| { | |
| "best_metric": 0.9736111111111111, | |
| "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": 19.130762100219727, | |
| "learning_rate": 1.0869565217391305e-05, | |
| "loss": 9.2287, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 28.356334686279297, | |
| "learning_rate": 2.173913043478261e-05, | |
| "loss": 8.2697, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19736842105263158, | |
| "grad_norm": 43.25581359863281, | |
| "learning_rate": 3.260869565217392e-05, | |
| "loss": 6.458, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 74.04042053222656, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 3.6689, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32894736842105265, | |
| "grad_norm": 50.38246154785156, | |
| "learning_rate": 4.951219512195122e-05, | |
| "loss": 2.3498, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 136.82254028320312, | |
| "learning_rate": 4.829268292682927e-05, | |
| "loss": 1.7253, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4605263157894737, | |
| "grad_norm": 98.45024871826172, | |
| "learning_rate": 4.707317073170732e-05, | |
| "loss": 1.7736, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 53.86070251464844, | |
| "learning_rate": 4.585365853658537e-05, | |
| "loss": 1.4594, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5921052631578947, | |
| "grad_norm": 36.17530822753906, | |
| "learning_rate": 4.4634146341463416e-05, | |
| "loss": 1.4207, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6578947368421053, | |
| "grad_norm": 51.99091720581055, | |
| "learning_rate": 4.3414634146341465e-05, | |
| "loss": 1.3567, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7236842105263158, | |
| "grad_norm": 59.832359313964844, | |
| "learning_rate": 4.2195121951219514e-05, | |
| "loss": 1.0944, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 48.91640090942383, | |
| "learning_rate": 4.097560975609756e-05, | |
| "loss": 1.1952, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8552631578947368, | |
| "grad_norm": 49.09730911254883, | |
| "learning_rate": 3.975609756097561e-05, | |
| "loss": 1.0752, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9210526315789473, | |
| "grad_norm": 56.97904968261719, | |
| "learning_rate": 3.853658536585366e-05, | |
| "loss": 1.171, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9868421052631579, | |
| "grad_norm": 61.84169387817383, | |
| "learning_rate": 3.731707317073171e-05, | |
| "loss": 1.0835, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.961574074074074, | |
| "eval_loss": 0.12408532202243805, | |
| "eval_runtime": 23.8704, | |
| "eval_samples_per_second": 90.489, | |
| "eval_steps_per_second": 2.849, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 119.2465591430664, | |
| "learning_rate": 3.609756097560976e-05, | |
| "loss": 0.9341, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.118421052631579, | |
| "grad_norm": 45.94481658935547, | |
| "learning_rate": 3.48780487804878e-05, | |
| "loss": 1.0458, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.1842105263157894, | |
| "grad_norm": 64.04853820800781, | |
| "learning_rate": 3.365853658536586e-05, | |
| "loss": 1.032, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 39.62248992919922, | |
| "learning_rate": 3.2439024390243906e-05, | |
| "loss": 0.8917, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 35.72687911987305, | |
| "learning_rate": 3.1219512195121955e-05, | |
| "loss": 0.7558, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.381578947368421, | |
| "grad_norm": 38.77418899536133, | |
| "learning_rate": 3e-05, | |
| "loss": 1.014, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.4473684210526316, | |
| "grad_norm": 41.882259368896484, | |
| "learning_rate": 2.8780487804878046e-05, | |
| "loss": 0.9277, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.513157894736842, | |
| "grad_norm": 46.56316375732422, | |
| "learning_rate": 2.7560975609756102e-05, | |
| "loss": 0.8188, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 55.792503356933594, | |
| "learning_rate": 2.6341463414634148e-05, | |
| "loss": 0.8394, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.6447368421052633, | |
| "grad_norm": 39.2772102355957, | |
| "learning_rate": 2.5121951219512197e-05, | |
| "loss": 0.9707, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.7105263157894737, | |
| "grad_norm": 59.400936126708984, | |
| "learning_rate": 2.3902439024390243e-05, | |
| "loss": 0.7565, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.776315789473684, | |
| "grad_norm": 26.559144973754883, | |
| "learning_rate": 2.2682926829268295e-05, | |
| "loss": 0.6974, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.8421052631578947, | |
| "grad_norm": 64.35377502441406, | |
| "learning_rate": 2.146341463414634e-05, | |
| "loss": 0.8674, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.9078947368421053, | |
| "grad_norm": 44.48635482788086, | |
| "learning_rate": 2.0243902439024393e-05, | |
| "loss": 0.7541, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.973684210526316, | |
| "grad_norm": 23.366674423217773, | |
| "learning_rate": 1.902439024390244e-05, | |
| "loss": 0.8216, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9685185185185186, | |
| "eval_loss": 0.09182646870613098, | |
| "eval_runtime": 19.3046, | |
| "eval_samples_per_second": 111.89, | |
| "eval_steps_per_second": 3.522, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 2.039473684210526, | |
| "grad_norm": 53.47382736206055, | |
| "learning_rate": 1.7804878048780488e-05, | |
| "loss": 0.7464, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 23.642396926879883, | |
| "learning_rate": 1.6585365853658537e-05, | |
| "loss": 0.5975, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.1710526315789473, | |
| "grad_norm": 21.876237869262695, | |
| "learning_rate": 1.5365853658536586e-05, | |
| "loss": 0.7217, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.236842105263158, | |
| "grad_norm": 30.563919067382812, | |
| "learning_rate": 1.4146341463414633e-05, | |
| "loss": 0.5704, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.3026315789473686, | |
| "grad_norm": 32.48651885986328, | |
| "learning_rate": 1.2926829268292684e-05, | |
| "loss": 0.6577, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.3684210526315788, | |
| "grad_norm": 30.508432388305664, | |
| "learning_rate": 1.1707317073170733e-05, | |
| "loss": 0.634, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.4342105263157894, | |
| "grad_norm": 82.79277801513672, | |
| "learning_rate": 1.048780487804878e-05, | |
| "loss": 0.759, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 22.392250061035156, | |
| "learning_rate": 9.26829268292683e-06, | |
| "loss": 0.7746, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.5657894736842106, | |
| "grad_norm": 40.53355407714844, | |
| "learning_rate": 8.048780487804879e-06, | |
| "loss": 0.6761, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 27.02751350402832, | |
| "learning_rate": 6.829268292682928e-06, | |
| "loss": 0.5675, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.6973684210526314, | |
| "grad_norm": 35.39690017700195, | |
| "learning_rate": 5.609756097560976e-06, | |
| "loss": 0.6561, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.763157894736842, | |
| "grad_norm": 22.88880729675293, | |
| "learning_rate": 4.390243902439024e-06, | |
| "loss": 0.5784, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.8289473684210527, | |
| "grad_norm": 41.70180130004883, | |
| "learning_rate": 3.1707317073170736e-06, | |
| "loss": 0.6287, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.8947368421052633, | |
| "grad_norm": 29.4859676361084, | |
| "learning_rate": 1.951219512195122e-06, | |
| "loss": 0.576, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.9605263157894735, | |
| "grad_norm": 42.99224090576172, | |
| "learning_rate": 7.317073170731708e-07, | |
| "loss": 0.6378, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9736111111111111, | |
| "eval_loss": 0.07401751726865768, | |
| "eval_runtime": 21.0021, | |
| "eval_samples_per_second": 102.847, | |
| "eval_steps_per_second": 3.238, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 456, | |
| "total_flos": 1.4499253204608614e+18, | |
| "train_loss": 1.4615749057970548, | |
| "train_runtime": 1293.6814, | |
| "train_samples_per_second": 45.081, | |
| "train_steps_per_second": 0.352 | |
| } | |
| ], | |
| "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 | |
| } | |