| { | |
| "best_metric": 1.3685582876205444, | |
| "best_model_checkpoint": "clinic_albert_v3/checkpoint-104500", | |
| "epoch": 3.0, | |
| "global_step": 112329, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.4500000000000003e-06, | |
| "loss": 6.2872, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 3.8396031856536865, | |
| "eval_runtime": 92.2647, | |
| "eval_samples_per_second": 161.806, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.950000000000001e-06, | |
| "loss": 3.6553, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 3.5483450889587402, | |
| "eval_runtime": 91.9838, | |
| "eval_samples_per_second": 162.3, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.45e-06, | |
| "loss": 3.4131, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 3.3662946224212646, | |
| "eval_runtime": 91.5787, | |
| "eval_samples_per_second": 163.018, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.950000000000001e-06, | |
| "loss": 3.2051, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 3.199434995651245, | |
| "eval_runtime": 91.5904, | |
| "eval_samples_per_second": 162.997, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.2450000000000001e-05, | |
| "loss": 3.1553, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 3.091717004776001, | |
| "eval_runtime": 91.2768, | |
| "eval_samples_per_second": 163.557, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.4950000000000001e-05, | |
| "loss": 3.0703, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 2.9730803966522217, | |
| "eval_runtime": 91.2688, | |
| "eval_samples_per_second": 163.572, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.745e-05, | |
| "loss": 2.9258, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 2.930089235305786, | |
| "eval_runtime": 91.4358, | |
| "eval_samples_per_second": 163.273, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.995e-05, | |
| "loss": 2.8627, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 2.842494249343872, | |
| "eval_runtime": 91.5055, | |
| "eval_samples_per_second": 163.149, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.245e-05, | |
| "loss": 2.797, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 2.8484582901000977, | |
| "eval_runtime": 91.4864, | |
| "eval_samples_per_second": 163.183, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.495e-05, | |
| "loss": 2.7408, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 2.784637928009033, | |
| "eval_runtime": 91.3143, | |
| "eval_samples_per_second": 163.49, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.7450000000000003e-05, | |
| "loss": 2.7552, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 2.731156349182129, | |
| "eval_runtime": 91.2004, | |
| "eval_samples_per_second": 163.694, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.995e-05, | |
| "loss": 2.7098, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 2.677649736404419, | |
| "eval_runtime": 91.2243, | |
| "eval_samples_per_second": 163.652, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.245e-05, | |
| "loss": 2.7015, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 2.7468419075012207, | |
| "eval_runtime": 91.3379, | |
| "eval_samples_per_second": 163.448, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.495e-05, | |
| "loss": 2.6226, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 2.6828126907348633, | |
| "eval_runtime": 91.2062, | |
| "eval_samples_per_second": 163.684, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.745e-05, | |
| "loss": 2.6738, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 2.622964382171631, | |
| "eval_runtime": 91.2339, | |
| "eval_samples_per_second": 163.634, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.995e-05, | |
| "loss": 2.6507, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 2.6091177463531494, | |
| "eval_runtime": 91.1569, | |
| "eval_samples_per_second": 163.773, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.245e-05, | |
| "loss": 2.6198, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 2.598926067352295, | |
| "eval_runtime": 91.2361, | |
| "eval_samples_per_second": 163.63, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.495e-05, | |
| "loss": 2.5921, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 2.59818959236145, | |
| "eval_runtime": 91.1835, | |
| "eval_samples_per_second": 163.725, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.745e-05, | |
| "loss": 2.5966, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 2.5808210372924805, | |
| "eval_runtime": 91.3208, | |
| "eval_samples_per_second": 163.479, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.995e-05, | |
| "loss": 2.5369, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 2.5975215435028076, | |
| "eval_runtime": 91.1933, | |
| "eval_samples_per_second": 163.707, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.9760576180750326e-05, | |
| "loss": 2.5351, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 2.507310152053833, | |
| "eval_runtime": 91.2579, | |
| "eval_samples_per_second": 163.591, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.9516754781147087e-05, | |
| "loss": 2.469, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 2.5691452026367188, | |
| "eval_runtime": 91.4338, | |
| "eval_samples_per_second": 163.277, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.927244476150456e-05, | |
| "loss": 2.5135, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 2.534702777862549, | |
| "eval_runtime": 91.54, | |
| "eval_samples_per_second": 163.087, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.9028134741862035e-05, | |
| "loss": 2.4175, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 2.506258726119995, | |
| "eval_runtime": 91.2029, | |
| "eval_samples_per_second": 163.69, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.878382472221951e-05, | |
| "loss": 2.4601, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 2.417022228240967, | |
| "eval_runtime": 91.3123, | |
| "eval_samples_per_second": 163.494, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.8539514702576984e-05, | |
| "loss": 2.3867, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 2.41973614692688, | |
| "eval_runtime": 91.3867, | |
| "eval_samples_per_second": 163.361, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.829520468293446e-05, | |
| "loss": 2.3704, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 2.3954126834869385, | |
| "eval_runtime": 91.334, | |
| "eval_samples_per_second": 163.455, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.805089466329193e-05, | |
| "loss": 2.3152, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 2.3748397827148438, | |
| "eval_runtime": 91.307, | |
| "eval_samples_per_second": 163.503, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.7806584643649414e-05, | |
| "loss": 2.3504, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 2.3295907974243164, | |
| "eval_runtime": 91.2388, | |
| "eval_samples_per_second": 163.626, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.756227462400688e-05, | |
| "loss": 2.325, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 2.315340518951416, | |
| "eval_runtime": 91.4211, | |
| "eval_samples_per_second": 163.299, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.7317964604364355e-05, | |
| "loss": 2.2768, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 2.323646306991577, | |
| "eval_runtime": 91.2326, | |
| "eval_samples_per_second": 163.637, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.707365458472183e-05, | |
| "loss": 2.2752, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 2.286576747894287, | |
| "eval_runtime": 91.2898, | |
| "eval_samples_per_second": 163.534, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.6829344565079304e-05, | |
| "loss": 2.2439, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 2.2795145511627197, | |
| "eval_runtime": 91.3133, | |
| "eval_samples_per_second": 163.492, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.6585523165476065e-05, | |
| "loss": 2.2255, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 2.226459503173828, | |
| "eval_runtime": 91.4081, | |
| "eval_samples_per_second": 163.323, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.634121314583354e-05, | |
| "loss": 2.177, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 2.252764940261841, | |
| "eval_runtime": 91.6167, | |
| "eval_samples_per_second": 162.951, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.60973917462303e-05, | |
| "loss": 2.2602, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 2.2427968978881836, | |
| "eval_runtime": 91.3698, | |
| "eval_samples_per_second": 163.391, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.585405896666634e-05, | |
| "loss": 2.2382, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 2.175690174102783, | |
| "eval_runtime": 91.3659, | |
| "eval_samples_per_second": 163.398, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.5609748947023814e-05, | |
| "loss": 2.1481, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 2.1878654956817627, | |
| "eval_runtime": 91.3436, | |
| "eval_samples_per_second": 163.438, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.5365438927381295e-05, | |
| "loss": 2.0507, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 2.210096597671509, | |
| "eval_runtime": 91.3869, | |
| "eval_samples_per_second": 163.36, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.512112890773877e-05, | |
| "loss": 2.1267, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 2.1687960624694824, | |
| "eval_runtime": 91.1987, | |
| "eval_samples_per_second": 163.697, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.487681888809624e-05, | |
| "loss": 2.1605, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 2.1389825344085693, | |
| "eval_runtime": 91.269, | |
| "eval_samples_per_second": 163.571, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.463250886845372e-05, | |
| "loss": 2.0474, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 2.107516288757324, | |
| "eval_runtime": 91.2438, | |
| "eval_samples_per_second": 163.617, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.438819884881119e-05, | |
| "loss": 2.1403, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 2.117351531982422, | |
| "eval_runtime": 91.3836, | |
| "eval_samples_per_second": 163.366, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.414388882916866e-05, | |
| "loss": 2.1505, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 2.103529214859009, | |
| "eval_runtime": 91.397, | |
| "eval_samples_per_second": 163.342, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.3899578809526134e-05, | |
| "loss": 2.0463, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 2.076082229614258, | |
| "eval_runtime": 91.3284, | |
| "eval_samples_per_second": 163.465, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.3655268789883615e-05, | |
| "loss": 2.0312, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 2.098130702972412, | |
| "eval_runtime": 91.4521, | |
| "eval_samples_per_second": 163.244, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.341095877024109e-05, | |
| "loss": 2.0562, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 2.0372567176818848, | |
| "eval_runtime": 91.2845, | |
| "eval_samples_per_second": 163.544, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.316664875059856e-05, | |
| "loss": 2.0185, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 2.0775225162506104, | |
| "eval_runtime": 91.1456, | |
| "eval_samples_per_second": 163.793, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.292233873095604e-05, | |
| "loss": 2.012, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 2.040658712387085, | |
| "eval_runtime": 91.1946, | |
| "eval_samples_per_second": 163.705, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.267802871131351e-05, | |
| "loss": 2.0448, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 2.0319766998291016, | |
| "eval_runtime": 91.2535, | |
| "eval_samples_per_second": 163.599, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.2433718691670987e-05, | |
| "loss": 1.9511, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 2.034172534942627, | |
| "eval_runtime": 91.3903, | |
| "eval_samples_per_second": 163.354, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.218940867202846e-05, | |
| "loss": 1.9424, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 2.0328168869018555, | |
| "eval_runtime": 91.2635, | |
| "eval_samples_per_second": 163.581, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.1945098652385935e-05, | |
| "loss": 1.9533, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.9927563667297363, | |
| "eval_runtime": 91.4616, | |
| "eval_samples_per_second": 163.227, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.170078863274341e-05, | |
| "loss": 1.9538, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 2.0190131664276123, | |
| "eval_runtime": 91.2642, | |
| "eval_samples_per_second": 163.58, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.145647861310088e-05, | |
| "loss": 1.9778, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 2.007988929748535, | |
| "eval_runtime": 91.4801, | |
| "eval_samples_per_second": 163.194, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.121216859345836e-05, | |
| "loss": 1.9567, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 2.0140700340270996, | |
| "eval_runtime": 91.3767, | |
| "eval_samples_per_second": 163.379, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.096834719385512e-05, | |
| "loss": 1.9589, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.9930866956710815, | |
| "eval_runtime": 91.1168, | |
| "eval_samples_per_second": 163.845, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.072403717421259e-05, | |
| "loss": 1.9605, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.9426169395446777, | |
| "eval_runtime": 91.226, | |
| "eval_samples_per_second": 163.648, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.047972715457006e-05, | |
| "loss": 1.9552, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.9635326862335205, | |
| "eval_runtime": 91.3172, | |
| "eval_samples_per_second": 163.485, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.023590575496682e-05, | |
| "loss": 1.9112, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.9517323970794678, | |
| "eval_runtime": 91.4036, | |
| "eval_samples_per_second": 163.331, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.99915957353243e-05, | |
| "loss": 1.8632, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.945887565612793, | |
| "eval_runtime": 91.1301, | |
| "eval_samples_per_second": 163.821, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.9747285715681777e-05, | |
| "loss": 1.8776, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 1.9599124193191528, | |
| "eval_runtime": 91.3256, | |
| "eval_samples_per_second": 163.47, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.9502975696039244e-05, | |
| "loss": 1.8564, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.93245530128479, | |
| "eval_runtime": 91.4657, | |
| "eval_samples_per_second": 163.22, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.9259154296436005e-05, | |
| "loss": 1.8988, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.9134759902954102, | |
| "eval_runtime": 91.4228, | |
| "eval_samples_per_second": 163.296, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.9014844276793486e-05, | |
| "loss": 1.8924, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 1.9036946296691895, | |
| "eval_runtime": 91.2342, | |
| "eval_samples_per_second": 163.634, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.8771022877190246e-05, | |
| "loss": 1.8543, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.8894397020339966, | |
| "eval_runtime": 91.3605, | |
| "eval_samples_per_second": 163.408, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.8526712857547714e-05, | |
| "loss": 1.8546, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 1.8986772298812866, | |
| "eval_runtime": 91.4907, | |
| "eval_samples_per_second": 163.175, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.828240283790519e-05, | |
| "loss": 1.7711, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.9133729934692383, | |
| "eval_runtime": 91.4658, | |
| "eval_samples_per_second": 163.219, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.803809281826267e-05, | |
| "loss": 1.8173, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 1.8876162767410278, | |
| "eval_runtime": 91.3085, | |
| "eval_samples_per_second": 163.501, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.779378279862014e-05, | |
| "loss": 1.8667, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.8843164443969727, | |
| "eval_runtime": 91.1747, | |
| "eval_samples_per_second": 163.741, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.75499613990169e-05, | |
| "loss": 1.7971, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.8736356496810913, | |
| "eval_runtime": 91.3988, | |
| "eval_samples_per_second": 163.339, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.730565137937437e-05, | |
| "loss": 1.8363, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.8734278678894043, | |
| "eval_runtime": 91.4136, | |
| "eval_samples_per_second": 163.313, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.7061341359731846e-05, | |
| "loss": 1.9108, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 1.8428773880004883, | |
| "eval_runtime": 91.3304, | |
| "eval_samples_per_second": 163.461, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.681703134008932e-05, | |
| "loss": 1.7966, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.863236427307129, | |
| "eval_runtime": 91.3214, | |
| "eval_samples_per_second": 163.478, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.6572721320446795e-05, | |
| "loss": 1.8191, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.826414704322815, | |
| "eval_runtime": 91.3739, | |
| "eval_samples_per_second": 163.384, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.632841130080427e-05, | |
| "loss": 1.7991, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 1.831282615661621, | |
| "eval_runtime": 91.5324, | |
| "eval_samples_per_second": 163.101, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.608410128116175e-05, | |
| "loss": 1.7797, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 1.8110054731369019, | |
| "eval_runtime": 91.6401, | |
| "eval_samples_per_second": 162.909, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.583979126151922e-05, | |
| "loss": 1.7492, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 1.827107548713684, | |
| "eval_runtime": 91.1498, | |
| "eval_samples_per_second": 163.785, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.559596986191598e-05, | |
| "loss": 1.7541, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 1.8055846691131592, | |
| "eval_runtime": 91.4418, | |
| "eval_samples_per_second": 163.262, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.535165984227345e-05, | |
| "loss": 1.7882, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.8122904300689697, | |
| "eval_runtime": 91.6628, | |
| "eval_samples_per_second": 162.869, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.510734982263093e-05, | |
| "loss": 1.7544, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 1.8098782300949097, | |
| "eval_runtime": 91.4346, | |
| "eval_samples_per_second": 163.275, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.48630398029884e-05, | |
| "loss": 1.7338, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 1.7867393493652344, | |
| "eval_runtime": 91.3421, | |
| "eval_samples_per_second": 163.44, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.4618729783345875e-05, | |
| "loss": 1.7529, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 1.7708940505981445, | |
| "eval_runtime": 91.2573, | |
| "eval_samples_per_second": 163.592, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.437441976370335e-05, | |
| "loss": 1.7782, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 1.7782670259475708, | |
| "eval_runtime": 91.5943, | |
| "eval_samples_per_second": 162.99, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.4130109744060824e-05, | |
| "loss": 1.7018, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 1.8046059608459473, | |
| "eval_runtime": 91.4265, | |
| "eval_samples_per_second": 163.29, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.38857997244183e-05, | |
| "loss": 1.6726, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 1.7743386030197144, | |
| "eval_runtime": 91.4777, | |
| "eval_samples_per_second": 163.198, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.364148970477577e-05, | |
| "loss": 1.6964, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 1.781007170677185, | |
| "eval_runtime": 91.4397, | |
| "eval_samples_per_second": 163.266, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.3397179685133254e-05, | |
| "loss": 1.7196, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 1.7817639112472534, | |
| "eval_runtime": 91.6102, | |
| "eval_samples_per_second": 162.962, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.315286966549072e-05, | |
| "loss": 1.7085, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 1.7810941934585571, | |
| "eval_runtime": 91.3943, | |
| "eval_samples_per_second": 163.347, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.2908559645848195e-05, | |
| "loss": 1.729, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.7492631673812866, | |
| "eval_runtime": 91.524, | |
| "eval_samples_per_second": 163.116, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.2664738246244956e-05, | |
| "loss": 1.6901, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 1.7426705360412598, | |
| "eval_runtime": 91.3863, | |
| "eval_samples_per_second": 163.362, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.242042822660243e-05, | |
| "loss": 1.6651, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 1.7624448537826538, | |
| "eval_runtime": 91.3919, | |
| "eval_samples_per_second": 163.352, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.2176118206959905e-05, | |
| "loss": 1.6679, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 1.7611286640167236, | |
| "eval_runtime": 91.3302, | |
| "eval_samples_per_second": 163.462, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.193180818731738e-05, | |
| "loss": 1.6635, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 1.7588094472885132, | |
| "eval_runtime": 91.421, | |
| "eval_samples_per_second": 163.299, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.168798678771414e-05, | |
| "loss": 1.6785, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 1.7499796152114868, | |
| "eval_runtime": 91.5104, | |
| "eval_samples_per_second": 163.14, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.1443676768071614e-05, | |
| "loss": 1.6805, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 1.7386727333068848, | |
| "eval_runtime": 91.2579, | |
| "eval_samples_per_second": 163.591, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.119936674842909e-05, | |
| "loss": 1.6603, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 1.7336368560791016, | |
| "eval_runtime": 91.5612, | |
| "eval_samples_per_second": 163.049, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.095505672878656e-05, | |
| "loss": 1.6551, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 1.7313791513442993, | |
| "eval_runtime": 91.2301, | |
| "eval_samples_per_second": 163.641, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.071123532918332e-05, | |
| "loss": 1.6739, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 1.7289615869522095, | |
| "eval_runtime": 91.2197, | |
| "eval_samples_per_second": 163.66, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.0466925309540794e-05, | |
| "loss": 1.677, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 1.7310763597488403, | |
| "eval_runtime": 91.2875, | |
| "eval_samples_per_second": 163.538, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.022261528989827e-05, | |
| "loss": 1.6545, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 1.7149819135665894, | |
| "eval_runtime": 91.59, | |
| "eval_samples_per_second": 162.998, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.9978305270255746e-05, | |
| "loss": 1.6666, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 1.7039389610290527, | |
| "eval_runtime": 91.4495, | |
| "eval_samples_per_second": 163.249, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.9733995250613217e-05, | |
| "loss": 1.6394, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 1.6981836557388306, | |
| "eval_runtime": 91.1406, | |
| "eval_samples_per_second": 163.802, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.948968523097069e-05, | |
| "loss": 1.6064, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 1.7015522718429565, | |
| "eval_runtime": 91.2276, | |
| "eval_samples_per_second": 163.646, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.9245863831367455e-05, | |
| "loss": 1.676, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 1.6849902868270874, | |
| "eval_runtime": 91.3094, | |
| "eval_samples_per_second": 163.499, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.900155381172493e-05, | |
| "loss": 1.6561, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 1.6929577589035034, | |
| "eval_runtime": 91.6129, | |
| "eval_samples_per_second": 162.957, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.87572437920824e-05, | |
| "loss": 1.6949, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 1.6772891283035278, | |
| "eval_runtime": 91.2759, | |
| "eval_samples_per_second": 163.559, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.8512933772439875e-05, | |
| "loss": 1.6279, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 1.6779346466064453, | |
| "eval_runtime": 91.1313, | |
| "eval_samples_per_second": 163.819, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.8268623752797352e-05, | |
| "loss": 1.6379, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 1.6741278171539307, | |
| "eval_runtime": 91.5237, | |
| "eval_samples_per_second": 163.116, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.8024313733154827e-05, | |
| "loss": 1.599, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.6729629039764404, | |
| "eval_runtime": 91.5904, | |
| "eval_samples_per_second": 162.997, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.7780003713512298e-05, | |
| "loss": 1.5784, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 1.6555140018463135, | |
| "eval_runtime": 91.3689, | |
| "eval_samples_per_second": 163.393, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.7535693693869775e-05, | |
| "loss": 1.577, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 1.665055751800537, | |
| "eval_runtime": 91.3871, | |
| "eval_samples_per_second": 163.36, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.7291872294266536e-05, | |
| "loss": 1.6282, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 1.6812142133712769, | |
| "eval_runtime": 91.4955, | |
| "eval_samples_per_second": 163.167, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.704756227462401e-05, | |
| "loss": 1.5585, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 1.6711357831954956, | |
| "eval_runtime": 91.5418, | |
| "eval_samples_per_second": 163.084, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.680325225498148e-05, | |
| "loss": 1.5593, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 1.6432082653045654, | |
| "eval_runtime": 91.3937, | |
| "eval_samples_per_second": 163.348, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.655894223533896e-05, | |
| "loss": 1.5348, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 1.6400490999221802, | |
| "eval_runtime": 91.215, | |
| "eval_samples_per_second": 163.668, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.6314632215696433e-05, | |
| "loss": 1.6154, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 1.647261381149292, | |
| "eval_runtime": 91.4792, | |
| "eval_samples_per_second": 163.196, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.6070810816093187e-05, | |
| "loss": 1.5831, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 1.6438063383102417, | |
| "eval_runtime": 91.2696, | |
| "eval_samples_per_second": 163.57, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.5826500796450665e-05, | |
| "loss": 1.6009, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 1.646418571472168, | |
| "eval_runtime": 91.2662, | |
| "eval_samples_per_second": 163.576, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.558219077680814e-05, | |
| "loss": 1.5858, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.645626425743103, | |
| "eval_runtime": 91.2497, | |
| "eval_samples_per_second": 163.606, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.5337880757165617e-05, | |
| "loss": 1.5251, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 1.6241323947906494, | |
| "eval_runtime": 91.2854, | |
| "eval_samples_per_second": 163.542, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.509405935756237e-05, | |
| "loss": 1.5767, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 1.6338564157485962, | |
| "eval_runtime": 91.3908, | |
| "eval_samples_per_second": 163.353, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.4849749337919848e-05, | |
| "loss": 1.5394, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 1.602984070777893, | |
| "eval_runtime": 91.3335, | |
| "eval_samples_per_second": 163.456, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.4605439318277322e-05, | |
| "loss": 1.5951, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 1.6044830083847046, | |
| "eval_runtime": 91.4386, | |
| "eval_samples_per_second": 163.268, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.4361129298634797e-05, | |
| "loss": 1.5563, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 1.6318944692611694, | |
| "eval_runtime": 91.2817, | |
| "eval_samples_per_second": 163.549, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.4117307899031554e-05, | |
| "loss": 1.5319, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 1.5991877317428589, | |
| "eval_runtime": 91.533, | |
| "eval_samples_per_second": 163.1, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.387299787938903e-05, | |
| "loss": 1.595, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 1.583760142326355, | |
| "eval_runtime": 91.246, | |
| "eval_samples_per_second": 163.613, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.362917647978579e-05, | |
| "loss": 1.5797, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 1.6295143365859985, | |
| "eval_runtime": 90.9781, | |
| "eval_samples_per_second": 164.094, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.3384866460143267e-05, | |
| "loss": 1.5298, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 1.599826455116272, | |
| "eval_runtime": 91.406, | |
| "eval_samples_per_second": 163.326, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.3140556440500737e-05, | |
| "loss": 1.5384, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 1.6063343286514282, | |
| "eval_runtime": 91.4223, | |
| "eval_samples_per_second": 163.297, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.2896246420858215e-05, | |
| "loss": 1.4986, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 1.5949381589889526, | |
| "eval_runtime": 91.3186, | |
| "eval_samples_per_second": 163.483, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.2651936401215686e-05, | |
| "loss": 1.5075, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 1.5914294719696045, | |
| "eval_runtime": 91.3212, | |
| "eval_samples_per_second": 163.478, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.2407626381573164e-05, | |
| "loss": 1.5303, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 1.5806745290756226, | |
| "eval_runtime": 91.0984, | |
| "eval_samples_per_second": 163.878, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.2163316361930635e-05, | |
| "loss": 1.5015, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 1.5750070810317993, | |
| "eval_runtime": 91.4316, | |
| "eval_samples_per_second": 163.281, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.1919006342288112e-05, | |
| "loss": 1.5542, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 1.6114143133163452, | |
| "eval_runtime": 91.4407, | |
| "eval_samples_per_second": 163.264, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.167518494268487e-05, | |
| "loss": 1.525, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 1.5729782581329346, | |
| "eval_runtime": 91.2691, | |
| "eval_samples_per_second": 163.571, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.1430874923042347e-05, | |
| "loss": 1.4573, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 1.598924994468689, | |
| "eval_runtime": 91.2081, | |
| "eval_samples_per_second": 163.681, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.1186564903399818e-05, | |
| "loss": 1.5125, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 1.5879831314086914, | |
| "eval_runtime": 91.4783, | |
| "eval_samples_per_second": 163.197, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.0942254883757292e-05, | |
| "loss": 1.5089, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 1.5672917366027832, | |
| "eval_runtime": 91.4841, | |
| "eval_samples_per_second": 163.187, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.0697944864114767e-05, | |
| "loss": 1.5231, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 1.5848079919815063, | |
| "eval_runtime": 91.2446, | |
| "eval_samples_per_second": 163.615, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.045363484447224e-05, | |
| "loss": 1.5283, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 1.5898315906524658, | |
| "eval_runtime": 91.1948, | |
| "eval_samples_per_second": 163.705, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.0209813444869e-05, | |
| "loss": 1.4879, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 1.554874300956726, | |
| "eval_runtime": 91.3983, | |
| "eval_samples_per_second": 163.34, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.9965503425226476e-05, | |
| "loss": 1.5034, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 1.5682209730148315, | |
| "eval_runtime": 91.3854, | |
| "eval_samples_per_second": 163.363, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.972119340558395e-05, | |
| "loss": 1.5024, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 1.5595961809158325, | |
| "eval_runtime": 91.4495, | |
| "eval_samples_per_second": 163.249, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.9476883385941425e-05, | |
| "loss": 1.4673, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 1.5504151582717896, | |
| "eval_runtime": 91.2318, | |
| "eval_samples_per_second": 163.638, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.92325733662989e-05, | |
| "loss": 1.4758, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 1.5395164489746094, | |
| "eval_runtime": 91.1184, | |
| "eval_samples_per_second": 163.842, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.898875196669566e-05, | |
| "loss": 1.4674, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 1.5537846088409424, | |
| "eval_runtime": 91.4847, | |
| "eval_samples_per_second": 163.186, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.8744441947053134e-05, | |
| "loss": 1.4528, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 1.552320957183838, | |
| "eval_runtime": 91.3075, | |
| "eval_samples_per_second": 163.502, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.8500131927410608e-05, | |
| "loss": 1.4829, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 1.5265352725982666, | |
| "eval_runtime": 91.4875, | |
| "eval_samples_per_second": 163.181, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8255821907768082e-05, | |
| "loss": 1.4611, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.5295826196670532, | |
| "eval_runtime": 91.5744, | |
| "eval_samples_per_second": 163.026, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.8012000508164843e-05, | |
| "loss": 1.4442, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 1.5388405323028564, | |
| "eval_runtime": 91.8129, | |
| "eval_samples_per_second": 162.602, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.7767690488522314e-05, | |
| "loss": 1.4465, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 1.5279512405395508, | |
| "eval_runtime": 91.5443, | |
| "eval_samples_per_second": 163.08, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.752338046887979e-05, | |
| "loss": 1.4253, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 1.5250307321548462, | |
| "eval_runtime": 91.2655, | |
| "eval_samples_per_second": 163.578, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.7279070449237263e-05, | |
| "loss": 1.4236, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 1.5277702808380127, | |
| "eval_runtime": 91.3984, | |
| "eval_samples_per_second": 163.34, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.703476042959474e-05, | |
| "loss": 1.4749, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 1.5159269571304321, | |
| "eval_runtime": 91.6205, | |
| "eval_samples_per_second": 162.944, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.6790450409952215e-05, | |
| "loss": 1.4373, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 1.4971988201141357, | |
| "eval_runtime": 91.5971, | |
| "eval_samples_per_second": 162.985, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.654614039030969e-05, | |
| "loss": 1.4307, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_loss": 1.5140836238861084, | |
| "eval_runtime": 91.3406, | |
| "eval_samples_per_second": 163.443, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.6301830370667163e-05, | |
| "loss": 1.4237, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 1.5364242792129517, | |
| "eval_runtime": 91.2725, | |
| "eval_samples_per_second": 163.565, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.6058008971063924e-05, | |
| "loss": 1.429, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 1.5153831243515015, | |
| "eval_runtime": 91.5247, | |
| "eval_samples_per_second": 163.114, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.581418757146068e-05, | |
| "loss": 1.4359, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 1.5109397172927856, | |
| "eval_runtime": 91.5239, | |
| "eval_samples_per_second": 163.116, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.556987755181816e-05, | |
| "loss": 1.3969, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_loss": 1.5034611225128174, | |
| "eval_runtime": 91.2642, | |
| "eval_samples_per_second": 163.58, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.532556753217563e-05, | |
| "loss": 1.4011, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 1.5004990100860596, | |
| "eval_runtime": 91.4331, | |
| "eval_samples_per_second": 163.278, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.5081257512533104e-05, | |
| "loss": 1.4231, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 1.4998698234558105, | |
| "eval_runtime": 91.3964, | |
| "eval_samples_per_second": 163.343, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.483694749289058e-05, | |
| "loss": 1.4476, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_loss": 1.5173091888427734, | |
| "eval_runtime": 91.4077, | |
| "eval_samples_per_second": 163.323, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.4592637473248052e-05, | |
| "loss": 1.4455, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 1.4715697765350342, | |
| "eval_runtime": 91.3644, | |
| "eval_samples_per_second": 163.401, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.4348327453605528e-05, | |
| "loss": 1.402, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 1.4942283630371094, | |
| "eval_runtime": 91.1381, | |
| "eval_samples_per_second": 163.806, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.4104506054002287e-05, | |
| "loss": 1.4352, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_loss": 1.4948195219039917, | |
| "eval_runtime": 91.3982, | |
| "eval_samples_per_second": 163.34, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.3860196034359763e-05, | |
| "loss": 1.4316, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 1.4814602136611938, | |
| "eval_runtime": 91.536, | |
| "eval_samples_per_second": 163.094, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.3615886014717236e-05, | |
| "loss": 1.413, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 1.492964267730713, | |
| "eval_runtime": 91.5767, | |
| "eval_samples_per_second": 163.022, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.3371575995074712e-05, | |
| "loss": 1.3647, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 1.5028858184814453, | |
| "eval_runtime": 91.453, | |
| "eval_samples_per_second": 163.242, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.3127265975432185e-05, | |
| "loss": 1.3549, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 1.4676295518875122, | |
| "eval_runtime": 91.2539, | |
| "eval_samples_per_second": 163.598, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.288295595578966e-05, | |
| "loss": 1.4649, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_loss": 1.4584786891937256, | |
| "eval_runtime": 91.7498, | |
| "eval_samples_per_second": 162.714, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.2638645936147133e-05, | |
| "loss": 1.401, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 1.478485107421875, | |
| "eval_runtime": 91.4585, | |
| "eval_samples_per_second": 163.232, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.2394335916504608e-05, | |
| "loss": 1.4047, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 1.4770060777664185, | |
| "eval_runtime": 91.2763, | |
| "eval_samples_per_second": 163.558, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.2150025896862084e-05, | |
| "loss": 1.3718, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 1.4772363901138306, | |
| "eval_runtime": 91.3427, | |
| "eval_samples_per_second": 163.439, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.1906693117298127e-05, | |
| "loss": 1.4123, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "eval_loss": 1.4651228189468384, | |
| "eval_runtime": 91.4724, | |
| "eval_samples_per_second": 163.208, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.1662383097655601e-05, | |
| "loss": 1.3914, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 1.439155101776123, | |
| "eval_runtime": 91.387, | |
| "eval_samples_per_second": 163.36, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.1418073078013077e-05, | |
| "loss": 1.3936, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_loss": 1.4595708847045898, | |
| "eval_runtime": 91.5308, | |
| "eval_samples_per_second": 163.104, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.1173763058370552e-05, | |
| "loss": 1.3448, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_loss": 1.4761011600494385, | |
| "eval_runtime": 91.6432, | |
| "eval_samples_per_second": 162.903, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.0929453038728024e-05, | |
| "loss": 1.352, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 1.468656063079834, | |
| "eval_runtime": 91.6903, | |
| "eval_samples_per_second": 162.82, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.0685143019085499e-05, | |
| "loss": 1.3459, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 1.4411649703979492, | |
| "eval_runtime": 91.7674, | |
| "eval_samples_per_second": 162.683, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1.0440832999442973e-05, | |
| "loss": 1.3732, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 1.4545894861221313, | |
| "eval_runtime": 91.5374, | |
| "eval_samples_per_second": 163.092, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 1.0196522979800447e-05, | |
| "loss": 1.3586, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_loss": 1.4413018226623535, | |
| "eval_runtime": 91.6716, | |
| "eval_samples_per_second": 162.853, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 9.952212960157921e-06, | |
| "loss": 1.3578, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 1.4500373601913452, | |
| "eval_runtime": 91.7404, | |
| "eval_samples_per_second": 162.731, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 9.708391560554682e-06, | |
| "loss": 1.3847, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 1.4499620199203491, | |
| "eval_runtime": 91.826, | |
| "eval_samples_per_second": 162.579, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 9.464081540912156e-06, | |
| "loss": 1.4119, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_loss": 1.4416851997375488, | |
| "eval_runtime": 91.623, | |
| "eval_samples_per_second": 162.939, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.21977152126963e-06, | |
| "loss": 1.3674, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 1.4545212984085083, | |
| "eval_runtime": 91.714, | |
| "eval_samples_per_second": 162.778, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 8.975461501627105e-06, | |
| "loss": 1.3805, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_loss": 1.4539984464645386, | |
| "eval_runtime": 91.7771, | |
| "eval_samples_per_second": 162.666, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.731640102023866e-06, | |
| "loss": 1.341, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 1.4235692024230957, | |
| "eval_runtime": 91.8087, | |
| "eval_samples_per_second": 162.61, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 8.48733008238134e-06, | |
| "loss": 1.3635, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 1.427968144416809, | |
| "eval_runtime": 91.7853, | |
| "eval_samples_per_second": 162.651, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 8.243020062738814e-06, | |
| "loss": 1.3217, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 1.4452221393585205, | |
| "eval_runtime": 91.4571, | |
| "eval_samples_per_second": 163.235, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.998710043096287e-06, | |
| "loss": 1.3753, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_loss": 1.4172078371047974, | |
| "eval_runtime": 91.6806, | |
| "eval_samples_per_second": 162.837, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.754400023453761e-06, | |
| "loss": 1.3509, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 1.426705002784729, | |
| "eval_runtime": 91.7131, | |
| "eval_samples_per_second": 162.779, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.510578623850522e-06, | |
| "loss": 1.35, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "eval_loss": 1.4170763492584229, | |
| "eval_runtime": 91.523, | |
| "eval_samples_per_second": 163.118, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.266268604207996e-06, | |
| "loss": 1.3277, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 1.4099535942077637, | |
| "eval_runtime": 91.6084, | |
| "eval_samples_per_second": 162.965, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 7.02195858456547e-06, | |
| "loss": 1.3574, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_loss": 1.429254174232483, | |
| "eval_runtime": 91.6665, | |
| "eval_samples_per_second": 162.862, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.7776485649229446e-06, | |
| "loss": 1.3347, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 1.3997344970703125, | |
| "eval_runtime": 91.8372, | |
| "eval_samples_per_second": 162.559, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.533827165319704e-06, | |
| "loss": 1.3655, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "eval_loss": 1.414544701576233, | |
| "eval_runtime": 91.8567, | |
| "eval_samples_per_second": 162.525, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 6.289517145677179e-06, | |
| "loss": 1.3037, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "eval_loss": 1.4175053834915161, | |
| "eval_runtime": 91.5715, | |
| "eval_samples_per_second": 163.031, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.045207126034654e-06, | |
| "loss": 1.3632, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 1.411368489265442, | |
| "eval_runtime": 91.9948, | |
| "eval_samples_per_second": 162.281, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.800897106392127e-06, | |
| "loss": 1.3346, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_loss": 1.4163134098052979, | |
| "eval_runtime": 91.6974, | |
| "eval_samples_per_second": 162.807, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.5565870867496015e-06, | |
| "loss": 1.3371, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 1.4231865406036377, | |
| "eval_runtime": 91.7114, | |
| "eval_samples_per_second": 162.782, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 5.312765687146361e-06, | |
| "loss": 1.3077, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 1.4206013679504395, | |
| "eval_runtime": 91.6392, | |
| "eval_samples_per_second": 162.911, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 5.068455667503836e-06, | |
| "loss": 1.3352, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_loss": 1.4135525226593018, | |
| "eval_runtime": 91.6091, | |
| "eval_samples_per_second": 162.964, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.824145647861311e-06, | |
| "loss": 1.3442, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "eval_loss": 1.413482904434204, | |
| "eval_runtime": 91.795, | |
| "eval_samples_per_second": 162.634, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.579835628218785e-06, | |
| "loss": 1.3061, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_loss": 1.4136689901351929, | |
| "eval_runtime": 92.0252, | |
| "eval_samples_per_second": 162.227, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.336014228615544e-06, | |
| "loss": 1.3456, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "eval_loss": 1.40234375, | |
| "eval_runtime": 92.0442, | |
| "eval_samples_per_second": 162.194, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.091704208973018e-06, | |
| "loss": 1.2899, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_loss": 1.3845499753952026, | |
| "eval_runtime": 91.7463, | |
| "eval_samples_per_second": 162.72, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.8473941893304926e-06, | |
| "loss": 1.313, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 1.3685582876205444, | |
| "eval_runtime": 91.9455, | |
| "eval_samples_per_second": 162.368, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.6030841696879673e-06, | |
| "loss": 1.3106, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 1.3997061252593994, | |
| "eval_runtime": 91.5804, | |
| "eval_samples_per_second": 163.015, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.358774150045442e-06, | |
| "loss": 1.2682, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_loss": 1.3713297843933105, | |
| "eval_runtime": 91.77, | |
| "eval_samples_per_second": 162.678, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.1149527504422013e-06, | |
| "loss": 1.3131, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 1.381724238395691, | |
| "eval_runtime": 91.533, | |
| "eval_samples_per_second": 163.1, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.8706427307996756e-06, | |
| "loss": 1.3206, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_loss": 1.3894230127334595, | |
| "eval_runtime": 91.9557, | |
| "eval_samples_per_second": 162.35, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.62633271115715e-06, | |
| "loss": 1.3516, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_loss": 1.3866136074066162, | |
| "eval_runtime": 91.8786, | |
| "eval_samples_per_second": 162.486, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.3820226915146242e-06, | |
| "loss": 1.271, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "eval_loss": 1.3788957595825195, | |
| "eval_runtime": 91.4774, | |
| "eval_samples_per_second": 163.199, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.138201291911384e-06, | |
| "loss": 1.3023, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 1.3791213035583496, | |
| "eval_runtime": 91.8238, | |
| "eval_samples_per_second": 162.583, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.8938912722688583e-06, | |
| "loss": 1.3217, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_loss": 1.393075704574585, | |
| "eval_runtime": 91.8262, | |
| "eval_samples_per_second": 162.579, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.6495812526263328e-06, | |
| "loss": 1.3333, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_loss": 1.3756201267242432, | |
| "eval_runtime": 91.6059, | |
| "eval_samples_per_second": 162.97, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.4052712329838073e-06, | |
| "loss": 1.2818, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 1.3732881546020508, | |
| "eval_runtime": 91.7604, | |
| "eval_samples_per_second": 162.696, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.1614498333805667e-06, | |
| "loss": 1.2944, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 1.3781006336212158, | |
| "eval_runtime": 91.6872, | |
| "eval_samples_per_second": 162.825, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 9.171398137380411e-07, | |
| "loss": 1.312, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "eval_loss": 1.3845880031585693, | |
| "eval_runtime": 92.0248, | |
| "eval_samples_per_second": 162.228, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 6.728297940955155e-07, | |
| "loss": 1.3098, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_loss": 1.383412480354309, | |
| "eval_runtime": 92.0563, | |
| "eval_samples_per_second": 162.172, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 4.285197744529899e-07, | |
| "loss": 1.2995, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 1.381857991218567, | |
| "eval_runtime": 91.7462, | |
| "eval_samples_per_second": 162.721, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.842097548104643e-07, | |
| "loss": 1.2507, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_loss": 1.3710229396820068, | |
| "eval_runtime": 92.2003, | |
| "eval_samples_per_second": 161.919, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 112329, | |
| "total_flos": 15705683781120.0, | |
| "train_runtime": 32291.4207, | |
| "train_samples_per_second": 3.479 | |
| } | |
| ], | |
| "max_steps": 112329, | |
| "num_train_epochs": 3, | |
| "total_flos": 15705683781120.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |