, | |
| "eval_runtime": 151.2775, | |
| "eval_samples_per_second": 24.544, | |
| "eval_steps_per_second": 3.074, | |
| "eval_wer": 0.18379013730832933, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.181818181818182e-05, | |
| "loss": 0.0366, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 0.19968333840370178, | |
| "eval_runtime": 151.4205, | |
| "eval_samples_per_second": 24.521, | |
| "eval_steps_per_second": 3.071, | |
| "eval_wer": 0.18298872682588022, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.090909090909091e-05, | |
| "loss": 0.0337, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 0.19987201690673828, | |
| "eval_runtime": 151.4399, | |
| "eval_samples_per_second": 24.518, | |
| "eval_steps_per_second": 3.071, | |
| "eval_wer": 0.18309558155687344, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0304, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.2001255452632904, | |
| "eval_runtime": 152.4344, | |
| "eval_samples_per_second": 24.358, | |
| "eval_steps_per_second": 3.05, | |
| "eval_wer": 0.18346957311534967, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.909090909090909e-05, | |
| "loss": 0.0362, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.20033375918865204, | |
| "eval_runtime": 151.5547, | |
| "eval_samples_per_second": 24.499, | |
| "eval_steps_per_second": 3.068, | |
| "eval_wer": 0.18293529946038362, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.8181818181818186e-05, | |
| "loss": 0.0482, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 0.20038414001464844, | |
| "eval_runtime": 151.9532, | |
| "eval_samples_per_second": 24.435, | |
| "eval_steps_per_second": 3.06, | |
| "eval_wer": 0.18250788053641076, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.7272727272727275e-05, | |
| "loss": 0.0362, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.20029421150684357, | |
| "eval_runtime": 153.417, | |
| "eval_samples_per_second": 24.202, | |
| "eval_steps_per_second": 3.031, | |
| "eval_wer": 0.1828284447293904, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.636363636363636e-05, | |
| "loss": 0.0301, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 0.20029130578041077, | |
| "eval_runtime": 151.1667, | |
| "eval_samples_per_second": 24.562, | |
| "eval_steps_per_second": 3.076, | |
| "eval_wer": 0.18293529946038362, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.031, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 0.200118288397789, | |
| "eval_runtime": 152.5561, | |
| "eval_samples_per_second": 24.339, | |
| "eval_steps_per_second": 3.048, | |
| "eval_wer": 0.18330929101885987, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.454545454545455e-05, | |
| "loss": 0.0377, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 0.1998458057641983, | |
| "eval_runtime": 152.057, | |
| "eval_samples_per_second": 24.418, | |
| "eval_steps_per_second": 3.058, | |
| "eval_wer": 0.18234759843992093, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.3636363636363636e-05, | |
| "loss": 0.0372, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 0.19953805208206177, | |
| "eval_runtime": 152.6899, | |
| "eval_samples_per_second": 24.317, | |
| "eval_steps_per_second": 3.045, | |
| "eval_wer": 0.18256130790190736, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.2727272727272724e-05, | |
| "loss": 0.0234, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.19939135015010834, | |
| "eval_runtime": 152.3549, | |
| "eval_samples_per_second": 24.371, | |
| "eval_steps_per_second": 3.052, | |
| "eval_wer": 0.18202703424694128, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.181818181818182e-05, | |
| "loss": 0.0539, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.19920985400676727, | |
| "eval_runtime": 151.8121, | |
| "eval_samples_per_second": 24.458, | |
| "eval_steps_per_second": 3.063, | |
| "eval_wer": 0.18154618795747182, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.0909090909090915e-05, | |
| "loss": 0.0446, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.19903059303760529, | |
| "eval_runtime": 153.3501, | |
| "eval_samples_per_second": 24.213, | |
| "eval_steps_per_second": 3.032, | |
| "eval_wer": 0.18181332478495485, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0373, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 0.19874274730682373, | |
| "eval_runtime": 153.2828, | |
| "eval_samples_per_second": 24.223, | |
| "eval_steps_per_second": 3.034, | |
| "eval_wer": 0.18154618795747182, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.909090909090909e-05, | |
| "loss": 0.0347, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.1984863579273224, | |
| "eval_runtime": 153.5045, | |
| "eval_samples_per_second": 24.188, | |
| "eval_steps_per_second": 3.029, | |
| "eval_wer": 0.1814393332264786, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.818181818181819e-05, | |
| "loss": 0.0477, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.19823090732097626, | |
| "eval_runtime": 153.2343, | |
| "eval_samples_per_second": 24.231, | |
| "eval_steps_per_second": 3.035, | |
| "eval_wer": 0.18186675215045145, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.7272727272727276e-05, | |
| "loss": 0.0365, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.1978393793106079, | |
| "eval_runtime": 153.4002, | |
| "eval_samples_per_second": 24.205, | |
| "eval_steps_per_second": 3.031, | |
| "eval_wer": 0.1814393332264786, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.0255, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 0.1975974142551422, | |
| "eval_runtime": 153.949, | |
| "eval_samples_per_second": 24.118, | |
| "eval_steps_per_second": 3.02, | |
| "eval_wer": 0.18101191430250574, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.545454545454546e-05, | |
| "loss": 0.0205, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.19747106730937958, | |
| "eval_runtime": 153.3875, | |
| "eval_samples_per_second": 24.207, | |
| "eval_steps_per_second": 3.032, | |
| "eval_wer": 0.18063792274402948, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.454545454545455e-05, | |
| "loss": 0.053, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 0.19707681238651276, | |
| "eval_runtime": 151.9804, | |
| "eval_samples_per_second": 24.431, | |
| "eval_steps_per_second": 3.06, | |
| "eval_wer": 0.18031735855104986, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.3636363636363636e-05, | |
| "loss": 0.0188, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 0.19678995013237, | |
| "eval_runtime": 156.2042, | |
| "eval_samples_per_second": 23.77, | |
| "eval_steps_per_second": 2.977, | |
| "eval_wer": 0.18053106801303628, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.272727272727273e-05, | |
| "loss": 0.018, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.1968337893486023, | |
| "eval_runtime": 151.8471, | |
| "eval_samples_per_second": 24.452, | |
| "eval_steps_per_second": 3.062, | |
| "eval_wer": 0.18015707645456003, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 0.0135, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 0.19669164717197418, | |
| "eval_runtime": 153.6158, | |
| "eval_samples_per_second": 24.171, | |
| "eval_steps_per_second": 3.027, | |
| "eval_wer": 0.18042421328204306, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.090909090909091e-05, | |
| "loss": 0.0099, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.1966254860162735, | |
| "eval_runtime": 153.1791, | |
| "eval_samples_per_second": 24.24, | |
| "eval_steps_per_second": 3.036, | |
| "eval_wer": 0.18010364908906343, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0283, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.19664821028709412, | |
| "eval_runtime": 152.9205, | |
| "eval_samples_per_second": 24.281, | |
| "eval_steps_per_second": 3.041, | |
| "eval_wer": 0.18042421328204306, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.909090909090909e-05, | |
| "loss": 0.0345, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.19662834703922272, | |
| "eval_runtime": 153.3485, | |
| "eval_samples_per_second": 24.213, | |
| "eval_steps_per_second": 3.032, | |
| "eval_wer": 0.1799433669925736, | |
| "step": 98 | |
| } | |
| ], | |
| "max_steps": 130, | |
| "num_train_epochs": 1, | |
| "total_flos": 2.245784209200768e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |