| { | |
| "best_metric": 0.6862635831707997, | |
| "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013-6e-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": 8.823529411764707e-06, | |
| "loss": 1.9374, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 1.7641, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.647058823529412e-05, | |
| "loss": 1.6103, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 1.4851, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.411764705882353e-05, | |
| "loss": 1.3986, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 5.294117647058824e-05, | |
| "loss": 1.3845, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 5.980132450331126e-05, | |
| "loss": 1.3898, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 5.880794701986755e-05, | |
| "loss": 1.3012, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 5.781456953642385e-05, | |
| "loss": 1.2911, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 5.682119205298013e-05, | |
| "loss": 1.312, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 5.582781456953642e-05, | |
| "loss": 1.2558, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 5.483443708609272e-05, | |
| "loss": 1.2446, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.384105960264901e-05, | |
| "loss": 1.1917, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 5.2847682119205294e-05, | |
| "loss": 1.2931, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.185430463576159e-05, | |
| "loss": 1.2252, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 5.086092715231788e-05, | |
| "loss": 1.3132, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.9867549668874174e-05, | |
| "loss": 1.2186, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.887417218543047e-05, | |
| "loss": 1.1821, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.7880794701986755e-05, | |
| "loss": 1.2076, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.6887417218543046e-05, | |
| "loss": 1.1957, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.589403973509934e-05, | |
| "loss": 1.1563, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 4.4900662251655635e-05, | |
| "loss": 1.1611, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6277514628030092, | |
| "eval_loss": 0.9903648495674133, | |
| "eval_runtime": 66.7287, | |
| "eval_samples_per_second": 107.57, | |
| "eval_steps_per_second": 3.372, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.390728476821192e-05, | |
| "loss": 1.2077, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.291390728476821e-05, | |
| "loss": 1.111, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.192052980132451e-05, | |
| "loss": 1.1273, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.09271523178808e-05, | |
| "loss": 1.1433, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.993377483443708e-05, | |
| "loss": 1.1409, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.894039735099338e-05, | |
| "loss": 1.1376, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.794701986754967e-05, | |
| "loss": 1.148, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.695364238410596e-05, | |
| "loss": 1.0761, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 3.596026490066225e-05, | |
| "loss": 1.1272, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 3.496688741721854e-05, | |
| "loss": 1.166, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 3.3973509933774834e-05, | |
| "loss": 1.0301, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 3.298013245033113e-05, | |
| "loss": 1.0463, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 3.1986754966887416e-05, | |
| "loss": 1.094, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 3.0993377483443707e-05, | |
| "loss": 1.0588, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0785, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.9006622516556295e-05, | |
| "loss": 1.1287, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.8013245033112582e-05, | |
| "loss": 1.123, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.7019867549668877e-05, | |
| "loss": 1.0555, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.6026490066225168e-05, | |
| "loss": 1.0518, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.503311258278146e-05, | |
| "loss": 1.1031, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.403973509933775e-05, | |
| "loss": 1.032, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.304635761589404e-05, | |
| "loss": 1.0324, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6666202284758985, | |
| "eval_loss": 0.9066485166549683, | |
| "eval_runtime": 61.9286, | |
| "eval_samples_per_second": 115.908, | |
| "eval_steps_per_second": 3.633, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.205298013245033e-05, | |
| "loss": 1.0672, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.1059602649006625e-05, | |
| "loss": 1.0094, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.0066225165562913e-05, | |
| "loss": 1.0612, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.9072847682119207e-05, | |
| "loss": 1.0056, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.8079470198675498e-05, | |
| "loss": 1.0377, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.708609271523179e-05, | |
| "loss": 1.0198, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.609271523178808e-05, | |
| "loss": 1.0134, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.5099337748344372e-05, | |
| "loss": 1.0194, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.4105960264900663e-05, | |
| "loss": 1.0323, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.3112582781456954e-05, | |
| "loss": 1.0017, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.2119205298013246e-05, | |
| "loss": 0.9889, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 1.1125827814569537e-05, | |
| "loss": 1.0433, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 1.0132450331125828e-05, | |
| "loss": 1.0061, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 9.139072847682119e-06, | |
| "loss": 1.0194, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 8.145695364238411e-06, | |
| "loss": 1.0129, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 7.152317880794702e-06, | |
| "loss": 1.031, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 6.158940397350993e-06, | |
| "loss": 1.017, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 5.165562913907285e-06, | |
| "loss": 0.9918, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 4.1721854304635756e-06, | |
| "loss": 0.9918, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 3.1788079470198677e-06, | |
| "loss": 0.9709, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.185430463576159e-06, | |
| "loss": 0.9588, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.1920529801324504e-06, | |
| "loss": 1.0307, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.9867549668874173e-07, | |
| "loss": 0.9725, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6862635831707997, | |
| "eval_loss": 0.8550847768783569, | |
| "eval_runtime": 69.639, | |
| "eval_samples_per_second": 103.074, | |
| "eval_steps_per_second": 3.231, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 672, | |
| "total_flos": 6.668732964123095e+18, | |
| "train_loss": 1.149514797897566, | |
| "train_runtime": 2108.5862, | |
| "train_samples_per_second": 40.846, | |
| "train_steps_per_second": 0.319 | |
| } | |
| ], | |
| "max_steps": 672, | |
| "num_train_epochs": 3, | |
| "total_flos": 6.668732964123095e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |