| { | |
| "best_metric": 0.8214882943143813, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-birds/checkpoint-666", | |
| "epoch": 9.989966555183946, | |
| "global_step": 740, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.702702702702703e-05, | |
| "loss": 6.0261, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 5.405405405405406e-05, | |
| "loss": 5.9893, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 8.108108108108109e-05, | |
| "loss": 5.8912, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00010810810810810812, | |
| "loss": 5.6283, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00013513513513513514, | |
| "loss": 5.1412, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00016216216216216218, | |
| "loss": 4.4976, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0001891891891891892, | |
| "loss": 3.8854, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.3039297658862876, | |
| "eval_loss": 3.016413688659668, | |
| "eval_runtime": 55.4337, | |
| "eval_samples_per_second": 43.151, | |
| "eval_steps_per_second": 0.613, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0001981981981981982, | |
| "loss": 3.5122, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0001951951951951952, | |
| "loss": 2.8685, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0001921921921921922, | |
| "loss": 2.7098, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0001891891891891892, | |
| "loss": 2.4524, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.0001861861861861862, | |
| "loss": 2.2264, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0001831831831831832, | |
| "loss": 2.1425, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00018018018018018018, | |
| "loss": 2.066, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.6095317725752508, | |
| "eval_loss": 1.4849172830581665, | |
| "eval_runtime": 53.4198, | |
| "eval_samples_per_second": 44.777, | |
| "eval_steps_per_second": 0.636, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0001771771771771772, | |
| "loss": 2.0492, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.0001741741741741742, | |
| "loss": 1.6848, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.0001711711711711712, | |
| "loss": 1.5999, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.00016816816816816817, | |
| "loss": 1.5694, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.00016516516516516518, | |
| "loss": 1.5405, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.00016216216216216218, | |
| "loss": 1.56, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.00015915915915915919, | |
| "loss": 1.5262, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.00015615615615615616, | |
| "loss": 1.5066, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.7144648829431438, | |
| "eval_loss": 1.0624045133590698, | |
| "eval_runtime": 53.8931, | |
| "eval_samples_per_second": 44.384, | |
| "eval_steps_per_second": 0.631, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.00015315315315315314, | |
| "loss": 1.4184, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 0.00015015015015015014, | |
| "loss": 1.1701, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 0.00014714714714714715, | |
| "loss": 1.2394, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 0.00014414414414414415, | |
| "loss": 1.2596, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 0.00014114114114114113, | |
| "loss": 1.2528, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 0.00013813813813813813, | |
| "loss": 1.1914, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 0.00013513513513513514, | |
| "loss": 1.1904, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.7449832775919732, | |
| "eval_loss": 0.9347118735313416, | |
| "eval_runtime": 53.4208, | |
| "eval_samples_per_second": 44.777, | |
| "eval_steps_per_second": 0.636, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.00013213213213213214, | |
| "loss": 1.2212, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 0.00012912912912912915, | |
| "loss": 1.0732, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 0.00012612612612612612, | |
| "loss": 1.0471, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 0.00012312312312312313, | |
| "loss": 1.0182, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 0.00012012012012012013, | |
| "loss": 1.0593, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 0.00011711711711711712, | |
| "loss": 1.0595, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 0.00011411411411411413, | |
| "loss": 1.0661, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 0.9986, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.7709030100334449, | |
| "eval_loss": 0.8414692878723145, | |
| "eval_runtime": 52.7969, | |
| "eval_samples_per_second": 45.306, | |
| "eval_steps_per_second": 0.644, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 0.00010810810810810812, | |
| "loss": 1.0043, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 0.00010510510510510511, | |
| "loss": 0.9405, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 0.00010210210210210212, | |
| "loss": 0.9549, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 9.90990990990991e-05, | |
| "loss": 0.9295, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 9.60960960960961e-05, | |
| "loss": 0.9364, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 9.30930930930931e-05, | |
| "loss": 0.9573, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 9.009009009009009e-05, | |
| "loss": 0.9437, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_accuracy": 0.790133779264214, | |
| "eval_loss": 0.7713439464569092, | |
| "eval_runtime": 53.9776, | |
| "eval_samples_per_second": 44.315, | |
| "eval_steps_per_second": 0.63, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 8.70870870870871e-05, | |
| "loss": 0.9526, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 8.408408408408409e-05, | |
| "loss": 0.7933, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 8.108108108108109e-05, | |
| "loss": 0.8394, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 7.807807807807808e-05, | |
| "loss": 0.8327, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 7.507507507507507e-05, | |
| "loss": 0.8468, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 7.207207207207208e-05, | |
| "loss": 0.8479, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 6.906906906906907e-05, | |
| "loss": 0.8297, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.8081103678929766, | |
| "eval_loss": 0.7216358184814453, | |
| "eval_runtime": 52.5646, | |
| "eval_samples_per_second": 45.506, | |
| "eval_steps_per_second": 0.647, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 6.606606606606607e-05, | |
| "loss": 0.8914, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 6.306306306306306e-05, | |
| "loss": 0.7991, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 6.0060060060060066e-05, | |
| "loss": 0.7353, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 5.705705705705706e-05, | |
| "loss": 0.7603, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 5.405405405405406e-05, | |
| "loss": 0.7625, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 5.105105105105106e-05, | |
| "loss": 0.7428, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 4.804804804804805e-05, | |
| "loss": 0.8369, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 4.5045045045045046e-05, | |
| "loss": 0.7805, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_accuracy": 0.8152173913043478, | |
| "eval_loss": 0.68564373254776, | |
| "eval_runtime": 51.6539, | |
| "eval_samples_per_second": 46.308, | |
| "eval_steps_per_second": 0.658, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 4.204204204204204e-05, | |
| "loss": 0.7779, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 3.903903903903904e-05, | |
| "loss": 0.7011, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 3.603603603603604e-05, | |
| "loss": 0.6612, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 3.3033033033033035e-05, | |
| "loss": 0.6625, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 3.0030030030030033e-05, | |
| "loss": 0.7031, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 2.702702702702703e-05, | |
| "loss": 0.7252, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 2.4024024024024024e-05, | |
| "loss": 0.6978, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8214882943143813, | |
| "eval_loss": 0.6642215847969055, | |
| "eval_runtime": 52.6331, | |
| "eval_samples_per_second": 45.447, | |
| "eval_steps_per_second": 0.646, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 2.102102102102102e-05, | |
| "loss": 0.7506, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 1.801801801801802e-05, | |
| "loss": 0.6608, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 1.5015015015015016e-05, | |
| "loss": 0.6772, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 1.2012012012012012e-05, | |
| "loss": 0.647, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 9.00900900900901e-06, | |
| "loss": 0.6837, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 6.006006006006006e-06, | |
| "loss": 0.6756, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 3.003003003003003e-06, | |
| "loss": 0.6959, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 0.0, | |
| "loss": 0.6147, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "eval_accuracy": 0.8206521739130435, | |
| "eval_loss": 0.6524847149848938, | |
| "eval_runtime": 53.3658, | |
| "eval_samples_per_second": 44.823, | |
| "eval_steps_per_second": 0.637, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "step": 740, | |
| "total_flos": 5.40401463321831e+18, | |
| "train_loss": 1.548523964753022, | |
| "train_runtime": 6742.5459, | |
| "train_samples_per_second": 31.917, | |
| "train_steps_per_second": 0.11 | |
| } | |
| ], | |
| "max_steps": 740, | |
| "num_train_epochs": 10, | |
| "total_flos": 5.40401463321831e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |