| { | |
| "best_metric": 0.6862635831707997, | |
| "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013-7e-05/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": 1.0294117647058823e-05, | |
| "loss": 1.9001, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2.0588235294117645e-05, | |
| "loss": 1.7513, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 3.088235294117647e-05, | |
| "loss": 1.6223, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.117647058823529e-05, | |
| "loss": 1.5127, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 5.147058823529412e-05, | |
| "loss": 1.414, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 6.176470588235294e-05, | |
| "loss": 1.3549, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.976821192052979e-05, | |
| "loss": 1.3773, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 6.86092715231788e-05, | |
| "loss": 1.2798, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 6.74503311258278e-05, | |
| "loss": 1.2661, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 6.629139072847681e-05, | |
| "loss": 1.3509, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 6.513245033112582e-05, | |
| "loss": 1.3001, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 6.397350993377483e-05, | |
| "loss": 1.2536, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 6.281456953642384e-05, | |
| "loss": 1.1808, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.165562913907283e-05, | |
| "loss": 1.2998, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 6.049668874172185e-05, | |
| "loss": 1.232, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.933774834437086e-05, | |
| "loss": 1.2809, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 5.8178807947019866e-05, | |
| "loss": 1.2072, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 5.7019867549668874e-05, | |
| "loss": 1.2004, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 5.5860927152317876e-05, | |
| "loss": 1.2, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.4701986754966884e-05, | |
| "loss": 1.2034, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 5.354304635761589e-05, | |
| "loss": 1.1671, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 5.23841059602649e-05, | |
| "loss": 1.1607, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6238506547784898, | |
| "eval_loss": 1.0028917789459229, | |
| "eval_runtime": 64.6131, | |
| "eval_samples_per_second": 111.092, | |
| "eval_steps_per_second": 3.482, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 5.12251655629139e-05, | |
| "loss": 1.2012, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 5.006622516556291e-05, | |
| "loss": 1.099, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.890728476821192e-05, | |
| "loss": 1.1241, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.7748344370860927e-05, | |
| "loss": 1.1595, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.658940397350993e-05, | |
| "loss": 1.1434, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.5430463576158936e-05, | |
| "loss": 1.1487, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 4.4271523178807944e-05, | |
| "loss": 1.1553, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 4.311258278145695e-05, | |
| "loss": 1.075, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 4.1953642384105954e-05, | |
| "loss": 1.1167, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 4.079470198675496e-05, | |
| "loss": 1.1692, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 3.963576158940397e-05, | |
| "loss": 1.0329, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 3.847682119205298e-05, | |
| "loss": 1.0411, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 3.731788079470198e-05, | |
| "loss": 1.0907, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 3.615894039735099e-05, | |
| "loss": 1.0668, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.0787, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 3.3841059602649005e-05, | |
| "loss": 1.1329, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.2682119205298013e-05, | |
| "loss": 1.1198, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.152317880794702e-05, | |
| "loss": 1.0488, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.0364238410596023e-05, | |
| "loss": 1.0372, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.920529801324503e-05, | |
| "loss": 1.1048, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.8046357615894036e-05, | |
| "loss": 1.0333, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.6887417218543045e-05, | |
| "loss": 1.0262, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6611869601560323, | |
| "eval_loss": 0.908954381942749, | |
| "eval_runtime": 68.0669, | |
| "eval_samples_per_second": 105.455, | |
| "eval_steps_per_second": 3.306, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.572847682119205e-05, | |
| "loss": 1.0595, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.4569536423841058e-05, | |
| "loss": 1.0029, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.3410596026490062e-05, | |
| "loss": 1.0359, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 2.225165562913907e-05, | |
| "loss": 1.0081, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.1092715231788076e-05, | |
| "loss": 1.0402, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.9933774834437084e-05, | |
| "loss": 0.9973, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.877483443708609e-05, | |
| "loss": 0.994, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.7615894039735097e-05, | |
| "loss": 1.0113, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.6456953642384105e-05, | |
| "loss": 1.03, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.529801324503311e-05, | |
| "loss": 0.9968, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.4139072847682118e-05, | |
| "loss": 0.9676, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 1.2980132450331125e-05, | |
| "loss": 1.0599, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 1.1821192052980131e-05, | |
| "loss": 1.0016, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 1.0662251655629138e-05, | |
| "loss": 1.0137, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 9.503311258278145e-06, | |
| "loss": 1.0053, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 8.344370860927151e-06, | |
| "loss": 1.0308, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 7.1854304635761585e-06, | |
| "loss": 1.0103, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 6.026490066225165e-06, | |
| "loss": 0.9795, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 4.867549668874172e-06, | |
| "loss": 0.9804, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 3.7086092715231786e-06, | |
| "loss": 0.9553, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.549668874172185e-06, | |
| "loss": 0.9442, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.390728476821192e-06, | |
| "loss": 1.0215, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2.3178807947019866e-07, | |
| "loss": 0.9666, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6862635831707997, | |
| "eval_loss": 0.8496666550636292, | |
| "eval_runtime": 64.1194, | |
| "eval_samples_per_second": 111.947, | |
| "eval_steps_per_second": 3.509, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 672, | |
| "total_flos": 6.668732964123095e+18, | |
| "train_loss": 1.1464171437990098, | |
| "train_runtime": 2129.0691, | |
| "train_samples_per_second": 40.453, | |
| "train_steps_per_second": 0.316 | |
| } | |
| ], | |
| "max_steps": 672, | |
| "num_train_epochs": 3, | |
| "total_flos": 6.668732964123095e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |