|
{ |
|
"best_metric": 0.62025, |
|
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-281", |
|
"epoch": 0.9991111111111111, |
|
"eval_steps": 500, |
|
"global_step": 281, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.035555555555555556, |
|
"grad_norm": 7.3984904289245605, |
|
"learning_rate": 1.7241379310344828e-05, |
|
"loss": 2.7474, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.07111111111111111, |
|
"grad_norm": 7.859865188598633, |
|
"learning_rate": 3.4482758620689657e-05, |
|
"loss": 2.6199, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.10666666666666667, |
|
"grad_norm": 21.349201202392578, |
|
"learning_rate": 4.9801587301587306e-05, |
|
"loss": 2.2658, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.14222222222222222, |
|
"grad_norm": 23.123310089111328, |
|
"learning_rate": 4.781746031746032e-05, |
|
"loss": 2.0242, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.17777777777777778, |
|
"grad_norm": 10.755074501037598, |
|
"learning_rate": 4.5833333333333334e-05, |
|
"loss": 1.866, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.21333333333333335, |
|
"grad_norm": 9.822580337524414, |
|
"learning_rate": 4.384920634920635e-05, |
|
"loss": 1.7276, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.24888888888888888, |
|
"grad_norm": 11.387887001037598, |
|
"learning_rate": 4.186507936507937e-05, |
|
"loss": 1.6602, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.28444444444444444, |
|
"grad_norm": 11.359118461608887, |
|
"learning_rate": 3.9880952380952386e-05, |
|
"loss": 1.6713, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"grad_norm": 10.438748359680176, |
|
"learning_rate": 3.7896825396825396e-05, |
|
"loss": 1.6469, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.35555555555555557, |
|
"grad_norm": 10.260947227478027, |
|
"learning_rate": 3.591269841269841e-05, |
|
"loss": 1.5134, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.39111111111111113, |
|
"grad_norm": 8.524605751037598, |
|
"learning_rate": 3.392857142857143e-05, |
|
"loss": 1.5694, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.4266666666666667, |
|
"grad_norm": 10.703609466552734, |
|
"learning_rate": 3.194444444444444e-05, |
|
"loss": 1.597, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.4622222222222222, |
|
"grad_norm": 10.19986629486084, |
|
"learning_rate": 2.996031746031746e-05, |
|
"loss": 1.4785, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.49777777777777776, |
|
"grad_norm": 9.872143745422363, |
|
"learning_rate": 2.797619047619048e-05, |
|
"loss": 1.4853, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.5333333333333333, |
|
"grad_norm": 8.166397094726562, |
|
"learning_rate": 2.5992063492063496e-05, |
|
"loss": 1.4354, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.5688888888888889, |
|
"grad_norm": 12.244831085205078, |
|
"learning_rate": 2.400793650793651e-05, |
|
"loss": 1.5286, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.6044444444444445, |
|
"grad_norm": 9.033407211303711, |
|
"learning_rate": 2.2023809523809524e-05, |
|
"loss": 1.3584, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"grad_norm": 7.281382083892822, |
|
"learning_rate": 2.003968253968254e-05, |
|
"loss": 1.4626, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.6755555555555556, |
|
"grad_norm": 7.3251519203186035, |
|
"learning_rate": 1.8055555555555555e-05, |
|
"loss": 1.3453, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.7111111111111111, |
|
"grad_norm": 9.071359634399414, |
|
"learning_rate": 1.6071428571428572e-05, |
|
"loss": 1.3493, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.7466666666666667, |
|
"grad_norm": 11.566309928894043, |
|
"learning_rate": 1.4087301587301587e-05, |
|
"loss": 1.3759, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.7822222222222223, |
|
"grad_norm": 9.21988582611084, |
|
"learning_rate": 1.2103174603174603e-05, |
|
"loss": 1.365, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.8177777777777778, |
|
"grad_norm": 8.32099437713623, |
|
"learning_rate": 1.011904761904762e-05, |
|
"loss": 1.3049, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.8533333333333334, |
|
"grad_norm": 10.410431861877441, |
|
"learning_rate": 8.134920634920636e-06, |
|
"loss": 1.3583, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.8888888888888888, |
|
"grad_norm": 7.7621073722839355, |
|
"learning_rate": 6.1507936507936505e-06, |
|
"loss": 1.3066, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.9244444444444444, |
|
"grad_norm": 9.822245597839355, |
|
"learning_rate": 4.166666666666667e-06, |
|
"loss": 1.3564, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"grad_norm": 11.113300323486328, |
|
"learning_rate": 2.1825396825396824e-06, |
|
"loss": 1.2959, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.9955555555555555, |
|
"grad_norm": 8.999974250793457, |
|
"learning_rate": 1.9841269841269841e-07, |
|
"loss": 1.3575, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.9991111111111111, |
|
"eval_accuracy": 0.62025, |
|
"eval_loss": 1.2218776941299438, |
|
"eval_runtime": 59.4645, |
|
"eval_samples_per_second": 67.267, |
|
"eval_steps_per_second": 2.102, |
|
"step": 281 |
|
}, |
|
{ |
|
"epoch": 0.9991111111111111, |
|
"step": 281, |
|
"total_flos": 8.943699469318226e+17, |
|
"train_loss": 1.6086162854768202, |
|
"train_runtime": 797.2781, |
|
"train_samples_per_second": 45.149, |
|
"train_steps_per_second": 0.352 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 281, |
|
"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": 8.943699469318226e+17, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|