| { | |
| "best_metric": 0.9859259259259259, | |
| "best_model_checkpoint": "vit-convnext-tiny-224-eurosat/checkpoint-588", | |
| "epoch": 4.99492385786802, | |
| "global_step": 735, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.7567567567567575e-06, | |
| "loss": 2.2859, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.3513513513513515e-05, | |
| "loss": 2.2442, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.0270270270270273e-05, | |
| "loss": 2.1563, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.702702702702703e-05, | |
| "loss": 2.0172, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.3783783783783784e-05, | |
| "loss": 1.8198, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.0540540540540545e-05, | |
| "loss": 1.5871, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.72972972972973e-05, | |
| "loss": 1.3185, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.9546142208774585e-05, | |
| "loss": 1.0524, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.878971255673222e-05, | |
| "loss": 0.849, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.803328290468986e-05, | |
| "loss": 0.6729, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.7276853252647505e-05, | |
| "loss": 0.5013, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.652042360060514e-05, | |
| "loss": 0.4268, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.576399394856278e-05, | |
| "loss": 0.3198, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.5007564296520425e-05, | |
| "loss": 0.2881, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.9587654320987654, | |
| "eval_loss": 0.23249287903308868, | |
| "eval_runtime": 26.3088, | |
| "eval_samples_per_second": 153.941, | |
| "eval_steps_per_second": 4.827, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.425113464447806e-05, | |
| "loss": 0.2379, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.34947049924357e-05, | |
| "loss": 0.1822, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.2738275340393345e-05, | |
| "loss": 0.1815, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 4.198184568835098e-05, | |
| "loss": 0.1558, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 4.122541603630862e-05, | |
| "loss": 0.1337, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.0468986384266265e-05, | |
| "loss": 0.1429, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 3.97125567322239e-05, | |
| "loss": 0.1149, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 3.895612708018154e-05, | |
| "loss": 0.1199, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 3.8199697428139184e-05, | |
| "loss": 0.1194, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 3.744326777609682e-05, | |
| "loss": 0.1027, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.668683812405446e-05, | |
| "loss": 0.1092, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.5930408472012104e-05, | |
| "loss": 0.1038, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.517397881996974e-05, | |
| "loss": 0.0811, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.441754916792738e-05, | |
| "loss": 0.0988, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 3.3661119515885024e-05, | |
| "loss": 0.0869, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.9753086419753086, | |
| "eval_loss": 0.09120676666498184, | |
| "eval_runtime": 25.7061, | |
| "eval_samples_per_second": 157.55, | |
| "eval_steps_per_second": 4.94, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 3.290468986384266e-05, | |
| "loss": 0.0707, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 3.21482602118003e-05, | |
| "loss": 0.0525, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 3.1391830559757944e-05, | |
| "loss": 0.0632, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 3.063540090771558e-05, | |
| "loss": 0.0926, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 2.9878971255673223e-05, | |
| "loss": 0.0628, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 2.9122541603630864e-05, | |
| "loss": 0.0677, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2.83661119515885e-05, | |
| "loss": 0.0436, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 2.7609682299546143e-05, | |
| "loss": 0.0821, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 2.6853252647503784e-05, | |
| "loss": 0.0567, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 2.609682299546142e-05, | |
| "loss": 0.0641, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.5340393343419063e-05, | |
| "loss": 0.0534, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.45839636913767e-05, | |
| "loss": 0.0454, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.382753403933434e-05, | |
| "loss": 0.0627, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 2.3071104387291982e-05, | |
| "loss": 0.036, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2.231467473524962e-05, | |
| "loss": 0.0687, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.9804938271604938, | |
| "eval_loss": 0.06631184369325638, | |
| "eval_runtime": 25.6488, | |
| "eval_samples_per_second": 157.902, | |
| "eval_steps_per_second": 4.952, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 2.155824508320726e-05, | |
| "loss": 0.0542, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 2.0801815431164902e-05, | |
| "loss": 0.044, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 2.004538577912254e-05, | |
| "loss": 0.0346, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 1.928895612708018e-05, | |
| "loss": 0.0406, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 1.8532526475037822e-05, | |
| "loss": 0.0496, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 1.777609682299546e-05, | |
| "loss": 0.046, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 1.70196671709531e-05, | |
| "loss": 0.0356, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 1.6263237518910742e-05, | |
| "loss": 0.0339, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 1.550680786686838e-05, | |
| "loss": 0.0384, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.4750378214826023e-05, | |
| "loss": 0.0319, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 1.3993948562783662e-05, | |
| "loss": 0.0333, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 1.3237518910741301e-05, | |
| "loss": 0.0258, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 1.248108925869894e-05, | |
| "loss": 0.0377, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.172465960665658e-05, | |
| "loss": 0.0272, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.9859259259259259, | |
| "eval_loss": 0.057608071714639664, | |
| "eval_runtime": 25.6469, | |
| "eval_samples_per_second": 157.914, | |
| "eval_steps_per_second": 4.952, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 1.0968229954614221e-05, | |
| "loss": 0.0313, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1.021180030257186e-05, | |
| "loss": 0.0232, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 9.4553706505295e-06, | |
| "loss": 0.0308, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 8.698940998487141e-06, | |
| "loss": 0.0245, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 7.94251134644478e-06, | |
| "loss": 0.0334, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 7.186081694402421e-06, | |
| "loss": 0.0318, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 6.429652042360061e-06, | |
| "loss": 0.0238, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 5.6732223903177e-06, | |
| "loss": 0.0333, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 4.9167927382753406e-06, | |
| "loss": 0.0266, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 4.16036308623298e-06, | |
| "loss": 0.0222, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 3.40393343419062e-06, | |
| "loss": 0.0229, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 2.64750378214826e-06, | |
| "loss": 0.0286, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 1.8910741301059002e-06, | |
| "loss": 0.0222, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 1.13464447806354e-06, | |
| "loss": 0.0197, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 3.7821482602118004e-07, | |
| "loss": 0.0247, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.9854320987654321, | |
| "eval_loss": 0.053181808441877365, | |
| "eval_runtime": 25.598, | |
| "eval_samples_per_second": 158.216, | |
| "eval_steps_per_second": 4.961, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "step": 735, | |
| "total_flos": 2.3729757133844644e+18, | |
| "train_loss": 0.2908774734962554, | |
| "train_runtime": 1704.3854, | |
| "train_samples_per_second": 55.445, | |
| "train_steps_per_second": 0.431 | |
| } | |
| ], | |
| "max_steps": 735, | |
| "num_train_epochs": 5, | |
| "total_flos": 2.3729757133844644e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |