| { | |
| "best_metric": 0.782608695652174, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-ve-U11-b-80\\checkpoint-156", | |
| "epoch": 73.84615384615384, | |
| "eval_steps": 500, | |
| "global_step": 480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.13043478260869565, | |
| "eval_loss": 1.3860031366348267, | |
| "eval_runtime": 0.6484, | |
| "eval_samples_per_second": 70.942, | |
| "eval_steps_per_second": 3.084, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 1.3859, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.2608695652173913, | |
| "eval_loss": 1.3832452297210693, | |
| "eval_runtime": 0.5945, | |
| "eval_samples_per_second": 77.375, | |
| "eval_steps_per_second": 3.364, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.2608695652173913, | |
| "eval_loss": 1.3772777318954468, | |
| "eval_runtime": 0.635, | |
| "eval_samples_per_second": 72.446, | |
| "eval_steps_per_second": 3.15, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 1.3791, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.21739130434782608, | |
| "eval_loss": 1.3568793535232544, | |
| "eval_runtime": 0.6436, | |
| "eval_samples_per_second": 71.475, | |
| "eval_steps_per_second": 3.108, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 3.125e-05, | |
| "loss": 1.3347, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_accuracy": 0.2608695652173913, | |
| "eval_loss": 1.3177119493484497, | |
| "eval_runtime": 0.591, | |
| "eval_samples_per_second": 77.837, | |
| "eval_steps_per_second": 3.384, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.391304347826087, | |
| "eval_loss": 1.209334373474121, | |
| "eval_runtime": 0.5875, | |
| "eval_samples_per_second": 78.298, | |
| "eval_steps_per_second": 3.404, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.2088, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.43478260869565216, | |
| "eval_loss": 1.1083430051803589, | |
| "eval_runtime": 0.6176, | |
| "eval_samples_per_second": 74.478, | |
| "eval_steps_per_second": 3.238, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 4.976851851851852e-05, | |
| "loss": 1.0456, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.0339664220809937, | |
| "eval_runtime": 0.6032, | |
| "eval_samples_per_second": 76.263, | |
| "eval_steps_per_second": 3.316, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0120112895965576, | |
| "eval_runtime": 0.6066, | |
| "eval_samples_per_second": 75.827, | |
| "eval_steps_per_second": 3.297, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.9278, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5652173913043478, | |
| "eval_loss": 0.9282457232475281, | |
| "eval_runtime": 0.6729, | |
| "eval_samples_per_second": 68.359, | |
| "eval_steps_per_second": 2.972, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 4.745370370370371e-05, | |
| "loss": 0.847, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "eval_accuracy": 0.5217391304347826, | |
| "eval_loss": 0.9934114217758179, | |
| "eval_runtime": 0.662, | |
| "eval_samples_per_second": 69.487, | |
| "eval_steps_per_second": 3.021, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4782608695652174, | |
| "eval_loss": 1.0171452760696411, | |
| "eval_runtime": 0.5865, | |
| "eval_samples_per_second": 78.425, | |
| "eval_steps_per_second": 3.41, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.7142, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 0.8889133334159851, | |
| "eval_runtime": 0.6111, | |
| "eval_samples_per_second": 75.276, | |
| "eval_steps_per_second": 3.273, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 0.5959, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 0.9391557574272156, | |
| "eval_runtime": 0.6025, | |
| "eval_samples_per_second": 76.352, | |
| "eval_steps_per_second": 3.32, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 0.9017554521560669, | |
| "eval_runtime": 0.6369, | |
| "eval_samples_per_second": 72.227, | |
| "eval_steps_per_second": 3.14, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 4.3981481481481486e-05, | |
| "loss": 0.5344, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8327335119247437, | |
| "eval_runtime": 0.6525, | |
| "eval_samples_per_second": 70.495, | |
| "eval_steps_per_second": 3.065, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 4.282407407407408e-05, | |
| "loss": 0.4438, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7308311462402344, | |
| "eval_runtime": 0.597, | |
| "eval_samples_per_second": 77.057, | |
| "eval_steps_per_second": 3.35, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.6833930015563965, | |
| "eval_runtime": 0.6251, | |
| "eval_samples_per_second": 73.594, | |
| "eval_steps_per_second": 3.2, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.4419, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 0.790928065776825, | |
| "eval_runtime": 0.618, | |
| "eval_samples_per_second": 74.438, | |
| "eval_steps_per_second": 3.236, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.0509259259259265e-05, | |
| "loss": 0.3989, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9102990627288818, | |
| "eval_runtime": 0.6228, | |
| "eval_samples_per_second": 73.862, | |
| "eval_steps_per_second": 3.211, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7534198760986328, | |
| "eval_runtime": 0.6142, | |
| "eval_samples_per_second": 74.896, | |
| "eval_steps_per_second": 3.256, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 3.935185185185186e-05, | |
| "loss": 0.3534, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.804267406463623, | |
| "eval_runtime": 0.6424, | |
| "eval_samples_per_second": 71.605, | |
| "eval_steps_per_second": 3.113, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7648376822471619, | |
| "eval_runtime": 0.5921, | |
| "eval_samples_per_second": 77.693, | |
| "eval_steps_per_second": 3.378, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 0.3265, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.7087794542312622, | |
| "eval_runtime": 0.6261, | |
| "eval_samples_per_second": 73.475, | |
| "eval_steps_per_second": 3.195, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2808, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8844515085220337, | |
| "eval_runtime": 0.7011, | |
| "eval_samples_per_second": 65.616, | |
| "eval_steps_per_second": 2.853, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7756012678146362, | |
| "eval_runtime": 0.593, | |
| "eval_samples_per_second": 77.567, | |
| "eval_steps_per_second": 3.372, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 3.587962962962963e-05, | |
| "loss": 0.2753, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.994417130947113, | |
| "eval_runtime": 0.6146, | |
| "eval_samples_per_second": 74.85, | |
| "eval_steps_per_second": 3.254, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.2837, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8091363310813904, | |
| "eval_runtime": 0.6137, | |
| "eval_samples_per_second": 74.956, | |
| "eval_steps_per_second": 3.259, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9965764880180359, | |
| "eval_runtime": 0.6287, | |
| "eval_samples_per_second": 73.162, | |
| "eval_steps_per_second": 3.181, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 3.3564814814814815e-05, | |
| "loss": 0.2667, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.7711070775985718, | |
| "eval_runtime": 0.6191, | |
| "eval_samples_per_second": 74.302, | |
| "eval_steps_per_second": 3.231, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.2325, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8946378231048584, | |
| "eval_runtime": 0.6216, | |
| "eval_samples_per_second": 74.004, | |
| "eval_steps_per_second": 3.218, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9079318046569824, | |
| "eval_runtime": 0.6887, | |
| "eval_samples_per_second": 66.789, | |
| "eval_steps_per_second": 2.904, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.2096, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 1.033783197402954, | |
| "eval_runtime": 0.6137, | |
| "eval_samples_per_second": 74.958, | |
| "eval_steps_per_second": 3.259, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 3.0092592592592593e-05, | |
| "loss": 0.1733, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.8190710544586182, | |
| "eval_runtime": 0.6007, | |
| "eval_samples_per_second": 76.576, | |
| "eval_steps_per_second": 3.329, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.0068279504776, | |
| "eval_runtime": 0.6206, | |
| "eval_samples_per_second": 74.119, | |
| "eval_steps_per_second": 3.223, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 2.8935185185185186e-05, | |
| "loss": 0.1975, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8644481897354126, | |
| "eval_runtime": 0.6022, | |
| "eval_samples_per_second": 76.38, | |
| "eval_steps_per_second": 3.321, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1844, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8681981563568115, | |
| "eval_runtime": 0.5982, | |
| "eval_samples_per_second": 76.901, | |
| "eval_steps_per_second": 3.344, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7914661765098572, | |
| "eval_runtime": 0.6505, | |
| "eval_samples_per_second": 70.715, | |
| "eval_steps_per_second": 3.075, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 2.6620370370370372e-05, | |
| "loss": 0.1701, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7553901672363281, | |
| "eval_runtime": 0.6592, | |
| "eval_samples_per_second": 69.787, | |
| "eval_steps_per_second": 3.034, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.5462962962962965e-05, | |
| "loss": 0.1696, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.876151442527771, | |
| "eval_runtime": 0.5904, | |
| "eval_samples_per_second": 77.91, | |
| "eval_steps_per_second": 3.387, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.017287015914917, | |
| "eval_runtime": 0.5971, | |
| "eval_samples_per_second": 77.038, | |
| "eval_steps_per_second": 3.349, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.1556, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9080155491828918, | |
| "eval_runtime": 0.6064, | |
| "eval_samples_per_second": 75.857, | |
| "eval_steps_per_second": 3.298, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 42.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.245595097541809, | |
| "eval_runtime": 0.6143, | |
| "eval_samples_per_second": 74.886, | |
| "eval_steps_per_second": 3.256, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.153, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9819903373718262, | |
| "eval_runtime": 0.5703, | |
| "eval_samples_per_second": 80.661, | |
| "eval_steps_per_second": 3.507, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 2.1990740740740743e-05, | |
| "loss": 0.1343, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 44.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9908002018928528, | |
| "eval_runtime": 0.598, | |
| "eval_samples_per_second": 76.917, | |
| "eval_steps_per_second": 3.344, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9435335397720337, | |
| "eval_runtime": 0.5858, | |
| "eval_samples_per_second": 78.524, | |
| "eval_steps_per_second": 3.414, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.1513, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 46.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.884244441986084, | |
| "eval_runtime": 0.5815, | |
| "eval_samples_per_second": 79.099, | |
| "eval_steps_per_second": 3.439, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 1.967592592592593e-05, | |
| "loss": 0.1402, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.020715355873108, | |
| "eval_runtime": 0.6172, | |
| "eval_samples_per_second": 74.532, | |
| "eval_steps_per_second": 3.241, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.991458535194397, | |
| "eval_runtime": 0.6173, | |
| "eval_samples_per_second": 74.513, | |
| "eval_steps_per_second": 3.24, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 49.23, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1648, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.1576015949249268, | |
| "eval_runtime": 0.5888, | |
| "eval_samples_per_second": 78.129, | |
| "eval_steps_per_second": 3.397, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 50.77, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 0.1047, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.2283185720443726, | |
| "eval_runtime": 0.5819, | |
| "eval_samples_per_second": 79.051, | |
| "eval_steps_per_second": 3.437, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.086944580078125, | |
| "eval_runtime": 0.6222, | |
| "eval_samples_per_second": 73.928, | |
| "eval_steps_per_second": 3.214, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "learning_rate": 1.6203703703703704e-05, | |
| "loss": 0.1223, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 52.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1203066110610962, | |
| "eval_runtime": 0.6184, | |
| "eval_samples_per_second": 74.384, | |
| "eval_steps_per_second": 3.234, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 1.5046296296296297e-05, | |
| "loss": 0.1223, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9684590101242065, | |
| "eval_runtime": 0.6193, | |
| "eval_samples_per_second": 74.275, | |
| "eval_steps_per_second": 3.229, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 54.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1926442384719849, | |
| "eval_runtime": 0.5863, | |
| "eval_samples_per_second": 78.462, | |
| "eval_steps_per_second": 3.411, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.1236, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.0087707042694092, | |
| "eval_runtime": 0.6028, | |
| "eval_samples_per_second": 76.305, | |
| "eval_steps_per_second": 3.318, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "learning_rate": 1.2731481481481482e-05, | |
| "loss": 0.1115, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9148852229118347, | |
| "eval_runtime": 0.5999, | |
| "eval_samples_per_second": 76.675, | |
| "eval_steps_per_second": 3.334, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.8820303082466125, | |
| "eval_runtime": 0.587, | |
| "eval_samples_per_second": 78.368, | |
| "eval_steps_per_second": 3.407, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 58.46, | |
| "learning_rate": 1.1574074074074075e-05, | |
| "loss": 0.1173, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 58.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9652788043022156, | |
| "eval_runtime": 0.6031, | |
| "eval_samples_per_second": 76.269, | |
| "eval_steps_per_second": 3.316, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 0.102, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.0046106576919556, | |
| "eval_runtime": 0.5819, | |
| "eval_samples_per_second": 79.053, | |
| "eval_steps_per_second": 3.437, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.0584660768508911, | |
| "eval_runtime": 0.6331, | |
| "eval_samples_per_second": 72.655, | |
| "eval_steps_per_second": 3.159, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.1206, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.0489917993545532, | |
| "eval_runtime": 0.5886, | |
| "eval_samples_per_second": 78.157, | |
| "eval_steps_per_second": 3.398, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 62.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.9683184623718262, | |
| "eval_runtime": 0.596, | |
| "eval_samples_per_second": 77.18, | |
| "eval_steps_per_second": 3.356, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 63.08, | |
| "learning_rate": 8.101851851851852e-06, | |
| "loss": 0.1124, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.9627043008804321, | |
| "eval_runtime": 0.5952, | |
| "eval_samples_per_second": 77.29, | |
| "eval_steps_per_second": 3.36, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 64.62, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.0927, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 64.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.9771474003791809, | |
| "eval_runtime": 0.588, | |
| "eval_samples_per_second": 78.231, | |
| "eval_steps_per_second": 3.401, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.0001524686813354, | |
| "eval_runtime": 0.686, | |
| "eval_samples_per_second": 67.054, | |
| "eval_steps_per_second": 2.915, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 66.15, | |
| "learning_rate": 5.787037037037038e-06, | |
| "loss": 0.0906, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 66.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9606509208679199, | |
| "eval_runtime": 0.6833, | |
| "eval_samples_per_second": 67.316, | |
| "eval_steps_per_second": 2.927, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 67.69, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.084, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9413502812385559, | |
| "eval_runtime": 0.6152, | |
| "eval_samples_per_second": 74.773, | |
| "eval_steps_per_second": 3.251, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 68.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9863032698631287, | |
| "eval_runtime": 0.6001, | |
| "eval_samples_per_second": 76.651, | |
| "eval_steps_per_second": 3.333, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 0.0866, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9929794669151306, | |
| "eval_runtime": 0.5767, | |
| "eval_samples_per_second": 79.757, | |
| "eval_steps_per_second": 3.468, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 70.77, | |
| "learning_rate": 2.3148148148148148e-06, | |
| "loss": 0.0944, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 70.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9980859160423279, | |
| "eval_runtime": 0.5702, | |
| "eval_samples_per_second": 80.667, | |
| "eval_steps_per_second": 3.507, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.0039031505584717, | |
| "eval_runtime": 0.5821, | |
| "eval_samples_per_second": 79.025, | |
| "eval_steps_per_second": 3.436, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 72.31, | |
| "learning_rate": 1.1574074074074074e-06, | |
| "loss": 0.1064, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 72.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9986555576324463, | |
| "eval_runtime": 0.5727, | |
| "eval_samples_per_second": 80.324, | |
| "eval_steps_per_second": 3.492, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "learning_rate": 0.0, | |
| "loss": 0.1074, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.996435821056366, | |
| "eval_runtime": 0.5762, | |
| "eval_samples_per_second": 79.839, | |
| "eval_steps_per_second": 3.471, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "step": 480, | |
| "total_flos": 1.5036476561209958e+18, | |
| "train_loss": 0.3537405064950387, | |
| "train_runtime": 582.8644, | |
| "train_samples_per_second": 112.41, | |
| "train_steps_per_second": 0.824 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 80, | |
| "save_steps": 500, | |
| "total_flos": 1.5036476561209958e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |