| { | |
| "best_metric": 0.7065624395501147, | |
| "best_model_checkpoint": "../pretrained_models/klue_roberta_large/checkpoint-44000", | |
| "epoch": 4.975686984055185, | |
| "global_step": 44000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 4.7552, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.2752, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3e-06, | |
| "loss": 1.9549, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.8509, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5e-06, | |
| "loss": 1.8299, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6e-06, | |
| "loss": 1.753, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 1.7313, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.6829, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9e-06, | |
| "loss": 1.6651, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1e-05, | |
| "loss": 1.655, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.5775465965270996, | |
| "eval_masked_accuracy": 0.6741395380950737, | |
| "eval_runtime": 331.6052, | |
| "eval_samples_per_second": 47.409, | |
| "eval_steps_per_second": 2.964, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 1.6543, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.656, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 1.6726, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 1.6471, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.6679, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.627, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 1.6763, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.6433, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.9e-05, | |
| "loss": 1.6442, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6203, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.562535047531128, | |
| "eval_masked_accuracy": 0.6760570671304924, | |
| "eval_runtime": 331.4685, | |
| "eval_samples_per_second": 47.428, | |
| "eval_steps_per_second": 2.966, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.1e-05, | |
| "loss": 1.6762, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 1.6907, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 1.6851, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.6431, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.6542, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 1.6946, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 1.683, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 1.7044, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.9e-05, | |
| "loss": 1.7157, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3e-05, | |
| "loss": 1.7084, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.6114859580993652, | |
| "eval_masked_accuracy": 0.6701131345533646, | |
| "eval_runtime": 331.5183, | |
| "eval_samples_per_second": 47.421, | |
| "eval_steps_per_second": 2.965, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.1e-05, | |
| "loss": 1.7268, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 1.715, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.3e-05, | |
| "loss": 1.7501, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 1.6992, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.7397, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.7577, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.7e-05, | |
| "loss": 1.728, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3.8e-05, | |
| "loss": 1.7584, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 1.7494, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7423, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.6563646793365479, | |
| "eval_masked_accuracy": 0.663584889424318, | |
| "eval_runtime": 331.7001, | |
| "eval_samples_per_second": 47.395, | |
| "eval_steps_per_second": 2.964, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.1e-05, | |
| "loss": 1.7778, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.2e-05, | |
| "loss": 1.7985, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.3e-05, | |
| "loss": 1.8133, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.8056, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.7452, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 1.8009, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.7e-05, | |
| "loss": 1.8066, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.8127, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.9e-05, | |
| "loss": 1.8454, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8455, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.7312405109405518, | |
| "eval_masked_accuracy": 0.6539095517673932, | |
| "eval_runtime": 331.4967, | |
| "eval_samples_per_second": 47.424, | |
| "eval_steps_per_second": 2.965, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.987249776871096e-05, | |
| "loss": 1.839, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.9744995537421905e-05, | |
| "loss": 1.8038, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.9617493306132864e-05, | |
| "loss": 1.837, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.948999107484381e-05, | |
| "loss": 1.8565, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.936248884355477e-05, | |
| "loss": 1.8285, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.923498661226572e-05, | |
| "loss": 1.856, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.910748438097667e-05, | |
| "loss": 1.8494, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.897998214968762e-05, | |
| "loss": 1.8239, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.885247991839857e-05, | |
| "loss": 1.8294, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.8724977687109524e-05, | |
| "loss": 1.8222, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.7369571924209595, | |
| "eval_masked_accuracy": 0.6525969197353448, | |
| "eval_runtime": 332.1886, | |
| "eval_samples_per_second": 47.326, | |
| "eval_steps_per_second": 2.959, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.859747545582048e-05, | |
| "loss": 1.8653, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.8469973224531434e-05, | |
| "loss": 1.8235, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.8342470993242385e-05, | |
| "loss": 1.8045, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.821496876195334e-05, | |
| "loss": 1.8237, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.808746653066429e-05, | |
| "loss": 1.8345, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.795996429937524e-05, | |
| "loss": 1.838, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.783246206808619e-05, | |
| "loss": 1.7893, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.770495983679715e-05, | |
| "loss": 1.8514, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.7577457605508094e-05, | |
| "loss": 1.8107, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.744995537421905e-05, | |
| "loss": 1.8154, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.7349368333816528, | |
| "eval_masked_accuracy": 0.6534969877432311, | |
| "eval_runtime": 332.4558, | |
| "eval_samples_per_second": 47.287, | |
| "eval_steps_per_second": 2.957, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.7322453142930004e-05, | |
| "loss": 1.8566, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.7194950911640956e-05, | |
| "loss": 1.8355, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.7067448680351914e-05, | |
| "loss": 1.8517, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.693994644906286e-05, | |
| "loss": 1.7926, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.681244421777382e-05, | |
| "loss": 1.8277, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.668494198648476e-05, | |
| "loss": 1.8247, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.655743975519572e-05, | |
| "loss": 1.8339, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.642993752390667e-05, | |
| "loss": 1.8542, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.630243529261762e-05, | |
| "loss": 1.8018, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.6174933061328574e-05, | |
| "loss": 1.8652, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 1.7150492668151855, | |
| "eval_masked_accuracy": 0.6540794101708254, | |
| "eval_runtime": 331.8362, | |
| "eval_samples_per_second": 47.376, | |
| "eval_steps_per_second": 2.962, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.6047430830039526e-05, | |
| "loss": 1.8236, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 4.591992859875048e-05, | |
| "loss": 1.8607, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.5792426367461436e-05, | |
| "loss": 1.8329, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.566492413617239e-05, | |
| "loss": 1.8319, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.553742190488334e-05, | |
| "loss": 1.8482, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 4.540991967359429e-05, | |
| "loss": 1.8508, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 4.528241744230524e-05, | |
| "loss": 1.8216, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.515491521101619e-05, | |
| "loss": 1.8211, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.5027412979727145e-05, | |
| "loss": 1.7892, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.48999107484381e-05, | |
| "loss": 1.7627, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 1.7102247476577759, | |
| "eval_masked_accuracy": 0.6570814695769431, | |
| "eval_runtime": 332.0611, | |
| "eval_samples_per_second": 47.344, | |
| "eval_steps_per_second": 2.96, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.477240851714905e-05, | |
| "loss": 1.773, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.4644906285860006e-05, | |
| "loss": 1.744, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.451740405457096e-05, | |
| "loss": 1.7884, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 4.438990182328191e-05, | |
| "loss": 1.7675, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.426239959199287e-05, | |
| "loss": 1.7457, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.413489736070381e-05, | |
| "loss": 1.7824, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.400739512941477e-05, | |
| "loss": 1.7991, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.387989289812572e-05, | |
| "loss": 1.768, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.375239066683667e-05, | |
| "loss": 1.7601, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 4.3624888435547625e-05, | |
| "loss": 1.7515, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 1.7048571109771729, | |
| "eval_masked_accuracy": 0.6552869443926557, | |
| "eval_runtime": 331.6676, | |
| "eval_samples_per_second": 47.4, | |
| "eval_steps_per_second": 2.964, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.3497386204258576e-05, | |
| "loss": 1.793, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.336988397296953e-05, | |
| "loss": 1.7734, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.324238174168048e-05, | |
| "loss": 1.746, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.311487951039143e-05, | |
| "loss": 1.7725, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.298737727910239e-05, | |
| "loss": 1.7721, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.285987504781334e-05, | |
| "loss": 1.7665, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 4.273237281652429e-05, | |
| "loss": 1.746, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.2604870585235244e-05, | |
| "loss": 1.7683, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 4.2477368353946195e-05, | |
| "loss": 1.8083, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 4.234986612265715e-05, | |
| "loss": 1.7701, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 1.6938451528549194, | |
| "eval_masked_accuracy": 0.660930511429812, | |
| "eval_runtime": 331.8416, | |
| "eval_samples_per_second": 47.375, | |
| "eval_steps_per_second": 2.962, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 4.22223638913681e-05, | |
| "loss": 1.802, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.2094861660079056e-05, | |
| "loss": 1.7632, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.196735942879e-05, | |
| "loss": 1.751, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 4.183985719750096e-05, | |
| "loss": 1.7969, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 4.171235496621191e-05, | |
| "loss": 1.7728, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 4.158485273492286e-05, | |
| "loss": 1.7399, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 4.145735050363382e-05, | |
| "loss": 1.7988, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 4.1329848272344765e-05, | |
| "loss": 1.7714, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 4.1202346041055724e-05, | |
| "loss": 1.7627, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.1074843809766675e-05, | |
| "loss": 1.7634, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 1.6735210418701172, | |
| "eval_masked_accuracy": 0.6616568320785755, | |
| "eval_runtime": 331.8906, | |
| "eval_samples_per_second": 47.368, | |
| "eval_steps_per_second": 2.962, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 4.0947341578477627e-05, | |
| "loss": 1.7647, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 4.081983934718858e-05, | |
| "loss": 1.7316, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 4.069233711589953e-05, | |
| "loss": 1.7505, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 4.056483488461048e-05, | |
| "loss": 1.7623, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 4.043733265332143e-05, | |
| "loss": 1.7462, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 4.0309830422032384e-05, | |
| "loss": 1.7351, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 4.018232819074334e-05, | |
| "loss": 1.7126, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 4.005482595945429e-05, | |
| "loss": 1.7453, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 3.9927323728165245e-05, | |
| "loss": 1.7464, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 3.97998214968762e-05, | |
| "loss": 1.7489, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 1.6684247255325317, | |
| "eval_masked_accuracy": 0.6630148312748695, | |
| "eval_runtime": 332.4376, | |
| "eval_samples_per_second": 47.29, | |
| "eval_steps_per_second": 2.957, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 3.967231926558715e-05, | |
| "loss": 1.7411, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 3.954481703429811e-05, | |
| "loss": 1.7478, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 3.941731480300905e-05, | |
| "loss": 1.7717, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 3.928981257172001e-05, | |
| "loss": 1.7647, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 3.9162310340430954e-05, | |
| "loss": 1.7796, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 3.903480810914191e-05, | |
| "loss": 1.7425, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 3.8907305877852864e-05, | |
| "loss": 1.7404, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 3.8779803646563816e-05, | |
| "loss": 1.7335, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 3.865230141527477e-05, | |
| "loss": 1.7171, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 3.852479918398572e-05, | |
| "loss": 1.7319, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 1.6560810804367065, | |
| "eval_masked_accuracy": 0.6637841256311287, | |
| "eval_runtime": 332.3385, | |
| "eval_samples_per_second": 47.304, | |
| "eval_steps_per_second": 2.958, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 3.839729695269668e-05, | |
| "loss": 1.7296, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 3.826979472140763e-05, | |
| "loss": 1.7562, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 3.814229249011858e-05, | |
| "loss": 1.7446, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 3.801479025882953e-05, | |
| "loss": 1.7525, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 3.788728802754048e-05, | |
| "loss": 1.715, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 3.7759785796251434e-05, | |
| "loss": 1.7302, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.763228356496239e-05, | |
| "loss": 1.7145, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3.750478133367334e-05, | |
| "loss": 1.7382, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.7377279102384296e-05, | |
| "loss": 1.7181, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.724977687109524e-05, | |
| "loss": 1.7744, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 1.6506950855255127, | |
| "eval_masked_accuracy": 0.6654687548499909, | |
| "eval_runtime": 332.5023, | |
| "eval_samples_per_second": 47.281, | |
| "eval_steps_per_second": 2.956, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 3.71222746398062e-05, | |
| "loss": 1.7438, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.699477240851715e-05, | |
| "loss": 1.6953, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 3.68672701772281e-05, | |
| "loss": 1.7364, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.673976794593906e-05, | |
| "loss": 1.7148, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.6612265714650005e-05, | |
| "loss": 1.7145, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.648476348336096e-05, | |
| "loss": 1.7098, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.6357261252071914e-05, | |
| "loss": 1.6816, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.6229759020782866e-05, | |
| "loss": 1.6903, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.610225678949382e-05, | |
| "loss": 1.7243, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.597475455820477e-05, | |
| "loss": 1.6786, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 1.633168339729309, | |
| "eval_masked_accuracy": 0.6682277179202242, | |
| "eval_runtime": 332.1898, | |
| "eval_samples_per_second": 47.325, | |
| "eval_steps_per_second": 2.959, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.584725232691572e-05, | |
| "loss": 1.7284, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.571975009562667e-05, | |
| "loss": 1.684, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.559224786433763e-05, | |
| "loss": 1.7172, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.546474563304858e-05, | |
| "loss": 1.7348, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.533724340175953e-05, | |
| "loss": 1.7033, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.5209741170470485e-05, | |
| "loss": 1.7349, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.5082238939181436e-05, | |
| "loss": 1.6813, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.495473670789239e-05, | |
| "loss": 1.7038, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 3.4827234476603346e-05, | |
| "loss": 1.6866, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.469973224531429e-05, | |
| "loss": 1.7186, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 1.6309564113616943, | |
| "eval_masked_accuracy": 0.6676820097569746, | |
| "eval_runtime": 332.3036, | |
| "eval_samples_per_second": 47.309, | |
| "eval_steps_per_second": 2.958, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 3.457223001402525e-05, | |
| "loss": 1.659, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 3.4444727782736194e-05, | |
| "loss": 1.6826, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 3.431722555144715e-05, | |
| "loss": 1.6723, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 3.418972332015811e-05, | |
| "loss": 1.7089, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 3.4062221088869055e-05, | |
| "loss": 1.681, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 3.393471885758001e-05, | |
| "loss": 1.6889, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.380721662629096e-05, | |
| "loss": 1.7217, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 3.3679714395001916e-05, | |
| "loss": 1.637, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 3.355221216371287e-05, | |
| "loss": 1.6631, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 3.342470993242382e-05, | |
| "loss": 1.6505, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 1.6221129894256592, | |
| "eval_masked_accuracy": 0.6697054625754659, | |
| "eval_runtime": 332.1519, | |
| "eval_samples_per_second": 47.331, | |
| "eval_steps_per_second": 2.959, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.329720770113477e-05, | |
| "loss": 1.6624, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 3.316970546984572e-05, | |
| "loss": 1.6445, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 3.3042203238556674e-05, | |
| "loss": 1.6377, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 3.291470100726763e-05, | |
| "loss": 1.6494, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 3.2787198775978584e-05, | |
| "loss": 1.6291, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 3.2659696544689535e-05, | |
| "loss": 1.6128, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 3.2532194313400487e-05, | |
| "loss": 1.648, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 3.240469208211144e-05, | |
| "loss": 1.6191, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 3.227718985082239e-05, | |
| "loss": 1.652, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.214968761953334e-05, | |
| "loss": 1.6222, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_loss": 1.6012800931930542, | |
| "eval_masked_accuracy": 0.6742498032867577, | |
| "eval_runtime": 332.2981, | |
| "eval_samples_per_second": 47.31, | |
| "eval_steps_per_second": 2.958, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 3.20221853882443e-05, | |
| "loss": 1.6378, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 3.1894683156955244e-05, | |
| "loss": 1.6373, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 3.17671809256662e-05, | |
| "loss": 1.643, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 3.1639678694377154e-05, | |
| "loss": 1.6504, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 3.1512176463088105e-05, | |
| "loss": 1.6707, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 3.1384674231799064e-05, | |
| "loss": 1.6684, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 3.125717200051001e-05, | |
| "loss": 1.6431, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 3.1129669769220967e-05, | |
| "loss": 1.6578, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 3.100216753793191e-05, | |
| "loss": 1.6471, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 3.087466530664287e-05, | |
| "loss": 1.6306, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 1.5895774364471436, | |
| "eval_masked_accuracy": 0.6750452664697661, | |
| "eval_runtime": 332.6359, | |
| "eval_samples_per_second": 47.262, | |
| "eval_steps_per_second": 2.955, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 3.074716307535382e-05, | |
| "loss": 1.6205, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 3.061966084406477e-05, | |
| "loss": 1.6493, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 3.0492158612775724e-05, | |
| "loss": 1.6142, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 3.036465638148668e-05, | |
| "loss": 1.6115, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 3.0237154150197627e-05, | |
| "loss": 1.6608, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 3.0109651918908582e-05, | |
| "loss": 1.6156, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2.9982149687619537e-05, | |
| "loss": 1.6199, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 2.985464745633049e-05, | |
| "loss": 1.6255, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 2.9727145225041443e-05, | |
| "loss": 1.6373, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 2.959964299375239e-05, | |
| "loss": 1.6165, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 1.5816543102264404, | |
| "eval_masked_accuracy": 0.6755305159120167, | |
| "eval_runtime": 332.6858, | |
| "eval_samples_per_second": 47.255, | |
| "eval_steps_per_second": 2.955, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 2.9472140762463346e-05, | |
| "loss": 1.6529, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.9344638531174294e-05, | |
| "loss": 1.5853, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 2.921713629988525e-05, | |
| "loss": 1.6273, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 2.90896340685962e-05, | |
| "loss": 1.6308, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 2.8962131837307156e-05, | |
| "loss": 1.6241, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 2.8834629606018104e-05, | |
| "loss": 1.6267, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2.870712737472906e-05, | |
| "loss": 1.5814, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 2.8579625143440013e-05, | |
| "loss": 1.6185, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 2.8452122912150965e-05, | |
| "loss": 1.5908, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 2.832462068086192e-05, | |
| "loss": 1.6495, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 1.5690662860870361, | |
| "eval_masked_accuracy": 0.6774331565563334, | |
| "eval_runtime": 332.6387, | |
| "eval_samples_per_second": 47.261, | |
| "eval_steps_per_second": 2.955, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2.8197118449572868e-05, | |
| "loss": 1.6091, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 2.8069616218283823e-05, | |
| "loss": 1.6058, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 2.794211398699477e-05, | |
| "loss": 1.6358, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 2.7814611755705726e-05, | |
| "loss": 1.6094, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 2.7687109524416677e-05, | |
| "loss": 1.6243, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.7559607293127632e-05, | |
| "loss": 1.6078, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 2.743210506183858e-05, | |
| "loss": 1.5921, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 2.7304602830549535e-05, | |
| "loss": 1.5934, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.717710059926049e-05, | |
| "loss": 1.6134, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 2.704959836797144e-05, | |
| "loss": 1.5809, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "eval_loss": 1.555253267288208, | |
| "eval_masked_accuracy": 0.6777390847722294, | |
| "eval_runtime": 332.6441, | |
| "eval_samples_per_second": 47.261, | |
| "eval_steps_per_second": 2.955, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2.6922096136682397e-05, | |
| "loss": 1.6062, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 2.6794593905393345e-05, | |
| "loss": 1.5813, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 2.66670916741043e-05, | |
| "loss": 1.6014, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 2.6539589442815248e-05, | |
| "loss": 1.5966, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 2.6412087211526203e-05, | |
| "loss": 1.5901, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 2.6284584980237154e-05, | |
| "loss": 1.5913, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.615708274894811e-05, | |
| "loss": 1.6249, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.6029580517659057e-05, | |
| "loss": 1.6162, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.5902078286370012e-05, | |
| "loss": 1.5866, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.5774576055080967e-05, | |
| "loss": 1.6091, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 1.544262170791626, | |
| "eval_masked_accuracy": 0.6812164740363877, | |
| "eval_runtime": 332.6866, | |
| "eval_samples_per_second": 47.255, | |
| "eval_steps_per_second": 2.955, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 2.5647073823791918e-05, | |
| "loss": 1.5909, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.5519571592502873e-05, | |
| "loss": 1.5965, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.539206936121382e-05, | |
| "loss": 1.5999, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.5264567129924776e-05, | |
| "loss": 1.6052, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.5137064898635728e-05, | |
| "loss": 1.5817, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 2.5009562667346683e-05, | |
| "loss": 1.6076, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.4882060436057634e-05, | |
| "loss": 1.6049, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.4754558204768586e-05, | |
| "loss": 1.5737, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 2.4627055973479537e-05, | |
| "loss": 1.5943, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.449955374219049e-05, | |
| "loss": 1.5687, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "eval_loss": 1.5361570119857788, | |
| "eval_masked_accuracy": 0.6823867711149114, | |
| "eval_runtime": 332.6448, | |
| "eval_samples_per_second": 47.261, | |
| "eval_steps_per_second": 2.955, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.4372051510901443e-05, | |
| "loss": 1.5948, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.4244549279612395e-05, | |
| "loss": 1.5808, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.4117047048323346e-05, | |
| "loss": 1.5756, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.3989544817034298e-05, | |
| "loss": 1.5723, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.386204258574525e-05, | |
| "loss": 1.5604, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 2.3734540354456204e-05, | |
| "loss": 1.5761, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2.360703812316716e-05, | |
| "loss": 1.5624, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 2.347953589187811e-05, | |
| "loss": 1.5607, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 2.3352033660589062e-05, | |
| "loss": 1.5428, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 2.3224531429300014e-05, | |
| "loss": 1.5725, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 1.537841796875, | |
| "eval_masked_accuracy": 0.6820021651738, | |
| "eval_runtime": 332.7089, | |
| "eval_samples_per_second": 47.252, | |
| "eval_steps_per_second": 2.955, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 2.3097029198010965e-05, | |
| "loss": 1.5788, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 2.296952696672192e-05, | |
| "loss": 1.5641, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.284202473543287e-05, | |
| "loss": 1.5451, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2.2714522504143823e-05, | |
| "loss": 1.6074, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.2587020272854775e-05, | |
| "loss": 1.5966, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 2.2459518041565726e-05, | |
| "loss": 1.5088, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 2.233201581027668e-05, | |
| "loss": 1.5411, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 2.2204513578987636e-05, | |
| "loss": 1.4903, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 2.2077011347698587e-05, | |
| "loss": 1.5135, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 2.194950911640954e-05, | |
| "loss": 1.5171, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_loss": 1.5317901372909546, | |
| "eval_masked_accuracy": 0.683750220460841, | |
| "eval_runtime": 332.6043, | |
| "eval_samples_per_second": 47.266, | |
| "eval_steps_per_second": 2.955, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 2.182200688512049e-05, | |
| "loss": 1.5076, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 2.1694504653831442e-05, | |
| "loss": 1.5401, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 2.1567002422542397e-05, | |
| "loss": 1.5463, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 2.1439500191253348e-05, | |
| "loss": 1.4955, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 2.13119979599643e-05, | |
| "loss": 1.5169, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 2.118449572867525e-05, | |
| "loss": 1.5295, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 2.1056993497386203e-05, | |
| "loss": 1.5197, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 2.0929491266097158e-05, | |
| "loss": 1.5525, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 2.0801989034808113e-05, | |
| "loss": 1.5558, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 2.0674486803519064e-05, | |
| "loss": 1.4809, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "eval_loss": 1.5124375820159912, | |
| "eval_masked_accuracy": 0.6863205757142956, | |
| "eval_runtime": 332.3275, | |
| "eval_samples_per_second": 47.306, | |
| "eval_steps_per_second": 2.958, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 2.0546984572230016e-05, | |
| "loss": 1.4992, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 2.0419482340940967e-05, | |
| "loss": 1.5481, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 2.0291980109651922e-05, | |
| "loss": 1.5201, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 2.0164477878362873e-05, | |
| "loss": 1.5024, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 2.0036975647073825e-05, | |
| "loss": 1.56, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 1.9909473415784776e-05, | |
| "loss": 1.5406, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 1.9781971184495728e-05, | |
| "loss": 1.5089, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 1.9654468953206683e-05, | |
| "loss": 1.4574, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 1.9526966721917634e-05, | |
| "loss": 1.4856, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 1.939946449062859e-05, | |
| "loss": 1.5158, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_loss": 1.4922306537628174, | |
| "eval_masked_accuracy": 0.690069818885663, | |
| "eval_runtime": 332.2549, | |
| "eval_samples_per_second": 47.316, | |
| "eval_steps_per_second": 2.959, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 1.927196225933954e-05, | |
| "loss": 1.5297, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 1.9144460028050492e-05, | |
| "loss": 1.4847, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 1.9016957796761444e-05, | |
| "loss": 1.5051, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 1.88894555654724e-05, | |
| "loss": 1.5038, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 1.876195333418335e-05, | |
| "loss": 1.5262, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 1.86344511028943e-05, | |
| "loss": 1.4712, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 1.8506948871605253e-05, | |
| "loss": 1.5132, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 1.8379446640316205e-05, | |
| "loss": 1.5035, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 1.825194440902716e-05, | |
| "loss": 1.5093, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 1.812444217773811e-05, | |
| "loss": 1.4825, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "eval_loss": 1.4842137098312378, | |
| "eval_masked_accuracy": 0.6907112508204083, | |
| "eval_runtime": 332.0229, | |
| "eval_samples_per_second": 47.349, | |
| "eval_steps_per_second": 2.961, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 1.7996939946449062e-05, | |
| "loss": 1.5421, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 1.7869437715160017e-05, | |
| "loss": 1.5267, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 1.774193548387097e-05, | |
| "loss": 1.4855, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 1.761443325258192e-05, | |
| "loss": 1.4843, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 1.7486931021292875e-05, | |
| "loss": 1.52, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 1.7359428790003827e-05, | |
| "loss": 1.5077, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 1.7231926558714778e-05, | |
| "loss": 1.4908, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 1.710442432742573e-05, | |
| "loss": 1.5223, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 1.697692209613668e-05, | |
| "loss": 1.5103, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1.6849419864847636e-05, | |
| "loss": 1.4568, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_loss": 1.4819023609161377, | |
| "eval_masked_accuracy": 0.6908566639188486, | |
| "eval_runtime": 332.2827, | |
| "eval_samples_per_second": 47.312, | |
| "eval_steps_per_second": 2.958, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 1.6721917633558588e-05, | |
| "loss": 1.5105, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 1.659441540226954e-05, | |
| "loss": 1.4714, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 1.6466913170980494e-05, | |
| "loss": 1.5056, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 1.6339410939691445e-05, | |
| "loss": 1.4777, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 1.6211908708402397e-05, | |
| "loss": 1.4735, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 1.6084406477113352e-05, | |
| "loss": 1.4784, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 1.5956904245824303e-05, | |
| "loss": 1.5037, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 1.5829402014535255e-05, | |
| "loss": 1.5295, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.5701899783246206e-05, | |
| "loss": 1.4655, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 1.5574397551957158e-05, | |
| "loss": 1.4868, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "eval_loss": 1.4802453517913818, | |
| "eval_masked_accuracy": 0.691725791186244, | |
| "eval_runtime": 332.2068, | |
| "eval_samples_per_second": 47.323, | |
| "eval_steps_per_second": 2.959, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1.5446895320668113e-05, | |
| "loss": 1.5108, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.5319393089379064e-05, | |
| "loss": 1.5234, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 1.5191890858090016e-05, | |
| "loss": 1.4669, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.506438862680097e-05, | |
| "loss": 1.4555, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 1.4936886395511924e-05, | |
| "loss": 1.4447, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.4809384164222875e-05, | |
| "loss": 1.4671, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.4681881932933827e-05, | |
| "loss": 1.4739, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 1.455437970164478e-05, | |
| "loss": 1.4673, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.4426877470355732e-05, | |
| "loss": 1.4821, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.4299375239066685e-05, | |
| "loss": 1.4826, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "eval_loss": 1.466788649559021, | |
| "eval_masked_accuracy": 0.6936922350866194, | |
| "eval_runtime": 332.3241, | |
| "eval_samples_per_second": 47.306, | |
| "eval_steps_per_second": 2.958, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 1.4171873007777636e-05, | |
| "loss": 1.4993, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.4044370776488588e-05, | |
| "loss": 1.498, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1.3916868545199541e-05, | |
| "loss": 1.4549, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 1.3789366313910492e-05, | |
| "loss": 1.4276, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.3661864082621447e-05, | |
| "loss": 1.4775, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 1.35343618513324e-05, | |
| "loss": 1.5056, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 1.3406859620043352e-05, | |
| "loss": 1.4488, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.3279357388754305e-05, | |
| "loss": 1.46, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 1.3151855157465257e-05, | |
| "loss": 1.4588, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 1.3024352926176208e-05, | |
| "loss": 1.4686, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "eval_loss": 1.4628050327301025, | |
| "eval_masked_accuracy": 0.695108458894874, | |
| "eval_runtime": 332.2343, | |
| "eval_samples_per_second": 47.319, | |
| "eval_steps_per_second": 2.959, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 1.2896850694887161e-05, | |
| "loss": 1.4673, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 1.2769348463598113e-05, | |
| "loss": 1.4501, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 1.2641846232309066e-05, | |
| "loss": 1.4532, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 1.2514344001020018e-05, | |
| "loss": 1.4439, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 1.238684176973097e-05, | |
| "loss": 1.4202, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 1.2259339538441924e-05, | |
| "loss": 1.4436, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 1.2131837307152875e-05, | |
| "loss": 1.466, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.2004335075863827e-05, | |
| "loss": 1.4696, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 1.1876832844574782e-05, | |
| "loss": 1.4775, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 1.1749330613285733e-05, | |
| "loss": 1.4343, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "eval_loss": 1.4424548149108887, | |
| "eval_masked_accuracy": 0.6971389490482162, | |
| "eval_runtime": 331.9906, | |
| "eval_samples_per_second": 47.354, | |
| "eval_steps_per_second": 2.961, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 1.1621828381996685e-05, | |
| "loss": 1.4501, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 1.1494326150707638e-05, | |
| "loss": 1.4867, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 1.136682391941859e-05, | |
| "loss": 1.4403, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.1239321688129543e-05, | |
| "loss": 1.4668, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 1.1111819456840496e-05, | |
| "loss": 1.3951, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 1.0984317225551447e-05, | |
| "loss": 1.4265, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 1.08568149942624e-05, | |
| "loss": 1.4097, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 1.0729312762973352e-05, | |
| "loss": 1.4165, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 1.0601810531684305e-05, | |
| "loss": 1.3991, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 1.0474308300395258e-05, | |
| "loss": 1.4286, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "eval_loss": 1.4411929845809937, | |
| "eval_masked_accuracy": 0.6979967481246483, | |
| "eval_runtime": 332.6761, | |
| "eval_samples_per_second": 47.256, | |
| "eval_steps_per_second": 2.955, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1.034680606910621e-05, | |
| "loss": 1.3967, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 1.0219303837817163e-05, | |
| "loss": 1.4079, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 1.0091801606528115e-05, | |
| "loss": 1.4176, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 9.964299375239066e-06, | |
| "loss": 1.4068, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 9.83679714395002e-06, | |
| "loss": 1.3876, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 9.709294912660973e-06, | |
| "loss": 1.424, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 9.581792681371924e-06, | |
| "loss": 1.3789, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 9.454290450082877e-06, | |
| "loss": 1.4157, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 9.326788218793829e-06, | |
| "loss": 1.394, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 9.199285987504782e-06, | |
| "loss": 1.439, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "eval_loss": 1.4216623306274414, | |
| "eval_masked_accuracy": 0.7010983390128082, | |
| "eval_runtime": 332.6207, | |
| "eval_samples_per_second": 47.264, | |
| "eval_steps_per_second": 2.955, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 9.071783756215735e-06, | |
| "loss": 1.4001, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 8.944281524926687e-06, | |
| "loss": 1.4253, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 8.81677929363764e-06, | |
| "loss": 1.4032, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 8.689277062348591e-06, | |
| "loss": 1.4022, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 8.561774831059543e-06, | |
| "loss": 1.3839, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 8.434272599770496e-06, | |
| "loss": 1.419, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 8.30677036848145e-06, | |
| "loss": 1.3744, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 8.1792681371924e-06, | |
| "loss": 1.438, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 8.051765905903354e-06, | |
| "loss": 1.3998, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 7.924263674614305e-06, | |
| "loss": 1.4095, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "eval_loss": 1.4295740127563477, | |
| "eval_masked_accuracy": 0.7001421356222228, | |
| "eval_runtime": 332.5672, | |
| "eval_samples_per_second": 47.272, | |
| "eval_steps_per_second": 2.956, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 7.796761443325259e-06, | |
| "loss": 1.4015, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 7.669259212036212e-06, | |
| "loss": 1.4069, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 7.541756980747164e-06, | |
| "loss": 1.3908, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 7.4142547494581165e-06, | |
| "loss": 1.3688, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 7.286752518169068e-06, | |
| "loss": 1.3833, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 7.15925028688002e-06, | |
| "loss": 1.367, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 7.031748055590973e-06, | |
| "loss": 1.3697, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 6.904245824301926e-06, | |
| "loss": 1.3803, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 6.776743593012878e-06, | |
| "loss": 1.4184, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 6.6492413617238305e-06, | |
| "loss": 1.3987, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "eval_loss": 1.4123162031173706, | |
| "eval_masked_accuracy": 0.702893200667927, | |
| "eval_runtime": 332.6371, | |
| "eval_samples_per_second": 47.262, | |
| "eval_steps_per_second": 2.955, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 6.521739130434783e-06, | |
| "loss": 1.3888, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 6.394236899145735e-06, | |
| "loss": 1.3931, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 6.266734667856687e-06, | |
| "loss": 1.4084, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 6.13923243656764e-06, | |
| "loss": 1.3912, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 6.011730205278593e-06, | |
| "loss": 1.3928, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 5.8842279739895455e-06, | |
| "loss": 1.3732, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 5.756725742700497e-06, | |
| "loss": 1.4292, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 5.62922351141145e-06, | |
| "loss": 1.378, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 5.5017212801224025e-06, | |
| "loss": 1.384, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 5.374219048833355e-06, | |
| "loss": 1.3725, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "eval_loss": 1.402807354927063, | |
| "eval_masked_accuracy": 0.7036279403495821, | |
| "eval_runtime": 332.6549, | |
| "eval_samples_per_second": 47.259, | |
| "eval_steps_per_second": 2.955, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 5.246716817544307e-06, | |
| "loss": 1.3307, | |
| "step": 40100 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 5.1192145862552595e-06, | |
| "loss": 1.3666, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 4.991712354966213e-06, | |
| "loss": 1.3802, | |
| "step": 40300 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 4.864210123677164e-06, | |
| "loss": 1.3732, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 4.7367078923881166e-06, | |
| "loss": 1.3749, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 4.60920566109907e-06, | |
| "loss": 1.4082, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 4.481703429810022e-06, | |
| "loss": 1.4303, | |
| "step": 40700 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 4.3542011985209745e-06, | |
| "loss": 1.3938, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 4.226698967231927e-06, | |
| "loss": 1.3797, | |
| "step": 40900 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 4.099196735942879e-06, | |
| "loss": 1.3663, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "eval_loss": 1.4048454761505127, | |
| "eval_masked_accuracy": 0.7044154426496801, | |
| "eval_runtime": 332.5757, | |
| "eval_samples_per_second": 47.27, | |
| "eval_steps_per_second": 2.956, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 3.9716945046538315e-06, | |
| "loss": 1.3761, | |
| "step": 41100 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 3.844192273364784e-06, | |
| "loss": 1.365, | |
| "step": 41200 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 3.716690042075736e-06, | |
| "loss": 1.3984, | |
| "step": 41300 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 3.5891878107866894e-06, | |
| "loss": 1.3449, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 3.4616855794976413e-06, | |
| "loss": 1.3671, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 3.3341833482085937e-06, | |
| "loss": 1.3752, | |
| "step": 41600 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 3.2066811169195464e-06, | |
| "loss": 1.348, | |
| "step": 41700 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 3.0791788856304988e-06, | |
| "loss": 1.3793, | |
| "step": 41800 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 2.951676654341451e-06, | |
| "loss": 1.405, | |
| "step": 41900 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 2.8241744230524035e-06, | |
| "loss": 1.3837, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "eval_loss": 1.3951770067214966, | |
| "eval_masked_accuracy": 0.7039473004213623, | |
| "eval_runtime": 332.7076, | |
| "eval_samples_per_second": 47.252, | |
| "eval_steps_per_second": 2.955, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 2.696672191763356e-06, | |
| "loss": 1.3924, | |
| "step": 42100 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 2.5691699604743086e-06, | |
| "loss": 1.3664, | |
| "step": 42200 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 2.4416677291852605e-06, | |
| "loss": 1.3525, | |
| "step": 42300 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 2.3141654978962133e-06, | |
| "loss": 1.3783, | |
| "step": 42400 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 2.1866632666071656e-06, | |
| "loss": 1.4034, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 2.0591610353181184e-06, | |
| "loss": 1.3807, | |
| "step": 42600 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 1.9316588040290703e-06, | |
| "loss": 1.3791, | |
| "step": 42700 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 1.804156572740023e-06, | |
| "loss": 1.3564, | |
| "step": 42800 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 1.6766543414509756e-06, | |
| "loss": 1.4057, | |
| "step": 42900 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 1.549152110161928e-06, | |
| "loss": 1.3752, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_loss": 1.3881962299346924, | |
| "eval_masked_accuracy": 0.7062402711958213, | |
| "eval_runtime": 332.7234, | |
| "eval_samples_per_second": 47.249, | |
| "eval_steps_per_second": 2.954, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 1.4216498788728803e-06, | |
| "loss": 1.3468, | |
| "step": 43100 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 1.2941476475838329e-06, | |
| "loss": 1.3939, | |
| "step": 43200 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 1.1666454162947852e-06, | |
| "loss": 1.4151, | |
| "step": 43300 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 1.0391431850057378e-06, | |
| "loss": 1.3698, | |
| "step": 43400 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 9.1164095371669e-07, | |
| "loss": 1.3676, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 7.841387224276426e-07, | |
| "loss": 1.3844, | |
| "step": 43600 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 6.566364911385949e-07, | |
| "loss": 1.3604, | |
| "step": 43700 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 5.291342598495474e-07, | |
| "loss": 1.3661, | |
| "step": 43800 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 4.0163202856049983e-07, | |
| "loss": 1.3635, | |
| "step": 43900 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 2.7412979727145223e-07, | |
| "loss": 1.3629, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "eval_loss": 1.388177514076233, | |
| "eval_masked_accuracy": 0.7065624395501147, | |
| "eval_runtime": 332.6649, | |
| "eval_samples_per_second": 47.258, | |
| "eval_steps_per_second": 2.955, | |
| "step": 44000 | |
| } | |
| ], | |
| "max_steps": 44215, | |
| "num_train_epochs": 5, | |
| "total_flos": 4.073071997007176e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |