| { | |
| "best_metric": 0.9975817923186344, | |
| "best_model_checkpoint": "VitDisease/checkpoint-384", | |
| "epoch": 2.9960988296488944, | |
| "eval_steps": 500, | |
| "global_step": 576, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.620689655172414e-06, | |
| "loss": 3.6405, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.7241379310344828e-05, | |
| "loss": 3.5875, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.5862068965517244e-05, | |
| "loss": 3.4689, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.4482758620689657e-05, | |
| "loss": 3.29, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.3103448275862066e-05, | |
| "loss": 3.0405, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.980694980694981e-05, | |
| "loss": 2.7252, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.884169884169885e-05, | |
| "loss": 2.3972, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.787644787644788e-05, | |
| "loss": 2.1134, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.6911196911196914e-05, | |
| "loss": 1.8631, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.594594594594595e-05, | |
| "loss": 1.6843, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.498069498069498e-05, | |
| "loss": 1.5059, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.401544401544402e-05, | |
| "loss": 1.3564, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.305019305019305e-05, | |
| "loss": 1.2375, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.2084942084942086e-05, | |
| "loss": 1.1429, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.111969111969112e-05, | |
| "loss": 1.05, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.015444015444015e-05, | |
| "loss": 0.9708, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.918918918918919e-05, | |
| "loss": 0.9041, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.822393822393823e-05, | |
| "loss": 0.8441, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.725868725868726e-05, | |
| "loss": 0.7869, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9927453769559033, | |
| "eval_loss": 0.7515802979469299, | |
| "eval_runtime": 71.4706, | |
| "eval_samples_per_second": 98.362, | |
| "eval_steps_per_second": 1.539, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.6293436293436295e-05, | |
| "loss": 0.7364, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.532818532818533e-05, | |
| "loss": 0.6957, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.436293436293436e-05, | |
| "loss": 0.6565, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.33976833976834e-05, | |
| "loss": 0.6302, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.2432432432432436e-05, | |
| "loss": 0.5991, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.1467181467181466e-05, | |
| "loss": 0.5714, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.0501930501930504e-05, | |
| "loss": 0.5468, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.953667953667954e-05, | |
| "loss": 0.5258, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.5043, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.7606177606177608e-05, | |
| "loss": 0.4892, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.6640926640926645e-05, | |
| "loss": 0.4738, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.5675675675675675e-05, | |
| "loss": 0.4531, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.4710424710424712e-05, | |
| "loss": 0.4447, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.3745173745173746e-05, | |
| "loss": 0.4344, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.277992277992278e-05, | |
| "loss": 0.422, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.1814671814671817e-05, | |
| "loss": 0.4091, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.084942084942085e-05, | |
| "loss": 0.396, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.9884169884169884e-05, | |
| "loss": 0.3917, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.891891891891892e-05, | |
| "loss": 0.3828, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9975817923186344, | |
| "eval_loss": 0.3735862076282501, | |
| "eval_runtime": 71.8988, | |
| "eval_samples_per_second": 97.776, | |
| "eval_steps_per_second": 1.53, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.7953667953667955e-05, | |
| "loss": 0.3697, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.698841698841699e-05, | |
| "loss": 0.3584, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.6023166023166026e-05, | |
| "loss": 0.3505, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.505791505791506e-05, | |
| "loss": 0.3437, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.4092664092664093e-05, | |
| "loss": 0.3378, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.3127413127413127e-05, | |
| "loss": 0.3344, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.2162162162162164e-05, | |
| "loss": 0.3294, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.1196911196911197e-05, | |
| "loss": 0.3237, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 1.0231660231660233e-05, | |
| "loss": 0.3187, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.266409266409266e-06, | |
| "loss": 0.3173, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 8.301158301158302e-06, | |
| "loss": 0.3168, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.335907335907337e-06, | |
| "loss": 0.3132, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.370656370656371e-06, | |
| "loss": 0.3111, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.405405405405406e-06, | |
| "loss": 0.3061, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.4401544401544405e-06, | |
| "loss": 0.3077, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.474903474903475e-06, | |
| "loss": 0.3033, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.5096525096525096e-06, | |
| "loss": 0.3021, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.5444015444015445e-06, | |
| "loss": 0.3015, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 5.791505791505791e-07, | |
| "loss": 0.299, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9975817923186344, | |
| "eval_loss": 0.30786001682281494, | |
| "eval_runtime": 70.6316, | |
| "eval_samples_per_second": 99.531, | |
| "eval_steps_per_second": 1.557, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 576, | |
| "total_flos": 1.142879536778512e+19, | |
| "train_loss": 0.932237885064549, | |
| "train_runtime": 3472.3536, | |
| "train_samples_per_second": 42.512, | |
| "train_steps_per_second": 0.166 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 576, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1.142879536778512e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |