| { | |
| "best_metric": 0.834983498349835, | |
| "best_model_checkpoint": "vit-base-patch16-224-finetuned-eurosat/checkpoint-798", | |
| "epoch": 2.9943714821763603, | |
| "eval_steps": 500, | |
| "global_step": 798, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 6.25e-06, | |
| "loss": 4.7733, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.25e-05, | |
| "loss": 4.7021, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 4.6191, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.5e-05, | |
| "loss": 4.487, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.125e-05, | |
| "loss": 4.2957, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 4.0441, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.375e-05, | |
| "loss": 3.7251, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3993, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.930362116991643e-05, | |
| "loss": 3.0075, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.860724233983287e-05, | |
| "loss": 2.6314, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.79108635097493e-05, | |
| "loss": 2.4011, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.721448467966574e-05, | |
| "loss": 2.1461, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.6518105849582176e-05, | |
| "loss": 1.9426, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.582172701949861e-05, | |
| "loss": 1.8008, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.5125348189415044e-05, | |
| "loss": 1.6983, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.442896935933148e-05, | |
| "loss": 1.6476, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.373259052924791e-05, | |
| "loss": 1.4829, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.303621169916435e-05, | |
| "loss": 1.4473, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.233983286908078e-05, | |
| "loss": 1.3767, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.164345403899722e-05, | |
| "loss": 1.2828, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.094707520891365e-05, | |
| "loss": 1.3095, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.0250696378830085e-05, | |
| "loss": 1.2064, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.955431754874652e-05, | |
| "loss": 1.1614, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.885793871866296e-05, | |
| "loss": 1.2123, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.816155988857939e-05, | |
| "loss": 1.1367, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.746518105849583e-05, | |
| "loss": 1.0954, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7898349834983498, | |
| "eval_loss": 0.9450869560241699, | |
| "eval_runtime": 67.1006, | |
| "eval_samples_per_second": 112.89, | |
| "eval_steps_per_second": 1.773, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.676880222841226e-05, | |
| "loss": 1.091, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.607242339832869e-05, | |
| "loss": 1.0539, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.5376044568245126e-05, | |
| "loss": 1.035, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.4679665738161556e-05, | |
| "loss": 0.9419, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.3983286908077994e-05, | |
| "loss": 1.0054, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.328690807799443e-05, | |
| "loss": 1.0022, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.259052924791087e-05, | |
| "loss": 0.9334, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.18941504178273e-05, | |
| "loss": 0.9022, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.1197771587743737e-05, | |
| "loss": 0.8882, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.050139275766017e-05, | |
| "loss": 0.9736, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.98050139275766e-05, | |
| "loss": 0.9085, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.9108635097493035e-05, | |
| "loss": 0.9588, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.841225626740947e-05, | |
| "loss": 0.9093, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.7715877437325903e-05, | |
| "loss": 0.8688, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.7019498607242337e-05, | |
| "loss": 0.8283, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.6323119777158778e-05, | |
| "loss": 0.886, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.562674094707521e-05, | |
| "loss": 0.9259, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.4930362116991646e-05, | |
| "loss": 0.8334, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.423398328690808e-05, | |
| "loss": 0.8748, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.3537604456824514e-05, | |
| "loss": 0.8367, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.2841225626740948e-05, | |
| "loss": 0.8054, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.214484679665738e-05, | |
| "loss": 0.85, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.144846796657382e-05, | |
| "loss": 0.85, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.0752089136490253e-05, | |
| "loss": 0.8617, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.0055710306406687e-05, | |
| "loss": 0.8337, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.935933147632312e-05, | |
| "loss": 0.8182, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.8662952646239558e-05, | |
| "loss": 0.8207, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8281188118811881, | |
| "eval_loss": 0.7111164331436157, | |
| "eval_runtime": 66.016, | |
| "eval_samples_per_second": 114.745, | |
| "eval_steps_per_second": 1.803, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.7966573816155992e-05, | |
| "loss": 0.7639, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.7270194986072426e-05, | |
| "loss": 0.7439, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.6573816155988857e-05, | |
| "loss": 0.7358, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.587743732590529e-05, | |
| "loss": 0.7454, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.518105849582173e-05, | |
| "loss": 0.7533, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.4484679665738164e-05, | |
| "loss": 0.7898, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.3788300835654596e-05, | |
| "loss": 0.734, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.309192200557103e-05, | |
| "loss": 0.793, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.2395543175487466e-05, | |
| "loss": 0.7409, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.16991643454039e-05, | |
| "loss": 0.7768, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.1002785515320335e-05, | |
| "loss": 0.7306, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 1.0306406685236769e-05, | |
| "loss": 0.7125, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 9.610027855153205e-06, | |
| "loss": 0.7176, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 8.913649025069639e-06, | |
| "loss": 0.7669, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 8.217270194986073e-06, | |
| "loss": 0.7372, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.5208913649025075e-06, | |
| "loss": 0.7574, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.8245125348189415e-06, | |
| "loss": 0.7493, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 6.128133704735376e-06, | |
| "loss": 0.7554, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.43175487465181e-06, | |
| "loss": 0.7465, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.735376044568245e-06, | |
| "loss": 0.7608, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.03899721448468e-06, | |
| "loss": 0.7534, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.3426183844011147e-06, | |
| "loss": 0.7744, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.6462395543175487e-06, | |
| "loss": 0.7158, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.9498607242339835e-06, | |
| "loss": 0.7324, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.253481894150418e-06, | |
| "loss": 0.749, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 5.571030640668524e-07, | |
| "loss": 0.771, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.834983498349835, | |
| "eval_loss": 0.6656444668769836, | |
| "eval_runtime": 66.6691, | |
| "eval_samples_per_second": 113.621, | |
| "eval_steps_per_second": 1.785, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "step": 798, | |
| "total_flos": 1.5837129276562944e+19, | |
| "train_loss": 1.3612600884640724, | |
| "train_runtime": 3195.3608, | |
| "train_samples_per_second": 64.007, | |
| "train_steps_per_second": 0.25 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 798, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1.5837129276562944e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |