| { | |
| "best_metric": 0.9994666666666666, | |
| "best_model_checkpoint": "plant-vit-model-1/checkpoint-332", | |
| "epoch": 10.0, | |
| "global_step": 830, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 6.024096385542169e-06, | |
| "loss": 2.6748, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.2048192771084338e-05, | |
| "loss": 2.5895, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.8072289156626505e-05, | |
| "loss": 2.4413, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.4096385542168677e-05, | |
| "loss": 2.2745, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.012048192771085e-05, | |
| "loss": 2.0245, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.614457831325301e-05, | |
| "loss": 1.7626, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.2168674698795186e-05, | |
| "loss": 1.5706, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.8192771084337354e-05, | |
| "loss": 1.296, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9226666666666666, | |
| "eval_loss": 1.0360676050186157, | |
| "eval_runtime": 28.5267, | |
| "eval_samples_per_second": 65.728, | |
| "eval_steps_per_second": 2.068, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.953145917001339e-05, | |
| "loss": 1.0868, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.886211512717537e-05, | |
| "loss": 0.8857, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 4.8192771084337354e-05, | |
| "loss": 0.8006, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 4.7523427041499336e-05, | |
| "loss": 0.6679, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.685408299866131e-05, | |
| "loss": 0.5875, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.61847389558233e-05, | |
| "loss": 0.5278, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 4.5515394912985275e-05, | |
| "loss": 0.4966, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 4.484605087014726e-05, | |
| "loss": 0.4476, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9904, | |
| "eval_loss": 0.3645952343940735, | |
| "eval_runtime": 27.9536, | |
| "eval_samples_per_second": 67.075, | |
| "eval_steps_per_second": 2.111, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.417670682730924e-05, | |
| "loss": 0.4392, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 4.350736278447122e-05, | |
| "loss": 0.381, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.2838018741633203e-05, | |
| "loss": 0.3494, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 4.2168674698795186e-05, | |
| "loss": 0.336, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.149933065595716e-05, | |
| "loss": 0.3078, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 4.082998661311915e-05, | |
| "loss": 0.3163, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 4.0160642570281125e-05, | |
| "loss": 0.2963, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.949129852744311e-05, | |
| "loss": 0.2731, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9952, | |
| "eval_loss": 0.21737419068813324, | |
| "eval_runtime": 27.9589, | |
| "eval_samples_per_second": 67.063, | |
| "eval_steps_per_second": 2.11, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.882195448460509e-05, | |
| "loss": 0.284, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 3.815261044176707e-05, | |
| "loss": 0.2695, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 3.748326639892905e-05, | |
| "loss": 0.2428, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 3.6813922356091035e-05, | |
| "loss": 0.239, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 3.614457831325301e-05, | |
| "loss": 0.2388, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 3.5475234270415e-05, | |
| "loss": 0.2138, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 3.4805890227576974e-05, | |
| "loss": 0.2001, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 3.413654618473896e-05, | |
| "loss": 0.2144, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 3.346720214190094e-05, | |
| "loss": 0.2097, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9994666666666666, | |
| "eval_loss": 0.15595677495002747, | |
| "eval_runtime": 27.9371, | |
| "eval_samples_per_second": 67.115, | |
| "eval_steps_per_second": 2.112, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 3.279785809906292e-05, | |
| "loss": 0.1877, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 3.21285140562249e-05, | |
| "loss": 0.1834, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 3.1459170013386885e-05, | |
| "loss": 0.1849, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 3.078982597054887e-05, | |
| "loss": 0.1581, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 3.012048192771085e-05, | |
| "loss": 0.1943, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 2.9451137884872827e-05, | |
| "loss": 0.1651, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 2.878179384203481e-05, | |
| "loss": 0.1896, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 2.8112449799196788e-05, | |
| "loss": 0.1679, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9973333333333333, | |
| "eval_loss": 0.12879624962806702, | |
| "eval_runtime": 27.9408, | |
| "eval_samples_per_second": 67.106, | |
| "eval_steps_per_second": 2.112, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 2.7443105756358774e-05, | |
| "loss": 0.1691, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 2.6773761713520752e-05, | |
| "loss": 0.1524, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 2.6104417670682734e-05, | |
| "loss": 0.1379, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 2.5435073627844713e-05, | |
| "loss": 0.1401, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 2.4765729585006695e-05, | |
| "loss": 0.1446, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 2.4096385542168677e-05, | |
| "loss": 0.1384, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 2.3427041499330656e-05, | |
| "loss": 0.1356, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 2.2757697456492638e-05, | |
| "loss": 0.135, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9984, | |
| "eval_loss": 0.10523158311843872, | |
| "eval_runtime": 27.794, | |
| "eval_samples_per_second": 67.461, | |
| "eval_steps_per_second": 2.123, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 2.208835341365462e-05, | |
| "loss": 0.135, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 2.1419009370816602e-05, | |
| "loss": 0.1418, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 2.074966532797858e-05, | |
| "loss": 0.1291, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 2.0080321285140562e-05, | |
| "loss": 0.1321, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 1.9410977242302544e-05, | |
| "loss": 0.1349, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 1.8741633199464527e-05, | |
| "loss": 0.1229, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 1.8072289156626505e-05, | |
| "loss": 0.1285, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 1.7402945113788487e-05, | |
| "loss": 0.1246, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 1.673360107095047e-05, | |
| "loss": 0.118, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9989333333333333, | |
| "eval_loss": 0.09175615012645721, | |
| "eval_runtime": 27.7375, | |
| "eval_samples_per_second": 67.598, | |
| "eval_steps_per_second": 2.127, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 1.606425702811245e-05, | |
| "loss": 0.1359, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 1.5394912985274433e-05, | |
| "loss": 0.1081, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 1.4725568942436414e-05, | |
| "loss": 0.1331, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 1.4056224899598394e-05, | |
| "loss": 0.1095, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 1.3386880856760376e-05, | |
| "loss": 0.1183, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 1.2717536813922356e-05, | |
| "loss": 0.1257, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 1.2048192771084338e-05, | |
| "loss": 0.1201, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 1.1378848728246319e-05, | |
| "loss": 0.1054, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9989333333333333, | |
| "eval_loss": 0.08257802575826645, | |
| "eval_runtime": 27.821, | |
| "eval_samples_per_second": 67.395, | |
| "eval_steps_per_second": 2.121, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 1.0709504685408301e-05, | |
| "loss": 0.0961, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 8.19, | |
| "learning_rate": 1.0040160642570281e-05, | |
| "loss": 0.1112, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 9.370816599732263e-06, | |
| "loss": 0.1009, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 8.701472556894244e-06, | |
| "loss": 0.0931, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.55, | |
| "learning_rate": 8.032128514056226e-06, | |
| "loss": 0.0987, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 7.362784471218207e-06, | |
| "loss": 0.1074, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 6.693440428380188e-06, | |
| "loss": 0.1096, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 6.024096385542169e-06, | |
| "loss": 0.1083, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9989333333333333, | |
| "eval_loss": 0.07765089720487595, | |
| "eval_runtime": 27.9635, | |
| "eval_samples_per_second": 67.052, | |
| "eval_steps_per_second": 2.11, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 5.3547523427041504e-06, | |
| "loss": 0.1025, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 4.685408299866132e-06, | |
| "loss": 0.0993, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 4.016064257028113e-06, | |
| "loss": 0.0878, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 3.346720214190094e-06, | |
| "loss": 0.1114, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 2.6773761713520752e-06, | |
| "loss": 0.1085, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 2.0080321285140564e-06, | |
| "loss": 0.0873, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 1.3386880856760376e-06, | |
| "loss": 0.1037, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 6.693440428380188e-07, | |
| "loss": 0.0947, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0918, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9994666666666666, | |
| "eval_loss": 0.07559256255626678, | |
| "eval_runtime": 27.9992, | |
| "eval_samples_per_second": 66.966, | |
| "eval_steps_per_second": 2.107, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 830, | |
| "total_flos": 8.232859423714222e+18, | |
| "train_loss": 0.4019865568861904, | |
| "train_runtime": 5542.9491, | |
| "train_samples_per_second": 19.165, | |
| "train_steps_per_second": 0.15 | |
| } | |
| ], | |
| "max_steps": 830, | |
| "num_train_epochs": 10, | |
| "total_flos": 8.232859423714222e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |