ALM-AHME's picture
End of training
bf5ddc8
raw
history blame
13.1 kB
{
"best_metric": 0.9995570321151717,
"best_model_checkpoint": "beit-large-patch16-224-finetuned-LungCancer-Classification-LC25000-AH-40-30-30/checkpoint-465",
"epoch": 4.96,
"global_step": 465,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05,
"learning_rate": 1.0729613733905579e-06,
"loss": 1.1839,
"step": 5
},
{
"epoch": 0.11,
"learning_rate": 2.1459227467811158e-06,
"loss": 0.9886,
"step": 10
},
{
"epoch": 0.16,
"learning_rate": 3.218884120171674e-06,
"loss": 0.742,
"step": 15
},
{
"epoch": 0.21,
"learning_rate": 4.2918454935622316e-06,
"loss": 0.4725,
"step": 20
},
{
"epoch": 0.27,
"learning_rate": 5.36480686695279e-06,
"loss": 0.2834,
"step": 25
},
{
"epoch": 0.32,
"learning_rate": 6.437768240343348e-06,
"loss": 0.2146,
"step": 30
},
{
"epoch": 0.37,
"learning_rate": 7.510729613733906e-06,
"loss": 0.1667,
"step": 35
},
{
"epoch": 0.43,
"learning_rate": 8.583690987124463e-06,
"loss": 0.129,
"step": 40
},
{
"epoch": 0.48,
"learning_rate": 9.65665236051502e-06,
"loss": 0.1718,
"step": 45
},
{
"epoch": 0.53,
"learning_rate": 1.072961373390558e-05,
"loss": 0.1387,
"step": 50
},
{
"epoch": 0.59,
"learning_rate": 1.1802575107296138e-05,
"loss": 0.1188,
"step": 55
},
{
"epoch": 0.64,
"learning_rate": 1.2875536480686696e-05,
"loss": 0.0936,
"step": 60
},
{
"epoch": 0.69,
"learning_rate": 1.3948497854077253e-05,
"loss": 0.1547,
"step": 65
},
{
"epoch": 0.75,
"learning_rate": 1.5021459227467813e-05,
"loss": 0.1528,
"step": 70
},
{
"epoch": 0.8,
"learning_rate": 1.609442060085837e-05,
"loss": 0.1509,
"step": 75
},
{
"epoch": 0.85,
"learning_rate": 1.7167381974248926e-05,
"loss": 0.1046,
"step": 80
},
{
"epoch": 0.91,
"learning_rate": 1.8240343347639486e-05,
"loss": 0.1003,
"step": 85
},
{
"epoch": 0.96,
"learning_rate": 1.931330472103004e-05,
"loss": 0.0508,
"step": 90
},
{
"epoch": 0.99,
"eval_accuracy": 0.9756367663344407,
"eval_loss": 0.06337086111307144,
"eval_runtime": 1162.9787,
"eval_samples_per_second": 3.882,
"eval_steps_per_second": 0.243,
"step": 93
},
{
"epoch": 1.01,
"learning_rate": 2.0386266094420604e-05,
"loss": 0.0488,
"step": 95
},
{
"epoch": 1.07,
"learning_rate": 2.145922746781116e-05,
"loss": 0.0625,
"step": 100
},
{
"epoch": 1.12,
"learning_rate": 2.2532188841201716e-05,
"loss": 0.1041,
"step": 105
},
{
"epoch": 1.17,
"learning_rate": 2.3605150214592276e-05,
"loss": 0.096,
"step": 110
},
{
"epoch": 1.23,
"learning_rate": 2.467811158798283e-05,
"loss": 0.0872,
"step": 115
},
{
"epoch": 1.28,
"learning_rate": 2.575107296137339e-05,
"loss": 0.119,
"step": 120
},
{
"epoch": 1.33,
"learning_rate": 2.6824034334763947e-05,
"loss": 0.0861,
"step": 125
},
{
"epoch": 1.39,
"learning_rate": 2.7896995708154506e-05,
"loss": 0.1535,
"step": 130
},
{
"epoch": 1.44,
"learning_rate": 2.896995708154507e-05,
"loss": 0.1654,
"step": 135
},
{
"epoch": 1.49,
"learning_rate": 3.0042918454935625e-05,
"loss": 0.0787,
"step": 140
},
{
"epoch": 1.55,
"learning_rate": 3.1115879828326185e-05,
"loss": 0.0531,
"step": 145
},
{
"epoch": 1.6,
"learning_rate": 3.218884120171674e-05,
"loss": 0.0825,
"step": 150
},
{
"epoch": 1.65,
"learning_rate": 3.3261802575107297e-05,
"loss": 0.0922,
"step": 155
},
{
"epoch": 1.71,
"learning_rate": 3.433476394849785e-05,
"loss": 0.0717,
"step": 160
},
{
"epoch": 1.76,
"learning_rate": 3.5407725321888415e-05,
"loss": 0.0787,
"step": 165
},
{
"epoch": 1.81,
"learning_rate": 3.648068669527897e-05,
"loss": 0.0244,
"step": 170
},
{
"epoch": 1.87,
"learning_rate": 3.755364806866953e-05,
"loss": 0.0837,
"step": 175
},
{
"epoch": 1.92,
"learning_rate": 3.862660944206008e-05,
"loss": 0.0572,
"step": 180
},
{
"epoch": 1.97,
"learning_rate": 3.9699570815450646e-05,
"loss": 0.0909,
"step": 185
},
{
"epoch": 1.99,
"eval_accuracy": 0.991140642303433,
"eval_loss": 0.022178057581186295,
"eval_runtime": 195.0995,
"eval_samples_per_second": 23.142,
"eval_steps_per_second": 1.451,
"step": 187
},
{
"epoch": 2.03,
"learning_rate": 4.077253218884121e-05,
"loss": 0.0909,
"step": 190
},
{
"epoch": 2.08,
"learning_rate": 4.1845493562231765e-05,
"loss": 0.0431,
"step": 195
},
{
"epoch": 2.13,
"learning_rate": 4.291845493562232e-05,
"loss": 0.0511,
"step": 200
},
{
"epoch": 2.19,
"learning_rate": 4.399141630901288e-05,
"loss": 0.0787,
"step": 205
},
{
"epoch": 2.24,
"learning_rate": 4.506437768240343e-05,
"loss": 0.0467,
"step": 210
},
{
"epoch": 2.29,
"learning_rate": 4.6137339055793995e-05,
"loss": 0.1184,
"step": 215
},
{
"epoch": 2.35,
"learning_rate": 4.721030042918455e-05,
"loss": 0.1344,
"step": 220
},
{
"epoch": 2.4,
"learning_rate": 4.828326180257511e-05,
"loss": 0.1384,
"step": 225
},
{
"epoch": 2.45,
"learning_rate": 4.935622317596566e-05,
"loss": 0.0953,
"step": 230
},
{
"epoch": 2.51,
"learning_rate": 4.9568965517241384e-05,
"loss": 0.0667,
"step": 235
},
{
"epoch": 2.56,
"learning_rate": 4.849137931034483e-05,
"loss": 0.0576,
"step": 240
},
{
"epoch": 2.61,
"learning_rate": 4.741379310344828e-05,
"loss": 0.1106,
"step": 245
},
{
"epoch": 2.67,
"learning_rate": 4.633620689655173e-05,
"loss": 0.1455,
"step": 250
},
{
"epoch": 2.72,
"learning_rate": 4.5258620689655176e-05,
"loss": 0.0161,
"step": 255
},
{
"epoch": 2.77,
"learning_rate": 4.418103448275862e-05,
"loss": 0.0959,
"step": 260
},
{
"epoch": 2.83,
"learning_rate": 4.3103448275862066e-05,
"loss": 0.1851,
"step": 265
},
{
"epoch": 2.88,
"learning_rate": 4.202586206896552e-05,
"loss": 0.0497,
"step": 270
},
{
"epoch": 2.93,
"learning_rate": 4.094827586206897e-05,
"loss": 0.0799,
"step": 275
},
{
"epoch": 2.99,
"learning_rate": 3.9870689655172416e-05,
"loss": 0.0641,
"step": 280
},
{
"epoch": 3.0,
"eval_accuracy": 0.9913621262458472,
"eval_loss": 0.022775284945964813,
"eval_runtime": 195.3033,
"eval_samples_per_second": 23.118,
"eval_steps_per_second": 1.449,
"step": 281
},
{
"epoch": 3.04,
"learning_rate": 3.8793103448275865e-05,
"loss": 0.0663,
"step": 285
},
{
"epoch": 3.09,
"learning_rate": 3.771551724137931e-05,
"loss": 0.045,
"step": 290
},
{
"epoch": 3.15,
"learning_rate": 3.663793103448276e-05,
"loss": 0.0787,
"step": 295
},
{
"epoch": 3.2,
"learning_rate": 3.556034482758621e-05,
"loss": 0.04,
"step": 300
},
{
"epoch": 3.25,
"learning_rate": 3.4482758620689657e-05,
"loss": 0.0534,
"step": 305
},
{
"epoch": 3.31,
"learning_rate": 3.3405172413793105e-05,
"loss": 0.0578,
"step": 310
},
{
"epoch": 3.36,
"learning_rate": 3.232758620689655e-05,
"loss": 0.021,
"step": 315
},
{
"epoch": 3.41,
"learning_rate": 3.125e-05,
"loss": 0.0138,
"step": 320
},
{
"epoch": 3.47,
"learning_rate": 3.017241379310345e-05,
"loss": 0.0461,
"step": 325
},
{
"epoch": 3.52,
"learning_rate": 2.9094827586206897e-05,
"loss": 0.0791,
"step": 330
},
{
"epoch": 3.57,
"learning_rate": 2.8017241379310345e-05,
"loss": 0.0544,
"step": 335
},
{
"epoch": 3.63,
"learning_rate": 2.6939655172413796e-05,
"loss": 0.0455,
"step": 340
},
{
"epoch": 3.68,
"learning_rate": 2.5862068965517244e-05,
"loss": 0.0334,
"step": 345
},
{
"epoch": 3.73,
"learning_rate": 2.4784482758620692e-05,
"loss": 0.0099,
"step": 350
},
{
"epoch": 3.79,
"learning_rate": 2.370689655172414e-05,
"loss": 0.0274,
"step": 355
},
{
"epoch": 3.84,
"learning_rate": 2.2629310344827588e-05,
"loss": 0.0298,
"step": 360
},
{
"epoch": 3.89,
"learning_rate": 2.1551724137931033e-05,
"loss": 0.0238,
"step": 365
},
{
"epoch": 3.95,
"learning_rate": 2.0474137931034484e-05,
"loss": 0.025,
"step": 370
},
{
"epoch": 4.0,
"learning_rate": 1.9396551724137932e-05,
"loss": 0.0717,
"step": 375
},
{
"epoch": 4.0,
"eval_accuracy": 0.9982281284606866,
"eval_loss": 0.005040737800300121,
"eval_runtime": 195.0025,
"eval_samples_per_second": 23.154,
"eval_steps_per_second": 1.451,
"step": 375
},
{
"epoch": 4.05,
"learning_rate": 1.831896551724138e-05,
"loss": 0.0287,
"step": 380
},
{
"epoch": 4.11,
"learning_rate": 1.7241379310344828e-05,
"loss": 0.0194,
"step": 385
},
{
"epoch": 4.16,
"learning_rate": 1.6163793103448276e-05,
"loss": 0.0255,
"step": 390
},
{
"epoch": 4.21,
"learning_rate": 1.5086206896551724e-05,
"loss": 0.0315,
"step": 395
},
{
"epoch": 4.27,
"learning_rate": 1.4008620689655172e-05,
"loss": 0.0677,
"step": 400
},
{
"epoch": 4.32,
"learning_rate": 1.2931034482758622e-05,
"loss": 0.0137,
"step": 405
},
{
"epoch": 4.37,
"learning_rate": 1.185344827586207e-05,
"loss": 0.0165,
"step": 410
},
{
"epoch": 4.43,
"learning_rate": 1.0775862068965516e-05,
"loss": 0.0133,
"step": 415
},
{
"epoch": 4.48,
"learning_rate": 9.698275862068966e-06,
"loss": 0.0235,
"step": 420
},
{
"epoch": 4.53,
"learning_rate": 8.620689655172414e-06,
"loss": 0.0158,
"step": 425
},
{
"epoch": 4.59,
"learning_rate": 7.543103448275862e-06,
"loss": 0.0428,
"step": 430
},
{
"epoch": 4.64,
"learning_rate": 6.465517241379311e-06,
"loss": 0.04,
"step": 435
},
{
"epoch": 4.69,
"learning_rate": 5.387931034482758e-06,
"loss": 0.0048,
"step": 440
},
{
"epoch": 4.75,
"learning_rate": 4.310344827586207e-06,
"loss": 0.0242,
"step": 445
},
{
"epoch": 4.8,
"learning_rate": 3.2327586206896555e-06,
"loss": 0.0141,
"step": 450
},
{
"epoch": 4.85,
"learning_rate": 2.1551724137931035e-06,
"loss": 0.0076,
"step": 455
},
{
"epoch": 4.91,
"learning_rate": 1.0775862068965518e-06,
"loss": 0.0206,
"step": 460
},
{
"epoch": 4.96,
"learning_rate": 0.0,
"loss": 0.0012,
"step": 465
},
{
"epoch": 4.96,
"eval_accuracy": 0.9995570321151717,
"eval_loss": 0.001114627462811768,
"eval_runtime": 194.5559,
"eval_samples_per_second": 23.207,
"eval_steps_per_second": 1.455,
"step": 465
},
{
"epoch": 4.96,
"step": 465,
"total_flos": 8.138660625246413e+18,
"train_loss": 0.10703883119408161,
"train_runtime": 7147.9833,
"train_samples_per_second": 4.186,
"train_steps_per_second": 0.065
}
],
"max_steps": 465,
"num_train_epochs": 5,
"total_flos": 8.138660625246413e+18,
"trial_name": null,
"trial_params": null
}