| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 35.986119743111665, | |
| "global_step": 43400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.95e-05, | |
| "loss": 0.6982, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.25508013367652893, | |
| "eval_runtime": 247.2382, | |
| "eval_samples_per_second": 20.907, | |
| "eval_steps_per_second": 2.617, | |
| "eval_wer": 0.24512755506258913, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 9.972560975609757e-05, | |
| "loss": 0.5209, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.21009531617164612, | |
| "eval_runtime": 249.2779, | |
| "eval_samples_per_second": 20.736, | |
| "eval_steps_per_second": 2.595, | |
| "eval_wer": 0.21507420905297628, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.944844789356985e-05, | |
| "loss": 0.4885, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.20174096524715424, | |
| "eval_runtime": 247.285, | |
| "eval_samples_per_second": 20.903, | |
| "eval_steps_per_second": 2.616, | |
| "eval_wer": 0.20297892568531137, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.917128603104213e-05, | |
| "loss": 0.474, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 0.18579010665416718, | |
| "eval_runtime": 250.2088, | |
| "eval_samples_per_second": 20.659, | |
| "eval_steps_per_second": 2.586, | |
| "eval_wer": 0.1948977974964348, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.889412416851441e-05, | |
| "loss": 0.4683, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 0.17479585111141205, | |
| "eval_runtime": 251.8549, | |
| "eval_samples_per_second": 20.524, | |
| "eval_steps_per_second": 2.569, | |
| "eval_wer": 0.17192204088100144, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 9.86169623059867e-05, | |
| "loss": 0.4497, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 0.15883031487464905, | |
| "eval_runtime": 251.9945, | |
| "eval_samples_per_second": 20.512, | |
| "eval_steps_per_second": 2.568, | |
| "eval_wer": 0.17171076955580203, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 9.833980044345899e-05, | |
| "loss": 0.4037, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 0.15540002286434174, | |
| "eval_runtime": 253.8837, | |
| "eval_samples_per_second": 20.36, | |
| "eval_steps_per_second": 2.548, | |
| "eval_wer": 0.15987957534463634, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 9.806263858093127e-05, | |
| "loss": 0.3999, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 0.1569492369890213, | |
| "eval_runtime": 253.8314, | |
| "eval_samples_per_second": 20.364, | |
| "eval_steps_per_second": 2.549, | |
| "eval_wer": 0.1581365869117414, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 9.778547671840356e-05, | |
| "loss": 0.4014, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 0.14257089793682098, | |
| "eval_runtime": 253.5715, | |
| "eval_samples_per_second": 20.385, | |
| "eval_steps_per_second": 2.552, | |
| "eval_wer": 0.1482068346273702, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 9.750831485587584e-05, | |
| "loss": 0.3887, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 0.14761227369308472, | |
| "eval_runtime": 262.7757, | |
| "eval_samples_per_second": 19.671, | |
| "eval_steps_per_second": 2.462, | |
| "eval_wer": 0.14361168330428353, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 9.723115299334812e-05, | |
| "loss": 0.3861, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 0.14095284044742584, | |
| "eval_runtime": 253.9647, | |
| "eval_samples_per_second": 20.353, | |
| "eval_steps_per_second": 2.548, | |
| "eval_wer": 0.14815401679607035, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 9.695399113082039e-05, | |
| "loss": 0.3881, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 0.13986040651798248, | |
| "eval_runtime": 253.8881, | |
| "eval_samples_per_second": 20.359, | |
| "eval_steps_per_second": 2.548, | |
| "eval_wer": 0.14012570643849365, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 9.667682926829269e-05, | |
| "loss": 0.3397, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 0.1451854407787323, | |
| "eval_runtime": 255.702, | |
| "eval_samples_per_second": 20.215, | |
| "eval_steps_per_second": 2.53, | |
| "eval_wer": 0.13178048909311785, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 9.639966740576497e-05, | |
| "loss": 0.3383, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 0.13278624415397644, | |
| "eval_runtime": 254.5924, | |
| "eval_samples_per_second": 20.303, | |
| "eval_steps_per_second": 2.541, | |
| "eval_wer": 0.13019595415412244, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 9.612250554323725e-05, | |
| "loss": 0.3366, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 0.1430414617061615, | |
| "eval_runtime": 253.9896, | |
| "eval_samples_per_second": 20.351, | |
| "eval_steps_per_second": 2.547, | |
| "eval_wer": 0.13251993873131568, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 9.584534368070954e-05, | |
| "loss": 0.3481, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 0.1356772631406784, | |
| "eval_runtime": 253.702, | |
| "eval_samples_per_second": 20.374, | |
| "eval_steps_per_second": 2.55, | |
| "eval_wer": 0.12829451222732793, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 9.556956762749447e-05, | |
| "loss": 0.337, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_loss": 0.1254938244819641, | |
| "eval_runtime": 254.1064, | |
| "eval_samples_per_second": 20.342, | |
| "eval_steps_per_second": 2.546, | |
| "eval_wer": 0.1273437912639307, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 9.529240576496675e-05, | |
| "loss": 0.3346, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 0.13027481734752655, | |
| "eval_runtime": 254.6218, | |
| "eval_samples_per_second": 20.301, | |
| "eval_steps_per_second": 2.541, | |
| "eval_wer": 0.1280304230708287, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 9.501524390243903e-05, | |
| "loss": 0.3192, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "eval_loss": 0.13303972780704498, | |
| "eval_runtime": 254.7219, | |
| "eval_samples_per_second": 20.293, | |
| "eval_steps_per_second": 2.54, | |
| "eval_wer": 0.12280145777214388, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 9.473808203991131e-05, | |
| "loss": 0.3093, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "eval_loss": 0.13668616116046906, | |
| "eval_runtime": 254.6369, | |
| "eval_samples_per_second": 20.299, | |
| "eval_steps_per_second": 2.541, | |
| "eval_wer": 0.12206200813394602, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 9.446092017738359e-05, | |
| "loss": 0.3119, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_loss": 0.1260731816291809, | |
| "eval_runtime": 255.6853, | |
| "eval_samples_per_second": 20.216, | |
| "eval_steps_per_second": 2.53, | |
| "eval_wer": 0.1149316009084667, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 9.418375831485588e-05, | |
| "loss": 0.3115, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "eval_loss": 0.11900634318590164, | |
| "eval_runtime": 255.3718, | |
| "eval_samples_per_second": 20.241, | |
| "eval_steps_per_second": 2.534, | |
| "eval_wer": 0.11514287223366608, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 9.390659645232817e-05, | |
| "loss": 0.3104, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "eval_loss": 0.11844547092914581, | |
| "eval_runtime": 253.3424, | |
| "eval_samples_per_second": 20.403, | |
| "eval_steps_per_second": 2.554, | |
| "eval_wer": 0.11994929488195215, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 9.362943458980045e-05, | |
| "loss": 0.3084, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "eval_loss": 0.12033428996801376, | |
| "eval_runtime": 253.1313, | |
| "eval_samples_per_second": 20.42, | |
| "eval_steps_per_second": 2.556, | |
| "eval_wer": 0.114139333438969, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 9.335227272727273e-05, | |
| "loss": 0.2879, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "eval_loss": 0.1269288957118988, | |
| "eval_runtime": 252.0701, | |
| "eval_samples_per_second": 20.506, | |
| "eval_steps_per_second": 2.567, | |
| "eval_wer": 0.11239634500607405, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 9.307511086474502e-05, | |
| "loss": 0.2865, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "eval_loss": 0.13235774636268616, | |
| "eval_runtime": 253.6428, | |
| "eval_samples_per_second": 20.379, | |
| "eval_steps_per_second": 2.551, | |
| "eval_wer": 0.11118153488617757, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 9.27979490022173e-05, | |
| "loss": 0.2845, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "eval_loss": 0.12866514921188354, | |
| "eval_runtime": 257.2798, | |
| "eval_samples_per_second": 20.091, | |
| "eval_steps_per_second": 2.515, | |
| "eval_wer": 0.11424496910156869, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 9.252078713968959e-05, | |
| "loss": 0.2856, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "eval_loss": 0.12589029967784882, | |
| "eval_runtime": 254.2212, | |
| "eval_samples_per_second": 20.333, | |
| "eval_steps_per_second": 2.545, | |
| "eval_wer": 0.11012517826018063, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 9.224362527716187e-05, | |
| "loss": 0.2801, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "eval_loss": 0.12850765883922577, | |
| "eval_runtime": 252.9838, | |
| "eval_samples_per_second": 20.432, | |
| "eval_steps_per_second": 2.557, | |
| "eval_wer": 0.11023081392278034, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 9.196646341463415e-05, | |
| "loss": 0.2882, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "eval_loss": 0.13433855772018433, | |
| "eval_runtime": 253.6459, | |
| "eval_samples_per_second": 20.379, | |
| "eval_steps_per_second": 2.551, | |
| "eval_wer": 0.10880473247768446, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 9.168930155210643e-05, | |
| "loss": 0.2701, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "eval_loss": 0.14238382875919342, | |
| "eval_runtime": 253.374, | |
| "eval_samples_per_second": 20.401, | |
| "eval_steps_per_second": 2.554, | |
| "eval_wer": 0.10531875561189458, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 9.141213968957871e-05, | |
| "loss": 0.2688, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "eval_loss": 0.1337863802909851, | |
| "eval_runtime": 253.8454, | |
| "eval_samples_per_second": 20.363, | |
| "eval_steps_per_second": 2.549, | |
| "eval_wer": 0.10288913537210162, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 9.1134977827051e-05, | |
| "loss": 0.2683, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "eval_loss": 0.14259789884090424, | |
| "eval_runtime": 252.7728, | |
| "eval_samples_per_second": 20.449, | |
| "eval_steps_per_second": 2.56, | |
| "eval_wer": 0.10732583320128876, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 9.085781596452329e-05, | |
| "loss": 0.2609, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "eval_loss": 0.13099780678749084, | |
| "eval_runtime": 252.7442, | |
| "eval_samples_per_second": 20.452, | |
| "eval_steps_per_second": 2.56, | |
| "eval_wer": 0.10257222838430254, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 9.058065410199557e-05, | |
| "loss": 0.267, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "eval_loss": 0.14180444180965424, | |
| "eval_runtime": 254.0779, | |
| "eval_samples_per_second": 20.344, | |
| "eval_steps_per_second": 2.546, | |
| "eval_wer": 0.10119896477050652, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 9.030487804878049e-05, | |
| "loss": 0.2638, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "eval_loss": 0.13856083154678345, | |
| "eval_runtime": 253.6851, | |
| "eval_samples_per_second": 20.376, | |
| "eval_steps_per_second": 2.55, | |
| "eval_wer": 0.1007236042888079, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 9.002771618625277e-05, | |
| "loss": 0.2604, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "eval_loss": 0.14975795149803162, | |
| "eval_runtime": 255.6414, | |
| "eval_samples_per_second": 20.22, | |
| "eval_steps_per_second": 2.531, | |
| "eval_wer": 0.10389267416679872, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 8.975055432372505e-05, | |
| "loss": 0.2484, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "eval_loss": 0.1300615817308426, | |
| "eval_runtime": 256.8835, | |
| "eval_samples_per_second": 20.122, | |
| "eval_steps_per_second": 2.519, | |
| "eval_wer": 0.10230813922780331, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 8.947339246119735e-05, | |
| "loss": 0.2515, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "eval_loss": 0.13480910658836365, | |
| "eval_runtime": 254.0211, | |
| "eval_samples_per_second": 20.349, | |
| "eval_steps_per_second": 2.547, | |
| "eval_wer": 0.10310040669730101, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 8.919623059866963e-05, | |
| "loss": 0.2529, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "eval_loss": 0.12069129198789597, | |
| "eval_runtime": 254.8765, | |
| "eval_samples_per_second": 20.28, | |
| "eval_steps_per_second": 2.538, | |
| "eval_wer": 0.10146305392700576, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 8.891906873614191e-05, | |
| "loss": 0.2498, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "eval_loss": 0.14146772027015686, | |
| "eval_runtime": 254.7381, | |
| "eval_samples_per_second": 20.291, | |
| "eval_steps_per_second": 2.54, | |
| "eval_wer": 0.1016215074209053, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 8.86419068736142e-05, | |
| "loss": 0.2502, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "eval_loss": 0.12623198330402374, | |
| "eval_runtime": 254.5919, | |
| "eval_samples_per_second": 20.303, | |
| "eval_steps_per_second": 2.541, | |
| "eval_wer": 0.09760735224211693, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 8.836474501108648e-05, | |
| "loss": 0.2404, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "eval_loss": 0.13511496782302856, | |
| "eval_runtime": 254.4607, | |
| "eval_samples_per_second": 20.314, | |
| "eval_steps_per_second": 2.543, | |
| "eval_wer": 0.09929752284371204, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 8.808758314855876e-05, | |
| "loss": 0.2337, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "eval_loss": 0.13152754306793213, | |
| "eval_runtime": 254.1423, | |
| "eval_samples_per_second": 20.339, | |
| "eval_steps_per_second": 2.546, | |
| "eval_wer": 0.09876934453071357, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 8.781042128603105e-05, | |
| "loss": 0.2396, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "eval_loss": 0.135118767619133, | |
| "eval_runtime": 255.0124, | |
| "eval_samples_per_second": 20.27, | |
| "eval_steps_per_second": 2.537, | |
| "eval_wer": 0.09834680188031479, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 8.753325942350333e-05, | |
| "loss": 0.2431, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "eval_loss": 0.13074836134910583, | |
| "eval_runtime": 255.0093, | |
| "eval_samples_per_second": 20.27, | |
| "eval_steps_per_second": 2.537, | |
| "eval_wer": 0.09707917392911847, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 8.725609756097561e-05, | |
| "loss": 0.2379, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "eval_loss": 0.13186238706111908, | |
| "eval_runtime": 255.2219, | |
| "eval_samples_per_second": 20.253, | |
| "eval_steps_per_second": 2.535, | |
| "eval_wer": 0.09950879416891142, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 8.697893569844789e-05, | |
| "loss": 0.2421, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "eval_loss": 0.1254909485578537, | |
| "eval_runtime": 255.0666, | |
| "eval_samples_per_second": 20.265, | |
| "eval_steps_per_second": 2.537, | |
| "eval_wer": 0.09882216236201341, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 8.670177383592018e-05, | |
| "loss": 0.2324, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "eval_loss": 0.13816988468170166, | |
| "eval_runtime": 257.5755, | |
| "eval_samples_per_second": 20.068, | |
| "eval_steps_per_second": 2.512, | |
| "eval_wer": 0.09628690645962076, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 8.642461197339246e-05, | |
| "loss": 0.2258, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "eval_loss": 0.15982431173324585, | |
| "eval_runtime": 257.1975, | |
| "eval_samples_per_second": 20.097, | |
| "eval_steps_per_second": 2.516, | |
| "eval_wer": 0.09750171657951724, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 8.614745011086475e-05, | |
| "loss": 0.2253, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "eval_loss": 0.15032005310058594, | |
| "eval_runtime": 256.9993, | |
| "eval_samples_per_second": 20.113, | |
| "eval_steps_per_second": 2.518, | |
| "eval_wer": 0.09422701103892674, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 8.587028824833703e-05, | |
| "loss": 0.2228, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "eval_loss": 0.12655803561210632, | |
| "eval_runtime": 258.0019, | |
| "eval_samples_per_second": 20.035, | |
| "eval_steps_per_second": 2.508, | |
| "eval_wer": 0.09581154597792214, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 8.559312638580932e-05, | |
| "loss": 0.2255, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "eval_loss": 0.14087137579917908, | |
| "eval_runtime": 252.7692, | |
| "eval_samples_per_second": 20.449, | |
| "eval_steps_per_second": 2.56, | |
| "eval_wer": 0.09623408862832092, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 8.53159645232816e-05, | |
| "loss": 0.2307, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "eval_loss": 0.13605473935604095, | |
| "eval_runtime": 255.7465, | |
| "eval_samples_per_second": 20.211, | |
| "eval_steps_per_second": 2.53, | |
| "eval_wer": 0.0974488987482174, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 8.503880266075388e-05, | |
| "loss": 0.2149, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "eval_loss": 0.13241790235042572, | |
| "eval_runtime": 254.7831, | |
| "eval_samples_per_second": 20.288, | |
| "eval_steps_per_second": 2.539, | |
| "eval_wer": 0.09338192573812919, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 8.476164079822618e-05, | |
| "loss": 0.2168, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "eval_loss": 0.1478220671415329, | |
| "eval_runtime": 255.9893, | |
| "eval_samples_per_second": 20.192, | |
| "eval_steps_per_second": 2.527, | |
| "eval_wer": 0.09792425922991602, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 8.448447893569845e-05, | |
| "loss": 0.2152, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "eval_loss": 0.13686269521713257, | |
| "eval_runtime": 254.4314, | |
| "eval_samples_per_second": 20.316, | |
| "eval_steps_per_second": 2.543, | |
| "eval_wer": 0.09306501875033012, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 8.420731707317073e-05, | |
| "loss": 0.2155, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "eval_loss": 0.13407327234745026, | |
| "eval_runtime": 254.6769, | |
| "eval_samples_per_second": 20.296, | |
| "eval_steps_per_second": 2.54, | |
| "eval_wer": 0.09449110019542598, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 8.393154101995566e-05, | |
| "loss": 0.2108, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "eval_loss": 0.13564249873161316, | |
| "eval_runtime": 254.2947, | |
| "eval_samples_per_second": 20.327, | |
| "eval_steps_per_second": 2.544, | |
| "eval_wer": 0.0948608250145249, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 8.365437915742794e-05, | |
| "loss": 0.2179, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "eval_loss": 0.15698903799057007, | |
| "eval_runtime": 254.2869, | |
| "eval_samples_per_second": 20.327, | |
| "eval_steps_per_second": 2.544, | |
| "eval_wer": 0.08994876670363915, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 10.12, | |
| "learning_rate": 8.337721729490022e-05, | |
| "loss": 0.1988, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 10.12, | |
| "eval_loss": 0.14923857152462006, | |
| "eval_runtime": 254.962, | |
| "eval_samples_per_second": 20.274, | |
| "eval_steps_per_second": 2.538, | |
| "eval_wer": 0.09132203031743516, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 8.310005543237252e-05, | |
| "loss": 0.2051, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "eval_loss": 0.1382753700017929, | |
| "eval_runtime": 254.97, | |
| "eval_samples_per_second": 20.273, | |
| "eval_steps_per_second": 2.538, | |
| "eval_wer": 0.08973749537843977, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "learning_rate": 8.28228935698448e-05, | |
| "loss": 0.2079, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "eval_loss": 0.14029560983181, | |
| "eval_runtime": 255.2219, | |
| "eval_samples_per_second": 20.253, | |
| "eval_steps_per_second": 2.535, | |
| "eval_wer": 0.09132203031743516, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 10.61, | |
| "learning_rate": 8.254573170731708e-05, | |
| "loss": 0.2056, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 10.61, | |
| "eval_loss": 0.13067609071731567, | |
| "eval_runtime": 255.0916, | |
| "eval_samples_per_second": 20.263, | |
| "eval_steps_per_second": 2.536, | |
| "eval_wer": 0.08994876670363915, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 10.78, | |
| "learning_rate": 8.226856984478936e-05, | |
| "loss": 0.2053, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 10.78, | |
| "eval_loss": 0.13401809334754944, | |
| "eval_runtime": 255.8654, | |
| "eval_samples_per_second": 20.202, | |
| "eval_steps_per_second": 2.529, | |
| "eval_wer": 0.09031849152273808, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 10.94, | |
| "learning_rate": 8.199140798226164e-05, | |
| "loss": 0.2015, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 10.94, | |
| "eval_loss": 0.12882278859615326, | |
| "eval_runtime": 263.8909, | |
| "eval_samples_per_second": 19.588, | |
| "eval_steps_per_second": 2.452, | |
| "eval_wer": 0.0923783869434321, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 8.171424611973392e-05, | |
| "loss": 0.2, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "eval_loss": 0.12576742470264435, | |
| "eval_runtime": 255.4818, | |
| "eval_samples_per_second": 20.232, | |
| "eval_steps_per_second": 2.532, | |
| "eval_wer": 0.08683251465694819, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 8.14370842572062e-05, | |
| "loss": 0.2029, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "eval_loss": 0.13859006762504578, | |
| "eval_runtime": 254.423, | |
| "eval_samples_per_second": 20.317, | |
| "eval_steps_per_second": 2.543, | |
| "eval_wer": 0.09000158453493899, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "learning_rate": 8.11599223946785e-05, | |
| "loss": 0.2044, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "eval_loss": 0.138057678937912, | |
| "eval_runtime": 255.1183, | |
| "eval_samples_per_second": 20.261, | |
| "eval_steps_per_second": 2.536, | |
| "eval_wer": 0.09185020863043364, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 8.088414634146342e-05, | |
| "loss": 0.1943, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "eval_loss": 0.1461963802576065, | |
| "eval_runtime": 255.5721, | |
| "eval_samples_per_second": 20.225, | |
| "eval_steps_per_second": 2.532, | |
| "eval_wer": 0.09206147995563302, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 11.77, | |
| "learning_rate": 8.06069844789357e-05, | |
| "loss": 0.2072, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 11.77, | |
| "eval_loss": 0.14551697671413422, | |
| "eval_runtime": 256.1094, | |
| "eval_samples_per_second": 20.183, | |
| "eval_steps_per_second": 2.526, | |
| "eval_wer": 0.08846986742724344, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 8.032982261640798e-05, | |
| "loss": 0.1998, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "eval_loss": 0.13519984483718872, | |
| "eval_runtime": 255.2141, | |
| "eval_samples_per_second": 20.254, | |
| "eval_steps_per_second": 2.535, | |
| "eval_wer": 0.09190302646173348, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 12.11, | |
| "learning_rate": 8.00540465631929e-05, | |
| "loss": 0.1952, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 12.11, | |
| "eval_loss": 0.1399640440940857, | |
| "eval_runtime": 254.8364, | |
| "eval_samples_per_second": 20.284, | |
| "eval_steps_per_second": 2.539, | |
| "eval_wer": 0.090688216341837, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "learning_rate": 7.977688470066519e-05, | |
| "loss": 0.1932, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 12.27, | |
| "eval_loss": 0.13122260570526123, | |
| "eval_runtime": 255.4641, | |
| "eval_samples_per_second": 20.234, | |
| "eval_steps_per_second": 2.533, | |
| "eval_wer": 0.09084666983573654, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 7.949972283813748e-05, | |
| "loss": 0.1885, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "eval_loss": 0.14805012941360474, | |
| "eval_runtime": 255.9292, | |
| "eval_samples_per_second": 20.197, | |
| "eval_steps_per_second": 2.528, | |
| "eval_wer": 0.08883959224634237, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "learning_rate": 7.922256097560976e-05, | |
| "loss": 0.1904, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "eval_loss": 0.13773396611213684, | |
| "eval_runtime": 254.593, | |
| "eval_samples_per_second": 20.303, | |
| "eval_steps_per_second": 2.541, | |
| "eval_wer": 0.08825859610204405, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "learning_rate": 7.894539911308204e-05, | |
| "loss": 0.1924, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "eval_loss": 0.14221470057964325, | |
| "eval_runtime": 254.58, | |
| "eval_samples_per_second": 20.304, | |
| "eval_steps_per_second": 2.541, | |
| "eval_wer": 0.09026567369143823, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 7.866823725055434e-05, | |
| "loss": 0.188, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "eval_loss": 0.14350585639476776, | |
| "eval_runtime": 258.9085, | |
| "eval_samples_per_second": 19.965, | |
| "eval_steps_per_second": 2.499, | |
| "eval_wer": 0.08540643321185232, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 7.839107538802661e-05, | |
| "loss": 0.1877, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "eval_loss": 0.1520785242319107, | |
| "eval_runtime": 255.8963, | |
| "eval_samples_per_second": 20.2, | |
| "eval_steps_per_second": 2.528, | |
| "eval_wer": 0.08899804574024191, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "learning_rate": 7.811391352549889e-05, | |
| "loss": 0.1825, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "eval_loss": 0.13483111560344696, | |
| "eval_runtime": 256.5689, | |
| "eval_samples_per_second": 20.147, | |
| "eval_steps_per_second": 2.522, | |
| "eval_wer": 0.08905086357154175, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 13.43, | |
| "learning_rate": 7.783675166297117e-05, | |
| "loss": 0.185, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 13.43, | |
| "eval_loss": 0.13759800791740417, | |
| "eval_runtime": 258.0191, | |
| "eval_samples_per_second": 20.033, | |
| "eval_steps_per_second": 2.508, | |
| "eval_wer": 0.08672687899434849, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 7.755958980044346e-05, | |
| "loss": 0.1805, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "eval_loss": 0.14212605357170105, | |
| "eval_runtime": 258.5566, | |
| "eval_samples_per_second": 19.992, | |
| "eval_steps_per_second": 2.502, | |
| "eval_wer": 0.0883114139333439, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 7.728242793791574e-05, | |
| "loss": 0.186, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "eval_loss": 0.1396447867155075, | |
| "eval_runtime": 257.807, | |
| "eval_samples_per_second": 20.05, | |
| "eval_steps_per_second": 2.51, | |
| "eval_wer": 0.08514234405535309, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 7.700526607538803e-05, | |
| "loss": 0.1869, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "eval_loss": 0.14811939001083374, | |
| "eval_runtime": 257.7698, | |
| "eval_samples_per_second": 20.053, | |
| "eval_steps_per_second": 2.51, | |
| "eval_wer": 0.08456134791105477, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 7.672949002217296e-05, | |
| "loss": 0.1808, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "eval_loss": 0.15346239507198334, | |
| "eval_runtime": 259.8127, | |
| "eval_samples_per_second": 19.895, | |
| "eval_steps_per_second": 2.49, | |
| "eval_wer": 0.08503670839275339, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "learning_rate": 7.645232815964524e-05, | |
| "loss": 0.1775, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "eval_loss": 0.14250528812408447, | |
| "eval_runtime": 257.4388, | |
| "eval_samples_per_second": 20.079, | |
| "eval_steps_per_second": 2.513, | |
| "eval_wer": 0.0876247821264459, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 14.43, | |
| "learning_rate": 7.617516629711752e-05, | |
| "loss": 0.1773, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 14.43, | |
| "eval_loss": 0.14766837656497955, | |
| "eval_runtime": 258.0221, | |
| "eval_samples_per_second": 20.033, | |
| "eval_steps_per_second": 2.508, | |
| "eval_wer": 0.08471980140495432, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "learning_rate": 7.58980044345898e-05, | |
| "loss": 0.1851, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "eval_loss": 0.15123723447322845, | |
| "eval_runtime": 262.1208, | |
| "eval_samples_per_second": 19.72, | |
| "eval_steps_per_second": 2.468, | |
| "eval_wer": 0.08667406116304864, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "learning_rate": 7.562084257206209e-05, | |
| "loss": 0.1775, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 14.76, | |
| "eval_loss": 0.14902031421661377, | |
| "eval_runtime": 257.8432, | |
| "eval_samples_per_second": 20.047, | |
| "eval_steps_per_second": 2.509, | |
| "eval_wer": 0.08329371995985844, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "learning_rate": 7.534368070953437e-05, | |
| "loss": 0.1802, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_loss": 0.15108011662960052, | |
| "eval_runtime": 257.3237, | |
| "eval_samples_per_second": 20.088, | |
| "eval_steps_per_second": 2.514, | |
| "eval_wer": 0.08709660381344742, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 15.09, | |
| "learning_rate": 7.50679046563193e-05, | |
| "loss": 0.1829, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 15.09, | |
| "eval_loss": 0.14215655624866486, | |
| "eval_runtime": 258.1845, | |
| "eval_samples_per_second": 20.021, | |
| "eval_steps_per_second": 2.506, | |
| "eval_wer": 0.0859346115248508, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 15.26, | |
| "learning_rate": 7.479074279379158e-05, | |
| "loss": 0.1704, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 15.26, | |
| "eval_loss": 0.1536380648612976, | |
| "eval_runtime": 258.2175, | |
| "eval_samples_per_second": 20.018, | |
| "eval_steps_per_second": 2.506, | |
| "eval_wer": 0.08535361538055247, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 15.42, | |
| "learning_rate": 7.451358093126386e-05, | |
| "loss": 0.1707, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 15.42, | |
| "eval_loss": 0.15412335097789764, | |
| "eval_runtime": 259.6526, | |
| "eval_samples_per_second": 19.907, | |
| "eval_steps_per_second": 2.492, | |
| "eval_wer": 0.08366344477895737, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 7.423641906873615e-05, | |
| "loss": 0.1716, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "eval_loss": 0.15734080970287323, | |
| "eval_runtime": 256.5213, | |
| "eval_samples_per_second": 20.15, | |
| "eval_steps_per_second": 2.522, | |
| "eval_wer": 0.08419162309195584, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 7.395925720620843e-05, | |
| "loss": 0.1755, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "eval_loss": 0.1497374176979065, | |
| "eval_runtime": 255.8623, | |
| "eval_samples_per_second": 20.202, | |
| "eval_steps_per_second": 2.529, | |
| "eval_wer": 0.08408598742935615, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 15.92, | |
| "learning_rate": 7.368209534368071e-05, | |
| "loss": 0.1695, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 15.92, | |
| "eval_loss": 0.14581099152565002, | |
| "eval_runtime": 256.4224, | |
| "eval_samples_per_second": 20.158, | |
| "eval_steps_per_second": 2.523, | |
| "eval_wer": 0.08371626261025722, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 16.09, | |
| "learning_rate": 7.340493348115299e-05, | |
| "loss": 0.1761, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 16.09, | |
| "eval_loss": 0.14683474600315094, | |
| "eval_runtime": 271.7581, | |
| "eval_samples_per_second": 19.021, | |
| "eval_steps_per_second": 2.381, | |
| "eval_wer": 0.08545925104315216, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "learning_rate": 7.312777161862528e-05, | |
| "loss": 0.1667, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "eval_loss": 0.1606747955083847, | |
| "eval_runtime": 271.8508, | |
| "eval_samples_per_second": 19.014, | |
| "eval_steps_per_second": 2.38, | |
| "eval_wer": 0.08751914646384619, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 16.42, | |
| "learning_rate": 7.285060975609756e-05, | |
| "loss": 0.1667, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 16.42, | |
| "eval_loss": 0.14115694165229797, | |
| "eval_runtime": 271.6689, | |
| "eval_samples_per_second": 19.027, | |
| "eval_steps_per_second": 2.382, | |
| "eval_wer": 0.08524797971795278, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 16.58, | |
| "learning_rate": 7.257344789356985e-05, | |
| "loss": 0.1653, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 16.58, | |
| "eval_loss": 0.13544563949108124, | |
| "eval_runtime": 271.5302, | |
| "eval_samples_per_second": 19.037, | |
| "eval_steps_per_second": 2.383, | |
| "eval_wer": 0.08477261923625416, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 16.75, | |
| "learning_rate": 7.229628603104214e-05, | |
| "loss": 0.1695, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 16.75, | |
| "eval_loss": 0.1354389786720276, | |
| "eval_runtime": 271.5697, | |
| "eval_samples_per_second": 19.034, | |
| "eval_steps_per_second": 2.382, | |
| "eval_wer": 0.08350499128505784, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "learning_rate": 7.201912416851442e-05, | |
| "loss": 0.171, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 16.91, | |
| "eval_loss": 0.14289897680282593, | |
| "eval_runtime": 258.0663, | |
| "eval_samples_per_second": 20.03, | |
| "eval_steps_per_second": 2.507, | |
| "eval_wer": 0.08435007658585539, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 17.08, | |
| "learning_rate": 7.17419623059867e-05, | |
| "loss": 0.167, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 17.08, | |
| "eval_loss": 0.13994231820106506, | |
| "eval_runtime": 256.5044, | |
| "eval_samples_per_second": 20.152, | |
| "eval_steps_per_second": 2.522, | |
| "eval_wer": 0.08207890983996197, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 7.146480044345898e-05, | |
| "loss": 0.1595, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "eval_loss": 0.16428013145923615, | |
| "eval_runtime": 256.5622, | |
| "eval_samples_per_second": 20.147, | |
| "eval_steps_per_second": 2.522, | |
| "eval_wer": 0.08192045634606243, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 17.41, | |
| "learning_rate": 7.118763858093127e-05, | |
| "loss": 0.1565, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 17.41, | |
| "eval_loss": 0.1530633270740509, | |
| "eval_runtime": 258.23, | |
| "eval_samples_per_second": 20.017, | |
| "eval_steps_per_second": 2.506, | |
| "eval_wer": 0.08456134791105477, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 17.58, | |
| "learning_rate": 7.091047671840355e-05, | |
| "loss": 0.1589, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 17.58, | |
| "eval_loss": 0.1481485366821289, | |
| "eval_runtime": 257.1667, | |
| "eval_samples_per_second": 20.1, | |
| "eval_steps_per_second": 2.516, | |
| "eval_wer": 0.08102255321396504, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 17.74, | |
| "learning_rate": 7.063331485587583e-05, | |
| "loss": 0.1602, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 17.74, | |
| "eval_loss": 0.16114427149295807, | |
| "eval_runtime": 257.6644, | |
| "eval_samples_per_second": 20.061, | |
| "eval_steps_per_second": 2.511, | |
| "eval_wer": 0.07838166164897269, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 7.035615299334812e-05, | |
| "loss": 0.1622, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "eval_loss": 0.14328357577323914, | |
| "eval_runtime": 258.6193, | |
| "eval_samples_per_second": 19.987, | |
| "eval_steps_per_second": 2.502, | |
| "eval_wer": 0.0832409021285586, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 7.00789911308204e-05, | |
| "loss": 0.1629, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "eval_loss": 0.14952301979064941, | |
| "eval_runtime": 253.7518, | |
| "eval_samples_per_second": 20.37, | |
| "eval_steps_per_second": 2.55, | |
| "eval_wer": 0.08202609200866212, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 6.980182926829268e-05, | |
| "loss": 0.1542, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "eval_loss": 0.1603306531906128, | |
| "eval_runtime": 252.9767, | |
| "eval_samples_per_second": 20.433, | |
| "eval_steps_per_second": 2.558, | |
| "eval_wer": 0.07864575080547193, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "learning_rate": 6.952466740576497e-05, | |
| "loss": 0.1577, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "eval_loss": 0.15311960875988007, | |
| "eval_runtime": 253.1091, | |
| "eval_samples_per_second": 20.422, | |
| "eval_steps_per_second": 2.556, | |
| "eval_wer": 0.08123382453916442, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 18.57, | |
| "learning_rate": 6.924750554323726e-05, | |
| "loss": 0.1592, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 18.57, | |
| "eval_loss": 0.15086284279823303, | |
| "eval_runtime": 257.495, | |
| "eval_samples_per_second": 20.074, | |
| "eval_steps_per_second": 2.513, | |
| "eval_wer": 0.08170918502086304, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 18.74, | |
| "learning_rate": 6.897172949002217e-05, | |
| "loss": 0.1608, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 18.74, | |
| "eval_loss": 0.14557667076587677, | |
| "eval_runtime": 255.6435, | |
| "eval_samples_per_second": 20.22, | |
| "eval_steps_per_second": 2.531, | |
| "eval_wer": 0.0799661965879681, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "learning_rate": 6.869456762749445e-05, | |
| "loss": 0.1573, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "eval_loss": 0.15521085262298584, | |
| "eval_runtime": 254.7778, | |
| "eval_samples_per_second": 20.288, | |
| "eval_steps_per_second": 2.539, | |
| "eval_wer": 0.08081128188876564, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 19.07, | |
| "learning_rate": 6.841740576496674e-05, | |
| "loss": 0.1559, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 19.07, | |
| "eval_loss": 0.1598125696182251, | |
| "eval_runtime": 255.4991, | |
| "eval_samples_per_second": 20.231, | |
| "eval_steps_per_second": 2.532, | |
| "eval_wer": 0.08123382453916442, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 19.24, | |
| "learning_rate": 6.814024390243903e-05, | |
| "loss": 0.1518, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 19.24, | |
| "eval_loss": 0.15756739675998688, | |
| "eval_runtime": 255.2152, | |
| "eval_samples_per_second": 20.253, | |
| "eval_steps_per_second": 2.535, | |
| "eval_wer": 0.08229018116516136, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 19.4, | |
| "learning_rate": 6.78630820399113e-05, | |
| "loss": 0.1583, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 19.4, | |
| "eval_loss": 0.1478932946920395, | |
| "eval_runtime": 254.8478, | |
| "eval_samples_per_second": 20.283, | |
| "eval_steps_per_second": 2.539, | |
| "eval_wer": 0.0790682934558707, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 6.75859201773836e-05, | |
| "loss": 0.1521, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "eval_loss": 0.15390987694263458, | |
| "eval_runtime": 255.3412, | |
| "eval_samples_per_second": 20.244, | |
| "eval_steps_per_second": 2.534, | |
| "eval_wer": 0.08144509586436381, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 19.73, | |
| "learning_rate": 6.730875831485588e-05, | |
| "loss": 0.1504, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 19.73, | |
| "eval_loss": 0.15799568593502045, | |
| "eval_runtime": 255.2877, | |
| "eval_samples_per_second": 20.248, | |
| "eval_steps_per_second": 2.534, | |
| "eval_wer": 0.07980774309406856, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 19.9, | |
| "learning_rate": 6.703159645232816e-05, | |
| "loss": 0.1591, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 19.9, | |
| "eval_loss": 0.14647792279720306, | |
| "eval_runtime": 255.0201, | |
| "eval_samples_per_second": 20.269, | |
| "eval_steps_per_second": 2.537, | |
| "eval_wer": 0.07700839803517667, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 20.07, | |
| "learning_rate": 6.675443458980046e-05, | |
| "loss": 0.1535, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 20.07, | |
| "eval_loss": 0.1589883714914322, | |
| "eval_runtime": 255.7034, | |
| "eval_samples_per_second": 20.215, | |
| "eval_steps_per_second": 2.53, | |
| "eval_wer": 0.07669149104737759, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 20.23, | |
| "learning_rate": 6.647727272727274e-05, | |
| "loss": 0.146, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 20.23, | |
| "eval_loss": 0.14599309861660004, | |
| "eval_runtime": 254.7694, | |
| "eval_samples_per_second": 20.289, | |
| "eval_steps_per_second": 2.54, | |
| "eval_wer": 0.07875138646807162, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 20.4, | |
| "learning_rate": 6.6200110864745e-05, | |
| "loss": 0.1492, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 20.4, | |
| "eval_loss": 0.14993605017662048, | |
| "eval_runtime": 254.9593, | |
| "eval_samples_per_second": 20.274, | |
| "eval_steps_per_second": 2.538, | |
| "eval_wer": 0.07706121586647652, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 20.56, | |
| "learning_rate": 6.592294900221729e-05, | |
| "loss": 0.1508, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 20.56, | |
| "eval_loss": 0.1447875052690506, | |
| "eval_runtime": 255.7358, | |
| "eval_samples_per_second": 20.212, | |
| "eval_steps_per_second": 2.53, | |
| "eval_wer": 0.07975492526276871, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 20.73, | |
| "learning_rate": 6.564578713968958e-05, | |
| "loss": 0.1525, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 20.73, | |
| "eval_loss": 0.14607439935207367, | |
| "eval_runtime": 255.9294, | |
| "eval_samples_per_second": 20.197, | |
| "eval_steps_per_second": 2.528, | |
| "eval_wer": 0.07838166164897269, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 20.89, | |
| "learning_rate": 6.53700110864745e-05, | |
| "loss": 0.1503, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 20.89, | |
| "eval_loss": 0.1411682814359665, | |
| "eval_runtime": 255.8366, | |
| "eval_samples_per_second": 20.204, | |
| "eval_steps_per_second": 2.529, | |
| "eval_wer": 0.07970210743146887, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 21.06, | |
| "learning_rate": 6.509284922394679e-05, | |
| "loss": 0.1497, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 21.06, | |
| "eval_loss": 0.14832888543605804, | |
| "eval_runtime": 255.5517, | |
| "eval_samples_per_second": 20.227, | |
| "eval_steps_per_second": 2.532, | |
| "eval_wer": 0.07943801827496963, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 21.23, | |
| "learning_rate": 6.481568736141908e-05, | |
| "loss": 0.1444, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 21.23, | |
| "eval_loss": 0.16129909455776215, | |
| "eval_runtime": 255.967, | |
| "eval_samples_per_second": 20.194, | |
| "eval_steps_per_second": 2.528, | |
| "eval_wer": 0.07864575080547193, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 21.39, | |
| "learning_rate": 6.453852549889136e-05, | |
| "loss": 0.1438, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 21.39, | |
| "eval_loss": 0.1477702409029007, | |
| "eval_runtime": 255.4815, | |
| "eval_samples_per_second": 20.232, | |
| "eval_steps_per_second": 2.532, | |
| "eval_wer": 0.07890983996197116, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 21.56, | |
| "learning_rate": 6.426136363636364e-05, | |
| "loss": 0.1439, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 21.56, | |
| "eval_loss": 0.15728013217449188, | |
| "eval_runtime": 255.4616, | |
| "eval_samples_per_second": 20.234, | |
| "eval_steps_per_second": 2.533, | |
| "eval_wer": 0.07774784767337453, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 21.72, | |
| "learning_rate": 6.398420177383592e-05, | |
| "loss": 0.1455, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 21.72, | |
| "eval_loss": 0.14868445694446564, | |
| "eval_runtime": 255.9049, | |
| "eval_samples_per_second": 20.199, | |
| "eval_steps_per_second": 2.528, | |
| "eval_wer": 0.0790682934558707, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 21.89, | |
| "learning_rate": 6.37070399113082e-05, | |
| "loss": 0.1395, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 21.89, | |
| "eval_loss": 0.16429665684700012, | |
| "eval_runtime": 262.3659, | |
| "eval_samples_per_second": 19.701, | |
| "eval_steps_per_second": 2.466, | |
| "eval_wer": 0.07600485924047959, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 22.06, | |
| "learning_rate": 6.342987804878049e-05, | |
| "loss": 0.1428, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 22.06, | |
| "eval_loss": 0.1581258475780487, | |
| "eval_runtime": 255.8292, | |
| "eval_samples_per_second": 20.205, | |
| "eval_steps_per_second": 2.529, | |
| "eval_wer": 0.0781703903237733, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 6.315271618625277e-05, | |
| "loss": 0.1342, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "eval_loss": 0.16277597844600677, | |
| "eval_runtime": 259.5604, | |
| "eval_samples_per_second": 19.914, | |
| "eval_steps_per_second": 2.493, | |
| "eval_wer": 0.0773781228542756, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 22.39, | |
| "learning_rate": 6.28769401330377e-05, | |
| "loss": 0.1401, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 22.39, | |
| "eval_loss": 0.1531515270471573, | |
| "eval_runtime": 260.5139, | |
| "eval_samples_per_second": 19.842, | |
| "eval_steps_per_second": 2.484, | |
| "eval_wer": 0.07859293297417208, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "learning_rate": 6.259977827050998e-05, | |
| "loss": 0.1401, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 22.55, | |
| "eval_loss": 0.15395356714725494, | |
| "eval_runtime": 257.8197, | |
| "eval_samples_per_second": 20.049, | |
| "eval_steps_per_second": 2.51, | |
| "eval_wer": 0.07727248719167591, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 6.232261640798226e-05, | |
| "loss": 0.1397, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "eval_loss": 0.1657487452030182, | |
| "eval_runtime": 258.5849, | |
| "eval_samples_per_second": 19.99, | |
| "eval_steps_per_second": 2.502, | |
| "eval_wer": 0.07774784767337453, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 22.89, | |
| "learning_rate": 6.204545454545455e-05, | |
| "loss": 0.1396, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 22.89, | |
| "eval_loss": 0.1595001220703125, | |
| "eval_runtime": 258.8028, | |
| "eval_samples_per_second": 19.973, | |
| "eval_steps_per_second": 2.5, | |
| "eval_wer": 0.07695558020387683, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 23.05, | |
| "learning_rate": 6.176829268292683e-05, | |
| "loss": 0.1425, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 23.05, | |
| "eval_loss": 0.14454737305641174, | |
| "eval_runtime": 257.5774, | |
| "eval_samples_per_second": 20.068, | |
| "eval_steps_per_second": 2.512, | |
| "eval_wer": 0.07695558020387683, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 23.22, | |
| "learning_rate": 6.149113082039911e-05, | |
| "loss": 0.1343, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 23.22, | |
| "eval_loss": 0.15258438885211945, | |
| "eval_runtime": 257.4198, | |
| "eval_samples_per_second": 20.08, | |
| "eval_steps_per_second": 2.513, | |
| "eval_wer": 0.07700839803517667, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 23.38, | |
| "learning_rate": 6.12139689578714e-05, | |
| "loss": 0.1388, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 23.38, | |
| "eval_loss": 0.15189868211746216, | |
| "eval_runtime": 261.1531, | |
| "eval_samples_per_second": 19.793, | |
| "eval_steps_per_second": 2.477, | |
| "eval_wer": 0.07447314213278403, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 23.55, | |
| "learning_rate": 6.0936807095343684e-05, | |
| "loss": 0.1364, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 23.55, | |
| "eval_loss": 0.15030239522457123, | |
| "eval_runtime": 259.6413, | |
| "eval_samples_per_second": 19.908, | |
| "eval_steps_per_second": 2.492, | |
| "eval_wer": 0.07415623514498494, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 23.71, | |
| "learning_rate": 6.0659645232815965e-05, | |
| "loss": 0.1444, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 23.71, | |
| "eval_loss": 0.16646933555603027, | |
| "eval_runtime": 260.1679, | |
| "eval_samples_per_second": 19.868, | |
| "eval_steps_per_second": 2.487, | |
| "eval_wer": 0.07875138646807162, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 23.88, | |
| "learning_rate": 6.038248337028826e-05, | |
| "loss": 0.1361, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 23.88, | |
| "eval_loss": 0.15915772318840027, | |
| "eval_runtime": 259.5414, | |
| "eval_samples_per_second": 19.916, | |
| "eval_steps_per_second": 2.493, | |
| "eval_wer": 0.0757935879152802, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 24.05, | |
| "learning_rate": 6.0105321507760534e-05, | |
| "loss": 0.1398, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 24.05, | |
| "eval_loss": 0.1606004387140274, | |
| "eval_runtime": 259.8476, | |
| "eval_samples_per_second": 19.892, | |
| "eval_steps_per_second": 2.49, | |
| "eval_wer": 0.07632176622827867, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 24.21, | |
| "learning_rate": 5.9828159645232815e-05, | |
| "loss": 0.1322, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 24.21, | |
| "eval_loss": 0.1486821323633194, | |
| "eval_runtime": 259.5122, | |
| "eval_samples_per_second": 19.918, | |
| "eval_steps_per_second": 2.493, | |
| "eval_wer": 0.07848729731157239, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 24.38, | |
| "learning_rate": 5.9550997782705096e-05, | |
| "loss": 0.1309, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 24.38, | |
| "eval_loss": 0.16220000386238098, | |
| "eval_runtime": 259.2803, | |
| "eval_samples_per_second": 19.936, | |
| "eval_steps_per_second": 2.495, | |
| "eval_wer": 0.07626894839697881, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 24.54, | |
| "learning_rate": 5.927383592017739e-05, | |
| "loss": 0.1351, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 24.54, | |
| "eval_loss": 0.17341530323028564, | |
| "eval_runtime": 262.8143, | |
| "eval_samples_per_second": 19.668, | |
| "eval_steps_per_second": 2.462, | |
| "eval_wer": 0.07795911899857391, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 24.71, | |
| "learning_rate": 5.899667405764967e-05, | |
| "loss": 0.1298, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 24.71, | |
| "eval_loss": 0.1510027050971985, | |
| "eval_runtime": 263.1767, | |
| "eval_samples_per_second": 19.641, | |
| "eval_steps_per_second": 2.458, | |
| "eval_wer": 0.07563513442138066, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 24.88, | |
| "learning_rate": 5.871951219512195e-05, | |
| "loss": 0.1369, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 24.88, | |
| "eval_loss": 0.13624520599842072, | |
| "eval_runtime": 263.8718, | |
| "eval_samples_per_second": 19.589, | |
| "eval_steps_per_second": 2.452, | |
| "eval_wer": 0.07626894839697881, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 25.04, | |
| "learning_rate": 5.844235033259424e-05, | |
| "loss": 0.1341, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 25.04, | |
| "eval_loss": 0.15082810819149017, | |
| "eval_runtime": 261.0919, | |
| "eval_samples_per_second": 19.798, | |
| "eval_steps_per_second": 2.478, | |
| "eval_wer": 0.07854011514287224, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 25.21, | |
| "learning_rate": 5.816518847006652e-05, | |
| "loss": 0.1249, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 25.21, | |
| "eval_loss": 0.16026806831359863, | |
| "eval_runtime": 260.2227, | |
| "eval_samples_per_second": 19.864, | |
| "eval_steps_per_second": 2.486, | |
| "eval_wer": 0.07558231659008081, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 25.37, | |
| "learning_rate": 5.78880266075388e-05, | |
| "loss": 0.129, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 25.37, | |
| "eval_loss": 0.16147717833518982, | |
| "eval_runtime": 258.8644, | |
| "eval_samples_per_second": 19.968, | |
| "eval_steps_per_second": 2.499, | |
| "eval_wer": 0.07457877779538372, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 25.54, | |
| "learning_rate": 5.7610864745011084e-05, | |
| "loss": 0.1336, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 25.54, | |
| "eval_loss": 0.15992993116378784, | |
| "eval_runtime": 258.9913, | |
| "eval_samples_per_second": 19.958, | |
| "eval_steps_per_second": 2.498, | |
| "eval_wer": 0.07505413827708235, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 25.7, | |
| "learning_rate": 5.733370288248338e-05, | |
| "loss": 0.127, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 25.7, | |
| "eval_loss": 0.17056865990161896, | |
| "eval_runtime": 259.4613, | |
| "eval_samples_per_second": 19.922, | |
| "eval_steps_per_second": 2.494, | |
| "eval_wer": 0.07484286695188296, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 25.87, | |
| "learning_rate": 5.705654101995565e-05, | |
| "loss": 0.126, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 25.87, | |
| "eval_loss": 0.1541663110256195, | |
| "eval_runtime": 258.8605, | |
| "eval_samples_per_second": 19.968, | |
| "eval_steps_per_second": 2.499, | |
| "eval_wer": 0.07442032430148418, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 26.04, | |
| "learning_rate": 5.6780764966740575e-05, | |
| "loss": 0.124, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 26.04, | |
| "eval_loss": 0.16358500719070435, | |
| "eval_runtime": 258.6242, | |
| "eval_samples_per_second": 19.987, | |
| "eval_steps_per_second": 2.502, | |
| "eval_wer": 0.07531822743358157, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 26.2, | |
| "learning_rate": 5.650360310421286e-05, | |
| "loss": 0.1268, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 26.2, | |
| "eval_loss": 0.16622310876846313, | |
| "eval_runtime": 258.7306, | |
| "eval_samples_per_second": 19.978, | |
| "eval_steps_per_second": 2.501, | |
| "eval_wer": 0.07220197538689062, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 26.37, | |
| "learning_rate": 5.6227827050997785e-05, | |
| "loss": 0.1286, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 26.37, | |
| "eval_loss": 0.16970515251159668, | |
| "eval_runtime": 258.9239, | |
| "eval_samples_per_second": 19.963, | |
| "eval_steps_per_second": 2.499, | |
| "eval_wer": 0.07257170020598955, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 26.53, | |
| "learning_rate": 5.5950665188470066e-05, | |
| "loss": 0.1299, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 26.53, | |
| "eval_loss": 0.17085173726081848, | |
| "eval_runtime": 259.6854, | |
| "eval_samples_per_second": 19.905, | |
| "eval_steps_per_second": 2.491, | |
| "eval_wer": 0.07167379707389214, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 26.7, | |
| "learning_rate": 5.5673503325942354e-05, | |
| "loss": 0.1303, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 26.7, | |
| "eval_loss": 0.16575023531913757, | |
| "eval_runtime": 259.4515, | |
| "eval_samples_per_second": 19.923, | |
| "eval_steps_per_second": 2.494, | |
| "eval_wer": 0.07352242116938679, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 26.87, | |
| "learning_rate": 5.5396341463414635e-05, | |
| "loss": 0.1246, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 26.87, | |
| "eval_loss": 0.16010864078998566, | |
| "eval_runtime": 259.7317, | |
| "eval_samples_per_second": 19.901, | |
| "eval_steps_per_second": 2.491, | |
| "eval_wer": 0.07204352189299107, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 27.03, | |
| "learning_rate": 5.5119179600886916e-05, | |
| "loss": 0.1234, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 27.03, | |
| "eval_loss": 0.1471298187971115, | |
| "eval_runtime": 259.2276, | |
| "eval_samples_per_second": 19.94, | |
| "eval_steps_per_second": 2.496, | |
| "eval_wer": 0.07214915755559077, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 5.484201773835921e-05, | |
| "loss": 0.1179, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "eval_loss": 0.16308201849460602, | |
| "eval_runtime": 259.2656, | |
| "eval_samples_per_second": 19.937, | |
| "eval_steps_per_second": 2.496, | |
| "eval_wer": 0.07114561876089368, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 5.456485587583149e-05, | |
| "loss": 0.1218, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "eval_loss": 0.1502005010843277, | |
| "eval_runtime": 259.8271, | |
| "eval_samples_per_second": 19.894, | |
| "eval_steps_per_second": 2.49, | |
| "eval_wer": 0.07199070406169122, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 27.53, | |
| "learning_rate": 5.4287694013303766e-05, | |
| "loss": 0.1249, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 27.53, | |
| "eval_loss": 0.15461181104183197, | |
| "eval_runtime": 271.8472, | |
| "eval_samples_per_second": 19.014, | |
| "eval_steps_per_second": 2.38, | |
| "eval_wer": 0.07214915755559077, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 5.401053215077606e-05, | |
| "loss": 0.1199, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "eval_loss": 0.14347407221794128, | |
| "eval_runtime": 271.4782, | |
| "eval_samples_per_second": 19.04, | |
| "eval_steps_per_second": 2.383, | |
| "eval_wer": 0.07304706068768817, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 27.86, | |
| "learning_rate": 5.373337028824834e-05, | |
| "loss": 0.1199, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 27.86, | |
| "eval_loss": 0.16159255802631378, | |
| "eval_runtime": 272.7821, | |
| "eval_samples_per_second": 18.949, | |
| "eval_steps_per_second": 2.372, | |
| "eval_wer": 0.07262451803728939, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 28.03, | |
| "learning_rate": 5.345620842572062e-05, | |
| "loss": 0.1213, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 28.03, | |
| "eval_loss": 0.1633623242378235, | |
| "eval_runtime": 267.8584, | |
| "eval_samples_per_second": 19.298, | |
| "eval_steps_per_second": 2.415, | |
| "eval_wer": 0.07188506839909153, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 28.19, | |
| "learning_rate": 5.3179046563192904e-05, | |
| "loss": 0.1166, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 28.19, | |
| "eval_loss": 0.15763157606124878, | |
| "eval_runtime": 258.2022, | |
| "eval_samples_per_second": 20.019, | |
| "eval_steps_per_second": 2.506, | |
| "eval_wer": 0.07278297153118893, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 28.36, | |
| "learning_rate": 5.290188470066519e-05, | |
| "loss": 0.1123, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 28.36, | |
| "eval_loss": 0.16512486338615417, | |
| "eval_runtime": 256.1777, | |
| "eval_samples_per_second": 20.177, | |
| "eval_steps_per_second": 2.526, | |
| "eval_wer": 0.07500132044578249, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "learning_rate": 5.262472283813747e-05, | |
| "loss": 0.121, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "eval_loss": 0.15457598865032196, | |
| "eval_runtime": 278.1382, | |
| "eval_samples_per_second": 18.584, | |
| "eval_steps_per_second": 2.326, | |
| "eval_wer": 0.07452595996408387, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 28.69, | |
| "learning_rate": 5.2347560975609754e-05, | |
| "loss": 0.1197, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 28.69, | |
| "eval_loss": 0.1601417064666748, | |
| "eval_runtime": 278.0073, | |
| "eval_samples_per_second": 18.593, | |
| "eval_steps_per_second": 2.327, | |
| "eval_wer": 0.07315269635028786, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "learning_rate": 5.207039911308205e-05, | |
| "loss": 0.1168, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "eval_loss": 0.16127680242061615, | |
| "eval_runtime": 278.2559, | |
| "eval_samples_per_second": 18.576, | |
| "eval_steps_per_second": 2.325, | |
| "eval_wer": 0.07468441345798342, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 5.179323725055433e-05, | |
| "loss": 0.1205, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "eval_loss": 0.15306903421878815, | |
| "eval_runtime": 276.9929, | |
| "eval_samples_per_second": 18.661, | |
| "eval_steps_per_second": 2.336, | |
| "eval_wer": 0.07346960333808694, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 29.19, | |
| "learning_rate": 5.151607538802661e-05, | |
| "loss": 0.1165, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 29.19, | |
| "eval_loss": 0.15544754266738892, | |
| "eval_runtime": 276.1997, | |
| "eval_samples_per_second": 18.715, | |
| "eval_steps_per_second": 2.343, | |
| "eval_wer": 0.07431468863888449, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 29.35, | |
| "learning_rate": 5.1238913525498885e-05, | |
| "loss": 0.1198, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 29.35, | |
| "eval_loss": 0.15731526911258698, | |
| "eval_runtime": 276.5622, | |
| "eval_samples_per_second": 18.69, | |
| "eval_steps_per_second": 2.339, | |
| "eval_wer": 0.07288860719378862, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 29.52, | |
| "learning_rate": 5.0963137472283814e-05, | |
| "loss": 0.1192, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 29.52, | |
| "eval_loss": 0.1620793640613556, | |
| "eval_runtime": 278.1544, | |
| "eval_samples_per_second": 18.583, | |
| "eval_steps_per_second": 2.326, | |
| "eval_wer": 0.07209633972429091, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 29.68, | |
| "learning_rate": 5.0685975609756095e-05, | |
| "loss": 0.1184, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 29.68, | |
| "eval_loss": 0.15125353634357452, | |
| "eval_runtime": 279.7716, | |
| "eval_samples_per_second": 18.476, | |
| "eval_steps_per_second": 2.313, | |
| "eval_wer": 0.07177943273649184, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 29.85, | |
| "learning_rate": 5.0408813747228376e-05, | |
| "loss": 0.1141, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 29.85, | |
| "eval_loss": 0.15804697573184967, | |
| "eval_runtime": 279.7652, | |
| "eval_samples_per_second": 18.476, | |
| "eval_steps_per_second": 2.313, | |
| "eval_wer": 0.07109280092959383, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "learning_rate": 5.013165188470067e-05, | |
| "loss": 0.1147, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "eval_loss": 0.15915371477603912, | |
| "eval_runtime": 260.2704, | |
| "eval_samples_per_second": 19.86, | |
| "eval_steps_per_second": 2.486, | |
| "eval_wer": 0.0700364443035969, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 30.18, | |
| "learning_rate": 4.985449002217295e-05, | |
| "loss": 0.1124, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 30.18, | |
| "eval_loss": 0.17016097903251648, | |
| "eval_runtime": 265.3722, | |
| "eval_samples_per_second": 19.478, | |
| "eval_steps_per_second": 2.438, | |
| "eval_wer": 0.07214915755559077, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 30.35, | |
| "learning_rate": 4.957732815964524e-05, | |
| "loss": 0.1128, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 30.35, | |
| "eval_loss": 0.16143444180488586, | |
| "eval_runtime": 255.9611, | |
| "eval_samples_per_second": 20.194, | |
| "eval_steps_per_second": 2.528, | |
| "eval_wer": 0.07193788623039138, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 30.51, | |
| "learning_rate": 4.9300166297117514e-05, | |
| "loss": 0.1082, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 30.51, | |
| "eval_loss": 0.16003426909446716, | |
| "eval_runtime": 255.199, | |
| "eval_samples_per_second": 20.255, | |
| "eval_steps_per_second": 2.535, | |
| "eval_wer": 0.07220197538689062, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 30.68, | |
| "learning_rate": 4.90230044345898e-05, | |
| "loss": 0.1159, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 30.68, | |
| "eval_loss": 0.15168212354183197, | |
| "eval_runtime": 255.5835, | |
| "eval_samples_per_second": 20.224, | |
| "eval_steps_per_second": 2.531, | |
| "eval_wer": 0.0748956847831828, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 30.85, | |
| "learning_rate": 4.874584257206209e-05, | |
| "loss": 0.1124, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 30.85, | |
| "eval_loss": 0.1633358746767044, | |
| "eval_runtime": 254.9468, | |
| "eval_samples_per_second": 20.275, | |
| "eval_steps_per_second": 2.538, | |
| "eval_wer": 0.07135689008609307, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 4.846868070953437e-05, | |
| "loss": 0.1153, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "eval_loss": 0.14990398287773132, | |
| "eval_runtime": 255.5087, | |
| "eval_samples_per_second": 20.23, | |
| "eval_steps_per_second": 2.532, | |
| "eval_wer": 0.07294142502508846, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 31.18, | |
| "learning_rate": 4.819151884700666e-05, | |
| "loss": 0.1083, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 31.18, | |
| "eval_loss": 0.15318718552589417, | |
| "eval_runtime": 255.4906, | |
| "eval_samples_per_second": 20.232, | |
| "eval_steps_per_second": 2.532, | |
| "eval_wer": 0.07146252574869276, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 31.34, | |
| "learning_rate": 4.791435698447893e-05, | |
| "loss": 0.1082, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 31.34, | |
| "eval_loss": 0.15611271560192108, | |
| "eval_runtime": 255.2065, | |
| "eval_samples_per_second": 20.254, | |
| "eval_steps_per_second": 2.535, | |
| "eval_wer": 0.07183225056779169, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 31.51, | |
| "learning_rate": 4.763719512195122e-05, | |
| "loss": 0.1114, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 31.51, | |
| "eval_loss": 0.15616507828235626, | |
| "eval_runtime": 255.2918, | |
| "eval_samples_per_second": 20.247, | |
| "eval_steps_per_second": 2.534, | |
| "eval_wer": 0.07204352189299107, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 31.67, | |
| "learning_rate": 4.73600332594235e-05, | |
| "loss": 0.1103, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 31.67, | |
| "eval_loss": 0.1566246598958969, | |
| "eval_runtime": 255.37, | |
| "eval_samples_per_second": 20.241, | |
| "eval_steps_per_second": 2.534, | |
| "eval_wer": 0.07146252574869276, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 31.84, | |
| "learning_rate": 4.708287139689579e-05, | |
| "loss": 0.1091, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 31.84, | |
| "eval_loss": 0.1507750004529953, | |
| "eval_runtime": 255.5097, | |
| "eval_samples_per_second": 20.23, | |
| "eval_steps_per_second": 2.532, | |
| "eval_wer": 0.07030053346009613, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 4.680570953436808e-05, | |
| "loss": 0.1111, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "eval_loss": 0.145137757062912, | |
| "eval_runtime": 254.9212, | |
| "eval_samples_per_second": 20.277, | |
| "eval_steps_per_second": 2.538, | |
| "eval_wer": 0.07336396767548724, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 32.17, | |
| "learning_rate": 4.652854767184035e-05, | |
| "loss": 0.1113, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 32.17, | |
| "eval_loss": 0.15428981184959412, | |
| "eval_runtime": 255.1259, | |
| "eval_samples_per_second": 20.261, | |
| "eval_steps_per_second": 2.536, | |
| "eval_wer": 0.07415623514498494, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 32.34, | |
| "learning_rate": 4.625138580931264e-05, | |
| "loss": 0.1072, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 32.34, | |
| "eval_loss": 0.14538711309432983, | |
| "eval_runtime": 255.0771, | |
| "eval_samples_per_second": 20.264, | |
| "eval_steps_per_second": 2.536, | |
| "eval_wer": 0.07299424285638832, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "learning_rate": 4.597422394678492e-05, | |
| "loss": 0.1033, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "eval_loss": 0.16375206410884857, | |
| "eval_runtime": 255.084, | |
| "eval_samples_per_second": 20.264, | |
| "eval_steps_per_second": 2.536, | |
| "eval_wer": 0.07135689008609307, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 32.67, | |
| "learning_rate": 4.569706208425721e-05, | |
| "loss": 0.1019, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 32.67, | |
| "eval_loss": 0.16679570078849792, | |
| "eval_runtime": 254.9797, | |
| "eval_samples_per_second": 20.272, | |
| "eval_steps_per_second": 2.537, | |
| "eval_wer": 0.07183225056779169, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 32.84, | |
| "learning_rate": 4.54199002217295e-05, | |
| "loss": 0.1053, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 32.84, | |
| "eval_loss": 0.16691266000270844, | |
| "eval_runtime": 257.5588, | |
| "eval_samples_per_second": 20.069, | |
| "eval_steps_per_second": 2.512, | |
| "eval_wer": 0.07082871177309459, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 4.514273835920178e-05, | |
| "loss": 0.1097, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 0.17189669609069824, | |
| "eval_runtime": 258.3507, | |
| "eval_samples_per_second": 20.008, | |
| "eval_steps_per_second": 2.504, | |
| "eval_wer": 0.07288860719378862, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 33.17, | |
| "learning_rate": 4.486557649667406e-05, | |
| "loss": 0.1021, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 33.17, | |
| "eval_loss": 0.16738824546337128, | |
| "eval_runtime": 257.6603, | |
| "eval_samples_per_second": 20.061, | |
| "eval_steps_per_second": 2.511, | |
| "eval_wer": 0.07177943273649184, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 4.458980044345898e-05, | |
| "loss": 0.1056, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "eval_loss": 0.15968775749206543, | |
| "eval_runtime": 257.6821, | |
| "eval_samples_per_second": 20.06, | |
| "eval_steps_per_second": 2.511, | |
| "eval_wer": 0.07098716526699414, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 33.5, | |
| "learning_rate": 4.431263858093126e-05, | |
| "loss": 0.1043, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 33.5, | |
| "eval_loss": 0.16819486021995544, | |
| "eval_runtime": 258.1617, | |
| "eval_samples_per_second": 20.022, | |
| "eval_steps_per_second": 2.506, | |
| "eval_wer": 0.07294142502508846, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 33.66, | |
| "learning_rate": 4.403547671840355e-05, | |
| "loss": 0.1015, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 33.66, | |
| "eval_loss": 0.17912797629833221, | |
| "eval_runtime": 257.4928, | |
| "eval_samples_per_second": 20.074, | |
| "eval_steps_per_second": 2.513, | |
| "eval_wer": 0.07389214598848572, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 33.83, | |
| "learning_rate": 4.375831485587583e-05, | |
| "loss": 0.1038, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 33.83, | |
| "eval_loss": 0.16278141736984253, | |
| "eval_runtime": 258.2425, | |
| "eval_samples_per_second": 20.016, | |
| "eval_steps_per_second": 2.505, | |
| "eval_wer": 0.07299424285638832, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 4.348115299334812e-05, | |
| "loss": 0.1018, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 0.17246678471565247, | |
| "eval_runtime": 257.824, | |
| "eval_samples_per_second": 20.049, | |
| "eval_steps_per_second": 2.509, | |
| "eval_wer": 0.07431468863888449, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 34.16, | |
| "learning_rate": 4.32039911308204e-05, | |
| "loss": 0.1002, | |
| "step": 41200 | |
| }, | |
| { | |
| "epoch": 34.16, | |
| "eval_loss": 0.17683491110801697, | |
| "eval_runtime": 259.2472, | |
| "eval_samples_per_second": 19.938, | |
| "eval_steps_per_second": 2.496, | |
| "eval_wer": 0.06998362647229704, | |
| "step": 41200 | |
| }, | |
| { | |
| "epoch": 34.33, | |
| "learning_rate": 4.292682926829268e-05, | |
| "loss": 0.1004, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 34.33, | |
| "eval_loss": 0.1728859543800354, | |
| "eval_runtime": 258.3657, | |
| "eval_samples_per_second": 20.007, | |
| "eval_steps_per_second": 2.504, | |
| "eval_wer": 0.0709343474356943, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 34.49, | |
| "learning_rate": 4.264966740576497e-05, | |
| "loss": 0.1023, | |
| "step": 41600 | |
| }, | |
| { | |
| "epoch": 34.49, | |
| "eval_loss": 0.1567125767469406, | |
| "eval_runtime": 258.2421, | |
| "eval_samples_per_second": 20.016, | |
| "eval_steps_per_second": 2.505, | |
| "eval_wer": 0.07378651032588601, | |
| "step": 41600 | |
| }, | |
| { | |
| "epoch": 34.66, | |
| "learning_rate": 4.237250554323725e-05, | |
| "loss": 0.1003, | |
| "step": 41800 | |
| }, | |
| { | |
| "epoch": 34.66, | |
| "eval_loss": 0.16443106532096863, | |
| "eval_runtime": 258.2982, | |
| "eval_samples_per_second": 20.012, | |
| "eval_steps_per_second": 2.505, | |
| "eval_wer": 0.07251888237468969, | |
| "step": 41800 | |
| }, | |
| { | |
| "epoch": 34.83, | |
| "learning_rate": 4.209534368070954e-05, | |
| "loss": 0.103, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 34.83, | |
| "eval_loss": 0.17008621990680695, | |
| "eval_runtime": 257.8252, | |
| "eval_samples_per_second": 20.048, | |
| "eval_steps_per_second": 2.509, | |
| "eval_wer": 0.0716209792425923, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 34.99, | |
| "learning_rate": 4.181818181818182e-05, | |
| "loss": 0.1056, | |
| "step": 42200 | |
| }, | |
| { | |
| "epoch": 34.99, | |
| "eval_loss": 0.16209852695465088, | |
| "eval_runtime": 258.245, | |
| "eval_samples_per_second": 20.016, | |
| "eval_steps_per_second": 2.505, | |
| "eval_wer": 0.06956108382189827, | |
| "step": 42200 | |
| }, | |
| { | |
| "epoch": 35.16, | |
| "learning_rate": 4.15410199556541e-05, | |
| "loss": 0.102, | |
| "step": 42400 | |
| }, | |
| { | |
| "epoch": 35.16, | |
| "eval_loss": 0.1503116935491562, | |
| "eval_runtime": 258.2089, | |
| "eval_samples_per_second": 20.019, | |
| "eval_steps_per_second": 2.506, | |
| "eval_wer": 0.07024771562879628, | |
| "step": 42400 | |
| }, | |
| { | |
| "epoch": 35.32, | |
| "learning_rate": 4.126385809312639e-05, | |
| "loss": 0.0979, | |
| "step": 42600 | |
| }, | |
| { | |
| "epoch": 35.32, | |
| "eval_loss": 0.15129025280475616, | |
| "eval_runtime": 258.9706, | |
| "eval_samples_per_second": 19.96, | |
| "eval_steps_per_second": 2.498, | |
| "eval_wer": 0.06977235514709766, | |
| "step": 42600 | |
| }, | |
| { | |
| "epoch": 35.49, | |
| "learning_rate": 4.098808203991131e-05, | |
| "loss": 0.0969, | |
| "step": 42800 | |
| }, | |
| { | |
| "epoch": 35.49, | |
| "eval_loss": 0.16101005673408508, | |
| "eval_runtime": 258.464, | |
| "eval_samples_per_second": 19.999, | |
| "eval_steps_per_second": 2.503, | |
| "eval_wer": 0.07082871177309459, | |
| "step": 42800 | |
| }, | |
| { | |
| "epoch": 35.65, | |
| "learning_rate": 4.071092017738359e-05, | |
| "loss": 0.1016, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 35.65, | |
| "eval_loss": 0.17464140057563782, | |
| "eval_runtime": 258.5693, | |
| "eval_samples_per_second": 19.991, | |
| "eval_steps_per_second": 2.502, | |
| "eval_wer": 0.07140970791739291, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 35.82, | |
| "learning_rate": 4.043375831485588e-05, | |
| "loss": 0.0994, | |
| "step": 43200 | |
| }, | |
| { | |
| "epoch": 35.82, | |
| "eval_loss": 0.16432413458824158, | |
| "eval_runtime": 259.177, | |
| "eval_samples_per_second": 19.944, | |
| "eval_steps_per_second": 2.496, | |
| "eval_wer": 0.07045898695399568, | |
| "step": 43200 | |
| }, | |
| { | |
| "epoch": 35.99, | |
| "learning_rate": 4.015659645232816e-05, | |
| "loss": 0.0966, | |
| "step": 43400 | |
| }, | |
| { | |
| "epoch": 35.99, | |
| "eval_loss": 0.1695939600467682, | |
| "eval_runtime": 258.2906, | |
| "eval_samples_per_second": 20.012, | |
| "eval_steps_per_second": 2.505, | |
| "eval_wer": 0.0707230761104949, | |
| "step": 43400 | |
| } | |
| ], | |
| "max_steps": 72360, | |
| "num_train_epochs": 60, | |
| "total_flos": 1.9733994835008543e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |