|
{ |
|
"best_metric": 0.9748217468805704, |
|
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-981", |
|
"epoch": 2.9977081741787623, |
|
"eval_steps": 500, |
|
"global_step": 981, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 5.050505050505051e-06, |
|
"loss": 0.7371, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 1.0101010101010101e-05, |
|
"loss": 0.6829, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.5151515151515153e-05, |
|
"loss": 0.5747, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 2.0202020202020203e-05, |
|
"loss": 0.4919, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 2.5252525252525256e-05, |
|
"loss": 0.3879, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 3.0303030303030306e-05, |
|
"loss": 0.3731, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 3.535353535353535e-05, |
|
"loss": 0.2958, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.0404040404040405e-05, |
|
"loss": 0.3414, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 4.545454545454546e-05, |
|
"loss": 0.3495, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 4.9943310657596374e-05, |
|
"loss": 0.2958, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 4.937641723356009e-05, |
|
"loss": 0.3242, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 4.880952380952381e-05, |
|
"loss": 0.3561, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.8242630385487533e-05, |
|
"loss": 0.2808, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 4.767573696145125e-05, |
|
"loss": 0.2741, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 4.710884353741497e-05, |
|
"loss": 0.2439, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 4.6541950113378686e-05, |
|
"loss": 0.2174, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 4.597505668934241e-05, |
|
"loss": 0.1839, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 4.5408163265306124e-05, |
|
"loss": 0.2663, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 4.4841269841269846e-05, |
|
"loss": 0.2561, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 4.427437641723356e-05, |
|
"loss": 0.2523, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 4.3707482993197277e-05, |
|
"loss": 0.2044, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 4.3140589569161e-05, |
|
"loss": 0.1665, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 4.257369614512472e-05, |
|
"loss": 0.1854, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 4.200680272108844e-05, |
|
"loss": 0.1847, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 4.143990929705215e-05, |
|
"loss": 0.1568, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 4.0873015873015874e-05, |
|
"loss": 0.2453, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 4.0306122448979596e-05, |
|
"loss": 0.1518, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 3.973922902494331e-05, |
|
"loss": 0.1955, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 3.9172335600907026e-05, |
|
"loss": 0.166, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 3.860544217687075e-05, |
|
"loss": 0.1496, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 3.803854875283447e-05, |
|
"loss": 0.1804, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 3.7471655328798186e-05, |
|
"loss": 0.1397, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9632352941176471, |
|
"eval_loss": 0.09683836996555328, |
|
"eval_runtime": 97.943, |
|
"eval_samples_per_second": 45.823, |
|
"eval_steps_per_second": 5.728, |
|
"step": 327 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 3.690476190476191e-05, |
|
"loss": 0.2158, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 3.633786848072562e-05, |
|
"loss": 0.1301, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 3.5770975056689345e-05, |
|
"loss": 0.1749, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 3.520408163265306e-05, |
|
"loss": 0.1453, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 3.463718820861678e-05, |
|
"loss": 0.1435, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 3.4070294784580505e-05, |
|
"loss": 0.1452, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 3.350340136054422e-05, |
|
"loss": 0.1099, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 3.2936507936507936e-05, |
|
"loss": 0.1161, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 3.236961451247166e-05, |
|
"loss": 0.1581, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 3.180272108843538e-05, |
|
"loss": 0.1569, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 3.1235827664399095e-05, |
|
"loss": 0.1531, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 3.066893424036281e-05, |
|
"loss": 0.1516, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 3.0102040816326533e-05, |
|
"loss": 0.1114, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 2.953514739229025e-05, |
|
"loss": 0.1487, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 2.8968253968253974e-05, |
|
"loss": 0.1003, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 2.8401360544217685e-05, |
|
"loss": 0.164, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 2.7834467120181408e-05, |
|
"loss": 0.1588, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 2.7267573696145126e-05, |
|
"loss": 0.1424, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 2.6700680272108845e-05, |
|
"loss": 0.129, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 2.613378684807256e-05, |
|
"loss": 0.109, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 2.5566893424036282e-05, |
|
"loss": 0.0918, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 2.5e-05, |
|
"loss": 0.1263, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 2.443310657596372e-05, |
|
"loss": 0.2354, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 2.386621315192744e-05, |
|
"loss": 0.1054, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 2.3299319727891157e-05, |
|
"loss": 0.1154, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 2.2732426303854876e-05, |
|
"loss": 0.1901, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 2.2165532879818595e-05, |
|
"loss": 0.0791, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 2.1598639455782314e-05, |
|
"loss": 0.1164, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 2.1031746031746032e-05, |
|
"loss": 0.1054, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 2.046485260770975e-05, |
|
"loss": 0.0895, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 1.989795918367347e-05, |
|
"loss": 0.0878, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 1.9331065759637192e-05, |
|
"loss": 0.1316, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 1.8764172335600907e-05, |
|
"loss": 0.1252, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.9725935828877005, |
|
"eval_loss": 0.08181790262460709, |
|
"eval_runtime": 95.4429, |
|
"eval_samples_per_second": 47.023, |
|
"eval_steps_per_second": 5.878, |
|
"step": 654 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 1.8197278911564626e-05, |
|
"loss": 0.0952, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 1.7630385487528345e-05, |
|
"loss": 0.1192, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 1.7063492063492063e-05, |
|
"loss": 0.1067, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 1.6496598639455782e-05, |
|
"loss": 0.1201, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 1.59297052154195e-05, |
|
"loss": 0.1207, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 1.5362811791383223e-05, |
|
"loss": 0.1117, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 1.479591836734694e-05, |
|
"loss": 0.0732, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 1.4229024943310659e-05, |
|
"loss": 0.0643, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 2.26, |
|
"learning_rate": 1.3662131519274376e-05, |
|
"loss": 0.0558, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 1.3095238095238096e-05, |
|
"loss": 0.0559, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 1.2528344671201813e-05, |
|
"loss": 0.0745, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"learning_rate": 1.1961451247165534e-05, |
|
"loss": 0.1001, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 2.38, |
|
"learning_rate": 1.1394557823129252e-05, |
|
"loss": 0.0915, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 2.41, |
|
"learning_rate": 1.0827664399092971e-05, |
|
"loss": 0.0899, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 1.026077097505669e-05, |
|
"loss": 0.1175, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 9.693877551020408e-06, |
|
"loss": 0.0748, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 9.126984126984127e-06, |
|
"loss": 0.1226, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 8.560090702947846e-06, |
|
"loss": 0.1351, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 2.57, |
|
"learning_rate": 7.993197278911566e-06, |
|
"loss": 0.0688, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 7.426303854875284e-06, |
|
"loss": 0.086, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 2.63, |
|
"learning_rate": 6.859410430839003e-06, |
|
"loss": 0.1631, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"learning_rate": 6.292517006802722e-06, |
|
"loss": 0.0451, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 5.72562358276644e-06, |
|
"loss": 0.0869, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 5.158730158730159e-06, |
|
"loss": 0.0662, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 4.591836734693878e-06, |
|
"loss": 0.0789, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 2.78, |
|
"learning_rate": 4.0249433106575965e-06, |
|
"loss": 0.0696, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 3.4580498866213153e-06, |
|
"loss": 0.0976, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 2.8911564625850344e-06, |
|
"loss": 0.0715, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 2.3242630385487527e-06, |
|
"loss": 0.0737, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 2.9, |
|
"learning_rate": 1.7573696145124719e-06, |
|
"loss": 0.0739, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 2.93, |
|
"learning_rate": 1.1904761904761904e-06, |
|
"loss": 0.1651, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 6.235827664399093e-07, |
|
"loss": 0.0782, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 2.99, |
|
"learning_rate": 5.668934240362812e-08, |
|
"loss": 0.1098, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9748217468805704, |
|
"eval_loss": 0.07243592292070389, |
|
"eval_runtime": 93.9793, |
|
"eval_samples_per_second": 47.755, |
|
"eval_steps_per_second": 5.969, |
|
"step": 981 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 981, |
|
"total_flos": 7.802294942660198e+17, |
|
"train_loss": 0.1717462847037782, |
|
"train_runtime": 1149.2673, |
|
"train_samples_per_second": 27.333, |
|
"train_steps_per_second": 0.854 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 981, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 7.802294942660198e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|