| { | |
| "best_metric": 0.9787037037037037, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-456", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 456, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06578947368421052, | |
| "grad_norm": 6.047317981719971, | |
| "learning_rate": 1.0869565217391305e-05, | |
| "loss": 2.3059, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 5.119813442230225, | |
| "learning_rate": 2.173913043478261e-05, | |
| "loss": 2.0868, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19736842105263158, | |
| "grad_norm": 8.138529777526855, | |
| "learning_rate": 3.260869565217392e-05, | |
| "loss": 1.5345, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 14.628665924072266, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 0.8696, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32894736842105265, | |
| "grad_norm": 14.560131072998047, | |
| "learning_rate": 4.951219512195122e-05, | |
| "loss": 0.6197, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 14.169949531555176, | |
| "learning_rate": 4.829268292682927e-05, | |
| "loss": 0.487, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4605263157894737, | |
| "grad_norm": 15.145587921142578, | |
| "learning_rate": 4.707317073170732e-05, | |
| "loss": 0.5187, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 14.87001895904541, | |
| "learning_rate": 4.585365853658537e-05, | |
| "loss": 0.4016, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5921052631578947, | |
| "grad_norm": 21.998821258544922, | |
| "learning_rate": 4.4634146341463416e-05, | |
| "loss": 0.3696, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6578947368421053, | |
| "grad_norm": 16.311429977416992, | |
| "learning_rate": 4.3414634146341465e-05, | |
| "loss": 0.3486, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7236842105263158, | |
| "grad_norm": 17.85744857788086, | |
| "learning_rate": 4.2195121951219514e-05, | |
| "loss": 0.3221, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 11.210858345031738, | |
| "learning_rate": 4.097560975609756e-05, | |
| "loss": 0.3001, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8552631578947368, | |
| "grad_norm": 14.170101165771484, | |
| "learning_rate": 3.975609756097561e-05, | |
| "loss": 0.2871, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9210526315789473, | |
| "grad_norm": 8.286581993103027, | |
| "learning_rate": 3.853658536585366e-05, | |
| "loss": 0.2954, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9868421052631579, | |
| "grad_norm": 8.435368537902832, | |
| "learning_rate": 3.731707317073171e-05, | |
| "loss": 0.2774, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9578703703703704, | |
| "eval_loss": 0.12819555401802063, | |
| "eval_runtime": 12.8415, | |
| "eval_samples_per_second": 168.205, | |
| "eval_steps_per_second": 5.295, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 11.784485816955566, | |
| "learning_rate": 3.609756097560976e-05, | |
| "loss": 0.2328, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.118421052631579, | |
| "grad_norm": 13.228792190551758, | |
| "learning_rate": 3.48780487804878e-05, | |
| "loss": 0.2462, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.1842105263157894, | |
| "grad_norm": 10.550958633422852, | |
| "learning_rate": 3.365853658536586e-05, | |
| "loss": 0.2399, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 5.997585296630859, | |
| "learning_rate": 3.2439024390243906e-05, | |
| "loss": 0.2252, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 8.08625602722168, | |
| "learning_rate": 3.1219512195121955e-05, | |
| "loss": 0.2357, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.381578947368421, | |
| "grad_norm": 17.572458267211914, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2258, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.4473684210526316, | |
| "grad_norm": 12.296513557434082, | |
| "learning_rate": 2.8780487804878046e-05, | |
| "loss": 0.2645, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.513157894736842, | |
| "grad_norm": 8.180034637451172, | |
| "learning_rate": 2.7560975609756102e-05, | |
| "loss": 0.2159, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 12.796661376953125, | |
| "learning_rate": 2.6341463414634148e-05, | |
| "loss": 0.2375, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.6447368421052633, | |
| "grad_norm": 10.516425132751465, | |
| "learning_rate": 2.5121951219512197e-05, | |
| "loss": 0.2049, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.7105263157894737, | |
| "grad_norm": 6.393877983093262, | |
| "learning_rate": 2.3902439024390243e-05, | |
| "loss": 0.211, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.776315789473684, | |
| "grad_norm": 9.698746681213379, | |
| "learning_rate": 2.2682926829268295e-05, | |
| "loss": 0.2134, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.8421052631578947, | |
| "grad_norm": 6.169530391693115, | |
| "learning_rate": 2.146341463414634e-05, | |
| "loss": 0.1787, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.9078947368421053, | |
| "grad_norm": 9.887014389038086, | |
| "learning_rate": 2.0243902439024393e-05, | |
| "loss": 0.1795, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.973684210526316, | |
| "grad_norm": 7.333874225616455, | |
| "learning_rate": 1.902439024390244e-05, | |
| "loss": 0.2199, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.975462962962963, | |
| "eval_loss": 0.07434366643428802, | |
| "eval_runtime": 12.8241, | |
| "eval_samples_per_second": 168.433, | |
| "eval_steps_per_second": 5.303, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 2.039473684210526, | |
| "grad_norm": 14.901606559753418, | |
| "learning_rate": 1.7804878048780488e-05, | |
| "loss": 0.1771, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 15.063396453857422, | |
| "learning_rate": 1.6585365853658537e-05, | |
| "loss": 0.1884, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.1710526315789473, | |
| "grad_norm": 11.021356582641602, | |
| "learning_rate": 1.5365853658536586e-05, | |
| "loss": 0.1874, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.236842105263158, | |
| "grad_norm": 12.141759872436523, | |
| "learning_rate": 1.4146341463414633e-05, | |
| "loss": 0.1737, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.3026315789473686, | |
| "grad_norm": 8.017112731933594, | |
| "learning_rate": 1.2926829268292684e-05, | |
| "loss": 0.1793, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.3684210526315788, | |
| "grad_norm": 8.373170852661133, | |
| "learning_rate": 1.1707317073170733e-05, | |
| "loss": 0.1863, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.4342105263157894, | |
| "grad_norm": 9.354153633117676, | |
| "learning_rate": 1.048780487804878e-05, | |
| "loss": 0.1579, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 8.749258041381836, | |
| "learning_rate": 9.26829268292683e-06, | |
| "loss": 0.1672, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.5657894736842106, | |
| "grad_norm": 8.372227668762207, | |
| "learning_rate": 8.048780487804879e-06, | |
| "loss": 0.1624, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 11.717450141906738, | |
| "learning_rate": 6.829268292682928e-06, | |
| "loss": 0.1826, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.6973684210526314, | |
| "grad_norm": 6.175394535064697, | |
| "learning_rate": 5.609756097560976e-06, | |
| "loss": 0.192, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.763157894736842, | |
| "grad_norm": 9.798537254333496, | |
| "learning_rate": 4.390243902439024e-06, | |
| "loss": 0.158, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.8289473684210527, | |
| "grad_norm": 7.753054141998291, | |
| "learning_rate": 3.1707317073170736e-06, | |
| "loss": 0.1463, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.8947368421052633, | |
| "grad_norm": 9.600172996520996, | |
| "learning_rate": 1.951219512195122e-06, | |
| "loss": 0.1926, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.9605263157894735, | |
| "grad_norm": 7.151966094970703, | |
| "learning_rate": 7.317073170731708e-07, | |
| "loss": 0.1356, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9787037037037037, | |
| "eval_loss": 0.06794986128807068, | |
| "eval_runtime": 13.1952, | |
| "eval_samples_per_second": 163.695, | |
| "eval_steps_per_second": 5.153, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 456, | |
| "total_flos": 1.4499253204608614e+18, | |
| "train_loss": 0.3743210191789426, | |
| "train_runtime": 869.999, | |
| "train_samples_per_second": 67.035, | |
| "train_steps_per_second": 0.524 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 456, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 1.4499253204608614e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |