| { | |
| "best_metric": 0.782608695652174, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-ve-U13-b-80\\checkpoint-240", | |
| "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": 1.385940432548523, | |
| "eval_runtime": 0.6339, | |
| "eval_samples_per_second": 72.571, | |
| "eval_steps_per_second": 3.155, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 1.3859, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.2826086956521739, | |
| "eval_loss": 1.382836103439331, | |
| "eval_runtime": 0.653, | |
| "eval_samples_per_second": 70.443, | |
| "eval_steps_per_second": 3.063, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.3768701553344727, | |
| "eval_runtime": 0.65, | |
| "eval_samples_per_second": 70.768, | |
| "eval_steps_per_second": 3.077, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 1.379, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.2826086956521739, | |
| "eval_loss": 1.3565824031829834, | |
| "eval_runtime": 0.6532, | |
| "eval_samples_per_second": 70.417, | |
| "eval_steps_per_second": 3.062, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 3.125e-05, | |
| "loss": 1.3356, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_accuracy": 0.2391304347826087, | |
| "eval_loss": 1.316235065460205, | |
| "eval_runtime": 0.6545, | |
| "eval_samples_per_second": 70.281, | |
| "eval_steps_per_second": 3.056, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.3695652173913043, | |
| "eval_loss": 1.2090449333190918, | |
| "eval_runtime": 0.6376, | |
| "eval_samples_per_second": 72.151, | |
| "eval_steps_per_second": 3.137, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.2023, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.41304347826086957, | |
| "eval_loss": 1.140857458114624, | |
| "eval_runtime": 0.6476, | |
| "eval_samples_per_second": 71.035, | |
| "eval_steps_per_second": 3.088, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 4.976851851851852e-05, | |
| "loss": 1.0289, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.0442323684692383, | |
| "eval_runtime": 0.6862, | |
| "eval_samples_per_second": 67.038, | |
| "eval_steps_per_second": 2.915, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_accuracy": 0.5217391304347826, | |
| "eval_loss": 0.9695850610733032, | |
| "eval_runtime": 0.6564, | |
| "eval_samples_per_second": 70.079, | |
| "eval_steps_per_second": 3.047, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.9132, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.43478260869565216, | |
| "eval_loss": 1.0133169889450073, | |
| "eval_runtime": 0.6439, | |
| "eval_samples_per_second": 71.444, | |
| "eval_steps_per_second": 3.106, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 4.745370370370371e-05, | |
| "loss": 0.7677, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0143684148788452, | |
| "eval_runtime": 0.6229, | |
| "eval_samples_per_second": 73.85, | |
| "eval_steps_per_second": 3.211, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.34782608695652173, | |
| "eval_loss": 1.137718915939331, | |
| "eval_runtime": 0.6502, | |
| "eval_samples_per_second": 70.745, | |
| "eval_steps_per_second": 3.076, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.6988, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 0.817061722278595, | |
| "eval_runtime": 0.6531, | |
| "eval_samples_per_second": 70.438, | |
| "eval_steps_per_second": 3.063, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 0.6051, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 0.8982558846473694, | |
| "eval_runtime": 0.6551, | |
| "eval_samples_per_second": 70.213, | |
| "eval_steps_per_second": 3.053, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.8593006134033203, | |
| "eval_runtime": 0.6479, | |
| "eval_samples_per_second": 71.003, | |
| "eval_steps_per_second": 3.087, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 4.3981481481481486e-05, | |
| "loss": 0.5175, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.818878173828125, | |
| "eval_runtime": 0.6394, | |
| "eval_samples_per_second": 71.94, | |
| "eval_steps_per_second": 3.128, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 4.282407407407408e-05, | |
| "loss": 0.429, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.6789580583572388, | |
| "eval_runtime": 0.6455, | |
| "eval_samples_per_second": 71.263, | |
| "eval_steps_per_second": 3.098, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 0.7073642015457153, | |
| "eval_runtime": 0.6678, | |
| "eval_samples_per_second": 68.88, | |
| "eval_steps_per_second": 2.995, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.4349, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8890200257301331, | |
| "eval_runtime": 0.6748, | |
| "eval_samples_per_second": 68.17, | |
| "eval_steps_per_second": 2.964, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.0509259259259265e-05, | |
| "loss": 0.3892, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.979804515838623, | |
| "eval_runtime": 0.6717, | |
| "eval_samples_per_second": 68.481, | |
| "eval_steps_per_second": 2.977, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8814191222190857, | |
| "eval_runtime": 0.6613, | |
| "eval_samples_per_second": 69.559, | |
| "eval_steps_per_second": 3.024, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 3.935185185185186e-05, | |
| "loss": 0.3613, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 0.8839537501335144, | |
| "eval_runtime": 0.6839, | |
| "eval_samples_per_second": 67.261, | |
| "eval_steps_per_second": 2.924, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7662139534950256, | |
| "eval_runtime": 0.6732, | |
| "eval_samples_per_second": 68.326, | |
| "eval_steps_per_second": 2.971, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 0.342, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7883625030517578, | |
| "eval_runtime": 0.6844, | |
| "eval_samples_per_second": 67.213, | |
| "eval_steps_per_second": 2.922, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2762, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.026755928993225, | |
| "eval_runtime": 0.6591, | |
| "eval_samples_per_second": 69.789, | |
| "eval_steps_per_second": 3.034, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9206076264381409, | |
| "eval_runtime": 0.6851, | |
| "eval_samples_per_second": 67.14, | |
| "eval_steps_per_second": 2.919, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 3.587962962962963e-05, | |
| "loss": 0.2759, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9079513549804688, | |
| "eval_runtime": 0.6802, | |
| "eval_samples_per_second": 67.623, | |
| "eval_steps_per_second": 2.94, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.2559, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9378835558891296, | |
| "eval_runtime": 0.6691, | |
| "eval_samples_per_second": 68.745, | |
| "eval_steps_per_second": 2.989, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.0121444463729858, | |
| "eval_runtime": 0.6814, | |
| "eval_samples_per_second": 67.504, | |
| "eval_steps_per_second": 2.935, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 3.3564814814814815e-05, | |
| "loss": 0.2455, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.8251720070838928, | |
| "eval_runtime": 0.6693, | |
| "eval_samples_per_second": 68.731, | |
| "eval_steps_per_second": 2.988, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.2125, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8500754237174988, | |
| "eval_runtime": 0.693, | |
| "eval_samples_per_second": 66.38, | |
| "eval_steps_per_second": 2.886, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.0364569425582886, | |
| "eval_runtime": 0.684, | |
| "eval_samples_per_second": 67.248, | |
| "eval_steps_per_second": 2.924, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.2204, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.0469846725463867, | |
| "eval_runtime": 0.6841, | |
| "eval_samples_per_second": 67.245, | |
| "eval_steps_per_second": 2.924, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 3.0092592592592593e-05, | |
| "loss": 0.1785, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8834150433540344, | |
| "eval_runtime": 0.6551, | |
| "eval_samples_per_second": 70.218, | |
| "eval_steps_per_second": 3.053, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.0779674053192139, | |
| "eval_runtime": 0.6643, | |
| "eval_samples_per_second": 69.243, | |
| "eval_steps_per_second": 3.011, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 2.8935185185185186e-05, | |
| "loss": 0.1912, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9327965378761292, | |
| "eval_runtime": 0.6863, | |
| "eval_samples_per_second": 67.022, | |
| "eval_steps_per_second": 2.914, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1518, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8900798559188843, | |
| "eval_runtime": 0.6842, | |
| "eval_samples_per_second": 67.236, | |
| "eval_steps_per_second": 2.923, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.1069260835647583, | |
| "eval_runtime": 0.6697, | |
| "eval_samples_per_second": 68.692, | |
| "eval_steps_per_second": 2.987, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 2.6620370370370372e-05, | |
| "loss": 0.166, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9823449850082397, | |
| "eval_runtime": 0.6724, | |
| "eval_samples_per_second": 68.414, | |
| "eval_steps_per_second": 2.975, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.5462962962962965e-05, | |
| "loss": 0.1775, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9712538719177246, | |
| "eval_runtime": 0.6616, | |
| "eval_samples_per_second": 69.532, | |
| "eval_steps_per_second": 3.023, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.972922146320343, | |
| "eval_runtime": 0.6677, | |
| "eval_samples_per_second": 68.892, | |
| "eval_steps_per_second": 2.995, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.1344, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9956928491592407, | |
| "eval_runtime": 0.6673, | |
| "eval_samples_per_second": 68.936, | |
| "eval_steps_per_second": 2.997, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 42.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0180084705352783, | |
| "eval_runtime": 0.6819, | |
| "eval_samples_per_second": 67.46, | |
| "eval_steps_per_second": 2.933, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.1232, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9668875336647034, | |
| "eval_runtime": 0.6863, | |
| "eval_samples_per_second": 67.023, | |
| "eval_steps_per_second": 2.914, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 2.1990740740740743e-05, | |
| "loss": 0.1267, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 44.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9764741063117981, | |
| "eval_runtime": 0.6906, | |
| "eval_samples_per_second": 66.611, | |
| "eval_steps_per_second": 2.896, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0389167070388794, | |
| "eval_runtime": 0.8195, | |
| "eval_samples_per_second": 56.133, | |
| "eval_steps_per_second": 2.441, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.1548, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 46.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.001569390296936, | |
| "eval_runtime": 0.6415, | |
| "eval_samples_per_second": 71.702, | |
| "eval_steps_per_second": 3.117, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 1.967592592592593e-05, | |
| "loss": 0.1267, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.156539797782898, | |
| "eval_runtime": 0.6692, | |
| "eval_samples_per_second": 68.739, | |
| "eval_steps_per_second": 2.989, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1795543432235718, | |
| "eval_runtime": 0.7207, | |
| "eval_samples_per_second": 63.831, | |
| "eval_steps_per_second": 2.775, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 49.23, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1403, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.2806681394577026, | |
| "eval_runtime": 0.6946, | |
| "eval_samples_per_second": 66.226, | |
| "eval_steps_per_second": 2.879, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 50.77, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 0.1096, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.2462576627731323, | |
| "eval_runtime": 0.7307, | |
| "eval_samples_per_second": 62.954, | |
| "eval_steps_per_second": 2.737, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.145448088645935, | |
| "eval_runtime": 0.7031, | |
| "eval_samples_per_second": 65.426, | |
| "eval_steps_per_second": 2.845, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "learning_rate": 1.6203703703703704e-05, | |
| "loss": 0.1106, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 52.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.1494420766830444, | |
| "eval_runtime": 0.6634, | |
| "eval_samples_per_second": 69.34, | |
| "eval_steps_per_second": 3.015, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 1.5046296296296297e-05, | |
| "loss": 0.1116, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.1299750804901123, | |
| "eval_runtime": 0.6843, | |
| "eval_samples_per_second": 67.217, | |
| "eval_steps_per_second": 2.922, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 54.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.2097675800323486, | |
| "eval_runtime": 0.7032, | |
| "eval_samples_per_second": 65.42, | |
| "eval_steps_per_second": 2.844, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.1229, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.0590535402297974, | |
| "eval_runtime": 0.6998, | |
| "eval_samples_per_second": 65.732, | |
| "eval_steps_per_second": 2.858, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "learning_rate": 1.2731481481481482e-05, | |
| "loss": 0.1235, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.1228772401809692, | |
| "eval_runtime": 0.6702, | |
| "eval_samples_per_second": 68.637, | |
| "eval_steps_per_second": 2.984, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.2034395933151245, | |
| "eval_runtime": 0.6511, | |
| "eval_samples_per_second": 70.647, | |
| "eval_steps_per_second": 3.072, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 58.46, | |
| "learning_rate": 1.1574074074074075e-05, | |
| "loss": 0.107, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 58.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.0628197193145752, | |
| "eval_runtime": 0.6967, | |
| "eval_samples_per_second": 66.021, | |
| "eval_steps_per_second": 2.87, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 0.107, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0070008039474487, | |
| "eval_runtime": 0.6853, | |
| "eval_samples_per_second": 67.122, | |
| "eval_steps_per_second": 2.918, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.16019868850708, | |
| "eval_runtime": 0.6966, | |
| "eval_samples_per_second": 66.035, | |
| "eval_steps_per_second": 2.871, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.1167, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.0720371007919312, | |
| "eval_runtime": 0.7007, | |
| "eval_samples_per_second": 65.652, | |
| "eval_steps_per_second": 2.854, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 62.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9726494550704956, | |
| "eval_runtime": 0.6716, | |
| "eval_samples_per_second": 68.496, | |
| "eval_steps_per_second": 2.978, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 63.08, | |
| "learning_rate": 8.101851851851852e-06, | |
| "loss": 0.1113, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.032416582107544, | |
| "eval_runtime": 0.684, | |
| "eval_samples_per_second": 67.253, | |
| "eval_steps_per_second": 2.924, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 64.62, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.0838, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 64.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1092015504837036, | |
| "eval_runtime": 0.6999, | |
| "eval_samples_per_second": 65.722, | |
| "eval_steps_per_second": 2.857, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.177163004875183, | |
| "eval_runtime": 0.7851, | |
| "eval_samples_per_second": 58.589, | |
| "eval_steps_per_second": 2.547, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 66.15, | |
| "learning_rate": 5.787037037037038e-06, | |
| "loss": 0.083, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 66.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1195148229599, | |
| "eval_runtime": 0.6775, | |
| "eval_samples_per_second": 67.893, | |
| "eval_steps_per_second": 2.952, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 67.69, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.0899, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.068082332611084, | |
| "eval_runtime": 0.668, | |
| "eval_samples_per_second": 68.86, | |
| "eval_steps_per_second": 2.994, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 68.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1160058975219727, | |
| "eval_runtime": 0.6862, | |
| "eval_samples_per_second": 67.036, | |
| "eval_steps_per_second": 2.915, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 0.0813, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.143452525138855, | |
| "eval_runtime": 0.6851, | |
| "eval_samples_per_second": 67.142, | |
| "eval_steps_per_second": 2.919, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 70.77, | |
| "learning_rate": 2.3148148148148148e-06, | |
| "loss": 0.0782, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 70.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1463539600372314, | |
| "eval_runtime": 0.6819, | |
| "eval_samples_per_second": 67.457, | |
| "eval_steps_per_second": 2.933, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1538991928100586, | |
| "eval_runtime": 0.7861, | |
| "eval_samples_per_second": 58.52, | |
| "eval_steps_per_second": 2.544, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 72.31, | |
| "learning_rate": 1.1574074074074074e-06, | |
| "loss": 0.1014, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 72.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.158526062965393, | |
| "eval_runtime": 0.7055, | |
| "eval_samples_per_second": 65.203, | |
| "eval_steps_per_second": 2.835, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "learning_rate": 0.0, | |
| "loss": 0.0944, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1592216491699219, | |
| "eval_runtime": 0.7479, | |
| "eval_samples_per_second": 61.508, | |
| "eval_steps_per_second": 2.674, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "step": 480, | |
| "total_flos": 1.5036476561209958e+18, | |
| "train_loss": 0.34541464410722256, | |
| "train_runtime": 589.4401, | |
| "train_samples_per_second": 111.156, | |
| "train_steps_per_second": 0.814 | |
| } | |
| ], | |
| "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 | |
| } | |