| { | |
| "best_metric": 0.9840740740740741, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-fine-eurosat/checkpoint-950", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 950, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 2.2726, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.0526315789473684e-05, | |
| "loss": 2.1343, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.5789473684210526e-05, | |
| "loss": 1.8799, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.105263157894737e-05, | |
| "loss": 1.4327, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.9323, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.157894736842105e-05, | |
| "loss": 0.5986, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.6842105263157895e-05, | |
| "loss": 0.5424, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.210526315789474e-05, | |
| "loss": 0.3922, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.736842105263158e-05, | |
| "loss": 0.4408, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.970760233918128e-05, | |
| "loss": 0.3497, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.912280701754386e-05, | |
| "loss": 0.3684, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.853801169590643e-05, | |
| "loss": 0.3542, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.7953216374269006e-05, | |
| "loss": 0.3441, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.736842105263158e-05, | |
| "loss": 0.3107, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.678362573099415e-05, | |
| "loss": 0.2927, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.619883040935672e-05, | |
| "loss": 0.3194, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.56140350877193e-05, | |
| "loss": 0.3002, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.502923976608187e-05, | |
| "loss": 0.2533, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.2682, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9625925925925926, | |
| "eval_loss": 0.1161627545952797, | |
| "eval_runtime": 17.7825, | |
| "eval_samples_per_second": 151.835, | |
| "eval_steps_per_second": 4.78, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.2332, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.327485380116959e-05, | |
| "loss": 0.201, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.269005847953216e-05, | |
| "loss": 0.2551, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 4.210526315789474e-05, | |
| "loss": 0.2132, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 4.152046783625731e-05, | |
| "loss": 0.1864, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 4.093567251461988e-05, | |
| "loss": 0.2568, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 4.0350877192982455e-05, | |
| "loss": 0.2341, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 3.976608187134503e-05, | |
| "loss": 0.2392, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 3.9181286549707604e-05, | |
| "loss": 0.2037, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 3.859649122807018e-05, | |
| "loss": 0.1707, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 3.8011695906432746e-05, | |
| "loss": 0.2211, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 3.742690058479532e-05, | |
| "loss": 0.2286, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.6842105263157895e-05, | |
| "loss": 0.2241, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.625730994152047e-05, | |
| "loss": 0.159, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.5672514619883044e-05, | |
| "loss": 0.1884, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 0.1843, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.4502923976608186e-05, | |
| "loss": 0.1986, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 3.391812865497076e-05, | |
| "loss": 0.1877, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1964, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9762962962962963, | |
| "eval_loss": 0.0753834992647171, | |
| "eval_runtime": 17.1307, | |
| "eval_samples_per_second": 157.611, | |
| "eval_steps_per_second": 4.962, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.274853801169591e-05, | |
| "loss": 0.1864, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 0.1658, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 3.157894736842105e-05, | |
| "loss": 0.1771, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 3.0994152046783626e-05, | |
| "loss": 0.1765, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 3.0409356725146197e-05, | |
| "loss": 0.1668, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 2.9824561403508772e-05, | |
| "loss": 0.1737, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 2.9239766081871346e-05, | |
| "loss": 0.1464, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 2.8654970760233917e-05, | |
| "loss": 0.1791, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 2.8070175438596492e-05, | |
| "loss": 0.1712, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 2.7485380116959063e-05, | |
| "loss": 0.1741, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 2.6900584795321637e-05, | |
| "loss": 0.1501, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.1648, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.5730994152046783e-05, | |
| "loss": 0.1583, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.5146198830409358e-05, | |
| "loss": 0.1499, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.456140350877193e-05, | |
| "loss": 0.1478, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.3976608187134503e-05, | |
| "loss": 0.1843, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 2.3391812865497074e-05, | |
| "loss": 0.1218, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 2.280701754385965e-05, | |
| "loss": 0.1934, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.1559, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9785185185185186, | |
| "eval_loss": 0.0649838000535965, | |
| "eval_runtime": 17.1669, | |
| "eval_samples_per_second": 157.28, | |
| "eval_steps_per_second": 4.951, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 2.1637426900584794e-05, | |
| "loss": 0.1331, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 2.105263157894737e-05, | |
| "loss": 0.1443, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 2.046783625730994e-05, | |
| "loss": 0.1233, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 1.9883040935672515e-05, | |
| "loss": 0.1625, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 1.929824561403509e-05, | |
| "loss": 0.143, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 1.871345029239766e-05, | |
| "loss": 0.1231, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 1.8128654970760235e-05, | |
| "loss": 0.1512, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.1177, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 1.695906432748538e-05, | |
| "loss": 0.1578, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 1.6374269005847955e-05, | |
| "loss": 0.1529, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 1.5789473684210526e-05, | |
| "loss": 0.1364, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1.5204678362573099e-05, | |
| "loss": 0.1291, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 1.4619883040935673e-05, | |
| "loss": 0.1307, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 1.4035087719298246e-05, | |
| "loss": 0.1396, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.3450292397660819e-05, | |
| "loss": 0.1409, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 1.2865497076023392e-05, | |
| "loss": 0.1047, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 1.2280701754385964e-05, | |
| "loss": 0.155, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 1.1695906432748537e-05, | |
| "loss": 0.1233, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.1403, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9725925925925926, | |
| "eval_loss": 0.07712921500205994, | |
| "eval_runtime": 17.723, | |
| "eval_samples_per_second": 152.345, | |
| "eval_steps_per_second": 4.796, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 1.0526315789473684e-05, | |
| "loss": 0.1195, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 9.941520467836257e-06, | |
| "loss": 0.1191, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 9.35672514619883e-06, | |
| "loss": 0.1313, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.1291, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 8.187134502923977e-06, | |
| "loss": 0.1415, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 7.602339181286549e-06, | |
| "loss": 0.1448, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 7.017543859649123e-06, | |
| "loss": 0.1222, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 6.432748538011696e-06, | |
| "loss": 0.0944, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 5.8479532163742686e-06, | |
| "loss": 0.1072, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 0.1104, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 4.678362573099415e-06, | |
| "loss": 0.0874, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 4.093567251461989e-06, | |
| "loss": 0.1083, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 3.5087719298245615e-06, | |
| "loss": 0.1183, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 2.9239766081871343e-06, | |
| "loss": 0.1168, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 2.3391812865497075e-06, | |
| "loss": 0.1072, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 1.7543859649122807e-06, | |
| "loss": 0.1234, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 1.1695906432748538e-06, | |
| "loss": 0.1048, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 5.847953216374269e-07, | |
| "loss": 0.0906, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1104, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9840740740740741, | |
| "eval_loss": 0.050109319388866425, | |
| "eval_runtime": 17.5996, | |
| "eval_samples_per_second": 153.413, | |
| "eval_steps_per_second": 4.83, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 950, | |
| "total_flos": 3.020677750960128e+18, | |
| "train_loss": 0.27060336539619845, | |
| "train_runtime": 1968.7839, | |
| "train_samples_per_second": 61.713, | |
| "train_steps_per_second": 0.483 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 950, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 3.020677750960128e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |