| { | |
| "best_global_step": 570, | |
| "best_metric": 0.9829629629629629, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-570", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 570, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 4.065399646759033, | |
| "learning_rate": 7.894736842105263e-06, | |
| "loss": 2.2613, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 5.319888114929199, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 2.01, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 6.084249496459961, | |
| "learning_rate": 2.5438596491228074e-05, | |
| "loss": 1.5179, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 7.026301860809326, | |
| "learning_rate": 3.421052631578947e-05, | |
| "loss": 0.8649, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 11.555365562438965, | |
| "learning_rate": 4.298245614035088e-05, | |
| "loss": 0.4874, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 17.860612869262695, | |
| "learning_rate": 4.980506822612086e-05, | |
| "loss": 0.3923, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 26.220460891723633, | |
| "learning_rate": 4.883040935672515e-05, | |
| "loss": 0.3607, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 11.298727035522461, | |
| "learning_rate": 4.7855750487329435e-05, | |
| "loss": 0.2858, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 13.609187126159668, | |
| "learning_rate": 4.6881091617933726e-05, | |
| "loss": 0.3207, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 10.572683334350586, | |
| "learning_rate": 4.590643274853802e-05, | |
| "loss": 0.2541, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 10.712231636047363, | |
| "learning_rate": 4.49317738791423e-05, | |
| "loss": 0.2205, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 8.657620429992676, | |
| "learning_rate": 4.395711500974659e-05, | |
| "loss": 0.1989, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 8.740941047668457, | |
| "learning_rate": 4.298245614035088e-05, | |
| "loss": 0.2312, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 9.41290283203125, | |
| "learning_rate": 4.200779727095517e-05, | |
| "loss": 0.2229, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 15.130921363830566, | |
| "learning_rate": 4.103313840155946e-05, | |
| "loss": 0.1919, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 10.599325180053711, | |
| "learning_rate": 4.005847953216375e-05, | |
| "loss": 0.2044, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 6.5861968994140625, | |
| "learning_rate": 3.908382066276803e-05, | |
| "loss": 0.2228, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 11.306436538696289, | |
| "learning_rate": 3.8109161793372323e-05, | |
| "loss": 0.1981, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 7.8563456535339355, | |
| "learning_rate": 3.713450292397661e-05, | |
| "loss": 0.2157, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9703703703703703, | |
| "eval_loss": 0.0875425785779953, | |
| "eval_runtime": 4.4626, | |
| "eval_samples_per_second": 605.031, | |
| "eval_steps_per_second": 19.047, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 13.41629409790039, | |
| "learning_rate": 3.61598440545809e-05, | |
| "loss": 0.201, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.1052631578947367, | |
| "grad_norm": 4.426482200622559, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.1957, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.1578947368421053, | |
| "grad_norm": 9.049041748046875, | |
| "learning_rate": 3.421052631578947e-05, | |
| "loss": 0.2389, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2105263157894737, | |
| "grad_norm": 5.128701686859131, | |
| "learning_rate": 3.3235867446393764e-05, | |
| "loss": 0.1702, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 7.488633632659912, | |
| "learning_rate": 3.2261208576998055e-05, | |
| "loss": 0.2236, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 9.638894081115723, | |
| "learning_rate": 3.128654970760234e-05, | |
| "loss": 0.2388, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.368421052631579, | |
| "grad_norm": 8.79790210723877, | |
| "learning_rate": 3.031189083820663e-05, | |
| "loss": 0.1877, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.4210526315789473, | |
| "grad_norm": 7.657425403594971, | |
| "learning_rate": 2.9337231968810917e-05, | |
| "loss": 0.1457, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 5.015496253967285, | |
| "learning_rate": 2.8362573099415208e-05, | |
| "loss": 0.147, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.526315789473684, | |
| "grad_norm": 3.1375253200531006, | |
| "learning_rate": 2.7387914230019495e-05, | |
| "loss": 0.1461, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 9.31838321685791, | |
| "learning_rate": 2.6413255360623783e-05, | |
| "loss": 0.1599, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.631578947368421, | |
| "grad_norm": 6.391341686248779, | |
| "learning_rate": 2.5438596491228074e-05, | |
| "loss": 0.1492, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 5.891468524932861, | |
| "learning_rate": 2.4463937621832358e-05, | |
| "loss": 0.1662, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.736842105263158, | |
| "grad_norm": 6.506641864776611, | |
| "learning_rate": 2.348927875243665e-05, | |
| "loss": 0.1448, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.7894736842105263, | |
| "grad_norm": 5.7794108390808105, | |
| "learning_rate": 2.2514619883040936e-05, | |
| "loss": 0.112, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.8421052631578947, | |
| "grad_norm": 8.3933744430542, | |
| "learning_rate": 2.1539961013645223e-05, | |
| "loss": 0.1292, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 6.196931838989258, | |
| "learning_rate": 2.056530214424951e-05, | |
| "loss": 0.1418, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.9473684210526314, | |
| "grad_norm": 7.739428997039795, | |
| "learning_rate": 1.9590643274853802e-05, | |
| "loss": 0.1129, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 7.849891185760498, | |
| "learning_rate": 1.861598440545809e-05, | |
| "loss": 0.1528, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9748148148148148, | |
| "eval_loss": 0.0713169053196907, | |
| "eval_runtime": 4.3996, | |
| "eval_samples_per_second": 613.688, | |
| "eval_steps_per_second": 19.32, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.0526315789473686, | |
| "grad_norm": 5.565265655517578, | |
| "learning_rate": 1.7641325536062377e-05, | |
| "loss": 0.1234, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 6.100377082824707, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.1248, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.1578947368421053, | |
| "grad_norm": 2.68096661567688, | |
| "learning_rate": 1.5692007797270955e-05, | |
| "loss": 0.0989, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.2105263157894735, | |
| "grad_norm": 2.9436898231506348, | |
| "learning_rate": 1.4717348927875244e-05, | |
| "loss": 0.1111, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.263157894736842, | |
| "grad_norm": 6.701323986053467, | |
| "learning_rate": 1.3742690058479531e-05, | |
| "loss": 0.1659, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.3157894736842106, | |
| "grad_norm": 6.343139171600342, | |
| "learning_rate": 1.276803118908382e-05, | |
| "loss": 0.103, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.3684210526315788, | |
| "grad_norm": 5.917227268218994, | |
| "learning_rate": 1.179337231968811e-05, | |
| "loss": 0.1059, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.4210526315789473, | |
| "grad_norm": 6.181001663208008, | |
| "learning_rate": 1.0818713450292397e-05, | |
| "loss": 0.116, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.473684210526316, | |
| "grad_norm": 7.878546714782715, | |
| "learning_rate": 9.844054580896686e-06, | |
| "loss": 0.1418, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 8.960369110107422, | |
| "learning_rate": 8.869395711500974e-06, | |
| "loss": 0.1609, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.5789473684210527, | |
| "grad_norm": 10.864946365356445, | |
| "learning_rate": 7.894736842105263e-06, | |
| "loss": 0.1314, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 6.69527530670166, | |
| "learning_rate": 6.920077972709551e-06, | |
| "loss": 0.1472, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.6842105263157894, | |
| "grad_norm": 8.905725479125977, | |
| "learning_rate": 5.94541910331384e-06, | |
| "loss": 0.1382, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.736842105263158, | |
| "grad_norm": 4.663083076477051, | |
| "learning_rate": 4.970760233918129e-06, | |
| "loss": 0.1509, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.7894736842105265, | |
| "grad_norm": 6.759707927703857, | |
| "learning_rate": 3.996101364522417e-06, | |
| "loss": 0.115, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.8421052631578947, | |
| "grad_norm": 4.101389408111572, | |
| "learning_rate": 3.0214424951267056e-06, | |
| "loss": 0.0855, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.8947368421052633, | |
| "grad_norm": 5.965505123138428, | |
| "learning_rate": 2.0467836257309943e-06, | |
| "loss": 0.1056, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 3.79522442817688, | |
| "learning_rate": 1.0721247563352826e-06, | |
| "loss": 0.0831, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 2.4792110919952393, | |
| "learning_rate": 9.746588693957116e-08, | |
| "loss": 0.0861, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9829629629629629, | |
| "eval_loss": 0.04924270510673523, | |
| "eval_runtime": 4.4303, | |
| "eval_samples_per_second": 609.434, | |
| "eval_steps_per_second": 19.186, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 570, | |
| "total_flos": 1.8124066505760768e+18, | |
| "train_loss": 0.2828052028229362, | |
| "train_runtime": 282.6955, | |
| "train_samples_per_second": 257.875, | |
| "train_steps_per_second": 2.016 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 570, | |
| "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": 1.8124066505760768e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |