| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 19.999153259949196, | |
| "global_step": 17700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.8749999999999998e-06, | |
| "loss": 9.7932, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 3.7125e-06, | |
| "loss": 9.6218, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 5.549999999999999e-06, | |
| "loss": 7.6384, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.425e-06, | |
| "loss": 5.5724, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 9.299999999999999e-06, | |
| "loss": 4.4527, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 4.014413833618164, | |
| "eval_runtime": 432.9366, | |
| "eval_samples_per_second": 14.339, | |
| "eval_steps_per_second": 0.896, | |
| "eval_wer": 1.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.1174999999999999e-05, | |
| "loss": 3.996, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.3049999999999999e-05, | |
| "loss": 3.6961, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.4925e-05, | |
| "loss": 3.4442, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.68e-05, | |
| "loss": 3.3442, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 1.8675e-05, | |
| "loss": 3.1828, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 3.136876106262207, | |
| "eval_runtime": 432.521, | |
| "eval_samples_per_second": 14.353, | |
| "eval_steps_per_second": 0.897, | |
| "eval_wer": 1.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.055e-05, | |
| "loss": 3.1052, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 2.2424999999999996e-05, | |
| "loss": 3.0545, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.4299999999999998e-05, | |
| "loss": 3.0155, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.6174999999999996e-05, | |
| "loss": 3.0148, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 2.8049999999999997e-05, | |
| "loss": 2.9927, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 3.0182671546936035, | |
| "eval_runtime": 435.1578, | |
| "eval_samples_per_second": 14.266, | |
| "eval_steps_per_second": 0.892, | |
| "eval_wer": 1.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.9925e-05, | |
| "loss": 2.9829, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.1799999999999994e-05, | |
| "loss": 2.9876, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.3675e-05, | |
| "loss": 3.0304, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.555e-05, | |
| "loss": 2.9783, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.7424999999999995e-05, | |
| "loss": 2.9591, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 2.999102830886841, | |
| "eval_runtime": 430.4872, | |
| "eval_samples_per_second": 14.421, | |
| "eval_steps_per_second": 0.901, | |
| "eval_wer": 1.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.93e-05, | |
| "loss": 2.9559, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 4.1175e-05, | |
| "loss": 2.9388, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 4.3049999999999996e-05, | |
| "loss": 2.9321, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.4924999999999994e-05, | |
| "loss": 2.9205, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 4.68e-05, | |
| "loss": 2.8989, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 2.9000213146209717, | |
| "eval_runtime": 431.5059, | |
| "eval_samples_per_second": 14.387, | |
| "eval_steps_per_second": 0.899, | |
| "eval_wer": 0.999990658308967, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 4.8675e-05, | |
| "loss": 2.8682, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 5.055e-05, | |
| "loss": 2.8476, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 5.2424999999999994e-05, | |
| "loss": 2.7956, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 5.429999999999999e-05, | |
| "loss": 2.6754, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 5.6175e-05, | |
| "loss": 2.4286, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 1.7688498497009277, | |
| "eval_runtime": 430.3663, | |
| "eval_samples_per_second": 14.425, | |
| "eval_steps_per_second": 0.902, | |
| "eval_wer": 0.9550384410586005, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 5.8049999999999995e-05, | |
| "loss": 2.218, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 5.9925e-05, | |
| "loss": 2.0095, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 6.18e-05, | |
| "loss": 1.8416, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.367499999999999e-05, | |
| "loss": 1.7642, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 6.555e-05, | |
| "loss": 1.6765, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 0.6841917037963867, | |
| "eval_runtime": 433.019, | |
| "eval_samples_per_second": 14.337, | |
| "eval_steps_per_second": 0.896, | |
| "eval_wer": 0.48551570805347183, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 6.7425e-05, | |
| "loss": 1.5994, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 6.93e-05, | |
| "loss": 1.5522, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 7.1175e-05, | |
| "loss": 1.52, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 7.304999999999999e-05, | |
| "loss": 1.5086, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.492499999999999e-05, | |
| "loss": 1.4521, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 0.5096011757850647, | |
| "eval_runtime": 431.8266, | |
| "eval_samples_per_second": 14.376, | |
| "eval_steps_per_second": 0.899, | |
| "eval_wer": 0.3735835660971349, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 7.477070063694266e-05, | |
| "loss": 1.4457, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 7.453184713375795e-05, | |
| "loss": 1.4276, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 7.429299363057323e-05, | |
| "loss": 1.4028, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 7.405414012738853e-05, | |
| "loss": 1.3887, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.38152866242038e-05, | |
| "loss": 1.3589, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 0.44788965582847595, | |
| "eval_runtime": 430.2855, | |
| "eval_samples_per_second": 14.428, | |
| "eval_steps_per_second": 0.902, | |
| "eval_wer": 0.3335450783300793, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.35764331210191e-05, | |
| "loss": 1.3935, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 7.333757961783438e-05, | |
| "loss": 1.3425, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 7.309872611464967e-05, | |
| "loss": 1.3657, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 7.285987261146495e-05, | |
| "loss": 1.3645, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 7.262101910828025e-05, | |
| "loss": 1.3136, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_loss": 0.40564054250717163, | |
| "eval_runtime": 428.4501, | |
| "eval_samples_per_second": 14.489, | |
| "eval_steps_per_second": 0.906, | |
| "eval_wer": 0.3123020729212402, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 7.238216560509553e-05, | |
| "loss": 1.3415, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 7.214331210191082e-05, | |
| "loss": 1.3345, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 7.19044585987261e-05, | |
| "loss": 1.3283, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.16656050955414e-05, | |
| "loss": 1.2788, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 7.142675159235667e-05, | |
| "loss": 1.2856, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "eval_loss": 0.38699424266815186, | |
| "eval_runtime": 430.1514, | |
| "eval_samples_per_second": 14.432, | |
| "eval_steps_per_second": 0.902, | |
| "eval_wer": 0.29870991246835504, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 7.118789808917197e-05, | |
| "loss": 1.2817, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 7.094904458598725e-05, | |
| "loss": 1.2502, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 7.071019108280254e-05, | |
| "loss": 1.2623, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 7.047133757961782e-05, | |
| "loss": 1.2302, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 7.023248407643311e-05, | |
| "loss": 1.2283, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "eval_loss": 0.3645668029785156, | |
| "eval_runtime": 430.0013, | |
| "eval_samples_per_second": 14.437, | |
| "eval_steps_per_second": 0.902, | |
| "eval_wer": 0.2828290377124067, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 6.99936305732484e-05, | |
| "loss": 1.1993, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 6.975477707006369e-05, | |
| "loss": 1.2627, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 6.951592356687897e-05, | |
| "loss": 1.1969, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 6.927707006369426e-05, | |
| "loss": 1.2054, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 6.903821656050954e-05, | |
| "loss": 1.2053, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "eval_loss": 0.3499177098274231, | |
| "eval_runtime": 429.329, | |
| "eval_samples_per_second": 14.46, | |
| "eval_steps_per_second": 0.904, | |
| "eval_wer": 0.2747578166599718, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 6.879936305732483e-05, | |
| "loss": 1.2144, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 6.856050955414011e-05, | |
| "loss": 1.1882, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 6.832165605095541e-05, | |
| "loss": 1.1901, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 6.808280254777069e-05, | |
| "loss": 1.2064, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 6.784394904458598e-05, | |
| "loss": 1.2087, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "eval_loss": 0.3345482349395752, | |
| "eval_runtime": 430.4222, | |
| "eval_samples_per_second": 14.423, | |
| "eval_steps_per_second": 0.901, | |
| "eval_wer": 0.2602781955589601, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 6.760509554140126e-05, | |
| "loss": 1.1945, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 6.736624203821655e-05, | |
| "loss": 1.1674, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 6.712738853503183e-05, | |
| "loss": 1.2197, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 6.688853503184713e-05, | |
| "loss": 1.1832, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 6.664968152866241e-05, | |
| "loss": 1.2002, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "eval_loss": 0.3320307731628418, | |
| "eval_runtime": 429.9654, | |
| "eval_samples_per_second": 14.438, | |
| "eval_steps_per_second": 0.902, | |
| "eval_wer": 0.25228170803478844, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 6.64108280254777e-05, | |
| "loss": 1.1655, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 6.617197452229298e-05, | |
| "loss": 1.1387, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 6.593312101910828e-05, | |
| "loss": 1.1344, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 6.569426751592356e-05, | |
| "loss": 1.169, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 6.545541401273885e-05, | |
| "loss": 1.1383, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "eval_loss": 0.31172633171081543, | |
| "eval_runtime": 428.4618, | |
| "eval_samples_per_second": 14.489, | |
| "eval_steps_per_second": 0.906, | |
| "eval_wer": 0.24393957794239912, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 6.521656050955413e-05, | |
| "loss": 1.1241, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 6.497770700636942e-05, | |
| "loss": 1.1505, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 6.47388535031847e-05, | |
| "loss": 1.1309, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 6.45e-05, | |
| "loss": 1.1368, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 6.426114649681528e-05, | |
| "loss": 1.1364, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "eval_loss": 0.3198467195034027, | |
| "eval_runtime": 427.239, | |
| "eval_samples_per_second": 14.531, | |
| "eval_steps_per_second": 0.908, | |
| "eval_wer": 0.2382878548674881, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 6.402229299363057e-05, | |
| "loss": 1.1185, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 6.378343949044585e-05, | |
| "loss": 1.1214, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 6.354458598726114e-05, | |
| "loss": 1.1188, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 6.330573248407642e-05, | |
| "loss": 1.1327, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 6.306687898089172e-05, | |
| "loss": 1.158, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "eval_loss": 0.3070796728134155, | |
| "eval_runtime": 427.2037, | |
| "eval_samples_per_second": 14.532, | |
| "eval_steps_per_second": 0.908, | |
| "eval_wer": 0.23418685250404028, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 6.2828025477707e-05, | |
| "loss": 1.1221, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 6.258917197452229e-05, | |
| "loss": 1.1167, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 6.235031847133757e-05, | |
| "loss": 1.1067, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 6.211146496815286e-05, | |
| "loss": 1.099, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 6.187261146496814e-05, | |
| "loss": 1.108, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "eval_loss": 0.3011206090450287, | |
| "eval_runtime": 430.4576, | |
| "eval_samples_per_second": 14.422, | |
| "eval_steps_per_second": 0.901, | |
| "eval_wer": 0.23136566181210122, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 6.163375796178344e-05, | |
| "loss": 1.1024, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 6.139490445859872e-05, | |
| "loss": 1.1039, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 6.115605095541401e-05, | |
| "loss": 1.1082, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 6.09171974522293e-05, | |
| "loss": 1.0982, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 6.0678343949044583e-05, | |
| "loss": 1.1025, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "eval_loss": 0.28753861784935, | |
| "eval_runtime": 431.3779, | |
| "eval_samples_per_second": 14.391, | |
| "eval_steps_per_second": 0.899, | |
| "eval_wer": 0.2289368221435444, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 6.043949044585987e-05, | |
| "loss": 1.089, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 6.020063694267516e-05, | |
| "loss": 1.0792, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 5.9961783439490444e-05, | |
| "loss": 1.1054, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 5.972770700636942e-05, | |
| "loss": 1.078, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 5.948885350318471e-05, | |
| "loss": 1.0697, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "eval_loss": 0.29261597990989685, | |
| "eval_runtime": 429.3286, | |
| "eval_samples_per_second": 14.46, | |
| "eval_steps_per_second": 0.904, | |
| "eval_wer": 0.22559249675376236, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 5.925e-05, | |
| "loss": 1.1183, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 5.9011146496815284e-05, | |
| "loss": 1.1614, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 5.877229299363057e-05, | |
| "loss": 1.075, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 5.853343949044586e-05, | |
| "loss": 1.0901, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 5.8294585987261144e-05, | |
| "loss": 1.0904, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "eval_loss": 0.2695116698741913, | |
| "eval_runtime": 431.1678, | |
| "eval_samples_per_second": 14.398, | |
| "eval_steps_per_second": 0.9, | |
| "eval_wer": 0.22445281044774726, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 5.805573248407643e-05, | |
| "loss": 1.0577, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 5.781687898089172e-05, | |
| "loss": 1.0693, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 5.7578025477707004e-05, | |
| "loss": 1.0784, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 5.733917197452229e-05, | |
| "loss": 1.0754, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 5.710031847133758e-05, | |
| "loss": 1.0802, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "eval_loss": 0.26020729541778564, | |
| "eval_runtime": 433.3184, | |
| "eval_samples_per_second": 14.327, | |
| "eval_steps_per_second": 0.895, | |
| "eval_wer": 0.21889450428316534, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 5.6861464968152864e-05, | |
| "loss": 1.0459, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 5.662261146496815e-05, | |
| "loss": 1.0492, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 5.638375796178344e-05, | |
| "loss": 1.0526, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 5.6144904458598724e-05, | |
| "loss": 1.079, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 5.590605095541401e-05, | |
| "loss": 1.0882, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "eval_loss": 0.2602781653404236, | |
| "eval_runtime": 434.4762, | |
| "eval_samples_per_second": 14.288, | |
| "eval_steps_per_second": 0.893, | |
| "eval_wer": 0.21684867394695787, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 5.56671974522293e-05, | |
| "loss": 1.0691, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 5.5428343949044585e-05, | |
| "loss": 1.0728, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 5.518949044585987e-05, | |
| "loss": 1.0308, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 5.4955414012738844e-05, | |
| "loss": 1.0894, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 5.471656050955413e-05, | |
| "loss": 1.0881, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "eval_loss": 0.25403761863708496, | |
| "eval_runtime": 433.991, | |
| "eval_samples_per_second": 14.304, | |
| "eval_steps_per_second": 0.894, | |
| "eval_wer": 0.2292544396386634, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 5.447770700636942e-05, | |
| "loss": 1.0295, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 5.4238853503184704e-05, | |
| "loss": 1.0389, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 5.399999999999999e-05, | |
| "loss": 1.0415, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 5.376114649681528e-05, | |
| "loss": 1.0492, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 5.3522292993630565e-05, | |
| "loss": 1.0378, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "eval_loss": 0.2614484429359436, | |
| "eval_runtime": 432.0675, | |
| "eval_samples_per_second": 14.368, | |
| "eval_steps_per_second": 0.898, | |
| "eval_wer": 0.21932422207067923, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 5.328343949044585e-05, | |
| "loss": 1.0362, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 5.304458598726114e-05, | |
| "loss": 1.0444, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 5.2805732484076425e-05, | |
| "loss": 1.0626, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 5.256687898089171e-05, | |
| "loss": 1.0307, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 5.2328025477707e-05, | |
| "loss": 1.0397, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "eval_loss": 0.27073222398757935, | |
| "eval_runtime": 432.0598, | |
| "eval_samples_per_second": 14.368, | |
| "eval_steps_per_second": 0.898, | |
| "eval_wer": 0.21041224882528237, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 5.2089171974522285e-05, | |
| "loss": 1.0481, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 5.185031847133757e-05, | |
| "loss": 1.042, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 5.161146496815286e-05, | |
| "loss": 1.0298, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 5.1372611464968145e-05, | |
| "loss": 1.0269, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 5.113375796178343e-05, | |
| "loss": 1.0296, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "eval_loss": 0.248311385512352, | |
| "eval_runtime": 431.8203, | |
| "eval_samples_per_second": 14.376, | |
| "eval_steps_per_second": 0.899, | |
| "eval_wer": 0.2119256027726139, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 5.089490445859872e-05, | |
| "loss": 1.0276, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 5.0656050955414005e-05, | |
| "loss": 1.0481, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 5.041719745222929e-05, | |
| "loss": 1.006, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 5.017834394904458e-05, | |
| "loss": 1.0215, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 4.9939490445859866e-05, | |
| "loss": 1.0249, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "eval_loss": 0.24828839302062988, | |
| "eval_runtime": 429.7696, | |
| "eval_samples_per_second": 14.445, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 0.20468579222210806, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 4.970063694267515e-05, | |
| "loss": 1.0109, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 4.946178343949044e-05, | |
| "loss": 1.0154, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 4.9222929936305726e-05, | |
| "loss": 1.0123, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 4.898407643312101e-05, | |
| "loss": 1.0126, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 4.87452229299363e-05, | |
| "loss": 1.013, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "eval_loss": 0.24869437515735626, | |
| "eval_runtime": 430.836, | |
| "eval_samples_per_second": 14.409, | |
| "eval_steps_per_second": 0.901, | |
| "eval_wer": 0.20419068259736378, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 4.8506369426751586e-05, | |
| "loss": 1.0077, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 4.826751592356687e-05, | |
| "loss": 1.0256, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 4.802866242038216e-05, | |
| "loss": 1.0627, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 4.7789808917197446e-05, | |
| "loss": 0.9883, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 4.755095541401273e-05, | |
| "loss": 1.0064, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "eval_loss": 0.24558775126934052, | |
| "eval_runtime": 430.9773, | |
| "eval_samples_per_second": 14.404, | |
| "eval_steps_per_second": 0.9, | |
| "eval_wer": 0.20164974263641205, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 4.731210191082802e-05, | |
| "loss": 1.0137, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 4.7073248407643306e-05, | |
| "loss": 1.0178, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 4.683439490445859e-05, | |
| "loss": 1.0035, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 4.659554140127388e-05, | |
| "loss": 1.0457, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 4.6356687898089167e-05, | |
| "loss": 1.0668, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "eval_loss": 0.2397284209728241, | |
| "eval_runtime": 430.6925, | |
| "eval_samples_per_second": 14.414, | |
| "eval_steps_per_second": 0.901, | |
| "eval_wer": 0.19949181200780966, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 4.611783439490445e-05, | |
| "loss": 1.0054, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 4.587898089171974e-05, | |
| "loss": 1.0224, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 4.564012738853503e-05, | |
| "loss": 1.0019, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 4.5401273885350314e-05, | |
| "loss": 1.0033, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 4.51624203821656e-05, | |
| "loss": 1.0129, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "eval_loss": 0.23742474615573883, | |
| "eval_runtime": 432.9935, | |
| "eval_samples_per_second": 14.337, | |
| "eval_steps_per_second": 0.896, | |
| "eval_wer": 0.19942642017057927, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 4.492356687898089e-05, | |
| "loss": 0.9864, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 4.4689490445859874e-05, | |
| "loss": 1.0021, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 4.445063694267516e-05, | |
| "loss": 1.0073, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 4.421178343949045e-05, | |
| "loss": 0.9999, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 4.3972929936305734e-05, | |
| "loss": 1.0164, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "eval_loss": 0.2206413298845291, | |
| "eval_runtime": 431.5354, | |
| "eval_samples_per_second": 14.386, | |
| "eval_steps_per_second": 0.899, | |
| "eval_wer": 0.19915551113062488, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 4.373407643312102e-05, | |
| "loss": 0.9956, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 4.349522292993631e-05, | |
| "loss": 0.9662, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 4.3256369426751594e-05, | |
| "loss": 0.9781, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 4.301751592356688e-05, | |
| "loss": 0.9863, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 4.277866242038217e-05, | |
| "loss": 0.975, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "eval_loss": 0.22473624348640442, | |
| "eval_runtime": 432.1534, | |
| "eval_samples_per_second": 14.365, | |
| "eval_steps_per_second": 0.898, | |
| "eval_wer": 0.19731519799714145, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 4.2539808917197454e-05, | |
| "loss": 0.9931, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.230095541401274e-05, | |
| "loss": 1.0101, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "learning_rate": 4.206210191082803e-05, | |
| "loss": 1.0034, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 4.1823248407643314e-05, | |
| "loss": 1.0018, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 10.17, | |
| "learning_rate": 4.15843949044586e-05, | |
| "loss": 0.9849, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 10.17, | |
| "eval_loss": 0.23245184123516083, | |
| "eval_runtime": 431.4778, | |
| "eval_samples_per_second": 14.388, | |
| "eval_steps_per_second": 0.899, | |
| "eval_wer": 0.19526002596990108, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 4.134554140127389e-05, | |
| "loss": 0.9953, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 10.28, | |
| "learning_rate": 4.1106687898089175e-05, | |
| "loss": 0.9639, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 10.34, | |
| "learning_rate": 4.086783439490446e-05, | |
| "loss": 0.9862, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 4.062898089171975e-05, | |
| "loss": 1.0222, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "learning_rate": 4.0390127388535035e-05, | |
| "loss": 0.9826, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "eval_loss": 0.2301308959722519, | |
| "eval_runtime": 432.6762, | |
| "eval_samples_per_second": 14.348, | |
| "eval_steps_per_second": 0.897, | |
| "eval_wer": 0.1933730043812531, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 10.51, | |
| "learning_rate": 4.015127388535032e-05, | |
| "loss": 0.9867, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 3.991242038216561e-05, | |
| "loss": 0.9687, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 3.9673566878980895e-05, | |
| "loss": 0.9715, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 10.68, | |
| "learning_rate": 3.943471337579618e-05, | |
| "loss": 0.9914, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 3.919585987261147e-05, | |
| "loss": 0.9835, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "eval_loss": 0.2191852629184723, | |
| "eval_runtime": 439.1976, | |
| "eval_samples_per_second": 14.135, | |
| "eval_steps_per_second": 0.883, | |
| "eval_wer": 0.19420441488318216, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 10.79, | |
| "learning_rate": 3.8957006369426755e-05, | |
| "loss": 0.9652, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 10.85, | |
| "learning_rate": 3.871815286624204e-05, | |
| "loss": 0.9614, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 3.847929936305733e-05, | |
| "loss": 0.97, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "learning_rate": 3.8240445859872615e-05, | |
| "loss": 0.9764, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 3.80015923566879e-05, | |
| "loss": 0.9676, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "eval_loss": 0.2265927493572235, | |
| "eval_runtime": 430.7748, | |
| "eval_samples_per_second": 14.411, | |
| "eval_steps_per_second": 0.901, | |
| "eval_wer": 0.19133651573607854, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 11.07, | |
| "learning_rate": 3.776273885350319e-05, | |
| "loss": 0.9609, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 3.7523885350318475e-05, | |
| "loss": 0.9721, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 3.7285031847133755e-05, | |
| "loss": 0.9669, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 11.24, | |
| "learning_rate": 3.704617834394904e-05, | |
| "loss": 0.9643, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 3.680732484076433e-05, | |
| "loss": 0.9627, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "eval_loss": 0.2193416953086853, | |
| "eval_runtime": 432.6083, | |
| "eval_samples_per_second": 14.35, | |
| "eval_steps_per_second": 0.897, | |
| "eval_wer": 0.19205582594561268, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 3.6568471337579616e-05, | |
| "loss": 1.0179, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 11.41, | |
| "learning_rate": 3.63296178343949e-05, | |
| "loss": 0.9575, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 11.47, | |
| "learning_rate": 3.609076433121019e-05, | |
| "loss": 0.98, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 3.5851910828025476e-05, | |
| "loss": 0.9542, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "learning_rate": 3.561305732484076e-05, | |
| "loss": 0.976, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "eval_loss": 0.23090308904647827, | |
| "eval_runtime": 432.1501, | |
| "eval_samples_per_second": 14.365, | |
| "eval_steps_per_second": 0.898, | |
| "eval_wer": 0.1881790241669547, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 3.537420382165605e-05, | |
| "loss": 0.972, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 11.69, | |
| "learning_rate": 3.5135350318471336e-05, | |
| "loss": 0.9634, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 11.75, | |
| "learning_rate": 3.489649681528662e-05, | |
| "loss": 0.9682, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 11.81, | |
| "learning_rate": 3.465764331210191e-05, | |
| "loss": 0.9638, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "learning_rate": 3.4418789808917196e-05, | |
| "loss": 0.969, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 11.86, | |
| "eval_loss": 0.2268366813659668, | |
| "eval_runtime": 433.2795, | |
| "eval_samples_per_second": 14.328, | |
| "eval_steps_per_second": 0.895, | |
| "eval_wer": 0.18859005857240277, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 11.92, | |
| "learning_rate": 3.417993630573248e-05, | |
| "loss": 0.9698, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "learning_rate": 3.394108280254777e-05, | |
| "loss": 0.9369, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 3.3702229299363056e-05, | |
| "loss": 0.9699, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "learning_rate": 3.346337579617834e-05, | |
| "loss": 1.0013, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "learning_rate": 3.322929936305732e-05, | |
| "loss": 0.9611, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 12.15, | |
| "eval_loss": 0.2322191596031189, | |
| "eval_runtime": 429.3587, | |
| "eval_samples_per_second": 14.459, | |
| "eval_steps_per_second": 0.904, | |
| "eval_wer": 0.18626397750520798, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 3.299044585987261e-05, | |
| "loss": 0.9418, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 3.2751592356687896e-05, | |
| "loss": 0.9582, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 3.251273885350318e-05, | |
| "loss": 0.945, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 3.227388535031847e-05, | |
| "loss": 0.9386, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 12.43, | |
| "learning_rate": 3.2035031847133757e-05, | |
| "loss": 0.9397, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 12.43, | |
| "eval_loss": 0.21969455480575562, | |
| "eval_runtime": 432.2628, | |
| "eval_samples_per_second": 14.362, | |
| "eval_steps_per_second": 0.898, | |
| "eval_wer": 0.1843676142255271, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 12.49, | |
| "learning_rate": 3.179617834394904e-05, | |
| "loss": 0.9594, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 12.54, | |
| "learning_rate": 3.155732484076433e-05, | |
| "loss": 0.9467, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "learning_rate": 3.131847133757962e-05, | |
| "loss": 0.9609, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 3.1079617834394904e-05, | |
| "loss": 0.9446, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "learning_rate": 3.084076433121019e-05, | |
| "loss": 0.9601, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "eval_loss": 0.22107979655265808, | |
| "eval_runtime": 432.9535, | |
| "eval_samples_per_second": 14.339, | |
| "eval_steps_per_second": 0.896, | |
| "eval_wer": 0.18711407138920289, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 12.77, | |
| "learning_rate": 3.060191082802548e-05, | |
| "loss": 0.9497, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 3.036305732484076e-05, | |
| "loss": 0.939, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 12.88, | |
| "learning_rate": 3.0124203821656047e-05, | |
| "loss": 0.9462, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 12.94, | |
| "learning_rate": 2.9885350318471334e-05, | |
| "loss": 0.9243, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "learning_rate": 2.964649681528662e-05, | |
| "loss": 0.9718, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_loss": 0.20792651176452637, | |
| "eval_runtime": 429.7801, | |
| "eval_samples_per_second": 14.445, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 0.189823161788747, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 2.9407643312101907e-05, | |
| "loss": 0.9543, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 13.11, | |
| "learning_rate": 2.9168789808917194e-05, | |
| "loss": 0.9386, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 2.892993630573248e-05, | |
| "loss": 0.9662, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 13.22, | |
| "learning_rate": 2.8691082802547767e-05, | |
| "loss": 0.9426, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 2.8452229299363054e-05, | |
| "loss": 0.9347, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "eval_loss": 0.2053879350423813, | |
| "eval_runtime": 427.5266, | |
| "eval_samples_per_second": 14.521, | |
| "eval_steps_per_second": 0.908, | |
| "eval_wer": 0.1842835390062309, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 2.821337579617834e-05, | |
| "loss": 0.9579, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 2.7974522292993628e-05, | |
| "loss": 0.9313, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 13.45, | |
| "learning_rate": 2.7735668789808914e-05, | |
| "loss": 0.9295, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 2.74968152866242e-05, | |
| "loss": 0.9437, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 13.56, | |
| "learning_rate": 2.7257961783439488e-05, | |
| "loss": 0.9377, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 13.56, | |
| "eval_loss": 0.20305366814136505, | |
| "eval_runtime": 429.8935, | |
| "eval_samples_per_second": 14.441, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 0.18423683055106635, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 13.62, | |
| "learning_rate": 2.7019108280254775e-05, | |
| "loss": 0.9273, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 13.67, | |
| "learning_rate": 2.678025477707006e-05, | |
| "loss": 0.9804, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "learning_rate": 2.6541401273885348e-05, | |
| "loss": 0.9392, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 13.78, | |
| "learning_rate": 2.6302547770700635e-05, | |
| "loss": 0.9379, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 13.84, | |
| "learning_rate": 2.606369426751592e-05, | |
| "loss": 0.934, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 13.84, | |
| "eval_loss": 0.20586800575256348, | |
| "eval_runtime": 428.3313, | |
| "eval_samples_per_second": 14.493, | |
| "eval_steps_per_second": 0.906, | |
| "eval_wer": 0.18060291273926407, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 13.9, | |
| "learning_rate": 2.5824840764331208e-05, | |
| "loss": 0.9177, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 13.95, | |
| "learning_rate": 2.5585987261146495e-05, | |
| "loss": 0.9369, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 2.534713375796178e-05, | |
| "loss": 0.9438, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 14.07, | |
| "learning_rate": 2.510828025477707e-05, | |
| "loss": 0.9341, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 14.12, | |
| "learning_rate": 2.4869426751592355e-05, | |
| "loss": 0.9295, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 14.12, | |
| "eval_loss": 0.21221554279327393, | |
| "eval_runtime": 432.7246, | |
| "eval_samples_per_second": 14.346, | |
| "eval_steps_per_second": 0.897, | |
| "eval_wer": 0.18605846030248396, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 2.4630573248407642e-05, | |
| "loss": 0.9239, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 2.439171974522293e-05, | |
| "loss": 0.9235, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 2.4152866242038215e-05, | |
| "loss": 0.9631, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 14.35, | |
| "learning_rate": 2.3914012738853502e-05, | |
| "loss": 0.9467, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "learning_rate": 2.367515923566879e-05, | |
| "loss": 0.935, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 14.41, | |
| "eval_loss": 0.20723822712898254, | |
| "eval_runtime": 429.493, | |
| "eval_samples_per_second": 14.454, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 0.17866918269545154, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 14.46, | |
| "learning_rate": 2.3436305732484076e-05, | |
| "loss": 0.9319, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 2.3197452229299362e-05, | |
| "loss": 0.9337, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 14.58, | |
| "learning_rate": 2.295859872611465e-05, | |
| "loss": 0.9259, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 14.63, | |
| "learning_rate": 2.2719745222929936e-05, | |
| "loss": 0.9228, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "learning_rate": 2.2480891719745222e-05, | |
| "loss": 0.9021, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 14.69, | |
| "eval_loss": 0.21045178174972534, | |
| "eval_runtime": 428.8167, | |
| "eval_samples_per_second": 14.477, | |
| "eval_steps_per_second": 0.905, | |
| "eval_wer": 0.1781273646155427, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "learning_rate": 2.224203821656051e-05, | |
| "loss": 0.9238, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "learning_rate": 2.2003184713375796e-05, | |
| "loss": 0.9373, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "learning_rate": 2.1764331210191083e-05, | |
| "loss": 0.9365, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 2.152547770700637e-05, | |
| "loss": 0.9656, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "learning_rate": 2.1286624203821656e-05, | |
| "loss": 0.9193, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "eval_loss": 0.20348267257213593, | |
| "eval_runtime": 430.2042, | |
| "eval_samples_per_second": 14.43, | |
| "eval_steps_per_second": 0.902, | |
| "eval_wer": 0.17860379085822115, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 2.1047770700636943e-05, | |
| "loss": 0.9366, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "learning_rate": 2.080891719745223e-05, | |
| "loss": 0.9129, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 15.14, | |
| "learning_rate": 2.0570063694267513e-05, | |
| "loss": 0.9032, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 2.03312101910828e-05, | |
| "loss": 0.9152, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 15.25, | |
| "learning_rate": 2.0092356687898086e-05, | |
| "loss": 0.9214, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 15.25, | |
| "eval_loss": 0.2034832239151001, | |
| "eval_runtime": 432.039, | |
| "eval_samples_per_second": 14.369, | |
| "eval_steps_per_second": 0.898, | |
| "eval_wer": 0.17661401066821117, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 15.31, | |
| "learning_rate": 1.9853503184713373e-05, | |
| "loss": 0.9438, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 15.37, | |
| "learning_rate": 1.961464968152866e-05, | |
| "loss": 0.9262, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 15.42, | |
| "learning_rate": 1.9375796178343947e-05, | |
| "loss": 0.9157, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 15.48, | |
| "learning_rate": 1.9136942675159233e-05, | |
| "loss": 0.9299, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 1.889808917197452e-05, | |
| "loss": 0.9048, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "eval_loss": 0.19639889895915985, | |
| "eval_runtime": 438.8483, | |
| "eval_samples_per_second": 14.146, | |
| "eval_steps_per_second": 0.884, | |
| "eval_wer": 0.17581062523938082, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 15.59, | |
| "learning_rate": 1.8659235668789807e-05, | |
| "loss": 0.9399, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 15.65, | |
| "learning_rate": 1.8420382165605094e-05, | |
| "loss": 0.9309, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 1.818152866242038e-05, | |
| "loss": 0.9646, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 15.76, | |
| "learning_rate": 1.7942675159235667e-05, | |
| "loss": 0.9095, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 15.82, | |
| "learning_rate": 1.7703821656050954e-05, | |
| "loss": 0.9006, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 15.82, | |
| "eval_loss": 0.19844159483909607, | |
| "eval_runtime": 435.4721, | |
| "eval_samples_per_second": 14.256, | |
| "eval_steps_per_second": 0.891, | |
| "eval_wer": 0.17574523340215045, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 15.87, | |
| "learning_rate": 1.746496815286624e-05, | |
| "loss": 0.8845, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 15.93, | |
| "learning_rate": 1.7226114649681527e-05, | |
| "loss": 0.8991, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "learning_rate": 1.6987261146496814e-05, | |
| "loss": 0.9266, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 16.05, | |
| "learning_rate": 1.67484076433121e-05, | |
| "loss": 0.9535, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "learning_rate": 1.6509554140127387e-05, | |
| "loss": 0.9027, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "eval_loss": 0.20223206281661987, | |
| "eval_runtime": 434.737, | |
| "eval_samples_per_second": 14.28, | |
| "eval_steps_per_second": 0.892, | |
| "eval_wer": 0.17431595467411512, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 1.6270700636942674e-05, | |
| "loss": 0.9095, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 16.21, | |
| "learning_rate": 1.603184713375796e-05, | |
| "loss": 0.9024, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 16.27, | |
| "learning_rate": 1.5792993630573248e-05, | |
| "loss": 0.9135, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 16.33, | |
| "learning_rate": 1.5554140127388534e-05, | |
| "loss": 0.9013, | |
| "step": 14450 | |
| }, | |
| { | |
| "epoch": 16.38, | |
| "learning_rate": 1.531528662420382e-05, | |
| "loss": 0.9083, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 16.38, | |
| "eval_loss": 0.19693595170974731, | |
| "eval_runtime": 437.2683, | |
| "eval_samples_per_second": 14.197, | |
| "eval_steps_per_second": 0.887, | |
| "eval_wer": 0.1744000298934113, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 1.5076433121019106e-05, | |
| "loss": 0.9173, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 16.5, | |
| "learning_rate": 1.4837579617834393e-05, | |
| "loss": 0.9133, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 16.55, | |
| "learning_rate": 1.459872611464968e-05, | |
| "loss": 0.9161, | |
| "step": 14650 | |
| }, | |
| { | |
| "epoch": 16.61, | |
| "learning_rate": 1.4359872611464966e-05, | |
| "loss": 0.8844, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 1.4121019108280253e-05, | |
| "loss": 0.9761, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 16.67, | |
| "eval_loss": 0.19631367921829224, | |
| "eval_runtime": 434.2237, | |
| "eval_samples_per_second": 14.297, | |
| "eval_steps_per_second": 0.894, | |
| "eval_wer": 0.17276523396265192, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 1.388216560509554e-05, | |
| "loss": 0.9057, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 16.78, | |
| "learning_rate": 1.3643312101910826e-05, | |
| "loss": 0.9128, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 16.84, | |
| "learning_rate": 1.3404458598726113e-05, | |
| "loss": 0.9056, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 1.31656050955414e-05, | |
| "loss": 0.9024, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 16.95, | |
| "learning_rate": 1.2926751592356687e-05, | |
| "loss": 0.9311, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 16.95, | |
| "eval_loss": 0.19600756466388702, | |
| "eval_runtime": 438.9128, | |
| "eval_samples_per_second": 14.144, | |
| "eval_steps_per_second": 0.884, | |
| "eval_wer": 0.1736807196838772, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 1.2687898089171973e-05, | |
| "loss": 0.9372, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 17.06, | |
| "learning_rate": 1.244904458598726e-05, | |
| "loss": 0.8955, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "learning_rate": 1.2210191082802547e-05, | |
| "loss": 0.909, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 17.17, | |
| "learning_rate": 1.1971337579617834e-05, | |
| "loss": 0.9092, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 17.23, | |
| "learning_rate": 1.173248407643312e-05, | |
| "loss": 0.886, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 17.23, | |
| "eval_loss": 0.1928754597902298, | |
| "eval_runtime": 438.297, | |
| "eval_samples_per_second": 14.164, | |
| "eval_steps_per_second": 0.885, | |
| "eval_wer": 0.17263445028819116, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 17.29, | |
| "learning_rate": 1.1493630573248407e-05, | |
| "loss": 0.9053, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 17.34, | |
| "learning_rate": 1.1254777070063694e-05, | |
| "loss": 0.9056, | |
| "step": 15350 | |
| }, | |
| { | |
| "epoch": 17.4, | |
| "learning_rate": 1.101592356687898e-05, | |
| "loss": 0.9219, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 17.46, | |
| "learning_rate": 1.0777070063694267e-05, | |
| "loss": 0.8967, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 17.51, | |
| "learning_rate": 1.0538216560509554e-05, | |
| "loss": 0.8969, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 17.51, | |
| "eval_loss": 0.1928360015153885, | |
| "eval_runtime": 442.1109, | |
| "eval_samples_per_second": 14.042, | |
| "eval_steps_per_second": 0.878, | |
| "eval_wer": 0.17337244387979112, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 17.57, | |
| "learning_rate": 1.029936305732484e-05, | |
| "loss": 0.8899, | |
| "step": 15550 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 1.0060509554140127e-05, | |
| "loss": 0.9056, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 17.68, | |
| "learning_rate": 9.821656050955414e-06, | |
| "loss": 0.9048, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 17.74, | |
| "learning_rate": 9.582802547770701e-06, | |
| "loss": 0.9572, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 9.34872611464968e-06, | |
| "loss": 0.9084, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "eval_loss": 0.19373278319835663, | |
| "eval_runtime": 446.3693, | |
| "eval_samples_per_second": 13.908, | |
| "eval_steps_per_second": 0.869, | |
| "eval_wer": 0.17133595523461656, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 17.85, | |
| "learning_rate": 9.109872611464967e-06, | |
| "loss": 0.8861, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 8.871019108280254e-06, | |
| "loss": 0.8842, | |
| "step": 15850 | |
| }, | |
| { | |
| "epoch": 17.97, | |
| "learning_rate": 8.63216560509554e-06, | |
| "loss": 0.8949, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 8.398089171974522e-06, | |
| "loss": 0.8977, | |
| "step": 15950 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 8.159235668789809e-06, | |
| "loss": 0.8795, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "eval_loss": 0.1977699100971222, | |
| "eval_runtime": 437.7611, | |
| "eval_samples_per_second": 14.181, | |
| "eval_steps_per_second": 0.886, | |
| "eval_wer": 0.17086887068297102, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 18.14, | |
| "learning_rate": 7.920382165605094e-06, | |
| "loss": 0.8984, | |
| "step": 16050 | |
| }, | |
| { | |
| "epoch": 18.19, | |
| "learning_rate": 7.68152866242038e-06, | |
| "loss": 0.9005, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 18.25, | |
| "learning_rate": 7.4426751592356675e-06, | |
| "loss": 0.8981, | |
| "step": 16150 | |
| }, | |
| { | |
| "epoch": 18.3, | |
| "learning_rate": 7.203821656050954e-06, | |
| "loss": 0.9029, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 18.36, | |
| "learning_rate": 6.964968152866241e-06, | |
| "loss": 0.8883, | |
| "step": 16250 | |
| }, | |
| { | |
| "epoch": 18.36, | |
| "eval_loss": 0.19563348591327667, | |
| "eval_runtime": 434.7761, | |
| "eval_samples_per_second": 14.279, | |
| "eval_steps_per_second": 0.892, | |
| "eval_wer": 0.17032705260306222, | |
| "step": 16250 | |
| }, | |
| { | |
| "epoch": 18.42, | |
| "learning_rate": 6.726114649681528e-06, | |
| "loss": 0.8919, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 18.47, | |
| "learning_rate": 6.4872611464968145e-06, | |
| "loss": 0.8978, | |
| "step": 16350 | |
| }, | |
| { | |
| "epoch": 18.53, | |
| "learning_rate": 6.248407643312101e-06, | |
| "loss": 0.8897, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 18.59, | |
| "learning_rate": 6.009554140127388e-06, | |
| "loss": 0.9477, | |
| "step": 16450 | |
| }, | |
| { | |
| "epoch": 18.64, | |
| "learning_rate": 5.770700636942675e-06, | |
| "loss": 0.8901, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 18.64, | |
| "eval_loss": 0.19332656264305115, | |
| "eval_runtime": 439.133, | |
| "eval_samples_per_second": 14.137, | |
| "eval_steps_per_second": 0.884, | |
| "eval_wer": 0.17053256980578624, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 18.7, | |
| "learning_rate": 5.531847133757961e-06, | |
| "loss": 0.8992, | |
| "step": 16550 | |
| }, | |
| { | |
| "epoch": 18.76, | |
| "learning_rate": 5.292993630573248e-06, | |
| "loss": 0.8988, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 18.81, | |
| "learning_rate": 5.054140127388535e-06, | |
| "loss": 0.8885, | |
| "step": 16650 | |
| }, | |
| { | |
| "epoch": 18.87, | |
| "learning_rate": 4.815286624203822e-06, | |
| "loss": 0.8837, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 18.93, | |
| "learning_rate": 4.576433121019108e-06, | |
| "loss": 0.8922, | |
| "step": 16750 | |
| }, | |
| { | |
| "epoch": 18.93, | |
| "eval_loss": 0.1962379515171051, | |
| "eval_runtime": 444.5287, | |
| "eval_samples_per_second": 13.965, | |
| "eval_steps_per_second": 0.873, | |
| "eval_wer": 0.17109307126776088, | |
| "step": 16750 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "learning_rate": 4.337579617834394e-06, | |
| "loss": 0.8943, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 4.098726114649681e-06, | |
| "loss": 0.9171, | |
| "step": 16850 | |
| }, | |
| { | |
| "epoch": 19.1, | |
| "learning_rate": 3.859872611464968e-06, | |
| "loss": 0.9144, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 19.15, | |
| "learning_rate": 3.6210191082802544e-06, | |
| "loss": 0.9517, | |
| "step": 16950 | |
| }, | |
| { | |
| "epoch": 19.21, | |
| "learning_rate": 3.382165605095541e-06, | |
| "loss": 0.8765, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 19.21, | |
| "eval_loss": 0.19622743129730225, | |
| "eval_runtime": 445.8046, | |
| "eval_samples_per_second": 13.925, | |
| "eval_steps_per_second": 0.87, | |
| "eval_wer": 0.17106504619466215, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 19.27, | |
| "learning_rate": 3.143312101910828e-06, | |
| "loss": 0.9072, | |
| "step": 17050 | |
| }, | |
| { | |
| "epoch": 19.32, | |
| "learning_rate": 2.9044585987261146e-06, | |
| "loss": 0.8897, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 19.38, | |
| "learning_rate": 2.6656050955414013e-06, | |
| "loss": 0.8879, | |
| "step": 17150 | |
| }, | |
| { | |
| "epoch": 19.43, | |
| "learning_rate": 2.426751592356688e-06, | |
| "loss": 0.883, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "learning_rate": 2.1878980891719744e-06, | |
| "loss": 0.8992, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 19.49, | |
| "eval_loss": 0.19645148515701294, | |
| "eval_runtime": 447.1526, | |
| "eval_samples_per_second": 13.883, | |
| "eval_steps_per_second": 0.868, | |
| "eval_wer": 0.17034573598512803, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 19.55, | |
| "learning_rate": 1.949044585987261e-06, | |
| "loss": 0.8969, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 19.6, | |
| "learning_rate": 1.7101910828025476e-06, | |
| "loss": 0.872, | |
| "step": 17350 | |
| }, | |
| { | |
| "epoch": 19.66, | |
| "learning_rate": 1.4713375796178341e-06, | |
| "loss": 0.8984, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 19.72, | |
| "learning_rate": 1.2324840764331209e-06, | |
| "loss": 0.8913, | |
| "step": 17450 | |
| }, | |
| { | |
| "epoch": 19.77, | |
| "learning_rate": 9.936305732484076e-07, | |
| "loss": 0.8778, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 19.77, | |
| "eval_loss": 0.19571013748645782, | |
| "eval_runtime": 442.6975, | |
| "eval_samples_per_second": 14.023, | |
| "eval_steps_per_second": 0.876, | |
| "eval_wer": 0.16990667650658123, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 19.83, | |
| "learning_rate": 7.547770700636942e-07, | |
| "loss": 0.8687, | |
| "step": 17550 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "learning_rate": 5.159235668789809e-07, | |
| "loss": 0.8858, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 19.94, | |
| "learning_rate": 2.770700636942675e-07, | |
| "loss": 0.8854, | |
| "step": 17650 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.821656050955413e-08, | |
| "loss": 0.8898, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 17700, | |
| "total_flos": 2.3221664293970497e+20, | |
| "train_loss": 1.2649466082470566, | |
| "train_runtime": 115228.5602, | |
| "train_samples_per_second": 9.837, | |
| "train_steps_per_second": 0.154 | |
| } | |
| ], | |
| "max_steps": 17700, | |
| "num_train_epochs": 20, | |
| "total_flos": 2.3221664293970497e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |