| { | |
| "best_metric": 0.9796511627906976, | |
| "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": 6.976014614105225, | |
| "learning_rate": 9.615384615384616e-06, | |
| "loss": 2.6613, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03875968992248062, | |
| "grad_norm": 7.513162612915039, | |
| "learning_rate": 1.923076923076923e-05, | |
| "loss": 2.5144, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05813953488372093, | |
| "grad_norm": 8.978872299194336, | |
| "learning_rate": 2.8846153846153845e-05, | |
| "loss": 2.289, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07751937984496124, | |
| "grad_norm": 9.438762664794922, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 2.0166, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09689922480620156, | |
| "grad_norm": 13.305523872375488, | |
| "learning_rate": 4.8076923076923084e-05, | |
| "loss": 1.6406, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11627906976744186, | |
| "grad_norm": 13.694558143615723, | |
| "learning_rate": 4.913793103448276e-05, | |
| "loss": 1.1596, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13565891472868216, | |
| "grad_norm": 12.902932167053223, | |
| "learning_rate": 4.806034482758621e-05, | |
| "loss": 0.9728, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.15503875968992248, | |
| "grad_norm": 10.918025016784668, | |
| "learning_rate": 4.698275862068966e-05, | |
| "loss": 0.7231, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1744186046511628, | |
| "grad_norm": 11.306808471679688, | |
| "learning_rate": 4.590517241379311e-05, | |
| "loss": 0.6395, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1937984496124031, | |
| "grad_norm": 33.67359924316406, | |
| "learning_rate": 4.482758620689655e-05, | |
| "loss": 0.6615, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2131782945736434, | |
| "grad_norm": 10.94041919708252, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.5263, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.23255813953488372, | |
| "grad_norm": 10.666516304016113, | |
| "learning_rate": 4.267241379310345e-05, | |
| "loss": 0.4751, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.25193798449612403, | |
| "grad_norm": 10.321724891662598, | |
| "learning_rate": 4.1594827586206896e-05, | |
| "loss": 0.4072, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2713178294573643, | |
| "grad_norm": 11.352335929870605, | |
| "learning_rate": 4.0517241379310344e-05, | |
| "loss": 0.3549, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.29069767441860467, | |
| "grad_norm": 13.436570167541504, | |
| "learning_rate": 3.94396551724138e-05, | |
| "loss": 0.3766, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.31007751937984496, | |
| "grad_norm": 9.901206016540527, | |
| "learning_rate": 3.8362068965517246e-05, | |
| "loss": 0.3293, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.32945736434108525, | |
| "grad_norm": 7.431344985961914, | |
| "learning_rate": 3.7284482758620694e-05, | |
| "loss": 0.3218, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3488372093023256, | |
| "grad_norm": 11.188233375549316, | |
| "learning_rate": 3.620689655172414e-05, | |
| "loss": 0.2562, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3682170542635659, | |
| "grad_norm": 28.794321060180664, | |
| "learning_rate": 3.512931034482759e-05, | |
| "loss": 0.3317, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3875968992248062, | |
| "grad_norm": 12.812822341918945, | |
| "learning_rate": 3.405172413793103e-05, | |
| "loss": 0.333, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4069767441860465, | |
| "grad_norm": 15.580060958862305, | |
| "learning_rate": 3.297413793103448e-05, | |
| "loss": 0.3234, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4263565891472868, | |
| "grad_norm": 13.454980850219727, | |
| "learning_rate": 3.1896551724137935e-05, | |
| "loss": 0.2975, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.44573643410852715, | |
| "grad_norm": 10.901363372802734, | |
| "learning_rate": 3.081896551724138e-05, | |
| "loss": 0.2117, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "grad_norm": 4.9573493003845215, | |
| "learning_rate": 2.974137931034483e-05, | |
| "loss": 0.1921, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4844961240310077, | |
| "grad_norm": 10.217713356018066, | |
| "learning_rate": 2.866379310344828e-05, | |
| "loss": 0.1963, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5038759689922481, | |
| "grad_norm": 11.932710647583008, | |
| "learning_rate": 2.7586206896551727e-05, | |
| "loss": 0.2642, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5232558139534884, | |
| "grad_norm": 61.47119140625, | |
| "learning_rate": 2.650862068965517e-05, | |
| "loss": 0.2581, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5426356589147286, | |
| "grad_norm": 14.920116424560547, | |
| "learning_rate": 2.543103448275862e-05, | |
| "loss": 0.2522, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.562015503875969, | |
| "grad_norm": 9.092141151428223, | |
| "learning_rate": 2.435344827586207e-05, | |
| "loss": 0.2536, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.5813953488372093, | |
| "grad_norm": 9.711197853088379, | |
| "learning_rate": 2.327586206896552e-05, | |
| "loss": 0.1451, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6007751937984496, | |
| "grad_norm": 16.53685760498047, | |
| "learning_rate": 2.2198275862068967e-05, | |
| "loss": 0.19, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6201550387596899, | |
| "grad_norm": 13.619780540466309, | |
| "learning_rate": 2.1120689655172415e-05, | |
| "loss": 0.1973, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6395348837209303, | |
| "grad_norm": 14.635655403137207, | |
| "learning_rate": 2.0043103448275863e-05, | |
| "loss": 0.2135, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6589147286821705, | |
| "grad_norm": 10.346831321716309, | |
| "learning_rate": 1.896551724137931e-05, | |
| "loss": 0.1712, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6782945736434108, | |
| "grad_norm": 3.3771607875823975, | |
| "learning_rate": 1.7887931034482762e-05, | |
| "loss": 0.2015, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6976744186046512, | |
| "grad_norm": 9.400130271911621, | |
| "learning_rate": 1.6810344827586207e-05, | |
| "loss": 0.2124, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7170542635658915, | |
| "grad_norm": 6.391541957855225, | |
| "learning_rate": 1.5732758620689655e-05, | |
| "loss": 0.1983, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.7364341085271318, | |
| "grad_norm": 12.541404724121094, | |
| "learning_rate": 1.4655172413793103e-05, | |
| "loss": 0.1571, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7558139534883721, | |
| "grad_norm": 12.3185396194458, | |
| "learning_rate": 1.3577586206896553e-05, | |
| "loss": 0.1778, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7751937984496124, | |
| "grad_norm": 12.450446128845215, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.137, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7945736434108527, | |
| "grad_norm": 3.400618314743042, | |
| "learning_rate": 1.1422413793103449e-05, | |
| "loss": 0.149, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.813953488372093, | |
| "grad_norm": 3.4296200275421143, | |
| "learning_rate": 1.0344827586206897e-05, | |
| "loss": 0.1692, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 8.436596870422363, | |
| "learning_rate": 9.267241379310346e-06, | |
| "loss": 0.1282, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.8527131782945736, | |
| "grad_norm": 13.49636459350586, | |
| "learning_rate": 8.189655172413793e-06, | |
| "loss": 0.2076, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.872093023255814, | |
| "grad_norm": 12.991996765136719, | |
| "learning_rate": 7.112068965517242e-06, | |
| "loss": 0.1375, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.8914728682170543, | |
| "grad_norm": 8.396629333496094, | |
| "learning_rate": 6.03448275862069e-06, | |
| "loss": 0.1238, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9108527131782945, | |
| "grad_norm": 10.368714332580566, | |
| "learning_rate": 4.9568965517241384e-06, | |
| "loss": 0.1866, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "grad_norm": 10.175681114196777, | |
| "learning_rate": 3.8793103448275865e-06, | |
| "loss": 0.1286, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9496124031007752, | |
| "grad_norm": 10.659682273864746, | |
| "learning_rate": 2.8017241379310345e-06, | |
| "loss": 0.1754, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9689922480620154, | |
| "grad_norm": 8.461567878723145, | |
| "learning_rate": 1.724137931034483e-06, | |
| "loss": 0.1282, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9883720930232558, | |
| "grad_norm": 12.434035301208496, | |
| "learning_rate": 6.46551724137931e-07, | |
| "loss": 0.1394, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9796511627906976, | |
| "eval_loss": 0.05999711528420448, | |
| "eval_runtime": 43.7399, | |
| "eval_samples_per_second": 94.376, | |
| "eval_steps_per_second": 11.797, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 516, | |
| "total_flos": 5.373364651307827e+17, | |
| "train_loss": 0.4849770265494206, | |
| "train_runtime": 814.9685, | |
| "train_samples_per_second": 20.258, | |
| "train_steps_per_second": 0.633 | |
| } | |
| ], | |
| "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 | |
| } | |