| { | |
| "best_metric": 16.15101446793939, | |
| "best_model_checkpoint": "./checkpoint-40000", | |
| "epoch": 2.183, | |
| "global_step": 40000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.2000000000000006e-07, | |
| "loss": 1.6852, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.200000000000001e-07, | |
| "loss": 1.5743, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.42e-06, | |
| "loss": 1.2718, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9200000000000003e-06, | |
| "loss": 1.1704, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.42e-06, | |
| "loss": 1.0509, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.92e-06, | |
| "loss": 0.7776, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.4200000000000007e-06, | |
| "loss": 0.8348, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.920000000000001e-06, | |
| "loss": 0.7947, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.42e-06, | |
| "loss": 0.743, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.92e-06, | |
| "loss": 0.8482, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.420000000000001e-06, | |
| "loss": 0.7226, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.92e-06, | |
| "loss": 0.7068, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.42e-06, | |
| "loss": 0.6329, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.92e-06, | |
| "loss": 0.7035, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.420000000000001e-06, | |
| "loss": 0.6298, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.92e-06, | |
| "loss": 0.7167, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.42e-06, | |
| "loss": 0.7104, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.920000000000001e-06, | |
| "loss": 0.6434, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.42e-06, | |
| "loss": 0.6046, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.920000000000002e-06, | |
| "loss": 0.6629, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.994683544303798e-06, | |
| "loss": 0.6469, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.988354430379748e-06, | |
| "loss": 0.617, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.982025316455697e-06, | |
| "loss": 0.6232, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.975696202531647e-06, | |
| "loss": 0.6766, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.969367088607596e-06, | |
| "loss": 0.5821, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.963037974683545e-06, | |
| "loss": 0.6666, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.956708860759495e-06, | |
| "loss": 0.6084, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.950379746835444e-06, | |
| "loss": 0.5496, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.944050632911392e-06, | |
| "loss": 0.62, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.937721518987341e-06, | |
| "loss": 0.5629, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.931392405063291e-06, | |
| "loss": 0.5347, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.92506329113924e-06, | |
| "loss": 0.5869, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.91873417721519e-06, | |
| "loss": 0.614, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.912405063291141e-06, | |
| "loss": 0.5689, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.90607594936709e-06, | |
| "loss": 0.6178, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.89974683544304e-06, | |
| "loss": 0.6134, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.89341772151899e-06, | |
| "loss": 0.5932, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.887341772151899e-06, | |
| "loss": 0.6773, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.881012658227848e-06, | |
| "loss": 0.7507, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.874683544303798e-06, | |
| "loss": 0.5664, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.868354430379747e-06, | |
| "loss": 0.4934, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.862025316455697e-06, | |
| "loss": 0.5561, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.855696202531646e-06, | |
| "loss": 0.6336, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.849367088607596e-06, | |
| "loss": 0.4965, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.843037974683545e-06, | |
| "loss": 0.4645, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.836708860759494e-06, | |
| "loss": 0.6469, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.830379746835444e-06, | |
| "loss": 0.5398, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.824050632911393e-06, | |
| "loss": 0.5969, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.817721518987343e-06, | |
| "loss": 0.4994, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.811392405063292e-06, | |
| "loss": 0.5301, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.805063291139241e-06, | |
| "loss": 0.527, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.798734177215191e-06, | |
| "loss": 0.5424, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.79240506329114e-06, | |
| "loss": 0.4419, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.78607594936709e-06, | |
| "loss": 0.4622, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.77974683544304e-06, | |
| "loss": 0.5263, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.773417721518989e-06, | |
| "loss": 0.5191, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.767088607594938e-06, | |
| "loss": 0.6094, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.760759493670887e-06, | |
| "loss": 0.5759, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.754430379746837e-06, | |
| "loss": 0.6031, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.748101265822786e-06, | |
| "loss": 0.5171, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.741772151898736e-06, | |
| "loss": 0.6238, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.735443037974685e-06, | |
| "loss": 0.55, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.729113924050635e-06, | |
| "loss": 0.5395, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.722784810126582e-06, | |
| "loss": 0.4911, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.716455696202532e-06, | |
| "loss": 0.524, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.710126582278481e-06, | |
| "loss": 0.4771, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.70379746835443e-06, | |
| "loss": 0.5305, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.69746835443038e-06, | |
| "loss": 0.5589, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.69113924050633e-06, | |
| "loss": 0.5956, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.684810126582279e-06, | |
| "loss": 0.446, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.678481012658228e-06, | |
| "loss": 0.5557, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.672151898734178e-06, | |
| "loss": 0.4853, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.665822784810127e-06, | |
| "loss": 0.5207, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.659493670886077e-06, | |
| "loss": 0.5753, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.653164556962026e-06, | |
| "loss": 0.5257, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.646835443037975e-06, | |
| "loss": 0.4626, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.640506329113925e-06, | |
| "loss": 0.5095, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.634177215189874e-06, | |
| "loss": 0.4848, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.627848101265824e-06, | |
| "loss": 0.4908, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.621518987341773e-06, | |
| "loss": 0.495, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.615189873417723e-06, | |
| "loss": 0.5705, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.60886075949367e-06, | |
| "loss": 0.4382, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.602531645569621e-06, | |
| "loss": 0.4829, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.596202531645571e-06, | |
| "loss": 0.5676, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.58987341772152e-06, | |
| "loss": 0.4929, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.58354430379747e-06, | |
| "loss": 0.4871, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.57721518987342e-06, | |
| "loss": 0.5028, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.570886075949369e-06, | |
| "loss": 0.4807, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.564556962025318e-06, | |
| "loss": 0.4985, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.558227848101267e-06, | |
| "loss": 0.5622, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.551898734177217e-06, | |
| "loss": 0.4998, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.545569620253166e-06, | |
| "loss": 0.5458, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.539240506329114e-06, | |
| "loss": 0.482, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.532911392405063e-06, | |
| "loss": 0.5677, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.526582278481013e-06, | |
| "loss": 0.4714, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.520253164556962e-06, | |
| "loss": 0.4993, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.513924050632912e-06, | |
| "loss": 0.3853, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.507594936708861e-06, | |
| "loss": 0.467, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.50126582278481e-06, | |
| "loss": 0.5533, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.49493670886076e-06, | |
| "loss": 0.5751, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.48860759493671e-06, | |
| "loss": 0.4985, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.482278481012659e-06, | |
| "loss": 0.5662, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.475949367088608e-06, | |
| "loss": 0.4398, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.469620253164558e-06, | |
| "loss": 0.4791, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.463291139240507e-06, | |
| "loss": 0.4777, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.456962025316457e-06, | |
| "loss": 0.5294, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.450632911392406e-06, | |
| "loss": 0.4441, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.444303797468355e-06, | |
| "loss": 0.4972, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.437974683544305e-06, | |
| "loss": 0.5192, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.431645569620254e-06, | |
| "loss": 0.5209, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.425316455696202e-06, | |
| "loss": 0.4344, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.418987341772152e-06, | |
| "loss": 0.5466, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.412658227848101e-06, | |
| "loss": 0.4845, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.40632911392405e-06, | |
| "loss": 0.4413, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.4e-06, | |
| "loss": 0.4946, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.393670886075951e-06, | |
| "loss": 0.517, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.3873417721519e-06, | |
| "loss": 0.5026, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.38101265822785e-06, | |
| "loss": 0.4185, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.3746835443038e-06, | |
| "loss": 0.5162, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.368354430379749e-06, | |
| "loss": 0.5227, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.362025316455698e-06, | |
| "loss": 0.4825, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.355696202531647e-06, | |
| "loss": 0.4092, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.349367088607595e-06, | |
| "loss": 0.5103, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.343037974683545e-06, | |
| "loss": 0.5256, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.336708860759494e-06, | |
| "loss": 0.4289, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.330379746835443e-06, | |
| "loss": 0.4829, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.324050632911393e-06, | |
| "loss": 0.5108, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.317721518987342e-06, | |
| "loss": 0.4781, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.311392405063292e-06, | |
| "loss": 0.4681, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.305063291139241e-06, | |
| "loss": 0.4487, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.29873417721519e-06, | |
| "loss": 0.4171, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.29240506329114e-06, | |
| "loss": 0.4537, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.28607594936709e-06, | |
| "loss": 0.5124, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.279746835443039e-06, | |
| "loss": 0.4742, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 9.273417721518988e-06, | |
| "loss": 0.4539, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.267088607594938e-06, | |
| "loss": 0.5328, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.260759493670887e-06, | |
| "loss": 0.5632, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.254430379746837e-06, | |
| "loss": 0.5312, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.248101265822786e-06, | |
| "loss": 0.4271, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.241772151898735e-06, | |
| "loss": 0.4776, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.235443037974683e-06, | |
| "loss": 0.3904, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.229113924050633e-06, | |
| "loss": 0.4998, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.222784810126582e-06, | |
| "loss": 0.4878, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.216455696202531e-06, | |
| "loss": 0.3845, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.210126582278481e-06, | |
| "loss": 0.5193, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.20379746835443e-06, | |
| "loss": 0.4537, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.19746835443038e-06, | |
| "loss": 0.4413, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.19113924050633e-06, | |
| "loss": 0.519, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.18481012658228e-06, | |
| "loss": 0.4088, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.17848101265823e-06, | |
| "loss": 0.5331, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.17215189873418e-06, | |
| "loss": 0.4513, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.165822784810129e-06, | |
| "loss": 0.4597, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.159493670886076e-06, | |
| "loss": 0.4986, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.153164556962026e-06, | |
| "loss": 0.3976, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.146835443037975e-06, | |
| "loss": 0.4769, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.140506329113925e-06, | |
| "loss": 0.3409, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.134430379746836e-06, | |
| "loss": 0.4042, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.128101265822786e-06, | |
| "loss": 0.5517, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.121772151898735e-06, | |
| "loss": 0.5513, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.115443037974684e-06, | |
| "loss": 0.4841, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.5078244805335999, | |
| "eval_runtime": 6518.8523, | |
| "eval_samples_per_second": 2.507, | |
| "eval_steps_per_second": 2.507, | |
| "eval_wer": 26.79736323944868, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.109113924050634e-06, | |
| "loss": 0.4645, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.102784810126583e-06, | |
| "loss": 0.5303, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.096455696202533e-06, | |
| "loss": 0.4339, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.09012658227848e-06, | |
| "loss": 0.4774, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.083797468354431e-06, | |
| "loss": 0.5013, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.077468354430381e-06, | |
| "loss": 0.5143, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.07113924050633e-06, | |
| "loss": 0.465, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.06481012658228e-06, | |
| "loss": 0.4856, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.05848101265823e-06, | |
| "loss": 0.471, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.052151898734179e-06, | |
| "loss": 0.4591, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.045822784810128e-06, | |
| "loss": 0.4239, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.039493670886077e-06, | |
| "loss": 0.4367, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.033164556962027e-06, | |
| "loss": 0.5036, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.026835443037976e-06, | |
| "loss": 0.5417, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.020506329113926e-06, | |
| "loss": 0.4638, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.014177215189874e-06, | |
| "loss": 0.5338, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.007848101265823e-06, | |
| "loss": 0.4771, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.001518987341772e-06, | |
| "loss": 0.4091, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.995189873417722e-06, | |
| "loss": 0.4116, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.988860759493671e-06, | |
| "loss": 0.4381, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.98253164556962e-06, | |
| "loss": 0.4343, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.97620253164557e-06, | |
| "loss": 0.3768, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8.96987341772152e-06, | |
| "loss": 0.3952, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.963544303797469e-06, | |
| "loss": 0.5177, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.957215189873418e-06, | |
| "loss": 0.4361, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.950886075949368e-06, | |
| "loss": 0.4693, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.944556962025317e-06, | |
| "loss": 0.3954, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.938227848101267e-06, | |
| "loss": 0.4873, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.931898734177216e-06, | |
| "loss": 0.4296, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.925569620253165e-06, | |
| "loss": 0.4191, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.919240506329115e-06, | |
| "loss": 0.3746, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.912911392405064e-06, | |
| "loss": 0.4347, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.906582278481014e-06, | |
| "loss": 0.3654, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.900253164556962e-06, | |
| "loss": 0.3887, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.893924050632911e-06, | |
| "loss": 0.4564, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.88759493670886e-06, | |
| "loss": 0.4855, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.88126582278481e-06, | |
| "loss": 0.4042, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.874936708860761e-06, | |
| "loss": 0.459, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.86860759493671e-06, | |
| "loss": 0.4849, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 8.86227848101266e-06, | |
| "loss": 0.3959, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.85594936708861e-06, | |
| "loss": 0.4176, | |
| "step": 5025 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.849620253164559e-06, | |
| "loss": 0.3943, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.843291139240508e-06, | |
| "loss": 0.4396, | |
| "step": 5075 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.836962025316457e-06, | |
| "loss": 0.4637, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.830632911392407e-06, | |
| "loss": 0.4206, | |
| "step": 5125 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.824303797468355e-06, | |
| "loss": 0.5061, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.817974683544304e-06, | |
| "loss": 0.5287, | |
| "step": 5175 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.811645569620254e-06, | |
| "loss": 0.4259, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.805316455696203e-06, | |
| "loss": 0.3896, | |
| "step": 5225 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.798987341772152e-06, | |
| "loss": 0.5181, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.792658227848102e-06, | |
| "loss": 0.4004, | |
| "step": 5275 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.786329113924051e-06, | |
| "loss": 0.4263, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.78e-06, | |
| "loss": 0.3388, | |
| "step": 5325 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.77367088607595e-06, | |
| "loss": 0.4846, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.7673417721519e-06, | |
| "loss": 0.4283, | |
| "step": 5375 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.761012658227849e-06, | |
| "loss": 0.4845, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.754683544303798e-06, | |
| "loss": 0.4403, | |
| "step": 5425 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.748354430379748e-06, | |
| "loss": 0.3729, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.742025316455697e-06, | |
| "loss": 0.4437, | |
| "step": 5475 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.735696202531647e-06, | |
| "loss": 0.4122, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.729367088607596e-06, | |
| "loss": 0.4552, | |
| "step": 5525 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.723037974683545e-06, | |
| "loss": 0.4393, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.716708860759495e-06, | |
| "loss": 0.5056, | |
| "step": 5575 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.710379746835443e-06, | |
| "loss": 0.3571, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.704050632911392e-06, | |
| "loss": 0.4501, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.697721518987342e-06, | |
| "loss": 0.4409, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.691392405063291e-06, | |
| "loss": 0.3875, | |
| "step": 5675 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.68506329113924e-06, | |
| "loss": 0.3925, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.67873417721519e-06, | |
| "loss": 0.3982, | |
| "step": 5725 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.67240506329114e-06, | |
| "loss": 0.3466, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.66607594936709e-06, | |
| "loss": 0.3945, | |
| "step": 5775 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.65974683544304e-06, | |
| "loss": 0.386, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.65341772151899e-06, | |
| "loss": 0.4658, | |
| "step": 5825 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.647088607594939e-06, | |
| "loss": 0.4189, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.640759493670886e-06, | |
| "loss": 0.4923, | |
| "step": 5875 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.634430379746836e-06, | |
| "loss": 0.4829, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.628101265822785e-06, | |
| "loss": 0.4544, | |
| "step": 5925 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.621772151898735e-06, | |
| "loss": 0.435, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.615443037974684e-06, | |
| "loss": 0.5216, | |
| "step": 5975 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.609113924050633e-06, | |
| "loss": 0.4366, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.602784810126583e-06, | |
| "loss": 0.4013, | |
| "step": 6025 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.596455696202532e-06, | |
| "loss": 0.4395, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.590126582278482e-06, | |
| "loss": 0.4621, | |
| "step": 6075 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.583797468354431e-06, | |
| "loss": 0.424, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.57746835443038e-06, | |
| "loss": 0.4921, | |
| "step": 6125 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.57113924050633e-06, | |
| "loss": 0.3712, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.56481012658228e-06, | |
| "loss": 0.4441, | |
| "step": 6175 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.558481012658229e-06, | |
| "loss": 0.4644, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.552151898734178e-06, | |
| "loss": 0.352, | |
| "step": 6225 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.545822784810128e-06, | |
| "loss": 0.3975, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.539493670886077e-06, | |
| "loss": 0.4969, | |
| "step": 6275 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.533164556962027e-06, | |
| "loss": 0.3795, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.526835443037974e-06, | |
| "loss": 0.4525, | |
| "step": 6325 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.520506329113924e-06, | |
| "loss": 0.3709, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.514177215189873e-06, | |
| "loss": 0.3499, | |
| "step": 6375 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.508101265822786e-06, | |
| "loss": 0.3822, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.501772151898736e-06, | |
| "loss": 0.3862, | |
| "step": 6425 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.495443037974685e-06, | |
| "loss": 0.4611, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.489113924050633e-06, | |
| "loss": 0.3971, | |
| "step": 6475 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.482784810126582e-06, | |
| "loss": 0.4778, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.476455696202532e-06, | |
| "loss": 0.4276, | |
| "step": 6525 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.470126582278481e-06, | |
| "loss": 0.4063, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.46379746835443e-06, | |
| "loss": 0.381, | |
| "step": 6575 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.45746835443038e-06, | |
| "loss": 0.3527, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.45113924050633e-06, | |
| "loss": 0.3836, | |
| "step": 6625 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.444810126582279e-06, | |
| "loss": 0.4008, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.438481012658228e-06, | |
| "loss": 0.3894, | |
| "step": 6675 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.432151898734178e-06, | |
| "loss": 0.3895, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.425822784810127e-06, | |
| "loss": 0.485, | |
| "step": 6725 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.419493670886077e-06, | |
| "loss": 0.4116, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.413164556962026e-06, | |
| "loss": 0.4548, | |
| "step": 6775 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.406835443037976e-06, | |
| "loss": 0.3369, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.400506329113925e-06, | |
| "loss": 0.416, | |
| "step": 6825 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.394177215189874e-06, | |
| "loss": 0.3342, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.387848101265824e-06, | |
| "loss": 0.3914, | |
| "step": 6875 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.381518987341773e-06, | |
| "loss": 0.4392, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.375189873417721e-06, | |
| "loss": 0.3944, | |
| "step": 6925 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.36886075949367e-06, | |
| "loss": 0.3034, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.36253164556962e-06, | |
| "loss": 0.4975, | |
| "step": 6975 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.356202531645571e-06, | |
| "loss": 0.3618, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.34987341772152e-06, | |
| "loss": 0.337, | |
| "step": 7025 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.34354430379747e-06, | |
| "loss": 0.3956, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.33721518987342e-06, | |
| "loss": 0.3648, | |
| "step": 7075 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.330886075949369e-06, | |
| "loss": 0.3249, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.324556962025318e-06, | |
| "loss": 0.403, | |
| "step": 7125 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.318227848101267e-06, | |
| "loss": 0.3155, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.311898734177217e-06, | |
| "loss": 0.3616, | |
| "step": 7175 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.305569620253165e-06, | |
| "loss": 0.3203, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.299240506329114e-06, | |
| "loss": 0.3823, | |
| "step": 7225 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.292911392405064e-06, | |
| "loss": 0.3353, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.286582278481013e-06, | |
| "loss": 0.4452, | |
| "step": 7275 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.280253164556962e-06, | |
| "loss": 0.4386, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.273924050632912e-06, | |
| "loss": 0.4161, | |
| "step": 7325 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.267594936708861e-06, | |
| "loss": 0.313, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.26126582278481e-06, | |
| "loss": 0.31, | |
| "step": 7375 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 8.25493670886076e-06, | |
| "loss": 0.3937, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.24860759493671e-06, | |
| "loss": 0.3055, | |
| "step": 7425 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.242278481012659e-06, | |
| "loss": 0.3673, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.235949367088608e-06, | |
| "loss": 0.3201, | |
| "step": 7475 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.229620253164558e-06, | |
| "loss": 0.3333, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.223291139240507e-06, | |
| "loss": 0.3441, | |
| "step": 7525 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.216962025316457e-06, | |
| "loss": 0.3682, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.210632911392406e-06, | |
| "loss": 0.3308, | |
| "step": 7575 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.204303797468356e-06, | |
| "loss": 0.3391, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.197974683544305e-06, | |
| "loss": 0.352, | |
| "step": 7625 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.191645569620253e-06, | |
| "loss": 0.3003, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.185316455696202e-06, | |
| "loss": 0.416, | |
| "step": 7675 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.178987341772152e-06, | |
| "loss": 0.3845, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.172658227848101e-06, | |
| "loss": 0.4108, | |
| "step": 7725 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.16632911392405e-06, | |
| "loss": 0.2749, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 8.16e-06, | |
| "loss": 0.3624, | |
| "step": 7775 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.153670886075951e-06, | |
| "loss": 0.3726, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.1473417721519e-06, | |
| "loss": 0.4032, | |
| "step": 7825 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.14101265822785e-06, | |
| "loss": 0.3856, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.1346835443038e-06, | |
| "loss": 0.3264, | |
| "step": 7875 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.128354430379749e-06, | |
| "loss": 0.305, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.122025316455698e-06, | |
| "loss": 0.3683, | |
| "step": 7925 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.115696202531646e-06, | |
| "loss": 0.4154, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.109367088607595e-06, | |
| "loss": 0.3062, | |
| "step": 7975 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.103037974683545e-06, | |
| "loss": 0.3116, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.45240867137908936, | |
| "eval_runtime": 6471.7586, | |
| "eval_samples_per_second": 2.525, | |
| "eval_steps_per_second": 2.525, | |
| "eval_wer": 22.945524070427762, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.096708860759494e-06, | |
| "loss": 0.2755, | |
| "step": 8025 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.090379746835444e-06, | |
| "loss": 0.3846, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.084050632911393e-06, | |
| "loss": 0.3823, | |
| "step": 8075 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.077721518987342e-06, | |
| "loss": 0.2875, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.071392405063292e-06, | |
| "loss": 0.2956, | |
| "step": 8125 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.065063291139241e-06, | |
| "loss": 0.2636, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.05873417721519e-06, | |
| "loss": 0.4318, | |
| "step": 8175 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.05240506329114e-06, | |
| "loss": 0.3456, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.04607594936709e-06, | |
| "loss": 0.2807, | |
| "step": 8225 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.039746835443039e-06, | |
| "loss": 0.306, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.033417721518988e-06, | |
| "loss": 0.3135, | |
| "step": 8275 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.027088607594938e-06, | |
| "loss": 0.325, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.020759493670887e-06, | |
| "loss": 0.302, | |
| "step": 8325 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.014430379746837e-06, | |
| "loss": 0.3477, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.008101265822786e-06, | |
| "loss": 0.2431, | |
| "step": 8375 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.001772151898734e-06, | |
| "loss": 0.2498, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.995443037974683e-06, | |
| "loss": 0.3386, | |
| "step": 8425 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.989113924050633e-06, | |
| "loss": 0.3444, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.982784810126582e-06, | |
| "loss": 0.2869, | |
| "step": 8475 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.976455696202532e-06, | |
| "loss": 0.386, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.970126582278481e-06, | |
| "loss": 0.3064, | |
| "step": 8525 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.96379746835443e-06, | |
| "loss": 0.2879, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.95746835443038e-06, | |
| "loss": 0.3693, | |
| "step": 8575 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 7.95113924050633e-06, | |
| "loss": 0.3273, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.94481012658228e-06, | |
| "loss": 0.3384, | |
| "step": 8625 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.93848101265823e-06, | |
| "loss": 0.3984, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.932151898734178e-06, | |
| "loss": 0.2294, | |
| "step": 8675 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.925822784810127e-06, | |
| "loss": 0.2873, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.919493670886076e-06, | |
| "loss": 0.3858, | |
| "step": 8725 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.913164556962026e-06, | |
| "loss": 0.2774, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.906835443037975e-06, | |
| "loss": 0.3443, | |
| "step": 8775 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.900506329113925e-06, | |
| "loss": 0.402, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.894177215189874e-06, | |
| "loss": 0.3688, | |
| "step": 8825 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.887848101265823e-06, | |
| "loss": 0.3253, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.881518987341773e-06, | |
| "loss": 0.3769, | |
| "step": 8875 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.875189873417722e-06, | |
| "loss": 0.2975, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.868860759493672e-06, | |
| "loss": 0.3221, | |
| "step": 8925 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.862531645569621e-06, | |
| "loss": 0.3369, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.85620253164557e-06, | |
| "loss": 0.3168, | |
| "step": 8975 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.84987341772152e-06, | |
| "loss": 0.3426, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.84354430379747e-06, | |
| "loss": 0.4143, | |
| "step": 9025 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.837215189873419e-06, | |
| "loss": 0.2826, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.830886075949368e-06, | |
| "loss": 0.3214, | |
| "step": 9075 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.824556962025318e-06, | |
| "loss": 0.3747, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.818227848101266e-06, | |
| "loss": 0.2768, | |
| "step": 9125 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.811898734177215e-06, | |
| "loss": 0.3738, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.805569620253164e-06, | |
| "loss": 0.3538, | |
| "step": 9175 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.799240506329114e-06, | |
| "loss": 0.4079, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.792911392405063e-06, | |
| "loss": 0.2782, | |
| "step": 9225 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.786582278481013e-06, | |
| "loss": 0.3919, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.780253164556962e-06, | |
| "loss": 0.3926, | |
| "step": 9275 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.773924050632912e-06, | |
| "loss": 0.3492, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.767594936708861e-06, | |
| "loss": 0.3435, | |
| "step": 9325 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.761518987341772e-06, | |
| "loss": 0.3825, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.755189873417722e-06, | |
| "loss": 0.2672, | |
| "step": 9375 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 7.748860759493671e-06, | |
| "loss": 0.3187, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.74253164556962e-06, | |
| "loss": 0.2822, | |
| "step": 9425 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.73620253164557e-06, | |
| "loss": 0.3543, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.72987341772152e-06, | |
| "loss": 0.3237, | |
| "step": 9475 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.723544303797469e-06, | |
| "loss": 0.2681, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.717215189873418e-06, | |
| "loss": 0.3514, | |
| "step": 9525 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.710886075949368e-06, | |
| "loss": 0.4098, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.704556962025317e-06, | |
| "loss": 0.3585, | |
| "step": 9575 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.698227848101267e-06, | |
| "loss": 0.322, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.691898734177216e-06, | |
| "loss": 0.3116, | |
| "step": 9625 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.685569620253166e-06, | |
| "loss": 0.3833, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.679240506329115e-06, | |
| "loss": 0.3247, | |
| "step": 9675 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.672911392405064e-06, | |
| "loss": 0.3178, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.666582278481012e-06, | |
| "loss": 0.3303, | |
| "step": 9725 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.660253164556962e-06, | |
| "loss": 0.2717, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.653924050632911e-06, | |
| "loss": 0.2472, | |
| "step": 9775 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 7.64759493670886e-06, | |
| "loss": 0.3801, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.64126582278481e-06, | |
| "loss": 0.2805, | |
| "step": 9825 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.634936708860761e-06, | |
| "loss": 0.3529, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.62860759493671e-06, | |
| "loss": 0.2795, | |
| "step": 9875 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.622278481012659e-06, | |
| "loss": 0.3788, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.615949367088608e-06, | |
| "loss": 0.3479, | |
| "step": 9925 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.609620253164558e-06, | |
| "loss": 0.3311, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.603291139240507e-06, | |
| "loss": 0.2944, | |
| "step": 9975 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.596962025316457e-06, | |
| "loss": 0.3669, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.590632911392406e-06, | |
| "loss": 0.3616, | |
| "step": 10025 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.5843037974683555e-06, | |
| "loss": 0.2922, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.577974683544305e-06, | |
| "loss": 0.3027, | |
| "step": 10075 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.571645569620254e-06, | |
| "loss": 0.2757, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.565316455696203e-06, | |
| "loss": 0.313, | |
| "step": 10125 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.558987341772152e-06, | |
| "loss": 0.3368, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 7.552658227848102e-06, | |
| "loss": 0.3805, | |
| "step": 10175 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.546329113924051e-06, | |
| "loss": 0.3547, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.540000000000001e-06, | |
| "loss": 0.3402, | |
| "step": 10225 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.53367088607595e-06, | |
| "loss": 0.3488, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.5273417721518995e-06, | |
| "loss": 0.4634, | |
| "step": 10275 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.521012658227849e-06, | |
| "loss": 0.2895, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.514683544303798e-06, | |
| "loss": 0.366, | |
| "step": 10325 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.508354430379747e-06, | |
| "loss": 0.3207, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.502025316455696e-06, | |
| "loss": 0.2923, | |
| "step": 10375 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.495696202531646e-06, | |
| "loss": 0.3277, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.489367088607595e-06, | |
| "loss": 0.3314, | |
| "step": 10425 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.483037974683545e-06, | |
| "loss": 0.3532, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.476708860759494e-06, | |
| "loss": 0.2748, | |
| "step": 10475 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.4703797468354435e-06, | |
| "loss": 0.4392, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.464050632911393e-06, | |
| "loss": 0.3385, | |
| "step": 10525 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.457721518987342e-06, | |
| "loss": 0.2886, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.451392405063291e-06, | |
| "loss": 0.4056, | |
| "step": 10575 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.44506329113924e-06, | |
| "loss": 0.3809, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.43873417721519e-06, | |
| "loss": 0.297, | |
| "step": 10625 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.432405063291139e-06, | |
| "loss": 0.4092, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.4260759493670895e-06, | |
| "loss": 0.3803, | |
| "step": 10675 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.419746835443039e-06, | |
| "loss": 0.436, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.413417721518988e-06, | |
| "loss": 0.3864, | |
| "step": 10725 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.407088607594938e-06, | |
| "loss": 0.363, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.400759493670887e-06, | |
| "loss": 0.3604, | |
| "step": 10775 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.394430379746837e-06, | |
| "loss": 0.2909, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.388101265822786e-06, | |
| "loss": 0.4321, | |
| "step": 10825 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.3817721518987355e-06, | |
| "loss": 0.398, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.375443037974684e-06, | |
| "loss": 0.3661, | |
| "step": 10875 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.3691139240506335e-06, | |
| "loss": 0.3276, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.362784810126583e-06, | |
| "loss": 0.3706, | |
| "step": 10925 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.356455696202532e-06, | |
| "loss": 0.3884, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.350126582278482e-06, | |
| "loss": 0.3488, | |
| "step": 10975 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.343797468354431e-06, | |
| "loss": 0.268, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.337468354430381e-06, | |
| "loss": 0.364, | |
| "step": 11025 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.33113924050633e-06, | |
| "loss": 0.4906, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.3248101265822795e-06, | |
| "loss": 0.3789, | |
| "step": 11075 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.318481012658228e-06, | |
| "loss": 0.4213, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.3121518987341775e-06, | |
| "loss": 0.3768, | |
| "step": 11125 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.305822784810127e-06, | |
| "loss": 0.4251, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.299493670886076e-06, | |
| "loss": 0.3866, | |
| "step": 11175 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.293164556962026e-06, | |
| "loss": 0.3936, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.286835443037975e-06, | |
| "loss": 0.368, | |
| "step": 11225 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.280506329113925e-06, | |
| "loss": 0.4564, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.274177215189874e-06, | |
| "loss": 0.3783, | |
| "step": 11275 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.267848101265823e-06, | |
| "loss": 0.3747, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.261518987341772e-06, | |
| "loss": 0.4399, | |
| "step": 11325 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.2551898734177215e-06, | |
| "loss": 0.3072, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.248860759493671e-06, | |
| "loss": 0.3467, | |
| "step": 11375 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.24253164556962e-06, | |
| "loss": 0.3137, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.23620253164557e-06, | |
| "loss": 0.31, | |
| "step": 11425 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.229873417721519e-06, | |
| "loss": 0.4034, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.223544303797469e-06, | |
| "loss": 0.346, | |
| "step": 11475 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.21746835443038e-06, | |
| "loss": 0.4188, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.2111392405063295e-06, | |
| "loss": 0.4307, | |
| "step": 11525 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.204810126582279e-06, | |
| "loss": 0.3454, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.198481012658228e-06, | |
| "loss": 0.3504, | |
| "step": 11575 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.192151898734178e-06, | |
| "loss": 0.3085, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.185822784810127e-06, | |
| "loss": 0.3863, | |
| "step": 11625 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.179493670886077e-06, | |
| "loss": 0.4829, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.173164556962025e-06, | |
| "loss": 0.2897, | |
| "step": 11675 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.166835443037975e-06, | |
| "loss": 0.3458, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.160506329113924e-06, | |
| "loss": 0.36, | |
| "step": 11725 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.1541772151898735e-06, | |
| "loss": 0.3402, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.147848101265823e-06, | |
| "loss": 0.3862, | |
| "step": 11775 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 7.141518987341772e-06, | |
| "loss": 0.3777, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.135189873417722e-06, | |
| "loss": 0.3528, | |
| "step": 11825 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.128860759493671e-06, | |
| "loss": 0.394, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.122531645569621e-06, | |
| "loss": 0.4255, | |
| "step": 11875 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.116202531645571e-06, | |
| "loss": 0.3979, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.10987341772152e-06, | |
| "loss": 0.3089, | |
| "step": 11925 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.10354430379747e-06, | |
| "loss": 0.3761, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.097215189873418e-06, | |
| "loss": 0.3358, | |
| "step": 11975 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.090886075949368e-06, | |
| "loss": 0.3971, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.428133100271225, | |
| "eval_runtime": 6457.4242, | |
| "eval_samples_per_second": 2.53, | |
| "eval_steps_per_second": 2.53, | |
| "eval_wer": 21.542676140741374, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.084556962025317e-06, | |
| "loss": 0.3202, | |
| "step": 12025 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.078227848101267e-06, | |
| "loss": 0.2945, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.071898734177216e-06, | |
| "loss": 0.3842, | |
| "step": 12075 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.0655696202531655e-06, | |
| "loss": 0.3285, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.059240506329115e-06, | |
| "loss": 0.4387, | |
| "step": 12125 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.052911392405064e-06, | |
| "loss": 0.3898, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.046582278481014e-06, | |
| "loss": 0.284, | |
| "step": 12175 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 7.040253164556962e-06, | |
| "loss": 0.3356, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.033924050632912e-06, | |
| "loss": 0.4664, | |
| "step": 12225 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.027594936708861e-06, | |
| "loss": 0.2903, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.021265822784811e-06, | |
| "loss": 0.3745, | |
| "step": 12275 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.01493670886076e-06, | |
| "loss": 0.339, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.0086075949367095e-06, | |
| "loss": 0.2986, | |
| "step": 12325 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 7.002278481012659e-06, | |
| "loss": 0.4388, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.995949367088608e-06, | |
| "loss": 0.3733, | |
| "step": 12375 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.989620253164558e-06, | |
| "loss": 0.3198, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.983291139240506e-06, | |
| "loss": 0.3697, | |
| "step": 12425 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.976962025316456e-06, | |
| "loss": 0.4036, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.970632911392405e-06, | |
| "loss": 0.3997, | |
| "step": 12475 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.964303797468355e-06, | |
| "loss": 0.3747, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.957974683544304e-06, | |
| "loss": 0.2972, | |
| "step": 12525 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.9516455696202535e-06, | |
| "loss": 0.3176, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.945316455696203e-06, | |
| "loss": 0.2633, | |
| "step": 12575 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.938987341772152e-06, | |
| "loss": 0.2031, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.932658227848102e-06, | |
| "loss": 0.312, | |
| "step": 12625 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.92632911392405e-06, | |
| "loss": 0.3291, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.92e-06, | |
| "loss": 0.3432, | |
| "step": 12675 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.913670886075949e-06, | |
| "loss": 0.3644, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.9073417721518995e-06, | |
| "loss": 0.2601, | |
| "step": 12725 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.901012658227849e-06, | |
| "loss": 0.2893, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.894683544303798e-06, | |
| "loss": 0.2935, | |
| "step": 12775 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.888354430379748e-06, | |
| "loss": 0.2978, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.882025316455697e-06, | |
| "loss": 0.1857, | |
| "step": 12825 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.875696202531647e-06, | |
| "loss": 0.3222, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.869367088607596e-06, | |
| "loss": 0.3287, | |
| "step": 12875 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.8630379746835455e-06, | |
| "loss": 0.3442, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.856708860759494e-06, | |
| "loss": 0.3182, | |
| "step": 12925 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.8503797468354435e-06, | |
| "loss": 0.1876, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.844050632911393e-06, | |
| "loss": 0.3192, | |
| "step": 12975 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.837721518987342e-06, | |
| "loss": 0.2121, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.831392405063292e-06, | |
| "loss": 0.3307, | |
| "step": 13025 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.825063291139241e-06, | |
| "loss": 0.2354, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.818734177215191e-06, | |
| "loss": 0.3287, | |
| "step": 13075 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.81240506329114e-06, | |
| "loss": 0.3791, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.8060759493670895e-06, | |
| "loss": 0.3062, | |
| "step": 13125 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.799746835443038e-06, | |
| "loss": 0.2515, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.7934177215189875e-06, | |
| "loss": 0.2445, | |
| "step": 13175 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.787088607594937e-06, | |
| "loss": 0.2162, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.780759493670886e-06, | |
| "loss": 0.3185, | |
| "step": 13225 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.774430379746836e-06, | |
| "loss": 0.2869, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.768101265822785e-06, | |
| "loss": 0.2712, | |
| "step": 13275 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.761772151898735e-06, | |
| "loss": 0.2533, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.755443037974684e-06, | |
| "loss": 0.2682, | |
| "step": 13325 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.7491139240506335e-06, | |
| "loss": 0.223, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.742784810126582e-06, | |
| "loss": 0.2679, | |
| "step": 13375 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.7364556962025315e-06, | |
| "loss": 0.2271, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.730126582278481e-06, | |
| "loss": 0.2177, | |
| "step": 13425 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.72379746835443e-06, | |
| "loss": 0.3389, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.71746835443038e-06, | |
| "loss": 0.2655, | |
| "step": 13475 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.711139240506329e-06, | |
| "loss": 0.2136, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.704810126582279e-06, | |
| "loss": 0.23, | |
| "step": 13525 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.698481012658229e-06, | |
| "loss": 0.3583, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.692151898734178e-06, | |
| "loss": 0.2856, | |
| "step": 13575 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.685822784810128e-06, | |
| "loss": 0.2417, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.679493670886077e-06, | |
| "loss": 0.2341, | |
| "step": 13625 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.673164556962027e-06, | |
| "loss": 0.3381, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.666835443037975e-06, | |
| "loss": 0.3089, | |
| "step": 13675 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.660506329113925e-06, | |
| "loss": 0.3029, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.654177215189874e-06, | |
| "loss": 0.3232, | |
| "step": 13725 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.6478481012658235e-06, | |
| "loss": 0.2373, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.641518987341773e-06, | |
| "loss": 0.2129, | |
| "step": 13775 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.635189873417722e-06, | |
| "loss": 0.299, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.628860759493672e-06, | |
| "loss": 0.2946, | |
| "step": 13825 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.622531645569621e-06, | |
| "loss": 0.2487, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.616202531645571e-06, | |
| "loss": 0.2858, | |
| "step": 13875 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.609873417721519e-06, | |
| "loss": 0.2198, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.6037974683544315e-06, | |
| "loss": 0.3874, | |
| "step": 13925 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.597468354430381e-06, | |
| "loss": 0.3244, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.59113924050633e-06, | |
| "loss": 0.3311, | |
| "step": 13975 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.58481012658228e-06, | |
| "loss": 0.3096, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.578481012658228e-06, | |
| "loss": 0.3183, | |
| "step": 14025 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.572151898734178e-06, | |
| "loss": 0.3764, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.565822784810127e-06, | |
| "loss": 0.2751, | |
| "step": 14075 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.559493670886077e-06, | |
| "loss": 0.3172, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.553164556962026e-06, | |
| "loss": 0.4344, | |
| "step": 14125 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.5468354430379755e-06, | |
| "loss": 0.2748, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.540506329113925e-06, | |
| "loss": 0.3229, | |
| "step": 14175 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.534177215189874e-06, | |
| "loss": 0.3362, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.527848101265824e-06, | |
| "loss": 0.4068, | |
| "step": 14225 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.521518987341772e-06, | |
| "loss": 0.2976, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.515189873417722e-06, | |
| "loss": 0.3054, | |
| "step": 14275 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.508860759493671e-06, | |
| "loss": 0.3845, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.502531645569621e-06, | |
| "loss": 0.2754, | |
| "step": 14325 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.49620253164557e-06, | |
| "loss": 0.3071, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.4898734177215195e-06, | |
| "loss": 0.3092, | |
| "step": 14375 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.483544303797469e-06, | |
| "loss": 0.3358, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.477215189873418e-06, | |
| "loss": 0.3733, | |
| "step": 14425 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.470886075949368e-06, | |
| "loss": 0.369, | |
| "step": 14450 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.464556962025316e-06, | |
| "loss": 0.3727, | |
| "step": 14475 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.458227848101266e-06, | |
| "loss": 0.4048, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.451898734177215e-06, | |
| "loss": 0.2926, | |
| "step": 14525 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.445569620253165e-06, | |
| "loss": 0.4092, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.439240506329114e-06, | |
| "loss": 0.3851, | |
| "step": 14575 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.4329113924050635e-06, | |
| "loss": 0.3738, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.426582278481013e-06, | |
| "loss": 0.4074, | |
| "step": 14625 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.420253164556962e-06, | |
| "loss": 0.336, | |
| "step": 14650 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.413924050632912e-06, | |
| "loss": 0.3718, | |
| "step": 14675 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.40759493670886e-06, | |
| "loss": 0.3331, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.40126582278481e-06, | |
| "loss": 0.2425, | |
| "step": 14725 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.394936708860761e-06, | |
| "loss": 0.2699, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.3886075949367095e-06, | |
| "loss": 0.359, | |
| "step": 14775 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.382278481012659e-06, | |
| "loss": 0.3366, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.375949367088608e-06, | |
| "loss": 0.3696, | |
| "step": 14825 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.369620253164558e-06, | |
| "loss": 0.2692, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.363291139240507e-06, | |
| "loss": 0.3418, | |
| "step": 14875 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.356962025316457e-06, | |
| "loss": 0.3252, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.350632911392406e-06, | |
| "loss": 0.3257, | |
| "step": 14925 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.3443037974683555e-06, | |
| "loss": 0.3065, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.337974683544305e-06, | |
| "loss": 0.3316, | |
| "step": 14975 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.3316455696202535e-06, | |
| "loss": 0.3906, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.325316455696203e-06, | |
| "loss": 0.2905, | |
| "step": 15025 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.318987341772152e-06, | |
| "loss": 0.2785, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.312658227848102e-06, | |
| "loss": 0.3429, | |
| "step": 15075 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.306329113924051e-06, | |
| "loss": 0.3522, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.300000000000001e-06, | |
| "loss": 0.3156, | |
| "step": 15125 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.29367088607595e-06, | |
| "loss": 0.2403, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.2873417721518995e-06, | |
| "loss": 0.3667, | |
| "step": 15175 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.281012658227849e-06, | |
| "loss": 0.4147, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.2746835443037975e-06, | |
| "loss": 0.3918, | |
| "step": 15225 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.268354430379747e-06, | |
| "loss": 0.2712, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.262025316455696e-06, | |
| "loss": 0.3402, | |
| "step": 15275 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.255696202531646e-06, | |
| "loss": 0.2861, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.249367088607595e-06, | |
| "loss": 0.3662, | |
| "step": 15325 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.243037974683545e-06, | |
| "loss": 0.3889, | |
| "step": 15350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 6.236708860759494e-06, | |
| "loss": 0.2737, | |
| "step": 15375 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.2303797468354435e-06, | |
| "loss": 0.2981, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.224050632911393e-06, | |
| "loss": 0.355, | |
| "step": 15425 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.2177215189873415e-06, | |
| "loss": 0.3078, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.211392405063291e-06, | |
| "loss": 0.4037, | |
| "step": 15475 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.20506329113924e-06, | |
| "loss": 0.4156, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.19873417721519e-06, | |
| "loss": 0.2983, | |
| "step": 15525 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.192405063291139e-06, | |
| "loss": 0.2756, | |
| "step": 15550 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.1860759493670895e-06, | |
| "loss": 0.3838, | |
| "step": 15575 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.179746835443039e-06, | |
| "loss": 0.2789, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.173417721518988e-06, | |
| "loss": 0.329, | |
| "step": 15625 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.167088607594938e-06, | |
| "loss": 0.3587, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.160759493670887e-06, | |
| "loss": 0.2437, | |
| "step": 15675 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.154430379746837e-06, | |
| "loss": 0.4391, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.148101265822785e-06, | |
| "loss": 0.3763, | |
| "step": 15725 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.141772151898735e-06, | |
| "loss": 0.3333, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.135443037974684e-06, | |
| "loss": 0.3801, | |
| "step": 15775 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.1291139240506335e-06, | |
| "loss": 0.2772, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.122784810126583e-06, | |
| "loss": 0.3164, | |
| "step": 15825 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.116455696202532e-06, | |
| "loss": 0.3588, | |
| "step": 15850 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.110126582278482e-06, | |
| "loss": 0.2755, | |
| "step": 15875 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.103797468354431e-06, | |
| "loss": 0.3116, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.097468354430381e-06, | |
| "loss": 0.3368, | |
| "step": 15925 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.091139240506329e-06, | |
| "loss": 0.3445, | |
| "step": 15950 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.084810126582279e-06, | |
| "loss": 0.3931, | |
| "step": 15975 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.078481012658228e-06, | |
| "loss": 0.2965, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.4036683738231659, | |
| "eval_runtime": 6423.128, | |
| "eval_samples_per_second": 2.544, | |
| "eval_steps_per_second": 2.544, | |
| "eval_wer": 20.30819279171304, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.0721518987341775e-06, | |
| "loss": 0.2831, | |
| "step": 16025 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.065822784810127e-06, | |
| "loss": 0.3638, | |
| "step": 16050 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.059493670886076e-06, | |
| "loss": 0.2782, | |
| "step": 16075 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.053164556962026e-06, | |
| "loss": 0.2845, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.046835443037975e-06, | |
| "loss": 0.3905, | |
| "step": 16125 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.040506329113925e-06, | |
| "loss": 0.3915, | |
| "step": 16150 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.034177215189873e-06, | |
| "loss": 0.2469, | |
| "step": 16175 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.027848101265823e-06, | |
| "loss": 0.3414, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.021518987341772e-06, | |
| "loss": 0.4348, | |
| "step": 16225 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.0151898734177215e-06, | |
| "loss": 0.3344, | |
| "step": 16250 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.008860759493671e-06, | |
| "loss": 0.2914, | |
| "step": 16275 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 6.00253164556962e-06, | |
| "loss": 0.4037, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 5.99620253164557e-06, | |
| "loss": 0.3614, | |
| "step": 16325 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.989873417721519e-06, | |
| "loss": 0.2778, | |
| "step": 16350 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.983544303797469e-06, | |
| "loss": 0.3776, | |
| "step": 16375 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.977215189873419e-06, | |
| "loss": 0.3799, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.970886075949368e-06, | |
| "loss": 0.3622, | |
| "step": 16425 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.964556962025318e-06, | |
| "loss": 0.2722, | |
| "step": 16450 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.958227848101266e-06, | |
| "loss": 0.3255, | |
| "step": 16475 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.951898734177216e-06, | |
| "loss": 0.3718, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.945569620253165e-06, | |
| "loss": 0.3273, | |
| "step": 16525 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.939240506329115e-06, | |
| "loss": 0.3016, | |
| "step": 16550 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.932911392405064e-06, | |
| "loss": 0.3597, | |
| "step": 16575 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.9265822784810135e-06, | |
| "loss": 0.3108, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.920253164556963e-06, | |
| "loss": 0.2725, | |
| "step": 16625 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.913924050632912e-06, | |
| "loss": 0.2655, | |
| "step": 16650 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.907594936708862e-06, | |
| "loss": 0.3454, | |
| "step": 16675 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.90126582278481e-06, | |
| "loss": 0.3463, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.89493670886076e-06, | |
| "loss": 0.3247, | |
| "step": 16725 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.888607594936709e-06, | |
| "loss": 0.3317, | |
| "step": 16750 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.882278481012659e-06, | |
| "loss": 0.3042, | |
| "step": 16775 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.875949367088608e-06, | |
| "loss": 0.2594, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.8696202531645575e-06, | |
| "loss": 0.4341, | |
| "step": 16825 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.863291139240507e-06, | |
| "loss": 0.3491, | |
| "step": 16850 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.856962025316456e-06, | |
| "loss": 0.2766, | |
| "step": 16875 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.850632911392406e-06, | |
| "loss": 0.3631, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5.844303797468354e-06, | |
| "loss": 0.4018, | |
| "step": 16925 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.837974683544304e-06, | |
| "loss": 0.3144, | |
| "step": 16950 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.831645569620253e-06, | |
| "loss": 0.3259, | |
| "step": 16975 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.825316455696203e-06, | |
| "loss": 0.3957, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.818987341772152e-06, | |
| "loss": 0.3269, | |
| "step": 17025 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.8126582278481015e-06, | |
| "loss": 0.3203, | |
| "step": 17050 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.806329113924051e-06, | |
| "loss": 0.243, | |
| "step": 17075 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.8e-06, | |
| "loss": 0.2687, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.793924050632912e-06, | |
| "loss": 0.3303, | |
| "step": 17125 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.787594936708861e-06, | |
| "loss": 0.2484, | |
| "step": 17150 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.781265822784811e-06, | |
| "loss": 0.3054, | |
| "step": 17175 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.77493670886076e-06, | |
| "loss": 0.4117, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.7686075949367095e-06, | |
| "loss": 0.3349, | |
| "step": 17225 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.762278481012659e-06, | |
| "loss": 0.3944, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.7559493670886075e-06, | |
| "loss": 0.2695, | |
| "step": 17275 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.749620253164557e-06, | |
| "loss": 0.2856, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 5.743291139240506e-06, | |
| "loss": 0.3291, | |
| "step": 17325 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.736962025316456e-06, | |
| "loss": 0.2703, | |
| "step": 17350 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.730632911392405e-06, | |
| "loss": 0.3244, | |
| "step": 17375 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.724303797468355e-06, | |
| "loss": 0.2807, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.717974683544304e-06, | |
| "loss": 0.2779, | |
| "step": 17425 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.7116455696202535e-06, | |
| "loss": 0.2254, | |
| "step": 17450 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.705316455696203e-06, | |
| "loss": 0.2836, | |
| "step": 17475 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.6989873417721515e-06, | |
| "loss": 0.2844, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.692658227848101e-06, | |
| "loss": 0.2712, | |
| "step": 17525 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.68632911392405e-06, | |
| "loss": 0.2399, | |
| "step": 17550 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.68e-06, | |
| "loss": 0.3384, | |
| "step": 17575 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.673670886075949e-06, | |
| "loss": 0.3719, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.6673417721518995e-06, | |
| "loss": 0.2823, | |
| "step": 17625 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.661012658227849e-06, | |
| "loss": 0.4026, | |
| "step": 17650 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.654683544303798e-06, | |
| "loss": 0.2885, | |
| "step": 17675 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.648354430379748e-06, | |
| "loss": 0.3919, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.642025316455697e-06, | |
| "loss": 0.3566, | |
| "step": 17725 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.635696202531647e-06, | |
| "loss": 0.3278, | |
| "step": 17750 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.629367088607596e-06, | |
| "loss": 0.3433, | |
| "step": 17775 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.623037974683545e-06, | |
| "loss": 0.364, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.616708860759494e-06, | |
| "loss": 0.2912, | |
| "step": 17825 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.6103797468354435e-06, | |
| "loss": 0.4, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.604050632911393e-06, | |
| "loss": 0.331, | |
| "step": 17875 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.597721518987342e-06, | |
| "loss": 0.2945, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.591392405063292e-06, | |
| "loss": 0.2969, | |
| "step": 17925 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.585063291139241e-06, | |
| "loss": 0.2196, | |
| "step": 17950 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.578734177215191e-06, | |
| "loss": 0.2325, | |
| "step": 17975 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.57240506329114e-06, | |
| "loss": 0.3686, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.566075949367089e-06, | |
| "loss": 0.3223, | |
| "step": 18025 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.559746835443038e-06, | |
| "loss": 0.2774, | |
| "step": 18050 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.5534177215189875e-06, | |
| "loss": 0.2562, | |
| "step": 18075 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.547088607594937e-06, | |
| "loss": 0.3084, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 5.540759493670886e-06, | |
| "loss": 0.2484, | |
| "step": 18125 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.534430379746836e-06, | |
| "loss": 0.2801, | |
| "step": 18150 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.528101265822785e-06, | |
| "loss": 0.2638, | |
| "step": 18175 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.521772151898735e-06, | |
| "loss": 0.3219, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.515443037974684e-06, | |
| "loss": 0.2892, | |
| "step": 18225 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.509113924050633e-06, | |
| "loss": 0.2601, | |
| "step": 18250 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.502784810126582e-06, | |
| "loss": 0.2575, | |
| "step": 18275 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.4964556962025315e-06, | |
| "loss": 0.2713, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.490126582278481e-06, | |
| "loss": 0.2532, | |
| "step": 18325 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.48379746835443e-06, | |
| "loss": 0.2603, | |
| "step": 18350 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.47746835443038e-06, | |
| "loss": 0.3418, | |
| "step": 18375 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.471139240506329e-06, | |
| "loss": 0.2976, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.464810126582279e-06, | |
| "loss": 0.2824, | |
| "step": 18425 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.458481012658229e-06, | |
| "loss": 0.2808, | |
| "step": 18450 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.452151898734178e-06, | |
| "loss": 0.2941, | |
| "step": 18475 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.445822784810128e-06, | |
| "loss": 0.2386, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5.439493670886077e-06, | |
| "loss": 0.379, | |
| "step": 18525 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.433164556962026e-06, | |
| "loss": 0.2812, | |
| "step": 18550 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.426835443037975e-06, | |
| "loss": 0.3171, | |
| "step": 18575 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.420506329113925e-06, | |
| "loss": 0.2732, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.414177215189874e-06, | |
| "loss": 0.2956, | |
| "step": 18625 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.4078481012658235e-06, | |
| "loss": 0.2571, | |
| "step": 18650 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.401518987341773e-06, | |
| "loss": 0.3947, | |
| "step": 18675 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.395189873417722e-06, | |
| "loss": 0.3314, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.388860759493672e-06, | |
| "loss": 0.2416, | |
| "step": 18725 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.382531645569621e-06, | |
| "loss": 0.2485, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.37620253164557e-06, | |
| "loss": 0.2758, | |
| "step": 18775 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.369873417721519e-06, | |
| "loss": 0.2831, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.363544303797469e-06, | |
| "loss": 0.2596, | |
| "step": 18825 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.357215189873418e-06, | |
| "loss": 0.2559, | |
| "step": 18850 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.3508860759493675e-06, | |
| "loss": 0.2418, | |
| "step": 18875 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.344556962025317e-06, | |
| "loss": 0.2557, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 5.338227848101266e-06, | |
| "loss": 0.2896, | |
| "step": 18925 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.331898734177216e-06, | |
| "loss": 0.2501, | |
| "step": 18950 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.325569620253165e-06, | |
| "loss": 0.2887, | |
| "step": 18975 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.319240506329114e-06, | |
| "loss": 0.3103, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.312911392405063e-06, | |
| "loss": 0.2979, | |
| "step": 19025 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.306582278481013e-06, | |
| "loss": 0.2823, | |
| "step": 19050 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.300253164556962e-06, | |
| "loss": 0.3281, | |
| "step": 19075 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.2939240506329115e-06, | |
| "loss": 0.2377, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.287594936708861e-06, | |
| "loss": 0.3037, | |
| "step": 19125 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.28126582278481e-06, | |
| "loss": 0.2382, | |
| "step": 19150 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.27493670886076e-06, | |
| "loss": 0.2643, | |
| "step": 19175 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.268607594936708e-06, | |
| "loss": 0.2978, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.262278481012658e-06, | |
| "loss": 0.2701, | |
| "step": 19225 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.255949367088607e-06, | |
| "loss": 0.287, | |
| "step": 19250 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.2496202531645575e-06, | |
| "loss": 0.3226, | |
| "step": 19275 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.243291139240507e-06, | |
| "loss": 0.2899, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.236962025316456e-06, | |
| "loss": 0.2478, | |
| "step": 19325 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.230632911392406e-06, | |
| "loss": 0.3056, | |
| "step": 19350 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.224303797468355e-06, | |
| "loss": 0.2954, | |
| "step": 19375 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.217974683544305e-06, | |
| "loss": 0.3084, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.211645569620254e-06, | |
| "loss": 0.2228, | |
| "step": 19425 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.2053164556962035e-06, | |
| "loss": 0.2576, | |
| "step": 19450 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.198987341772153e-06, | |
| "loss": 0.2395, | |
| "step": 19475 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.1926582278481015e-06, | |
| "loss": 0.3023, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.186329113924051e-06, | |
| "loss": 0.3186, | |
| "step": 19525 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.18e-06, | |
| "loss": 0.2616, | |
| "step": 19550 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.17367088607595e-06, | |
| "loss": 0.2596, | |
| "step": 19575 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.167341772151899e-06, | |
| "loss": 0.2433, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.161012658227849e-06, | |
| "loss": 0.2524, | |
| "step": 19625 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.154683544303798e-06, | |
| "loss": 0.3035, | |
| "step": 19650 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.1483544303797475e-06, | |
| "loss": 0.3074, | |
| "step": 19675 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.142025316455697e-06, | |
| "loss": 0.3342, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 5.1356962025316455e-06, | |
| "loss": 0.3663, | |
| "step": 19725 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.129367088607595e-06, | |
| "loss": 0.2432, | |
| "step": 19750 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.123037974683544e-06, | |
| "loss": 0.3891, | |
| "step": 19775 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.116708860759494e-06, | |
| "loss": 0.2654, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.110379746835443e-06, | |
| "loss": 0.3776, | |
| "step": 19825 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.104050632911393e-06, | |
| "loss": 0.2318, | |
| "step": 19850 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.097721518987342e-06, | |
| "loss": 0.2608, | |
| "step": 19875 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.0913924050632915e-06, | |
| "loss": 0.2643, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.085063291139241e-06, | |
| "loss": 0.3452, | |
| "step": 19925 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.0787341772151895e-06, | |
| "loss": 0.3176, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.072405063291139e-06, | |
| "loss": 0.2615, | |
| "step": 19975 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.066075949367088e-06, | |
| "loss": 0.2634, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 0.38753828406333923, | |
| "eval_runtime": 6405.7217, | |
| "eval_samples_per_second": 2.551, | |
| "eval_steps_per_second": 2.551, | |
| "eval_wer": 18.79804811231915, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.059746835443038e-06, | |
| "loss": 0.3248, | |
| "step": 20025 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.053417721518987e-06, | |
| "loss": 0.2984, | |
| "step": 20050 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.047088607594937e-06, | |
| "loss": 0.2861, | |
| "step": 20075 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.040759493670887e-06, | |
| "loss": 0.3108, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 5.0346835443037975e-06, | |
| "loss": 0.3334, | |
| "step": 20125 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.028354430379747e-06, | |
| "loss": 0.2814, | |
| "step": 20150 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.022025316455696e-06, | |
| "loss": 0.3155, | |
| "step": 20175 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.015696202531646e-06, | |
| "loss": 0.2717, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.009367088607595e-06, | |
| "loss": 0.2978, | |
| "step": 20225 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.003037974683545e-06, | |
| "loss": 0.2598, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.996708860759494e-06, | |
| "loss": 0.3203, | |
| "step": 20275 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.9903797468354435e-06, | |
| "loss": 0.3447, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.984050632911393e-06, | |
| "loss": 0.3088, | |
| "step": 20325 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.977721518987342e-06, | |
| "loss": 0.3046, | |
| "step": 20350 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.971392405063292e-06, | |
| "loss": 0.2966, | |
| "step": 20375 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.965063291139241e-06, | |
| "loss": 0.2836, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.958734177215191e-06, | |
| "loss": 0.2983, | |
| "step": 20425 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.952405063291139e-06, | |
| "loss": 0.2386, | |
| "step": 20450 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.946075949367089e-06, | |
| "loss": 0.1755, | |
| "step": 20475 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.939746835443038e-06, | |
| "loss": 0.3237, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.9334177215189875e-06, | |
| "loss": 0.2627, | |
| "step": 20525 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.927088607594937e-06, | |
| "loss": 0.2187, | |
| "step": 20550 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.920759493670886e-06, | |
| "loss": 0.2788, | |
| "step": 20575 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.914430379746836e-06, | |
| "loss": 0.2414, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.908101265822785e-06, | |
| "loss": 0.2673, | |
| "step": 20625 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.901772151898735e-06, | |
| "loss": 0.2704, | |
| "step": 20650 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.895443037974683e-06, | |
| "loss": 0.2221, | |
| "step": 20675 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.8891139240506335e-06, | |
| "loss": 0.3068, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.882784810126583e-06, | |
| "loss": 0.3473, | |
| "step": 20725 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.876455696202532e-06, | |
| "loss": 0.32, | |
| "step": 20750 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.870126582278482e-06, | |
| "loss": 0.2976, | |
| "step": 20775 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.863797468354431e-06, | |
| "loss": 0.308, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.85746835443038e-06, | |
| "loss": 0.2527, | |
| "step": 20825 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.851139240506329e-06, | |
| "loss": 0.257, | |
| "step": 20850 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.844810126582279e-06, | |
| "loss": 0.2833, | |
| "step": 20875 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.838481012658228e-06, | |
| "loss": 0.2511, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.8321518987341775e-06, | |
| "loss": 0.2675, | |
| "step": 20925 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.825822784810127e-06, | |
| "loss": 0.3223, | |
| "step": 20950 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.819493670886076e-06, | |
| "loss": 0.3664, | |
| "step": 20975 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.813164556962026e-06, | |
| "loss": 0.3527, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.806835443037975e-06, | |
| "loss": 0.2911, | |
| "step": 21025 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.800506329113924e-06, | |
| "loss": 0.4069, | |
| "step": 21050 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.794177215189873e-06, | |
| "loss": 0.3287, | |
| "step": 21075 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.7878481012658235e-06, | |
| "loss": 0.2457, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.781518987341773e-06, | |
| "loss": 0.2065, | |
| "step": 21125 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.775189873417722e-06, | |
| "loss": 0.2459, | |
| "step": 21150 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.768860759493672e-06, | |
| "loss": 0.3097, | |
| "step": 21175 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.76253164556962e-06, | |
| "loss": 0.2755, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.75620253164557e-06, | |
| "loss": 0.2835, | |
| "step": 21225 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.749873417721519e-06, | |
| "loss": 0.3363, | |
| "step": 21250 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.743544303797469e-06, | |
| "loss": 0.2328, | |
| "step": 21275 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.737215189873418e-06, | |
| "loss": 0.2963, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.7308860759493675e-06, | |
| "loss": 0.3502, | |
| "step": 21325 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.724556962025317e-06, | |
| "loss": 0.296, | |
| "step": 21350 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.718227848101266e-06, | |
| "loss": 0.3265, | |
| "step": 21375 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.711898734177216e-06, | |
| "loss": 0.2916, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.705569620253164e-06, | |
| "loss": 0.286, | |
| "step": 21425 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.699240506329114e-06, | |
| "loss": 0.3229, | |
| "step": 21450 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.692911392405063e-06, | |
| "loss": 0.3414, | |
| "step": 21475 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.686582278481013e-06, | |
| "loss": 0.2591, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.680253164556963e-06, | |
| "loss": 0.2159, | |
| "step": 21525 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.673924050632912e-06, | |
| "loss": 0.2932, | |
| "step": 21550 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.667594936708861e-06, | |
| "loss": 0.3495, | |
| "step": 21575 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.66126582278481e-06, | |
| "loss": 0.3187, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.65493670886076e-06, | |
| "loss": 0.3234, | |
| "step": 21625 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.648607594936709e-06, | |
| "loss": 0.2095, | |
| "step": 21650 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.642278481012659e-06, | |
| "loss": 0.2832, | |
| "step": 21675 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.635949367088608e-06, | |
| "loss": 0.2441, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.6296202531645575e-06, | |
| "loss": 0.2434, | |
| "step": 21725 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.623291139240507e-06, | |
| "loss": 0.4166, | |
| "step": 21750 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.616962025316456e-06, | |
| "loss": 0.2116, | |
| "step": 21775 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.610632911392405e-06, | |
| "loss": 0.3126, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.604303797468354e-06, | |
| "loss": 0.2838, | |
| "step": 21825 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.597974683544304e-06, | |
| "loss": 0.2966, | |
| "step": 21850 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.591645569620253e-06, | |
| "loss": 0.2834, | |
| "step": 21875 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.585316455696203e-06, | |
| "loss": 0.2767, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.578987341772153e-06, | |
| "loss": 0.2993, | |
| "step": 21925 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.5726582278481015e-06, | |
| "loss": 0.2688, | |
| "step": 21950 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.566329113924051e-06, | |
| "loss": 0.2621, | |
| "step": 21975 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.56e-06, | |
| "loss": 0.251, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.55367088607595e-06, | |
| "loss": 0.3077, | |
| "step": 22025 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.547341772151899e-06, | |
| "loss": 0.3357, | |
| "step": 22050 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.541012658227849e-06, | |
| "loss": 0.2242, | |
| "step": 22075 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.534683544303798e-06, | |
| "loss": 0.3338, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.5283544303797475e-06, | |
| "loss": 0.2947, | |
| "step": 22125 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.522025316455697e-06, | |
| "loss": 0.314, | |
| "step": 22150 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.5156962025316455e-06, | |
| "loss": 0.3304, | |
| "step": 22175 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.509367088607595e-06, | |
| "loss": 0.2821, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.503037974683544e-06, | |
| "loss": 0.2458, | |
| "step": 22225 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.496708860759494e-06, | |
| "loss": 0.2667, | |
| "step": 22250 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.490379746835443e-06, | |
| "loss": 0.4398, | |
| "step": 22275 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.484050632911393e-06, | |
| "loss": 0.2768, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.477721518987342e-06, | |
| "loss": 0.3378, | |
| "step": 22325 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.4713924050632915e-06, | |
| "loss": 0.2313, | |
| "step": 22350 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.465063291139241e-06, | |
| "loss": 0.2867, | |
| "step": 22375 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.45873417721519e-06, | |
| "loss": 0.2652, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.45240506329114e-06, | |
| "loss": 0.2885, | |
| "step": 22425 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.446075949367089e-06, | |
| "loss": 0.2508, | |
| "step": 22450 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.439746835443039e-06, | |
| "loss": 0.3095, | |
| "step": 22475 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.433417721518988e-06, | |
| "loss": 0.3118, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.427088607594937e-06, | |
| "loss": 0.3077, | |
| "step": 22525 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.420759493670886e-06, | |
| "loss": 0.2957, | |
| "step": 22550 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.4144303797468355e-06, | |
| "loss": 0.3265, | |
| "step": 22575 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.408101265822785e-06, | |
| "loss": 0.3196, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.401772151898734e-06, | |
| "loss": 0.2187, | |
| "step": 22625 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.395443037974684e-06, | |
| "loss": 0.2856, | |
| "step": 22650 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.389113924050633e-06, | |
| "loss": 0.2226, | |
| "step": 22675 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.382784810126583e-06, | |
| "loss": 0.2723, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.376455696202532e-06, | |
| "loss": 0.2109, | |
| "step": 22725 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.3701265822784815e-06, | |
| "loss": 0.2628, | |
| "step": 22750 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.363797468354431e-06, | |
| "loss": 0.2251, | |
| "step": 22775 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.35746835443038e-06, | |
| "loss": 0.3126, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.35113924050633e-06, | |
| "loss": 0.2875, | |
| "step": 22825 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.344810126582279e-06, | |
| "loss": 0.3104, | |
| "step": 22850 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.338481012658229e-06, | |
| "loss": 0.2779, | |
| "step": 22875 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.332151898734177e-06, | |
| "loss": 0.2559, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.325822784810127e-06, | |
| "loss": 0.2856, | |
| "step": 22925 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.319493670886076e-06, | |
| "loss": 0.3389, | |
| "step": 22950 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.3131645569620255e-06, | |
| "loss": 0.2245, | |
| "step": 22975 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.306835443037975e-06, | |
| "loss": 0.2039, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.300506329113924e-06, | |
| "loss": 0.3053, | |
| "step": 23025 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.294177215189874e-06, | |
| "loss": 0.1924, | |
| "step": 23050 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.287848101265823e-06, | |
| "loss": 0.3013, | |
| "step": 23075 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.281518987341773e-06, | |
| "loss": 0.2707, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.275189873417721e-06, | |
| "loss": 0.2961, | |
| "step": 23125 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.268860759493671e-06, | |
| "loss": 0.2775, | |
| "step": 23150 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.262531645569621e-06, | |
| "loss": 0.2211, | |
| "step": 23175 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.25620253164557e-06, | |
| "loss": 0.2582, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.24987341772152e-06, | |
| "loss": 0.3195, | |
| "step": 23225 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.243544303797469e-06, | |
| "loss": 0.3131, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.237215189873418e-06, | |
| "loss": 0.2678, | |
| "step": 23275 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.230886075949367e-06, | |
| "loss": 0.2058, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.224556962025317e-06, | |
| "loss": 0.2712, | |
| "step": 23325 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.218227848101266e-06, | |
| "loss": 0.2915, | |
| "step": 23350 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.2118987341772155e-06, | |
| "loss": 0.3083, | |
| "step": 23375 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.205569620253165e-06, | |
| "loss": 0.2373, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.199240506329114e-06, | |
| "loss": 0.2379, | |
| "step": 23425 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.192911392405064e-06, | |
| "loss": 0.2677, | |
| "step": 23450 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.186582278481013e-06, | |
| "loss": 0.3201, | |
| "step": 23475 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.180253164556962e-06, | |
| "loss": 0.2931, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.173924050632911e-06, | |
| "loss": 0.3009, | |
| "step": 23525 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.167594936708861e-06, | |
| "loss": 0.3014, | |
| "step": 23550 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.161265822784811e-06, | |
| "loss": 0.2289, | |
| "step": 23575 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.15493670886076e-06, | |
| "loss": 0.2948, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.14860759493671e-06, | |
| "loss": 0.3733, | |
| "step": 23625 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.142278481012658e-06, | |
| "loss": 0.2987, | |
| "step": 23650 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.135949367088608e-06, | |
| "loss": 0.2575, | |
| "step": 23675 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.129620253164557e-06, | |
| "loss": 0.2518, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.123291139240507e-06, | |
| "loss": 0.2288, | |
| "step": 23725 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.116962025316456e-06, | |
| "loss": 0.3228, | |
| "step": 23750 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.1106329113924055e-06, | |
| "loss": 0.3251, | |
| "step": 23775 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.104303797468355e-06, | |
| "loss": 0.3173, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.097974683544304e-06, | |
| "loss": 0.2296, | |
| "step": 23825 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.091645569620254e-06, | |
| "loss": 0.2378, | |
| "step": 23850 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.085316455696202e-06, | |
| "loss": 0.3203, | |
| "step": 23875 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.079240506329114e-06, | |
| "loss": 0.3217, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.072911392405063e-06, | |
| "loss": 0.2775, | |
| "step": 23925 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.066582278481013e-06, | |
| "loss": 0.2785, | |
| "step": 23950 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.060253164556963e-06, | |
| "loss": 0.2603, | |
| "step": 23975 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.0539240506329115e-06, | |
| "loss": 0.2163, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 0.375421404838562, | |
| "eval_runtime": 6448.631, | |
| "eval_samples_per_second": 2.534, | |
| "eval_steps_per_second": 2.534, | |
| "eval_wer": 17.816967725365977, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.047594936708861e-06, | |
| "loss": 0.2493, | |
| "step": 24025 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.04126582278481e-06, | |
| "loss": 0.2318, | |
| "step": 24050 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.03493670886076e-06, | |
| "loss": 0.2878, | |
| "step": 24075 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.028607594936709e-06, | |
| "loss": 0.2375, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.022278481012659e-06, | |
| "loss": 0.2753, | |
| "step": 24125 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.015949367088608e-06, | |
| "loss": 0.313, | |
| "step": 24150 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.0096202531645575e-06, | |
| "loss": 0.2198, | |
| "step": 24175 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.003291139240507e-06, | |
| "loss": 0.2675, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.9969620253164555e-06, | |
| "loss": 0.2675, | |
| "step": 24225 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.990632911392405e-06, | |
| "loss": 0.2225, | |
| "step": 24250 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.984303797468354e-06, | |
| "loss": 0.2732, | |
| "step": 24275 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.977974683544304e-06, | |
| "loss": 0.2561, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.971645569620253e-06, | |
| "loss": 0.2679, | |
| "step": 24325 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.965316455696203e-06, | |
| "loss": 0.2276, | |
| "step": 24350 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.958987341772152e-06, | |
| "loss": 0.2684, | |
| "step": 24375 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.9526582278481015e-06, | |
| "loss": 0.2512, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.946329113924051e-06, | |
| "loss": 0.2186, | |
| "step": 24425 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.94e-06, | |
| "loss": 0.3084, | |
| "step": 24450 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.93367088607595e-06, | |
| "loss": 0.2187, | |
| "step": 24475 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.927594936708861e-06, | |
| "loss": 0.2655, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.921265822784811e-06, | |
| "loss": 0.2415, | |
| "step": 24525 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.91493670886076e-06, | |
| "loss": 0.2513, | |
| "step": 24550 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.9086075949367096e-06, | |
| "loss": 0.2036, | |
| "step": 24575 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.902278481012658e-06, | |
| "loss": 0.2547, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.8959493670886076e-06, | |
| "loss": 0.2945, | |
| "step": 24625 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.889620253164557e-06, | |
| "loss": 0.2431, | |
| "step": 24650 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.883291139240506e-06, | |
| "loss": 0.1977, | |
| "step": 24675 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.876962025316456e-06, | |
| "loss": 0.2468, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.870632911392405e-06, | |
| "loss": 0.2357, | |
| "step": 24725 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.864303797468355e-06, | |
| "loss": 0.2802, | |
| "step": 24750 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.857974683544304e-06, | |
| "loss": 0.2091, | |
| "step": 24775 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.8516455696202536e-06, | |
| "loss": 0.2315, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.845316455696203e-06, | |
| "loss": 0.2961, | |
| "step": 24825 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.838987341772152e-06, | |
| "loss": 0.1994, | |
| "step": 24850 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.832658227848102e-06, | |
| "loss": 0.3196, | |
| "step": 24875 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.826329113924051e-06, | |
| "loss": 0.2631, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.820000000000001e-06, | |
| "loss": 0.2508, | |
| "step": 24925 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.8136708860759497e-06, | |
| "loss": 0.3074, | |
| "step": 24950 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.807341772151899e-06, | |
| "loss": 0.2477, | |
| "step": 24975 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.8010126582278486e-06, | |
| "loss": 0.3217, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.7946835443037976e-06, | |
| "loss": 0.217, | |
| "step": 25025 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.788354430379747e-06, | |
| "loss": 0.1763, | |
| "step": 25050 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.7820253164556964e-06, | |
| "loss": 0.2872, | |
| "step": 25075 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.775696202531646e-06, | |
| "loss": 0.3117, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.769367088607595e-06, | |
| "loss": 0.3193, | |
| "step": 25125 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.7630379746835443e-06, | |
| "loss": 0.2247, | |
| "step": 25150 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.7567088607594937e-06, | |
| "loss": 0.2596, | |
| "step": 25175 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.7503797468354436e-06, | |
| "loss": 0.2978, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.744050632911393e-06, | |
| "loss": 0.3185, | |
| "step": 25225 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.7377215189873424e-06, | |
| "loss": 0.2603, | |
| "step": 25250 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.7313924050632914e-06, | |
| "loss": 0.2518, | |
| "step": 25275 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.725063291139241e-06, | |
| "loss": 0.2797, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.7187341772151903e-06, | |
| "loss": 0.3152, | |
| "step": 25325 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.7124050632911397e-06, | |
| "loss": 0.3428, | |
| "step": 25350 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.706075949367089e-06, | |
| "loss": 0.3059, | |
| "step": 25375 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.699746835443038e-06, | |
| "loss": 0.2453, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.6934177215189876e-06, | |
| "loss": 0.2264, | |
| "step": 25425 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.687088607594937e-06, | |
| "loss": 0.2952, | |
| "step": 25450 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.6807594936708864e-06, | |
| "loss": 0.3314, | |
| "step": 25475 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.6744303797468354e-06, | |
| "loss": 0.2397, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.668101265822785e-06, | |
| "loss": 0.2865, | |
| "step": 25525 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.6617721518987343e-06, | |
| "loss": 0.2975, | |
| "step": 25550 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.6554430379746837e-06, | |
| "loss": 0.2099, | |
| "step": 25575 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.6491139240506335e-06, | |
| "loss": 0.3007, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.642784810126583e-06, | |
| "loss": 0.2744, | |
| "step": 25625 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.636455696202532e-06, | |
| "loss": 0.2213, | |
| "step": 25650 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.6301265822784814e-06, | |
| "loss": 0.2857, | |
| "step": 25675 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.623797468354431e-06, | |
| "loss": 0.3988, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.6174683544303803e-06, | |
| "loss": 0.235, | |
| "step": 25725 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.6111392405063293e-06, | |
| "loss": 0.1814, | |
| "step": 25750 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.6048101265822787e-06, | |
| "loss": 0.2098, | |
| "step": 25775 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.598481012658228e-06, | |
| "loss": 0.263, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.5921518987341776e-06, | |
| "loss": 0.255, | |
| "step": 25825 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.585822784810127e-06, | |
| "loss": 0.3128, | |
| "step": 25850 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.579493670886076e-06, | |
| "loss": 0.2447, | |
| "step": 25875 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.5731645569620254e-06, | |
| "loss": 0.293, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.566835443037975e-06, | |
| "loss": 0.2925, | |
| "step": 25925 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.5605063291139243e-06, | |
| "loss": 0.2824, | |
| "step": 25950 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.5541772151898733e-06, | |
| "loss": 0.2786, | |
| "step": 25975 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.5478481012658235e-06, | |
| "loss": 0.3393, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.5415189873417725e-06, | |
| "loss": 0.2224, | |
| "step": 26025 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.535189873417722e-06, | |
| "loss": 0.324, | |
| "step": 26050 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.5288607594936714e-06, | |
| "loss": 0.2444, | |
| "step": 26075 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.522531645569621e-06, | |
| "loss": 0.2962, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.51620253164557e-06, | |
| "loss": 0.364, | |
| "step": 26125 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.5098734177215193e-06, | |
| "loss": 0.1953, | |
| "step": 26150 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.5035443037974687e-06, | |
| "loss": 0.3467, | |
| "step": 26175 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.497215189873418e-06, | |
| "loss": 0.229, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.4908860759493675e-06, | |
| "loss": 0.2335, | |
| "step": 26225 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.4845569620253166e-06, | |
| "loss": 0.2529, | |
| "step": 26250 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.478227848101266e-06, | |
| "loss": 0.3679, | |
| "step": 26275 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.4718987341772154e-06, | |
| "loss": 0.1613, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.465569620253165e-06, | |
| "loss": 0.3408, | |
| "step": 26325 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.459240506329114e-06, | |
| "loss": 0.2821, | |
| "step": 26350 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.4529113924050633e-06, | |
| "loss": 0.2857, | |
| "step": 26375 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.4465822784810127e-06, | |
| "loss": 0.3341, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.4402531645569625e-06, | |
| "loss": 0.3073, | |
| "step": 26425 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.433924050632912e-06, | |
| "loss": 0.2725, | |
| "step": 26450 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.4275949367088614e-06, | |
| "loss": 0.2719, | |
| "step": 26475 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.4212658227848104e-06, | |
| "loss": 0.294, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.41493670886076e-06, | |
| "loss": 0.2469, | |
| "step": 26525 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.4086075949367093e-06, | |
| "loss": 0.2991, | |
| "step": 26550 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.4022784810126587e-06, | |
| "loss": 0.3372, | |
| "step": 26575 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.3959493670886077e-06, | |
| "loss": 0.3129, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.389620253164557e-06, | |
| "loss": 0.2269, | |
| "step": 26625 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.3832911392405065e-06, | |
| "loss": 0.3383, | |
| "step": 26650 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.376962025316456e-06, | |
| "loss": 0.2604, | |
| "step": 26675 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.3706329113924054e-06, | |
| "loss": 0.2886, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.3643037974683544e-06, | |
| "loss": 0.2631, | |
| "step": 26725 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.357974683544304e-06, | |
| "loss": 0.2482, | |
| "step": 26750 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.3516455696202533e-06, | |
| "loss": 0.3179, | |
| "step": 26775 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.3453164556962027e-06, | |
| "loss": 0.3054, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.3389873417721525e-06, | |
| "loss": 0.22, | |
| "step": 26825 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.332658227848102e-06, | |
| "loss": 0.2502, | |
| "step": 26850 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.326329113924051e-06, | |
| "loss": 0.2862, | |
| "step": 26875 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.3200000000000004e-06, | |
| "loss": 0.254, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.31367088607595e-06, | |
| "loss": 0.2301, | |
| "step": 26925 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.3073417721518993e-06, | |
| "loss": 0.3324, | |
| "step": 26950 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.3010126582278483e-06, | |
| "loss": 0.2449, | |
| "step": 26975 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.2946835443037977e-06, | |
| "loss": 0.2183, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.288354430379747e-06, | |
| "loss": 0.359, | |
| "step": 27025 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.2820253164556965e-06, | |
| "loss": 0.3335, | |
| "step": 27050 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.275696202531646e-06, | |
| "loss": 0.2191, | |
| "step": 27075 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.269367088607595e-06, | |
| "loss": 0.2846, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.2630379746835444e-06, | |
| "loss": 0.1943, | |
| "step": 27125 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.256708860759494e-06, | |
| "loss": 0.2939, | |
| "step": 27150 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.2503797468354433e-06, | |
| "loss": 0.2242, | |
| "step": 27175 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.2440506329113923e-06, | |
| "loss": 0.2703, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.2377215189873417e-06, | |
| "loss": 0.2913, | |
| "step": 27225 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.2313924050632915e-06, | |
| "loss": 0.2228, | |
| "step": 27250 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.225063291139241e-06, | |
| "loss": 0.2671, | |
| "step": 27275 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.2187341772151904e-06, | |
| "loss": 0.2275, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.21240506329114e-06, | |
| "loss": 0.3968, | |
| "step": 27325 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.206075949367089e-06, | |
| "loss": 0.2617, | |
| "step": 27350 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.1997468354430383e-06, | |
| "loss": 0.2294, | |
| "step": 27375 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.1934177215189877e-06, | |
| "loss": 0.232, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.187088607594937e-06, | |
| "loss": 0.2835, | |
| "step": 27425 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.180759493670886e-06, | |
| "loss": 0.3987, | |
| "step": 27450 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.1744303797468355e-06, | |
| "loss": 0.3136, | |
| "step": 27475 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.168101265822785e-06, | |
| "loss": 0.3164, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.1617721518987344e-06, | |
| "loss": 0.2453, | |
| "step": 27525 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.155443037974684e-06, | |
| "loss": 0.2593, | |
| "step": 27550 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.149113924050633e-06, | |
| "loss": 0.2288, | |
| "step": 27575 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.1427848101265823e-06, | |
| "loss": 0.3306, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.1364556962025317e-06, | |
| "loss": 0.3349, | |
| "step": 27625 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.1301265822784815e-06, | |
| "loss": 0.3142, | |
| "step": 27650 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.123797468354431e-06, | |
| "loss": 0.277, | |
| "step": 27675 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.1174683544303804e-06, | |
| "loss": 0.2267, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.1111392405063294e-06, | |
| "loss": 0.2431, | |
| "step": 27725 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.104810126582279e-06, | |
| "loss": 0.2511, | |
| "step": 27750 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.0984810126582283e-06, | |
| "loss": 0.2422, | |
| "step": 27775 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.0921518987341777e-06, | |
| "loss": 0.3149, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.0858227848101267e-06, | |
| "loss": 0.2255, | |
| "step": 27825 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.079493670886076e-06, | |
| "loss": 0.2632, | |
| "step": 27850 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.0731645569620255e-06, | |
| "loss": 0.2489, | |
| "step": 27875 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.066835443037975e-06, | |
| "loss": 0.2338, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.0605063291139244e-06, | |
| "loss": 0.2578, | |
| "step": 27925 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.0541772151898734e-06, | |
| "loss": 0.3353, | |
| "step": 27950 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.047848101265823e-06, | |
| "loss": 0.2242, | |
| "step": 27975 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.0415189873417723e-06, | |
| "loss": 0.3182, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 0.3695291578769684, | |
| "eval_runtime": 6419.0787, | |
| "eval_samples_per_second": 2.546, | |
| "eval_steps_per_second": 2.546, | |
| "eval_wer": 16.858716434095257, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.0351898734177217e-06, | |
| "loss": 0.2769, | |
| "step": 28025 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.0288607594936707e-06, | |
| "loss": 0.2684, | |
| "step": 28050 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.022531645569621e-06, | |
| "loss": 0.2161, | |
| "step": 28075 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.01620253164557e-06, | |
| "loss": 0.2222, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.0098734177215194e-06, | |
| "loss": 0.2914, | |
| "step": 28125 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.003544303797469e-06, | |
| "loss": 0.2773, | |
| "step": 28150 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.9972151898734182e-06, | |
| "loss": 0.3133, | |
| "step": 28175 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.9908860759493673e-06, | |
| "loss": 0.295, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.9845569620253167e-06, | |
| "loss": 0.2387, | |
| "step": 28225 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.978227848101266e-06, | |
| "loss": 0.2818, | |
| "step": 28250 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.9718987341772155e-06, | |
| "loss": 0.2853, | |
| "step": 28275 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.9655696202531645e-06, | |
| "loss": 0.2743, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.959240506329114e-06, | |
| "loss": 0.3024, | |
| "step": 28325 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.9529113924050634e-06, | |
| "loss": 0.2817, | |
| "step": 28350 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.946582278481013e-06, | |
| "loss": 0.3625, | |
| "step": 28375 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.9402531645569622e-06, | |
| "loss": 0.2005, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.9341772151898733e-06, | |
| "loss": 0.2672, | |
| "step": 28425 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.9278481012658227e-06, | |
| "loss": 0.2584, | |
| "step": 28450 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.9215189873417726e-06, | |
| "loss": 0.287, | |
| "step": 28475 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.915189873417722e-06, | |
| "loss": 0.2995, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.9088607594936714e-06, | |
| "loss": 0.3217, | |
| "step": 28525 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.902531645569621e-06, | |
| "loss": 0.276, | |
| "step": 28550 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.89620253164557e-06, | |
| "loss": 0.2314, | |
| "step": 28575 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.8898734177215193e-06, | |
| "loss": 0.261, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.8835443037974687e-06, | |
| "loss": 0.2526, | |
| "step": 28625 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.877215189873418e-06, | |
| "loss": 0.3004, | |
| "step": 28650 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.870886075949367e-06, | |
| "loss": 0.2563, | |
| "step": 28675 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.8645569620253166e-06, | |
| "loss": 0.3067, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.858227848101266e-06, | |
| "loss": 0.2072, | |
| "step": 28725 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.8518987341772154e-06, | |
| "loss": 0.2436, | |
| "step": 28750 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.845569620253165e-06, | |
| "loss": 0.2941, | |
| "step": 28775 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.839240506329114e-06, | |
| "loss": 0.2454, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.8329113924050633e-06, | |
| "loss": 0.3026, | |
| "step": 28825 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.8265822784810127e-06, | |
| "loss": 0.2011, | |
| "step": 28850 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.8202531645569626e-06, | |
| "loss": 0.2864, | |
| "step": 28875 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.813924050632912e-06, | |
| "loss": 0.2134, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.807594936708861e-06, | |
| "loss": 0.2734, | |
| "step": 28925 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.8012658227848104e-06, | |
| "loss": 0.2836, | |
| "step": 28950 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.79493670886076e-06, | |
| "loss": 0.2555, | |
| "step": 28975 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.7886075949367093e-06, | |
| "loss": 0.2683, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.7822784810126587e-06, | |
| "loss": 0.2568, | |
| "step": 29025 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.7759493670886077e-06, | |
| "loss": 0.2345, | |
| "step": 29050 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.769620253164557e-06, | |
| "loss": 0.237, | |
| "step": 29075 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.7632911392405066e-06, | |
| "loss": 0.2567, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.756962025316456e-06, | |
| "loss": 0.2238, | |
| "step": 29125 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.750632911392405e-06, | |
| "loss": 0.2043, | |
| "step": 29150 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.7443037974683544e-06, | |
| "loss": 0.1757, | |
| "step": 29175 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.737974683544304e-06, | |
| "loss": 0.2294, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.7316455696202533e-06, | |
| "loss": 0.2949, | |
| "step": 29225 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.7253164556962027e-06, | |
| "loss": 0.3004, | |
| "step": 29250 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.7189873417721517e-06, | |
| "loss": 0.3117, | |
| "step": 29275 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.7126582278481016e-06, | |
| "loss": 0.286, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.706329113924051e-06, | |
| "loss": 0.242, | |
| "step": 29325 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.7000000000000004e-06, | |
| "loss": 0.2493, | |
| "step": 29350 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.69367088607595e-06, | |
| "loss": 0.3206, | |
| "step": 29375 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.6873417721518993e-06, | |
| "loss": 0.3665, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.6810126582278483e-06, | |
| "loss": 0.268, | |
| "step": 29425 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.6746835443037977e-06, | |
| "loss": 0.264, | |
| "step": 29450 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.668354430379747e-06, | |
| "loss": 0.2831, | |
| "step": 29475 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.6620253164556965e-06, | |
| "loss": 0.2384, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.6556962025316456e-06, | |
| "loss": 0.1576, | |
| "step": 29525 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.649367088607595e-06, | |
| "loss": 0.2091, | |
| "step": 29550 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.6430379746835444e-06, | |
| "loss": 0.2633, | |
| "step": 29575 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.636708860759494e-06, | |
| "loss": 0.295, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.6303797468354433e-06, | |
| "loss": 0.3101, | |
| "step": 29625 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.6240506329113923e-06, | |
| "loss": 0.3355, | |
| "step": 29650 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.6177215189873417e-06, | |
| "loss": 0.2967, | |
| "step": 29675 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.6113924050632915e-06, | |
| "loss": 0.2745, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.605063291139241e-06, | |
| "loss": 0.3033, | |
| "step": 29725 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.5987341772151904e-06, | |
| "loss": 0.2443, | |
| "step": 29750 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.5924050632911394e-06, | |
| "loss": 0.3725, | |
| "step": 29775 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.586075949367089e-06, | |
| "loss": 0.2596, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.5797468354430383e-06, | |
| "loss": 0.2276, | |
| "step": 29825 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.5734177215189877e-06, | |
| "loss": 0.2469, | |
| "step": 29850 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.567088607594937e-06, | |
| "loss": 0.2895, | |
| "step": 29875 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.560759493670886e-06, | |
| "loss": 0.3488, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.5544303797468355e-06, | |
| "loss": 0.271, | |
| "step": 29925 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.548101265822785e-06, | |
| "loss": 0.3119, | |
| "step": 29950 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.5417721518987344e-06, | |
| "loss": 0.2858, | |
| "step": 29975 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.5354430379746834e-06, | |
| "loss": 0.2229, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.529113924050633e-06, | |
| "loss": 0.206, | |
| "step": 30025 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.5227848101265823e-06, | |
| "loss": 0.3484, | |
| "step": 30050 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.5164556962025317e-06, | |
| "loss": 0.2262, | |
| "step": 30075 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.5101265822784815e-06, | |
| "loss": 0.2783, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.503797468354431e-06, | |
| "loss": 0.263, | |
| "step": 30125 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.49746835443038e-06, | |
| "loss": 0.2644, | |
| "step": 30150 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.4911392405063294e-06, | |
| "loss": 0.325, | |
| "step": 30175 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.4848101265822784e-06, | |
| "loss": 0.2032, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.4784810126582283e-06, | |
| "loss": 0.2803, | |
| "step": 30225 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.4721518987341777e-06, | |
| "loss": 0.2053, | |
| "step": 30250 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.4658227848101267e-06, | |
| "loss": 0.2673, | |
| "step": 30275 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.459493670886076e-06, | |
| "loss": 0.2513, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.4531645569620255e-06, | |
| "loss": 0.2171, | |
| "step": 30325 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.446835443037975e-06, | |
| "loss": 0.302, | |
| "step": 30350 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.440506329113924e-06, | |
| "loss": 0.2458, | |
| "step": 30375 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.4341772151898734e-06, | |
| "loss": 0.2626, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.4278481012658233e-06, | |
| "loss": 0.3192, | |
| "step": 30425 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.4215189873417723e-06, | |
| "loss": 0.224, | |
| "step": 30450 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.4151898734177217e-06, | |
| "loss": 0.2465, | |
| "step": 30475 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.408860759493671e-06, | |
| "loss": 0.1951, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.4025316455696205e-06, | |
| "loss": 0.2624, | |
| "step": 30525 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.39620253164557e-06, | |
| "loss": 0.2152, | |
| "step": 30550 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.389873417721519e-06, | |
| "loss": 0.2215, | |
| "step": 30575 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.3835443037974684e-06, | |
| "loss": 0.2685, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.377215189873418e-06, | |
| "loss": 0.2647, | |
| "step": 30625 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.3708860759493673e-06, | |
| "loss": 0.2983, | |
| "step": 30650 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.3645569620253167e-06, | |
| "loss": 0.2951, | |
| "step": 30675 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.358227848101266e-06, | |
| "loss": 0.2416, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.3518987341772155e-06, | |
| "loss": 0.276, | |
| "step": 30725 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.3455696202531645e-06, | |
| "loss": 0.1878, | |
| "step": 30750 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.339240506329114e-06, | |
| "loss": 0.2641, | |
| "step": 30775 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.3331645569620254e-06, | |
| "loss": 0.3948, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.326835443037975e-06, | |
| "loss": 0.3081, | |
| "step": 30825 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.3205063291139243e-06, | |
| "loss": 0.268, | |
| "step": 30850 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.3141772151898737e-06, | |
| "loss": 0.2987, | |
| "step": 30875 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.307848101265823e-06, | |
| "loss": 0.2931, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.301518987341772e-06, | |
| "loss": 0.2308, | |
| "step": 30925 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.2951898734177216e-06, | |
| "loss": 0.2782, | |
| "step": 30950 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.288860759493671e-06, | |
| "loss": 0.2398, | |
| "step": 30975 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.2825316455696204e-06, | |
| "loss": 0.286, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.27620253164557e-06, | |
| "loss": 0.2095, | |
| "step": 31025 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.2698734177215193e-06, | |
| "loss": 0.273, | |
| "step": 31050 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.2635443037974687e-06, | |
| "loss": 0.1825, | |
| "step": 31075 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.257215189873418e-06, | |
| "loss": 0.2576, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.250886075949367e-06, | |
| "loss": 0.2964, | |
| "step": 31125 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.2445569620253166e-06, | |
| "loss": 0.2776, | |
| "step": 31150 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.238227848101266e-06, | |
| "loss": 0.2117, | |
| "step": 31175 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.2318987341772154e-06, | |
| "loss": 0.175, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.225569620253165e-06, | |
| "loss": 0.2813, | |
| "step": 31225 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.2192405063291143e-06, | |
| "loss": 0.1497, | |
| "step": 31250 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.2129113924050637e-06, | |
| "loss": 0.2992, | |
| "step": 31275 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.2065822784810127e-06, | |
| "loss": 0.3126, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.200253164556962e-06, | |
| "loss": 0.1847, | |
| "step": 31325 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.1939240506329116e-06, | |
| "loss": 0.2921, | |
| "step": 31350 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.187594936708861e-06, | |
| "loss": 0.2855, | |
| "step": 31375 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.18126582278481e-06, | |
| "loss": 0.3025, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.17493670886076e-06, | |
| "loss": 0.3418, | |
| "step": 31425 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.1686075949367093e-06, | |
| "loss": 0.3014, | |
| "step": 31450 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.1622784810126583e-06, | |
| "loss": 0.2986, | |
| "step": 31475 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.1559493670886077e-06, | |
| "loss": 0.3538, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.149620253164557e-06, | |
| "loss": 0.2921, | |
| "step": 31525 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.1432911392405066e-06, | |
| "loss": 0.237, | |
| "step": 31550 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.136962025316456e-06, | |
| "loss": 0.2251, | |
| "step": 31575 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.130632911392405e-06, | |
| "loss": 0.3053, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.1243037974683544e-06, | |
| "loss": 0.1975, | |
| "step": 31625 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.1179746835443043e-06, | |
| "loss": 0.2898, | |
| "step": 31650 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.1116455696202533e-06, | |
| "loss": 0.2582, | |
| "step": 31675 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.1053164556962027e-06, | |
| "loss": 0.1979, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.098987341772152e-06, | |
| "loss": 0.3184, | |
| "step": 31725 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.0926582278481016e-06, | |
| "loss": 0.3177, | |
| "step": 31750 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.0863291139240506e-06, | |
| "loss": 0.2008, | |
| "step": 31775 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.08e-06, | |
| "loss": 0.265, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.0736708860759494e-06, | |
| "loss": 0.2883, | |
| "step": 31825 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.067341772151899e-06, | |
| "loss": 0.2435, | |
| "step": 31850 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.0610126582278483e-06, | |
| "loss": 0.2137, | |
| "step": 31875 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.0546835443037977e-06, | |
| "loss": 0.2431, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.048354430379747e-06, | |
| "loss": 0.265, | |
| "step": 31925 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.0420253164556966e-06, | |
| "loss": 0.2077, | |
| "step": 31950 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.0356962025316456e-06, | |
| "loss": 0.2624, | |
| "step": 31975 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.029367088607595e-06, | |
| "loss": 0.2201, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 0.36131182312965393, | |
| "eval_runtime": 6493.11, | |
| "eval_samples_per_second": 2.517, | |
| "eval_steps_per_second": 2.517, | |
| "eval_wer": 16.578489284593214, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.0230379746835444e-06, | |
| "loss": 0.2641, | |
| "step": 32025 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.016708860759494e-06, | |
| "loss": 0.2812, | |
| "step": 32050 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.0103797468354433e-06, | |
| "loss": 0.1528, | |
| "step": 32075 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.0040506329113927e-06, | |
| "loss": 0.2643, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.997721518987342e-06, | |
| "loss": 0.219, | |
| "step": 32125 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.991392405063291e-06, | |
| "loss": 0.3391, | |
| "step": 32150 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.9850632911392406e-06, | |
| "loss": 0.2455, | |
| "step": 32175 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.97873417721519e-06, | |
| "loss": 0.2421, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.9724050632911394e-06, | |
| "loss": 0.3423, | |
| "step": 32225 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.966075949367089e-06, | |
| "loss": 0.2184, | |
| "step": 32250 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.9597468354430383e-06, | |
| "loss": 0.2745, | |
| "step": 32275 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.9534177215189877e-06, | |
| "loss": 0.2711, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.9470886075949367e-06, | |
| "loss": 0.3084, | |
| "step": 32325 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.940759493670886e-06, | |
| "loss": 0.2556, | |
| "step": 32350 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.9344303797468356e-06, | |
| "loss": 0.2887, | |
| "step": 32375 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.928101265822785e-06, | |
| "loss": 0.2732, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.9217721518987344e-06, | |
| "loss": 0.2949, | |
| "step": 32425 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.915443037974684e-06, | |
| "loss": 0.2628, | |
| "step": 32450 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.9091139240506333e-06, | |
| "loss": 0.325, | |
| "step": 32475 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.9027848101265825e-06, | |
| "loss": 0.2752, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 1.896455696202532e-06, | |
| "loss": 0.247, | |
| "step": 32525 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.8901265822784811e-06, | |
| "loss": 0.3119, | |
| "step": 32550 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.8837974683544306e-06, | |
| "loss": 0.2541, | |
| "step": 32575 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.8774683544303798e-06, | |
| "loss": 0.3145, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.8711392405063292e-06, | |
| "loss": 0.2268, | |
| "step": 32625 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.8648101265822784e-06, | |
| "loss": 0.2127, | |
| "step": 32650 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.858481012658228e-06, | |
| "loss": 0.2357, | |
| "step": 32675 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8521518987341775e-06, | |
| "loss": 0.2982, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8458227848101267e-06, | |
| "loss": 0.2769, | |
| "step": 32725 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8394936708860761e-06, | |
| "loss": 0.2541, | |
| "step": 32750 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8331645569620253e-06, | |
| "loss": 0.275, | |
| "step": 32775 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8268354430379748e-06, | |
| "loss": 0.2104, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8205063291139242e-06, | |
| "loss": 0.222, | |
| "step": 32825 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8141772151898734e-06, | |
| "loss": 0.2574, | |
| "step": 32850 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.807848101265823e-06, | |
| "loss": 0.1805, | |
| "step": 32875 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.8015189873417725e-06, | |
| "loss": 0.2351, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.7951898734177217e-06, | |
| "loss": 0.1837, | |
| "step": 32925 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.7888607594936711e-06, | |
| "loss": 0.194, | |
| "step": 32950 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.7825316455696203e-06, | |
| "loss": 0.267, | |
| "step": 32975 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.7762025316455698e-06, | |
| "loss": 0.1986, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.769873417721519e-06, | |
| "loss": 0.2241, | |
| "step": 33025 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.7635443037974684e-06, | |
| "loss": 0.266, | |
| "step": 33050 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.757215189873418e-06, | |
| "loss": 0.2048, | |
| "step": 33075 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.7508860759493673e-06, | |
| "loss": 0.2397, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.7445569620253167e-06, | |
| "loss": 0.1633, | |
| "step": 33125 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.738227848101266e-06, | |
| "loss": 0.2575, | |
| "step": 33150 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.7318987341772153e-06, | |
| "loss": 0.1562, | |
| "step": 33175 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.7255696202531646e-06, | |
| "loss": 0.2383, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.719240506329114e-06, | |
| "loss": 0.1567, | |
| "step": 33225 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.7129113924050634e-06, | |
| "loss": 0.2127, | |
| "step": 33250 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.7065822784810128e-06, | |
| "loss": 0.1826, | |
| "step": 33275 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.7002531645569623e-06, | |
| "loss": 0.1809, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6939240506329117e-06, | |
| "loss": 0.2453, | |
| "step": 33325 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.687594936708861e-06, | |
| "loss": 0.2066, | |
| "step": 33350 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6812658227848103e-06, | |
| "loss": 0.1969, | |
| "step": 33375 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6749367088607596e-06, | |
| "loss": 0.1987, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.668607594936709e-06, | |
| "loss": 0.1774, | |
| "step": 33425 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6622784810126582e-06, | |
| "loss": 0.2687, | |
| "step": 33450 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6559493670886076e-06, | |
| "loss": 0.147, | |
| "step": 33475 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6496202531645573e-06, | |
| "loss": 0.1648, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6432911392405065e-06, | |
| "loss": 0.2474, | |
| "step": 33525 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.636962025316456e-06, | |
| "loss": 0.2013, | |
| "step": 33550 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6306329113924051e-06, | |
| "loss": 0.1886, | |
| "step": 33575 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6243037974683545e-06, | |
| "loss": 0.1765, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6179746835443038e-06, | |
| "loss": 0.2064, | |
| "step": 33625 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6116455696202532e-06, | |
| "loss": 0.2299, | |
| "step": 33650 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6053164556962026e-06, | |
| "loss": 0.1796, | |
| "step": 33675 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.598987341772152e-06, | |
| "loss": 0.1774, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5926582278481015e-06, | |
| "loss": 0.1569, | |
| "step": 33725 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.586329113924051e-06, | |
| "loss": 0.1543, | |
| "step": 33750 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5800000000000001e-06, | |
| "loss": 0.194, | |
| "step": 33775 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5736708860759495e-06, | |
| "loss": 0.2105, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5673417721518988e-06, | |
| "loss": 0.1698, | |
| "step": 33825 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5610126582278482e-06, | |
| "loss": 0.1367, | |
| "step": 33850 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5546835443037974e-06, | |
| "loss": 0.1723, | |
| "step": 33875 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.548354430379747e-06, | |
| "loss": 0.1903, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5420253164556965e-06, | |
| "loss": 0.2113, | |
| "step": 33925 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5356962025316457e-06, | |
| "loss": 0.1264, | |
| "step": 33950 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5293670886075951e-06, | |
| "loss": 0.1578, | |
| "step": 33975 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5230379746835443e-06, | |
| "loss": 0.2333, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5167088607594938e-06, | |
| "loss": 0.1774, | |
| "step": 34025 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5103797468354432e-06, | |
| "loss": 0.17, | |
| "step": 34050 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.5040506329113924e-06, | |
| "loss": 0.2285, | |
| "step": 34075 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.497721518987342e-06, | |
| "loss": 0.234, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.4913924050632913e-06, | |
| "loss": 0.2069, | |
| "step": 34125 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.4850632911392407e-06, | |
| "loss": 0.1736, | |
| "step": 34150 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.4787341772151901e-06, | |
| "loss": 0.1929, | |
| "step": 34175 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.4724050632911393e-06, | |
| "loss": 0.2181, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.4660759493670888e-06, | |
| "loss": 0.1597, | |
| "step": 34225 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.459746835443038e-06, | |
| "loss": 0.1731, | |
| "step": 34250 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.4534177215189874e-06, | |
| "loss": 0.1907, | |
| "step": 34275 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.4470886075949366e-06, | |
| "loss": 0.2332, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.4407594936708863e-06, | |
| "loss": 0.1752, | |
| "step": 34325 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.4344303797468357e-06, | |
| "loss": 0.1873, | |
| "step": 34350 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.428101265822785e-06, | |
| "loss": 0.2065, | |
| "step": 34375 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.4217721518987343e-06, | |
| "loss": 0.1624, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.4154430379746835e-06, | |
| "loss": 0.1844, | |
| "step": 34425 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.409113924050633e-06, | |
| "loss": 0.1771, | |
| "step": 34450 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.4027848101265824e-06, | |
| "loss": 0.1476, | |
| "step": 34475 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.3964556962025316e-06, | |
| "loss": 0.1885, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.3901265822784813e-06, | |
| "loss": 0.1818, | |
| "step": 34525 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.3837974683544305e-06, | |
| "loss": 0.1457, | |
| "step": 34550 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.37746835443038e-06, | |
| "loss": 0.2295, | |
| "step": 34575 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.3711392405063293e-06, | |
| "loss": 0.1818, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.3648101265822785e-06, | |
| "loss": 0.1782, | |
| "step": 34625 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.358481012658228e-06, | |
| "loss": 0.1861, | |
| "step": 34650 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.3521518987341772e-06, | |
| "loss": 0.1515, | |
| "step": 34675 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.3458227848101266e-06, | |
| "loss": 0.2058, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.3394936708860763e-06, | |
| "loss": 0.2107, | |
| "step": 34725 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.3331645569620255e-06, | |
| "loss": 0.1864, | |
| "step": 34750 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.326835443037975e-06, | |
| "loss": 0.17, | |
| "step": 34775 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.3205063291139241e-06, | |
| "loss": 0.1907, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.3141772151898735e-06, | |
| "loss": 0.2187, | |
| "step": 34825 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.3078481012658228e-06, | |
| "loss": 0.1992, | |
| "step": 34850 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.3015189873417722e-06, | |
| "loss": 0.2077, | |
| "step": 34875 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2951898734177216e-06, | |
| "loss": 0.1788, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.288860759493671e-06, | |
| "loss": 0.1674, | |
| "step": 34925 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2825316455696205e-06, | |
| "loss": 0.1736, | |
| "step": 34950 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2762025316455697e-06, | |
| "loss": 0.1637, | |
| "step": 34975 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2698734177215191e-06, | |
| "loss": 0.1799, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2635443037974685e-06, | |
| "loss": 0.1927, | |
| "step": 35025 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2572151898734178e-06, | |
| "loss": 0.1959, | |
| "step": 35050 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2511392405063292e-06, | |
| "loss": 0.1822, | |
| "step": 35075 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2448101265822786e-06, | |
| "loss": 0.1474, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2384810126582278e-06, | |
| "loss": 0.2045, | |
| "step": 35125 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2324050632911393e-06, | |
| "loss": 0.1588, | |
| "step": 35150 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2260759493670887e-06, | |
| "loss": 0.2414, | |
| "step": 35175 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2197468354430382e-06, | |
| "loss": 0.132, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2134177215189874e-06, | |
| "loss": 0.2141, | |
| "step": 35225 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2070886075949368e-06, | |
| "loss": 0.1978, | |
| "step": 35250 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.2007594936708862e-06, | |
| "loss": 0.1775, | |
| "step": 35275 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.1944303797468354e-06, | |
| "loss": 0.1697, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.1881012658227849e-06, | |
| "loss": 0.1815, | |
| "step": 35325 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.1817721518987343e-06, | |
| "loss": 0.1285, | |
| "step": 35350 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.1754430379746837e-06, | |
| "loss": 0.1834, | |
| "step": 35375 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.169113924050633e-06, | |
| "loss": 0.1885, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.1627848101265824e-06, | |
| "loss": 0.163, | |
| "step": 35425 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.1564556962025316e-06, | |
| "loss": 0.2082, | |
| "step": 35450 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.1501265822784812e-06, | |
| "loss": 0.2311, | |
| "step": 35475 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.1437974683544304e-06, | |
| "loss": 0.1512, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.1374683544303799e-06, | |
| "loss": 0.1341, | |
| "step": 35525 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.131139240506329e-06, | |
| "loss": 0.1283, | |
| "step": 35550 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.1248101265822785e-06, | |
| "loss": 0.1876, | |
| "step": 35575 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.118481012658228e-06, | |
| "loss": 0.2165, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.1121518987341774e-06, | |
| "loss": 0.1228, | |
| "step": 35625 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.1058227848101266e-06, | |
| "loss": 0.1389, | |
| "step": 35650 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.099493670886076e-06, | |
| "loss": 0.155, | |
| "step": 35675 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.0931645569620254e-06, | |
| "loss": 0.1628, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.0868354430379747e-06, | |
| "loss": 0.1587, | |
| "step": 35725 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.080506329113924e-06, | |
| "loss": 0.2413, | |
| "step": 35750 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.0741772151898735e-06, | |
| "loss": 0.1904, | |
| "step": 35775 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.067848101265823e-06, | |
| "loss": 0.1904, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.0615189873417722e-06, | |
| "loss": 0.2098, | |
| "step": 35825 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.0551898734177216e-06, | |
| "loss": 0.146, | |
| "step": 35850 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.048860759493671e-06, | |
| "loss": 0.1746, | |
| "step": 35875 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.0425316455696204e-06, | |
| "loss": 0.1392, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.0362025316455697e-06, | |
| "loss": 0.1462, | |
| "step": 35925 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.029873417721519e-06, | |
| "loss": 0.1795, | |
| "step": 35950 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.0235443037974685e-06, | |
| "loss": 0.1482, | |
| "step": 35975 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.017215189873418e-06, | |
| "loss": 0.155, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 0.3633396327495575, | |
| "eval_runtime": 6459.3372, | |
| "eval_samples_per_second": 2.53, | |
| "eval_steps_per_second": 2.53, | |
| "eval_wer": 16.395856519133638, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.0108860759493672e-06, | |
| "loss": 0.139, | |
| "step": 36025 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.0045569620253166e-06, | |
| "loss": 0.1554, | |
| "step": 36050 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 9.98227848101266e-07, | |
| "loss": 0.173, | |
| "step": 36075 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.918987341772152e-07, | |
| "loss": 0.1603, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.855696202531646e-07, | |
| "loss": 0.1895, | |
| "step": 36125 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.792405063291139e-07, | |
| "loss": 0.1912, | |
| "step": 36150 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.729113924050635e-07, | |
| "loss": 0.2239, | |
| "step": 36175 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.665822784810127e-07, | |
| "loss": 0.1956, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.602531645569621e-07, | |
| "loss": 0.1504, | |
| "step": 36225 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.539240506329114e-07, | |
| "loss": 0.2081, | |
| "step": 36250 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.475949367088608e-07, | |
| "loss": 0.1854, | |
| "step": 36275 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.412658227848102e-07, | |
| "loss": 0.1257, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.349367088607595e-07, | |
| "loss": 0.1625, | |
| "step": 36325 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.286075949367089e-07, | |
| "loss": 0.2021, | |
| "step": 36350 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.222784810126583e-07, | |
| "loss": 0.147, | |
| "step": 36375 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.159493670886077e-07, | |
| "loss": 0.1836, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.09620253164557e-07, | |
| "loss": 0.1478, | |
| "step": 36425 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.032911392405064e-07, | |
| "loss": 0.172, | |
| "step": 36450 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 8.969620253164557e-07, | |
| "loss": 0.1896, | |
| "step": 36475 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.906329113924052e-07, | |
| "loss": 0.2566, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.843037974683545e-07, | |
| "loss": 0.1821, | |
| "step": 36525 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.779746835443039e-07, | |
| "loss": 0.1918, | |
| "step": 36550 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.716455696202532e-07, | |
| "loss": 0.11, | |
| "step": 36575 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.653164556962026e-07, | |
| "loss": 0.1448, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.589873417721519e-07, | |
| "loss": 0.2038, | |
| "step": 36625 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.526582278481014e-07, | |
| "loss": 0.1344, | |
| "step": 36650 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.463291139240507e-07, | |
| "loss": 0.1403, | |
| "step": 36675 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.400000000000001e-07, | |
| "loss": 0.1433, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.336708860759494e-07, | |
| "loss": 0.1713, | |
| "step": 36725 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.273417721518988e-07, | |
| "loss": 0.1847, | |
| "step": 36750 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.210126582278481e-07, | |
| "loss": 0.2015, | |
| "step": 36775 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.146835443037976e-07, | |
| "loss": 0.1894, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.083544303797469e-07, | |
| "loss": 0.1611, | |
| "step": 36825 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 8.020253164556963e-07, | |
| "loss": 0.1465, | |
| "step": 36850 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 7.956962025316456e-07, | |
| "loss": 0.2455, | |
| "step": 36875 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.893670886075951e-07, | |
| "loss": 0.2087, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.830379746835444e-07, | |
| "loss": 0.1676, | |
| "step": 36925 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.767088607594938e-07, | |
| "loss": 0.1781, | |
| "step": 36950 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.703797468354431e-07, | |
| "loss": 0.1707, | |
| "step": 36975 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.640506329113925e-07, | |
| "loss": 0.1487, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.577215189873418e-07, | |
| "loss": 0.2339, | |
| "step": 37025 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.513924050632911e-07, | |
| "loss": 0.1718, | |
| "step": 37050 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.450632911392406e-07, | |
| "loss": 0.1745, | |
| "step": 37075 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.3873417721519e-07, | |
| "loss": 0.1631, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.324050632911393e-07, | |
| "loss": 0.1408, | |
| "step": 37125 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.260759493670886e-07, | |
| "loss": 0.1267, | |
| "step": 37150 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.19746835443038e-07, | |
| "loss": 0.2191, | |
| "step": 37175 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.134177215189873e-07, | |
| "loss": 0.1996, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.070886075949368e-07, | |
| "loss": 0.1991, | |
| "step": 37225 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 7.007594936708861e-07, | |
| "loss": 0.1473, | |
| "step": 37250 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 6.944303797468355e-07, | |
| "loss": 0.1583, | |
| "step": 37275 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.881012658227848e-07, | |
| "loss": 0.2122, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.817721518987343e-07, | |
| "loss": 0.1567, | |
| "step": 37325 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.754430379746836e-07, | |
| "loss": 0.2715, | |
| "step": 37350 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.69113924050633e-07, | |
| "loss": 0.1482, | |
| "step": 37375 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.627848101265823e-07, | |
| "loss": 0.147, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.564556962025317e-07, | |
| "loss": 0.1426, | |
| "step": 37425 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.50126582278481e-07, | |
| "loss": 0.1799, | |
| "step": 37450 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.437974683544305e-07, | |
| "loss": 0.1787, | |
| "step": 37475 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.374683544303798e-07, | |
| "loss": 0.1479, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.311392405063292e-07, | |
| "loss": 0.1852, | |
| "step": 37525 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.248101265822785e-07, | |
| "loss": 0.1427, | |
| "step": 37550 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.184810126582279e-07, | |
| "loss": 0.1572, | |
| "step": 37575 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.121518987341773e-07, | |
| "loss": 0.1575, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 6.058227848101266e-07, | |
| "loss": 0.1236, | |
| "step": 37625 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 5.99493670886076e-07, | |
| "loss": 0.1662, | |
| "step": 37650 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 5.931645569620254e-07, | |
| "loss": 0.1561, | |
| "step": 37675 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.868354430379748e-07, | |
| "loss": 0.1614, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.805063291139241e-07, | |
| "loss": 0.2134, | |
| "step": 37725 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.741772151898735e-07, | |
| "loss": 0.1771, | |
| "step": 37750 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.678481012658229e-07, | |
| "loss": 0.1254, | |
| "step": 37775 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.615189873417722e-07, | |
| "loss": 0.204, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.551898734177216e-07, | |
| "loss": 0.198, | |
| "step": 37825 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.488607594936709e-07, | |
| "loss": 0.188, | |
| "step": 37850 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.425316455696202e-07, | |
| "loss": 0.1605, | |
| "step": 37875 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.362025316455697e-07, | |
| "loss": 0.1501, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.29873417721519e-07, | |
| "loss": 0.1273, | |
| "step": 37925 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.235443037974684e-07, | |
| "loss": 0.177, | |
| "step": 37950 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.172151898734177e-07, | |
| "loss": 0.1128, | |
| "step": 37975 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.108860759493672e-07, | |
| "loss": 0.1552, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 5.045569620253165e-07, | |
| "loss": 0.2035, | |
| "step": 38025 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 4.982278481012658e-07, | |
| "loss": 0.1156, | |
| "step": 38050 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 4.918987341772152e-07, | |
| "loss": 0.106, | |
| "step": 38075 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.855696202531646e-07, | |
| "loss": 0.1351, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.79493670886076e-07, | |
| "loss": 0.1863, | |
| "step": 38125 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.731645569620254e-07, | |
| "loss": 0.1761, | |
| "step": 38150 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.668354430379747e-07, | |
| "loss": 0.1485, | |
| "step": 38175 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.605063291139241e-07, | |
| "loss": 0.1448, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.5417721518987346e-07, | |
| "loss": 0.2688, | |
| "step": 38225 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.4784810126582284e-07, | |
| "loss": 0.1914, | |
| "step": 38250 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.4151898734177216e-07, | |
| "loss": 0.2008, | |
| "step": 38275 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.351898734177216e-07, | |
| "loss": 0.1337, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.288607594936709e-07, | |
| "loss": 0.1989, | |
| "step": 38325 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.2253164556962034e-07, | |
| "loss": 0.1062, | |
| "step": 38350 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.1620253164556966e-07, | |
| "loss": 0.1711, | |
| "step": 38375 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.0987341772151903e-07, | |
| "loss": 0.1516, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 4.0354430379746836e-07, | |
| "loss": 0.1941, | |
| "step": 38425 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.972151898734178e-07, | |
| "loss": 0.1393, | |
| "step": 38450 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.908860759493671e-07, | |
| "loss": 0.1347, | |
| "step": 38475 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.8455696202531653e-07, | |
| "loss": 0.1806, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.7822784810126585e-07, | |
| "loss": 0.1478, | |
| "step": 38525 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.7189873417721523e-07, | |
| "loss": 0.141, | |
| "step": 38550 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.655696202531646e-07, | |
| "loss": 0.1644, | |
| "step": 38575 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.592405063291139e-07, | |
| "loss": 0.1266, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.529113924050633e-07, | |
| "loss": 0.1441, | |
| "step": 38625 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.465822784810127e-07, | |
| "loss": 0.1214, | |
| "step": 38650 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.4025316455696205e-07, | |
| "loss": 0.138, | |
| "step": 38675 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.3392405063291137e-07, | |
| "loss": 0.1626, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.275949367088608e-07, | |
| "loss": 0.1433, | |
| "step": 38725 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.212658227848101e-07, | |
| "loss": 0.138, | |
| "step": 38750 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.1493670886075955e-07, | |
| "loss": 0.2162, | |
| "step": 38775 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.0860759493670887e-07, | |
| "loss": 0.1126, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.0227848101265825e-07, | |
| "loss": 0.1327, | |
| "step": 38825 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 2.959493670886076e-07, | |
| "loss": 0.1757, | |
| "step": 38850 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 2.89620253164557e-07, | |
| "loss": 0.1543, | |
| "step": 38875 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.8329113924050637e-07, | |
| "loss": 0.167, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.7696202531645574e-07, | |
| "loss": 0.1876, | |
| "step": 38925 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.706329113924051e-07, | |
| "loss": 0.1447, | |
| "step": 38950 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.6430379746835444e-07, | |
| "loss": 0.1873, | |
| "step": 38975 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.579746835443038e-07, | |
| "loss": 0.1631, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.516455696202532e-07, | |
| "loss": 0.1383, | |
| "step": 39025 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.453164556962025e-07, | |
| "loss": 0.1515, | |
| "step": 39050 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.389873417721519e-07, | |
| "loss": 0.19, | |
| "step": 39075 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.3265822784810126e-07, | |
| "loss": 0.1476, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.2632911392405064e-07, | |
| "loss": 0.1614, | |
| "step": 39125 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.2e-07, | |
| "loss": 0.1626, | |
| "step": 39150 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.1367088607594939e-07, | |
| "loss": 0.1583, | |
| "step": 39175 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.0734177215189873e-07, | |
| "loss": 0.1863, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.010126582278481e-07, | |
| "loss": 0.1202, | |
| "step": 39225 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.9468354430379748e-07, | |
| "loss": 0.1921, | |
| "step": 39250 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.8835443037974683e-07, | |
| "loss": 0.1385, | |
| "step": 39275 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.820253164556962e-07, | |
| "loss": 0.161, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.7569620253164558e-07, | |
| "loss": 0.1507, | |
| "step": 39325 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.6936708860759496e-07, | |
| "loss": 0.1869, | |
| "step": 39350 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.630379746835443e-07, | |
| "loss": 0.1218, | |
| "step": 39375 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.5670886075949368e-07, | |
| "loss": 0.1715, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.5037974683544305e-07, | |
| "loss": 0.1804, | |
| "step": 39425 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.4405063291139243e-07, | |
| "loss": 0.147, | |
| "step": 39450 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.3772151898734178e-07, | |
| "loss": 0.134, | |
| "step": 39475 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.3139240506329115e-07, | |
| "loss": 0.1619, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.2506329113924053e-07, | |
| "loss": 0.177, | |
| "step": 39525 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.1873417721518989e-07, | |
| "loss": 0.12, | |
| "step": 39550 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.1240506329113925e-07, | |
| "loss": 0.1008, | |
| "step": 39575 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.0607594936708862e-07, | |
| "loss": 0.1401, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 9.974683544303799e-08, | |
| "loss": 0.1275, | |
| "step": 39625 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 9.341772151898736e-08, | |
| "loss": 0.1162, | |
| "step": 39650 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.708860759493672e-08, | |
| "loss": 0.0763, | |
| "step": 39675 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.07594936708861e-08, | |
| "loss": 0.111, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 7.443037974683545e-08, | |
| "loss": 0.1147, | |
| "step": 39725 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 6.810126582278482e-08, | |
| "loss": 0.0552, | |
| "step": 39750 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 6.177215189873418e-08, | |
| "loss": 0.1377, | |
| "step": 39775 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 5.544303797468355e-08, | |
| "loss": 0.0969, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 4.911392405063291e-08, | |
| "loss": 0.1242, | |
| "step": 39825 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 4.278481012658228e-08, | |
| "loss": 0.1458, | |
| "step": 39850 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 3.645569620253165e-08, | |
| "loss": 0.1232, | |
| "step": 39875 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 3.0126582278481015e-08, | |
| "loss": 0.108, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 2.379746835443038e-08, | |
| "loss": 0.1352, | |
| "step": 39925 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.7468354430379748e-08, | |
| "loss": 0.1264, | |
| "step": 39950 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.1139240506329115e-08, | |
| "loss": 0.081, | |
| "step": 39975 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 4.810126582278481e-09, | |
| "loss": 0.0904, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 0.36083361506462097, | |
| "eval_runtime": 6490.7798, | |
| "eval_samples_per_second": 2.517, | |
| "eval_steps_per_second": 2.517, | |
| "eval_wer": 16.15101446793939, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "step": 40000, | |
| "total_flos": 5.1887996928e+18, | |
| "train_loss": 0.31283938461542127, | |
| "train_runtime": 80827.6559, | |
| "train_samples_per_second": 0.99, | |
| "train_steps_per_second": 0.495 | |
| } | |
| ], | |
| "max_steps": 40000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 5.1887996928e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |