|
{ |
|
"best_metric": 1.0, |
|
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-wuhan/checkpoint-51", |
|
"epoch": 50.0, |
|
"global_step": 150, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.7777777777777778, |
|
"eval_loss": 0.6245499849319458, |
|
"eval_runtime": 24.4847, |
|
"eval_samples_per_second": 1.47, |
|
"eval_steps_per_second": 0.041, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.7777777777777778, |
|
"eval_loss": 0.5320722460746765, |
|
"eval_runtime": 1.652, |
|
"eval_samples_per_second": 21.791, |
|
"eval_steps_per_second": 0.605, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.7777777777777778, |
|
"eval_loss": 0.5123355388641357, |
|
"eval_runtime": 1.6429, |
|
"eval_samples_per_second": 21.912, |
|
"eval_steps_per_second": 0.609, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 3.33, |
|
"learning_rate": 3.3333333333333335e-05, |
|
"loss": 0.6482, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.7777777777777778, |
|
"eval_loss": 0.4955737888813019, |
|
"eval_runtime": 1.6364, |
|
"eval_samples_per_second": 22.0, |
|
"eval_steps_per_second": 0.611, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.7777777777777778, |
|
"eval_loss": 0.4585157632827759, |
|
"eval_runtime": 1.6942, |
|
"eval_samples_per_second": 21.249, |
|
"eval_steps_per_second": 0.59, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_accuracy": 0.8611111111111112, |
|
"eval_loss": 0.374308705329895, |
|
"eval_runtime": 1.632, |
|
"eval_samples_per_second": 22.058, |
|
"eval_steps_per_second": 0.613, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 6.67, |
|
"learning_rate": 4.814814814814815e-05, |
|
"loss": 0.5574, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_accuracy": 0.9166666666666666, |
|
"eval_loss": 0.28418225049972534, |
|
"eval_runtime": 1.6051, |
|
"eval_samples_per_second": 22.429, |
|
"eval_steps_per_second": 0.623, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_accuracy": 0.9166666666666666, |
|
"eval_loss": 0.21250946819782257, |
|
"eval_runtime": 1.6507, |
|
"eval_samples_per_second": 21.809, |
|
"eval_steps_per_second": 0.606, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_accuracy": 0.9166666666666666, |
|
"eval_loss": 0.268328458070755, |
|
"eval_runtime": 1.6501, |
|
"eval_samples_per_second": 21.816, |
|
"eval_steps_per_second": 0.606, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 4.4444444444444447e-05, |
|
"loss": 0.4882, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_accuracy": 0.9444444444444444, |
|
"eval_loss": 0.13163453340530396, |
|
"eval_runtime": 1.6879, |
|
"eval_samples_per_second": 21.329, |
|
"eval_steps_per_second": 0.592, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 11.0, |
|
"eval_accuracy": 0.9444444444444444, |
|
"eval_loss": 0.13660234212875366, |
|
"eval_runtime": 1.7137, |
|
"eval_samples_per_second": 21.007, |
|
"eval_steps_per_second": 0.584, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 12.0, |
|
"eval_accuracy": 0.9722222222222222, |
|
"eval_loss": 0.07448268681764603, |
|
"eval_runtime": 1.7626, |
|
"eval_samples_per_second": 20.424, |
|
"eval_steps_per_second": 0.567, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 13.0, |
|
"eval_accuracy": 0.9444444444444444, |
|
"eval_loss": 0.10653182864189148, |
|
"eval_runtime": 1.7029, |
|
"eval_samples_per_second": 21.14, |
|
"eval_steps_per_second": 0.587, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 13.33, |
|
"learning_rate": 4.074074074074074e-05, |
|
"loss": 0.0907, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 14.0, |
|
"eval_accuracy": 0.9722222222222222, |
|
"eval_loss": 0.04769667983055115, |
|
"eval_runtime": 1.7434, |
|
"eval_samples_per_second": 20.65, |
|
"eval_steps_per_second": 0.574, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"eval_accuracy": 0.9444444444444444, |
|
"eval_loss": 0.045971717685461044, |
|
"eval_runtime": 1.6711, |
|
"eval_samples_per_second": 21.543, |
|
"eval_steps_per_second": 0.598, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"eval_accuracy": 0.9722222222222222, |
|
"eval_loss": 0.04381129518151283, |
|
"eval_runtime": 1.6352, |
|
"eval_samples_per_second": 22.016, |
|
"eval_steps_per_second": 0.612, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 16.67, |
|
"learning_rate": 3.7037037037037037e-05, |
|
"loss": 0.0481, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 17.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.020261267200112343, |
|
"eval_runtime": 1.6614, |
|
"eval_samples_per_second": 21.668, |
|
"eval_steps_per_second": 0.602, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 18.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.009294789284467697, |
|
"eval_runtime": 1.6224, |
|
"eval_samples_per_second": 22.19, |
|
"eval_steps_per_second": 0.616, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 19.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.008234969340264797, |
|
"eval_runtime": 1.6449, |
|
"eval_samples_per_second": 21.885, |
|
"eval_steps_per_second": 0.608, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"learning_rate": 3.3333333333333335e-05, |
|
"loss": 0.013, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.0017433015163987875, |
|
"eval_runtime": 1.6486, |
|
"eval_samples_per_second": 21.837, |
|
"eval_steps_per_second": 0.607, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 21.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.0007768174400553107, |
|
"eval_runtime": 1.7052, |
|
"eval_samples_per_second": 21.112, |
|
"eval_steps_per_second": 0.586, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 22.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.00018507178174331784, |
|
"eval_runtime": 1.7002, |
|
"eval_samples_per_second": 21.174, |
|
"eval_steps_per_second": 0.588, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 23.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.00012737045472022146, |
|
"eval_runtime": 1.6699, |
|
"eval_samples_per_second": 21.558, |
|
"eval_steps_per_second": 0.599, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 23.33, |
|
"learning_rate": 2.962962962962963e-05, |
|
"loss": 0.0101, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 24.0, |
|
"eval_accuracy": 0.9722222222222222, |
|
"eval_loss": 0.09382671862840652, |
|
"eval_runtime": 1.6527, |
|
"eval_samples_per_second": 21.783, |
|
"eval_steps_per_second": 0.605, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 25.0, |
|
"eval_accuracy": 0.9722222222222222, |
|
"eval_loss": 0.10189218819141388, |
|
"eval_runtime": 1.6545, |
|
"eval_samples_per_second": 21.758, |
|
"eval_steps_per_second": 0.604, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 26.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.0005055955843999982, |
|
"eval_runtime": 1.7212, |
|
"eval_samples_per_second": 20.916, |
|
"eval_steps_per_second": 0.581, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 26.67, |
|
"learning_rate": 2.5925925925925925e-05, |
|
"loss": 0.0085, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 27.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 1.9300923668197356e-05, |
|
"eval_runtime": 1.7849, |
|
"eval_samples_per_second": 20.17, |
|
"eval_steps_per_second": 0.56, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 28.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 1.1416644156270195e-05, |
|
"eval_runtime": 1.7789, |
|
"eval_samples_per_second": 20.237, |
|
"eval_steps_per_second": 0.562, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 29.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 5.5924607295310125e-05, |
|
"eval_runtime": 1.6926, |
|
"eval_samples_per_second": 21.269, |
|
"eval_steps_per_second": 0.591, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"learning_rate": 2.2222222222222223e-05, |
|
"loss": 0.0196, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.00011896187061211094, |
|
"eval_runtime": 1.6527, |
|
"eval_samples_per_second": 21.782, |
|
"eval_steps_per_second": 0.605, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 31.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 0.00012139210593886673, |
|
"eval_runtime": 1.6483, |
|
"eval_samples_per_second": 21.841, |
|
"eval_steps_per_second": 0.607, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 32.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 4.184916542726569e-05, |
|
"eval_runtime": 1.6727, |
|
"eval_samples_per_second": 21.523, |
|
"eval_steps_per_second": 0.598, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 33.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 1.933595194714144e-05, |
|
"eval_runtime": 1.6406, |
|
"eval_samples_per_second": 21.943, |
|
"eval_steps_per_second": 0.61, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 33.33, |
|
"learning_rate": 1.8518518518518518e-05, |
|
"loss": 0.0027, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 34.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 1.333714862994384e-05, |
|
"eval_runtime": 1.6592, |
|
"eval_samples_per_second": 21.697, |
|
"eval_steps_per_second": 0.603, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 35.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 8.897241968952585e-06, |
|
"eval_runtime": 1.6396, |
|
"eval_samples_per_second": 21.957, |
|
"eval_steps_per_second": 0.61, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 36.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 7.099337835825281e-06, |
|
"eval_runtime": 1.6407, |
|
"eval_samples_per_second": 21.942, |
|
"eval_steps_per_second": 0.61, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 36.67, |
|
"learning_rate": 1.4814814814814815e-05, |
|
"loss": 0.0016, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 37.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 5.609323125099763e-06, |
|
"eval_runtime": 1.6715, |
|
"eval_samples_per_second": 21.538, |
|
"eval_steps_per_second": 0.598, |
|
"step": 111 |
|
}, |
|
{ |
|
"epoch": 38.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 4.562983122013975e-06, |
|
"eval_runtime": 1.9201, |
|
"eval_samples_per_second": 18.749, |
|
"eval_steps_per_second": 0.521, |
|
"step": 114 |
|
}, |
|
{ |
|
"epoch": 39.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 3.596098849811824e-06, |
|
"eval_runtime": 2.0826, |
|
"eval_samples_per_second": 17.286, |
|
"eval_steps_per_second": 0.48, |
|
"step": 117 |
|
}, |
|
{ |
|
"epoch": 40.0, |
|
"learning_rate": 1.1111111111111112e-05, |
|
"loss": 0.0021, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 40.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 3.2384773476223927e-06, |
|
"eval_runtime": 1.6679, |
|
"eval_samples_per_second": 21.585, |
|
"eval_steps_per_second": 0.6, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 41.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 3.013309651578311e-06, |
|
"eval_runtime": 1.6498, |
|
"eval_samples_per_second": 21.82, |
|
"eval_steps_per_second": 0.606, |
|
"step": 123 |
|
}, |
|
{ |
|
"epoch": 42.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 2.781519697236945e-06, |
|
"eval_runtime": 1.6569, |
|
"eval_samples_per_second": 21.728, |
|
"eval_steps_per_second": 0.604, |
|
"step": 126 |
|
}, |
|
{ |
|
"epoch": 43.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 2.4669488993822597e-06, |
|
"eval_runtime": 1.6535, |
|
"eval_samples_per_second": 21.772, |
|
"eval_steps_per_second": 0.605, |
|
"step": 129 |
|
}, |
|
{ |
|
"epoch": 43.33, |
|
"learning_rate": 7.4074074074074075e-06, |
|
"loss": 0.0024, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 44.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 2.09608538170869e-06, |
|
"eval_runtime": 1.6274, |
|
"eval_samples_per_second": 22.121, |
|
"eval_steps_per_second": 0.614, |
|
"step": 132 |
|
}, |
|
{ |
|
"epoch": 45.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 1.89409422546305e-06, |
|
"eval_runtime": 1.6472, |
|
"eval_samples_per_second": 21.856, |
|
"eval_steps_per_second": 0.607, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 46.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 1.821245518840442e-06, |
|
"eval_runtime": 1.646, |
|
"eval_samples_per_second": 21.872, |
|
"eval_steps_per_second": 0.608, |
|
"step": 138 |
|
}, |
|
{ |
|
"epoch": 46.67, |
|
"learning_rate": 3.7037037037037037e-06, |
|
"loss": 0.0009, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 47.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 1.8709155256146914e-06, |
|
"eval_runtime": 1.6474, |
|
"eval_samples_per_second": 21.852, |
|
"eval_steps_per_second": 0.607, |
|
"step": 141 |
|
}, |
|
{ |
|
"epoch": 48.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 1.9536980744305765e-06, |
|
"eval_runtime": 1.6639, |
|
"eval_samples_per_second": 21.636, |
|
"eval_steps_per_second": 0.601, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 49.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 2.006679324040306e-06, |
|
"eval_runtime": 1.6581, |
|
"eval_samples_per_second": 21.712, |
|
"eval_steps_per_second": 0.603, |
|
"step": 147 |
|
}, |
|
{ |
|
"epoch": 50.0, |
|
"learning_rate": 0.0, |
|
"loss": 0.0006, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 50.0, |
|
"eval_accuracy": 1.0, |
|
"eval_loss": 2.0265476905478863e-06, |
|
"eval_runtime": 1.7006, |
|
"eval_samples_per_second": 21.169, |
|
"eval_steps_per_second": 0.588, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 50.0, |
|
"step": 150, |
|
"total_flos": 3.989386232229888e+17, |
|
"train_loss": 0.12627770403089622, |
|
"train_runtime": 1656.8438, |
|
"train_samples_per_second": 9.687, |
|
"train_steps_per_second": 0.091 |
|
} |
|
], |
|
"max_steps": 150, |
|
"num_train_epochs": 50, |
|
"total_flos": 3.989386232229888e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|