| { | |
| "best_metric": 0.6859849540261911, | |
| "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-FER-5e-05-3/checkpoint-672", | |
| "epoch": 2.997772828507795, | |
| "global_step": 672, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.3529411764705884e-06, | |
| "loss": 1.9779, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.4705882352941177e-05, | |
| "loss": 1.7879, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.2058823529411766e-05, | |
| "loss": 1.6926, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 1.5514, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.6764705882352945e-05, | |
| "loss": 1.4553, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.411764705882353e-05, | |
| "loss": 1.3886, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.983443708609272e-05, | |
| "loss": 1.3704, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.900662251655629e-05, | |
| "loss": 1.3282, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.8178807947019873e-05, | |
| "loss": 1.3225, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.735099337748345e-05, | |
| "loss": 1.3088, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.652317880794702e-05, | |
| "loss": 1.2985, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.56953642384106e-05, | |
| "loss": 1.2617, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.4867549668874174e-05, | |
| "loss": 1.2069, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.403973509933775e-05, | |
| "loss": 1.3025, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.321192052980133e-05, | |
| "loss": 1.2373, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.23841059602649e-05, | |
| "loss": 1.2601, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.155629139072848e-05, | |
| "loss": 1.2049, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.0728476821192055e-05, | |
| "loss": 1.1789, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.990066225165563e-05, | |
| "loss": 1.1893, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.907284768211921e-05, | |
| "loss": 1.1995, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.824503311258278e-05, | |
| "loss": 1.1578, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.741721854304636e-05, | |
| "loss": 1.1566, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6310950125383115, | |
| "eval_loss": 0.983033299446106, | |
| "eval_runtime": 63.2135, | |
| "eval_samples_per_second": 113.552, | |
| "eval_steps_per_second": 3.559, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.6589403973509936e-05, | |
| "loss": 1.203, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.576158940397351e-05, | |
| "loss": 1.1033, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.493377483443709e-05, | |
| "loss": 1.1168, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.410596026490066e-05, | |
| "loss": 1.1488, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.3278145695364236e-05, | |
| "loss": 1.1506, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.2450331125827816e-05, | |
| "loss": 1.1466, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.162251655629139e-05, | |
| "loss": 1.1541, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.079470198675497e-05, | |
| "loss": 1.0784, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.9966887417218544e-05, | |
| "loss": 1.1244, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.913907284768212e-05, | |
| "loss": 1.1782, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.8311258278145697e-05, | |
| "loss": 1.0317, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.7483443708609274e-05, | |
| "loss": 1.0463, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.6655629139072848e-05, | |
| "loss": 1.0926, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.5827814569536424e-05, | |
| "loss": 1.049, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.086, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.4172185430463578e-05, | |
| "loss": 1.133, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.3344370860927155e-05, | |
| "loss": 1.114, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.2516556291390732e-05, | |
| "loss": 1.052, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.1688741721854305e-05, | |
| "loss": 1.0361, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.0860927152317882e-05, | |
| "loss": 1.1056, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.003311258278146e-05, | |
| "loss": 1.0433, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.9205298013245036e-05, | |
| "loss": 1.0301, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6730286988018946, | |
| "eval_loss": 0.893949568271637, | |
| "eval_runtime": 68.4812, | |
| "eval_samples_per_second": 104.817, | |
| "eval_steps_per_second": 3.286, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.837748344370861e-05, | |
| "loss": 1.0772, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.7549668874172186e-05, | |
| "loss": 1.0201, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.6721854304635763e-05, | |
| "loss": 1.059, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.589403973509934e-05, | |
| "loss": 1.0124, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.5066225165562913e-05, | |
| "loss": 1.0423, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.4238410596026492e-05, | |
| "loss": 1.0075, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.3410596026490067e-05, | |
| "loss": 1.0121, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.2582781456953644e-05, | |
| "loss": 1.0227, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.1754966887417219e-05, | |
| "loss": 1.0459, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.0927152317880796e-05, | |
| "loss": 1.0092, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.0099337748344372e-05, | |
| "loss": 0.9953, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.271523178807948e-06, | |
| "loss": 1.0551, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 8.443708609271524e-06, | |
| "loss": 1.0081, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.6158940397350995e-06, | |
| "loss": 1.0273, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.7880794701986755e-06, | |
| "loss": 1.0192, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 5.9602649006622515e-06, | |
| "loss": 1.0455, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 5.1324503311258275e-06, | |
| "loss": 1.0254, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 4.304635761589404e-06, | |
| "loss": 0.9835, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.47682119205298e-06, | |
| "loss": 0.9875, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.6490066225165563e-06, | |
| "loss": 0.9708, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.8211920529801325e-06, | |
| "loss": 0.9624, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 9.933774834437087e-07, | |
| "loss": 1.0394, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.6556291390728477e-07, | |
| "loss": 0.991, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6859849540261911, | |
| "eval_loss": 0.8598430752754211, | |
| "eval_runtime": 66.2708, | |
| "eval_samples_per_second": 108.313, | |
| "eval_steps_per_second": 3.395, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 672, | |
| "total_flos": 6.668732964123095e+18, | |
| "train_loss": 1.15604233954634, | |
| "train_runtime": 2196.8246, | |
| "train_samples_per_second": 39.205, | |
| "train_steps_per_second": 0.306 | |
| } | |
| ], | |
| "max_steps": 672, | |
| "num_train_epochs": 3, | |
| "total_flos": 6.668732964123095e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |