| { | |
| "best_metric": 0.9777131782945736, | |
| "best_model_checkpoint": "swinv2-tiny-patch4-window16-256-finetuned-plantdisease/checkpoint-516", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 516, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01937984496124031, | |
| "grad_norm": 6.709539890289307, | |
| "learning_rate": 9.615384615384616e-06, | |
| "loss": 2.7078, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03875968992248062, | |
| "grad_norm": 7.255009651184082, | |
| "learning_rate": 1.923076923076923e-05, | |
| "loss": 2.5761, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05813953488372093, | |
| "grad_norm": 7.875271320343018, | |
| "learning_rate": 2.8846153846153845e-05, | |
| "loss": 2.331, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07751937984496124, | |
| "grad_norm": 9.543013572692871, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 2.1674, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09689922480620156, | |
| "grad_norm": 13.559645652770996, | |
| "learning_rate": 4.8076923076923084e-05, | |
| "loss": 1.7745, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11627906976744186, | |
| "grad_norm": 16.62691307067871, | |
| "learning_rate": 4.913793103448276e-05, | |
| "loss": 1.3937, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13565891472868216, | |
| "grad_norm": 15.683610916137695, | |
| "learning_rate": 4.806034482758621e-05, | |
| "loss": 1.0158, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.15503875968992248, | |
| "grad_norm": 14.473851203918457, | |
| "learning_rate": 4.698275862068966e-05, | |
| "loss": 0.8055, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1744186046511628, | |
| "grad_norm": 14.953446388244629, | |
| "learning_rate": 4.590517241379311e-05, | |
| "loss": 0.6449, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1937984496124031, | |
| "grad_norm": 11.831011772155762, | |
| "learning_rate": 4.482758620689655e-05, | |
| "loss": 0.6051, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2131782945736434, | |
| "grad_norm": 13.278793334960938, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.5566, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.23255813953488372, | |
| "grad_norm": 11.702147483825684, | |
| "learning_rate": 4.267241379310345e-05, | |
| "loss": 0.4845, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.25193798449612403, | |
| "grad_norm": 10.426274299621582, | |
| "learning_rate": 4.1594827586206896e-05, | |
| "loss": 0.3641, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2713178294573643, | |
| "grad_norm": 17.529104232788086, | |
| "learning_rate": 4.0517241379310344e-05, | |
| "loss": 0.3593, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.29069767441860467, | |
| "grad_norm": 12.532708168029785, | |
| "learning_rate": 3.94396551724138e-05, | |
| "loss": 0.3459, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.31007751937984496, | |
| "grad_norm": 16.44886589050293, | |
| "learning_rate": 3.8362068965517246e-05, | |
| "loss": 0.4475, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.32945736434108525, | |
| "grad_norm": 8.827244758605957, | |
| "learning_rate": 3.7284482758620694e-05, | |
| "loss": 0.3544, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3488372093023256, | |
| "grad_norm": 6.035519123077393, | |
| "learning_rate": 3.620689655172414e-05, | |
| "loss": 0.3214, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3682170542635659, | |
| "grad_norm": 7.568902969360352, | |
| "learning_rate": 3.512931034482759e-05, | |
| "loss": 0.2359, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3875968992248062, | |
| "grad_norm": 13.209157943725586, | |
| "learning_rate": 3.405172413793103e-05, | |
| "loss": 0.34, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4069767441860465, | |
| "grad_norm": 19.102611541748047, | |
| "learning_rate": 3.297413793103448e-05, | |
| "loss": 0.3697, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4263565891472868, | |
| "grad_norm": 12.98582649230957, | |
| "learning_rate": 3.1896551724137935e-05, | |
| "loss": 0.2864, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.44573643410852715, | |
| "grad_norm": 14.064764976501465, | |
| "learning_rate": 3.081896551724138e-05, | |
| "loss": 0.2606, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "grad_norm": 13.41550064086914, | |
| "learning_rate": 2.974137931034483e-05, | |
| "loss": 0.2949, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4844961240310077, | |
| "grad_norm": 7.437551498413086, | |
| "learning_rate": 2.866379310344828e-05, | |
| "loss": 0.1955, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5038759689922481, | |
| "grad_norm": 8.963953018188477, | |
| "learning_rate": 2.7586206896551727e-05, | |
| "loss": 0.2536, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5232558139534884, | |
| "grad_norm": 11.374913215637207, | |
| "learning_rate": 2.650862068965517e-05, | |
| "loss": 0.2592, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5426356589147286, | |
| "grad_norm": 7.7792768478393555, | |
| "learning_rate": 2.543103448275862e-05, | |
| "loss": 0.2024, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.562015503875969, | |
| "grad_norm": 14.774372100830078, | |
| "learning_rate": 2.435344827586207e-05, | |
| "loss": 0.228, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.5813953488372093, | |
| "grad_norm": 8.32029914855957, | |
| "learning_rate": 2.327586206896552e-05, | |
| "loss": 0.1849, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6007751937984496, | |
| "grad_norm": 14.661565780639648, | |
| "learning_rate": 2.2198275862068967e-05, | |
| "loss": 0.1835, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6201550387596899, | |
| "grad_norm": 15.804061889648438, | |
| "learning_rate": 2.1120689655172415e-05, | |
| "loss": 0.1828, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6395348837209303, | |
| "grad_norm": 19.60464859008789, | |
| "learning_rate": 2.0043103448275863e-05, | |
| "loss": 0.1874, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6589147286821705, | |
| "grad_norm": 5.921483516693115, | |
| "learning_rate": 1.896551724137931e-05, | |
| "loss": 0.1741, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6782945736434108, | |
| "grad_norm": 8.562132835388184, | |
| "learning_rate": 1.7887931034482762e-05, | |
| "loss": 0.2541, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6976744186046512, | |
| "grad_norm": 7.037123680114746, | |
| "learning_rate": 1.6810344827586207e-05, | |
| "loss": 0.2101, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7170542635658915, | |
| "grad_norm": 4.712380886077881, | |
| "learning_rate": 1.5732758620689655e-05, | |
| "loss": 0.2088, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.7364341085271318, | |
| "grad_norm": 5.721762180328369, | |
| "learning_rate": 1.4655172413793103e-05, | |
| "loss": 0.2245, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7558139534883721, | |
| "grad_norm": 8.76972484588623, | |
| "learning_rate": 1.3577586206896553e-05, | |
| "loss": 0.1713, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7751937984496124, | |
| "grad_norm": 8.067720413208008, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.1822, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7945736434108527, | |
| "grad_norm": 8.3314208984375, | |
| "learning_rate": 1.1422413793103449e-05, | |
| "loss": 0.1781, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.813953488372093, | |
| "grad_norm": 22.368515014648438, | |
| "learning_rate": 1.0344827586206897e-05, | |
| "loss": 0.1921, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 11.097426414489746, | |
| "learning_rate": 9.267241379310346e-06, | |
| "loss": 0.1627, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.8527131782945736, | |
| "grad_norm": 20.73263168334961, | |
| "learning_rate": 8.189655172413793e-06, | |
| "loss": 0.1884, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.872093023255814, | |
| "grad_norm": 2.5283663272857666, | |
| "learning_rate": 7.112068965517242e-06, | |
| "loss": 0.2005, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.8914728682170543, | |
| "grad_norm": 4.581237316131592, | |
| "learning_rate": 6.03448275862069e-06, | |
| "loss": 0.1945, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9108527131782945, | |
| "grad_norm": 4.513861656188965, | |
| "learning_rate": 4.9568965517241384e-06, | |
| "loss": 0.1427, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "grad_norm": 13.439146041870117, | |
| "learning_rate": 3.8793103448275865e-06, | |
| "loss": 0.1233, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9496124031007752, | |
| "grad_norm": 9.163981437683105, | |
| "learning_rate": 2.8017241379310345e-06, | |
| "loss": 0.1171, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9689922480620154, | |
| "grad_norm": 6.725685119628906, | |
| "learning_rate": 1.724137931034483e-06, | |
| "loss": 0.2016, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9883720930232558, | |
| "grad_norm": 5.155745029449463, | |
| "learning_rate": 6.46551724137931e-07, | |
| "loss": 0.103, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9777131782945736, | |
| "eval_loss": 0.06364382058382034, | |
| "eval_runtime": 43.5867, | |
| "eval_samples_per_second": 94.708, | |
| "eval_steps_per_second": 11.838, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 516, | |
| "total_flos": 5.373364651307827e+17, | |
| "train_loss": 0.5084914574327395, | |
| "train_runtime": 598.2279, | |
| "train_samples_per_second": 27.598, | |
| "train_steps_per_second": 0.863 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 516, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.373364651307827e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |