Brain_Tumor_Class_swin / trainer_state.json
Devarshi's picture
End of training
0ed70cd
{
"best_metric": 0.9936204146730463,
"best_model_checkpoint": "Brain_Tumor_Class_swin/checkpoint-660",
"epoch": 2.997732426303855,
"global_step": 660,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05,
"learning_rate": 7.5757575757575764e-06,
"loss": 1.4262,
"step": 10
},
{
"epoch": 0.09,
"learning_rate": 1.5151515151515153e-05,
"loss": 1.1655,
"step": 20
},
{
"epoch": 0.14,
"learning_rate": 2.272727272727273e-05,
"loss": 0.8214,
"step": 30
},
{
"epoch": 0.18,
"learning_rate": 3.0303030303030306e-05,
"loss": 0.5529,
"step": 40
},
{
"epoch": 0.23,
"learning_rate": 3.787878787878788e-05,
"loss": 0.4809,
"step": 50
},
{
"epoch": 0.27,
"learning_rate": 4.545454545454546e-05,
"loss": 0.3331,
"step": 60
},
{
"epoch": 0.32,
"learning_rate": 4.966329966329967e-05,
"loss": 0.2898,
"step": 70
},
{
"epoch": 0.36,
"learning_rate": 4.882154882154882e-05,
"loss": 0.2294,
"step": 80
},
{
"epoch": 0.41,
"learning_rate": 4.797979797979798e-05,
"loss": 0.2239,
"step": 90
},
{
"epoch": 0.45,
"learning_rate": 4.713804713804714e-05,
"loss": 0.2285,
"step": 100
},
{
"epoch": 0.5,
"learning_rate": 4.62962962962963e-05,
"loss": 0.1986,
"step": 110
},
{
"epoch": 0.54,
"learning_rate": 4.545454545454546e-05,
"loss": 0.2205,
"step": 120
},
{
"epoch": 0.59,
"learning_rate": 4.4612794612794616e-05,
"loss": 0.2039,
"step": 130
},
{
"epoch": 0.63,
"learning_rate": 4.3771043771043774e-05,
"loss": 0.1516,
"step": 140
},
{
"epoch": 0.68,
"learning_rate": 4.292929292929293e-05,
"loss": 0.1656,
"step": 150
},
{
"epoch": 0.73,
"learning_rate": 4.208754208754209e-05,
"loss": 0.2107,
"step": 160
},
{
"epoch": 0.77,
"learning_rate": 4.124579124579125e-05,
"loss": 0.1502,
"step": 170
},
{
"epoch": 0.82,
"learning_rate": 4.0404040404040405e-05,
"loss": 0.1566,
"step": 180
},
{
"epoch": 0.86,
"learning_rate": 3.956228956228956e-05,
"loss": 0.1468,
"step": 190
},
{
"epoch": 0.91,
"learning_rate": 3.872053872053872e-05,
"loss": 0.1507,
"step": 200
},
{
"epoch": 0.95,
"learning_rate": 3.787878787878788e-05,
"loss": 0.1334,
"step": 210
},
{
"epoch": 1.0,
"learning_rate": 3.7037037037037037e-05,
"loss": 0.1248,
"step": 220
},
{
"epoch": 1.0,
"eval_accuracy": 0.9767145135566189,
"eval_f1": 0.9767145135566189,
"eval_loss": 0.060983214527368546,
"eval_precision": 0.9767145135566189,
"eval_recall": 0.9767145135566189,
"eval_runtime": 420.9001,
"eval_samples_per_second": 7.448,
"eval_steps_per_second": 0.233,
"step": 220
},
{
"epoch": 1.05,
"learning_rate": 3.61952861952862e-05,
"loss": 0.1459,
"step": 230
},
{
"epoch": 1.09,
"learning_rate": 3.535353535353535e-05,
"loss": 0.1481,
"step": 240
},
{
"epoch": 1.14,
"learning_rate": 3.451178451178451e-05,
"loss": 0.1443,
"step": 250
},
{
"epoch": 1.18,
"learning_rate": 3.3670033670033675e-05,
"loss": 0.1318,
"step": 260
},
{
"epoch": 1.23,
"learning_rate": 3.282828282828283e-05,
"loss": 0.1296,
"step": 270
},
{
"epoch": 1.27,
"learning_rate": 3.198653198653199e-05,
"loss": 0.094,
"step": 280
},
{
"epoch": 1.32,
"learning_rate": 3.114478114478115e-05,
"loss": 0.096,
"step": 290
},
{
"epoch": 1.36,
"learning_rate": 3.0303030303030306e-05,
"loss": 0.1289,
"step": 300
},
{
"epoch": 1.41,
"learning_rate": 2.946127946127946e-05,
"loss": 0.0931,
"step": 310
},
{
"epoch": 1.45,
"learning_rate": 2.8619528619528618e-05,
"loss": 0.1031,
"step": 320
},
{
"epoch": 1.5,
"learning_rate": 2.777777777777778e-05,
"loss": 0.0982,
"step": 330
},
{
"epoch": 1.54,
"learning_rate": 2.6936026936026937e-05,
"loss": 0.11,
"step": 340
},
{
"epoch": 1.59,
"learning_rate": 2.6094276094276095e-05,
"loss": 0.0974,
"step": 350
},
{
"epoch": 1.63,
"learning_rate": 2.5252525252525256e-05,
"loss": 0.0739,
"step": 360
},
{
"epoch": 1.68,
"learning_rate": 2.441077441077441e-05,
"loss": 0.0712,
"step": 370
},
{
"epoch": 1.73,
"learning_rate": 2.356902356902357e-05,
"loss": 0.1139,
"step": 380
},
{
"epoch": 1.77,
"learning_rate": 2.272727272727273e-05,
"loss": 0.0882,
"step": 390
},
{
"epoch": 1.82,
"learning_rate": 2.1885521885521887e-05,
"loss": 0.1168,
"step": 400
},
{
"epoch": 1.86,
"learning_rate": 2.1043771043771045e-05,
"loss": 0.0851,
"step": 410
},
{
"epoch": 1.91,
"learning_rate": 2.0202020202020203e-05,
"loss": 0.0816,
"step": 420
},
{
"epoch": 1.95,
"learning_rate": 1.936026936026936e-05,
"loss": 0.0786,
"step": 430
},
{
"epoch": 2.0,
"learning_rate": 1.8518518518518518e-05,
"loss": 0.0887,
"step": 440
},
{
"epoch": 2.0,
"eval_accuracy": 0.9920255183413078,
"eval_f1": 0.9920255183413078,
"eval_loss": 0.03002375364303589,
"eval_precision": 0.9920255183413078,
"eval_recall": 0.9920255183413078,
"eval_runtime": 377.2212,
"eval_samples_per_second": 8.311,
"eval_steps_per_second": 0.26,
"step": 440
},
{
"epoch": 2.05,
"learning_rate": 1.7676767676767676e-05,
"loss": 0.0823,
"step": 450
},
{
"epoch": 2.09,
"learning_rate": 1.6835016835016837e-05,
"loss": 0.0786,
"step": 460
},
{
"epoch": 2.14,
"learning_rate": 1.5993265993265995e-05,
"loss": 0.0641,
"step": 470
},
{
"epoch": 2.18,
"learning_rate": 1.5151515151515153e-05,
"loss": 0.0808,
"step": 480
},
{
"epoch": 2.23,
"learning_rate": 1.4309764309764309e-05,
"loss": 0.0761,
"step": 490
},
{
"epoch": 2.27,
"learning_rate": 1.3468013468013468e-05,
"loss": 0.0761,
"step": 500
},
{
"epoch": 2.32,
"learning_rate": 1.2626262626262628e-05,
"loss": 0.0721,
"step": 510
},
{
"epoch": 2.36,
"learning_rate": 1.1784511784511786e-05,
"loss": 0.0712,
"step": 520
},
{
"epoch": 2.41,
"learning_rate": 1.0942760942760944e-05,
"loss": 0.0659,
"step": 530
},
{
"epoch": 2.45,
"learning_rate": 1.0101010101010101e-05,
"loss": 0.0699,
"step": 540
},
{
"epoch": 2.5,
"learning_rate": 9.259259259259259e-06,
"loss": 0.0569,
"step": 550
},
{
"epoch": 2.54,
"learning_rate": 8.417508417508419e-06,
"loss": 0.0582,
"step": 560
},
{
"epoch": 2.59,
"learning_rate": 7.5757575757575764e-06,
"loss": 0.0712,
"step": 570
},
{
"epoch": 2.63,
"learning_rate": 6.734006734006734e-06,
"loss": 0.0586,
"step": 580
},
{
"epoch": 2.68,
"learning_rate": 5.892255892255893e-06,
"loss": 0.0751,
"step": 590
},
{
"epoch": 2.73,
"learning_rate": 5.050505050505051e-06,
"loss": 0.052,
"step": 600
},
{
"epoch": 2.77,
"learning_rate": 4.208754208754209e-06,
"loss": 0.0764,
"step": 610
},
{
"epoch": 2.82,
"learning_rate": 3.367003367003367e-06,
"loss": 0.0568,
"step": 620
},
{
"epoch": 2.86,
"learning_rate": 2.5252525252525253e-06,
"loss": 0.0573,
"step": 630
},
{
"epoch": 2.91,
"learning_rate": 1.6835016835016836e-06,
"loss": 0.052,
"step": 640
},
{
"epoch": 2.95,
"learning_rate": 8.417508417508418e-07,
"loss": 0.0571,
"step": 650
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 0.0449,
"step": 660
},
{
"epoch": 3.0,
"eval_accuracy": 0.9936204146730463,
"eval_f1": 0.9936204146730463,
"eval_loss": 0.022031184285879135,
"eval_precision": 0.9936204146730463,
"eval_recall": 0.9936204146730463,
"eval_runtime": 377.6762,
"eval_samples_per_second": 8.301,
"eval_steps_per_second": 0.259,
"step": 660
},
{
"epoch": 3.0,
"step": 660,
"total_flos": 6.627407168486523e+18,
"train_loss": 0.17479625046253205,
"train_runtime": 48488.9343,
"train_samples_per_second": 1.746,
"train_steps_per_second": 0.014
}
],
"max_steps": 660,
"num_train_epochs": 3,
"total_flos": 6.627407168486523e+18,
"trial_name": null,
"trial_params": null
}