tea-cup's picture
End of training
551608b
{
"best_metric": 0.9835456475583864,
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-396",
"epoch": 2.988679245283019,
"eval_steps": 500,
"global_step": 396,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08,
"learning_rate": 1.25e-05,
"loss": 1.9794,
"step": 10
},
{
"epoch": 0.15,
"learning_rate": 2.5e-05,
"loss": 1.6377,
"step": 20
},
{
"epoch": 0.23,
"learning_rate": 3.7500000000000003e-05,
"loss": 1.0057,
"step": 30
},
{
"epoch": 0.3,
"learning_rate": 5e-05,
"loss": 0.5551,
"step": 40
},
{
"epoch": 0.38,
"learning_rate": 4.859550561797753e-05,
"loss": 0.3821,
"step": 50
},
{
"epoch": 0.45,
"learning_rate": 4.719101123595506e-05,
"loss": 0.377,
"step": 60
},
{
"epoch": 0.53,
"learning_rate": 4.578651685393259e-05,
"loss": 0.3476,
"step": 70
},
{
"epoch": 0.6,
"learning_rate": 4.438202247191011e-05,
"loss": 0.2476,
"step": 80
},
{
"epoch": 0.68,
"learning_rate": 4.297752808988764e-05,
"loss": 0.2463,
"step": 90
},
{
"epoch": 0.75,
"learning_rate": 4.157303370786517e-05,
"loss": 0.2539,
"step": 100
},
{
"epoch": 0.83,
"learning_rate": 4.01685393258427e-05,
"loss": 0.2105,
"step": 110
},
{
"epoch": 0.91,
"learning_rate": 3.876404494382023e-05,
"loss": 0.2458,
"step": 120
},
{
"epoch": 0.98,
"learning_rate": 3.735955056179776e-05,
"loss": 0.2611,
"step": 130
},
{
"epoch": 1.0,
"eval_accuracy": 0.9750530785562632,
"eval_loss": 0.07518858462572098,
"eval_runtime": 459.3366,
"eval_samples_per_second": 4.102,
"eval_steps_per_second": 0.128,
"step": 132
},
{
"epoch": 1.06,
"learning_rate": 3.595505617977528e-05,
"loss": 0.2334,
"step": 140
},
{
"epoch": 1.13,
"learning_rate": 3.455056179775281e-05,
"loss": 0.1939,
"step": 150
},
{
"epoch": 1.21,
"learning_rate": 3.314606741573034e-05,
"loss": 0.1915,
"step": 160
},
{
"epoch": 1.28,
"learning_rate": 3.1741573033707866e-05,
"loss": 0.1762,
"step": 170
},
{
"epoch": 1.36,
"learning_rate": 3.0337078651685396e-05,
"loss": 0.1839,
"step": 180
},
{
"epoch": 1.43,
"learning_rate": 2.893258426966292e-05,
"loss": 0.2072,
"step": 190
},
{
"epoch": 1.51,
"learning_rate": 2.752808988764045e-05,
"loss": 0.1524,
"step": 200
},
{
"epoch": 1.58,
"learning_rate": 2.6123595505617983e-05,
"loss": 0.1765,
"step": 210
},
{
"epoch": 1.66,
"learning_rate": 2.4719101123595505e-05,
"loss": 0.1896,
"step": 220
},
{
"epoch": 1.74,
"learning_rate": 2.3314606741573034e-05,
"loss": 0.1885,
"step": 230
},
{
"epoch": 1.81,
"learning_rate": 2.1910112359550563e-05,
"loss": 0.2096,
"step": 240
},
{
"epoch": 1.89,
"learning_rate": 2.0505617977528092e-05,
"loss": 0.1615,
"step": 250
},
{
"epoch": 1.96,
"learning_rate": 1.9101123595505618e-05,
"loss": 0.1302,
"step": 260
},
{
"epoch": 2.0,
"eval_accuracy": 0.9808917197452229,
"eval_loss": 0.06093698740005493,
"eval_runtime": 13.5835,
"eval_samples_per_second": 138.698,
"eval_steps_per_second": 4.344,
"step": 265
},
{
"epoch": 2.04,
"learning_rate": 1.7696629213483147e-05,
"loss": 0.1431,
"step": 270
},
{
"epoch": 2.11,
"learning_rate": 1.6292134831460676e-05,
"loss": 0.1488,
"step": 280
},
{
"epoch": 2.19,
"learning_rate": 1.4887640449438203e-05,
"loss": 0.1623,
"step": 290
},
{
"epoch": 2.26,
"learning_rate": 1.348314606741573e-05,
"loss": 0.1517,
"step": 300
},
{
"epoch": 2.34,
"learning_rate": 1.207865168539326e-05,
"loss": 0.1487,
"step": 310
},
{
"epoch": 2.42,
"learning_rate": 1.0674157303370787e-05,
"loss": 0.1189,
"step": 320
},
{
"epoch": 2.49,
"learning_rate": 9.269662921348316e-06,
"loss": 0.1416,
"step": 330
},
{
"epoch": 2.57,
"learning_rate": 7.865168539325843e-06,
"loss": 0.1586,
"step": 340
},
{
"epoch": 2.64,
"learning_rate": 6.460674157303372e-06,
"loss": 0.1403,
"step": 350
},
{
"epoch": 2.72,
"learning_rate": 5.056179775280899e-06,
"loss": 0.1101,
"step": 360
},
{
"epoch": 2.79,
"learning_rate": 3.651685393258427e-06,
"loss": 0.1463,
"step": 370
},
{
"epoch": 2.87,
"learning_rate": 2.247191011235955e-06,
"loss": 0.1324,
"step": 380
},
{
"epoch": 2.94,
"learning_rate": 8.426966292134832e-07,
"loss": 0.1486,
"step": 390
},
{
"epoch": 2.99,
"eval_accuracy": 0.9835456475583864,
"eval_loss": 0.05185917764902115,
"eval_runtime": 13.8769,
"eval_samples_per_second": 135.765,
"eval_steps_per_second": 4.252,
"step": 396
},
{
"epoch": 2.99,
"step": 396,
"total_flos": 1.2596143944940093e+18,
"train_loss": 0.304791094678821,
"train_runtime": 5290.6872,
"train_samples_per_second": 9.611,
"train_steps_per_second": 0.075
}
],
"logging_steps": 10,
"max_steps": 396,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 1.2596143944940093e+18,
"trial_name": null,
"trial_params": null
}