raedinkhaled's picture
End of training
a51fae6
{
"best_metric": 0.9806603773584905,
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-mri/checkpoint-1341",
"epoch": 2.999441028507546,
"global_step": 1341,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 3.7037037037037037e-06,
"loss": 0.4997,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 7.4074074074074075e-06,
"loss": 0.4757,
"step": 20
},
{
"epoch": 0.07,
"learning_rate": 1.1111111111111112e-05,
"loss": 0.4668,
"step": 30
},
{
"epoch": 0.09,
"learning_rate": 1.4814814814814815e-05,
"loss": 0.4247,
"step": 40
},
{
"epoch": 0.11,
"learning_rate": 1.8518518518518518e-05,
"loss": 0.3901,
"step": 50
},
{
"epoch": 0.13,
"learning_rate": 2.2222222222222223e-05,
"loss": 0.3659,
"step": 60
},
{
"epoch": 0.16,
"learning_rate": 2.5925925925925925e-05,
"loss": 0.3264,
"step": 70
},
{
"epoch": 0.18,
"learning_rate": 2.962962962962963e-05,
"loss": 0.2907,
"step": 80
},
{
"epoch": 0.2,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.2786,
"step": 90
},
{
"epoch": 0.22,
"learning_rate": 3.7037037037037037e-05,
"loss": 0.2198,
"step": 100
},
{
"epoch": 0.25,
"learning_rate": 4.074074074074074e-05,
"loss": 0.2128,
"step": 110
},
{
"epoch": 0.27,
"learning_rate": 4.4444444444444447e-05,
"loss": 0.1964,
"step": 120
},
{
"epoch": 0.29,
"learning_rate": 4.814814814814815e-05,
"loss": 0.1769,
"step": 130
},
{
"epoch": 0.31,
"learning_rate": 4.979270315091211e-05,
"loss": 0.1848,
"step": 140
},
{
"epoch": 0.34,
"learning_rate": 4.9378109452736324e-05,
"loss": 0.1667,
"step": 150
},
{
"epoch": 0.36,
"learning_rate": 4.896351575456054e-05,
"loss": 0.1766,
"step": 160
},
{
"epoch": 0.38,
"learning_rate": 4.8548922056384746e-05,
"loss": 0.1647,
"step": 170
},
{
"epoch": 0.4,
"learning_rate": 4.817578772802654e-05,
"loss": 0.1408,
"step": 180
},
{
"epoch": 0.42,
"learning_rate": 4.7761194029850745e-05,
"loss": 0.1196,
"step": 190
},
{
"epoch": 0.45,
"learning_rate": 4.734660033167496e-05,
"loss": 0.1494,
"step": 200
},
{
"epoch": 0.47,
"learning_rate": 4.693200663349917e-05,
"loss": 0.1374,
"step": 210
},
{
"epoch": 0.49,
"learning_rate": 4.651741293532338e-05,
"loss": 0.1103,
"step": 220
},
{
"epoch": 0.51,
"learning_rate": 4.6102819237147596e-05,
"loss": 0.1022,
"step": 230
},
{
"epoch": 0.54,
"learning_rate": 4.568822553897181e-05,
"loss": 0.1162,
"step": 240
},
{
"epoch": 0.56,
"learning_rate": 4.5273631840796025e-05,
"loss": 0.1039,
"step": 250
},
{
"epoch": 0.58,
"learning_rate": 4.485903814262023e-05,
"loss": 0.1057,
"step": 260
},
{
"epoch": 0.6,
"learning_rate": 4.4444444444444447e-05,
"loss": 0.1047,
"step": 270
},
{
"epoch": 0.63,
"learning_rate": 4.402985074626866e-05,
"loss": 0.1001,
"step": 280
},
{
"epoch": 0.65,
"learning_rate": 4.3615257048092875e-05,
"loss": 0.0874,
"step": 290
},
{
"epoch": 0.67,
"learning_rate": 4.320066334991708e-05,
"loss": 0.0888,
"step": 300
},
{
"epoch": 0.69,
"learning_rate": 4.27860696517413e-05,
"loss": 0.1011,
"step": 310
},
{
"epoch": 0.72,
"learning_rate": 4.237147595356551e-05,
"loss": 0.0868,
"step": 320
},
{
"epoch": 0.74,
"learning_rate": 4.195688225538972e-05,
"loss": 0.094,
"step": 330
},
{
"epoch": 0.76,
"learning_rate": 4.1542288557213934e-05,
"loss": 0.1121,
"step": 340
},
{
"epoch": 0.78,
"learning_rate": 4.112769485903815e-05,
"loss": 0.0703,
"step": 350
},
{
"epoch": 0.8,
"learning_rate": 4.0713101160862356e-05,
"loss": 0.0858,
"step": 360
},
{
"epoch": 0.83,
"learning_rate": 4.029850746268657e-05,
"loss": 0.0729,
"step": 370
},
{
"epoch": 0.85,
"learning_rate": 3.9883913764510784e-05,
"loss": 0.0652,
"step": 380
},
{
"epoch": 0.87,
"learning_rate": 3.946932006633499e-05,
"loss": 0.073,
"step": 390
},
{
"epoch": 0.89,
"learning_rate": 3.9054726368159206e-05,
"loss": 0.0711,
"step": 400
},
{
"epoch": 0.92,
"learning_rate": 3.864013266998342e-05,
"loss": 0.0739,
"step": 410
},
{
"epoch": 0.94,
"learning_rate": 3.822553897180763e-05,
"loss": 0.074,
"step": 420
},
{
"epoch": 0.96,
"learning_rate": 3.781094527363184e-05,
"loss": 0.066,
"step": 430
},
{
"epoch": 0.98,
"learning_rate": 3.739635157545606e-05,
"loss": 0.0592,
"step": 440
},
{
"epoch": 1.0,
"eval_accuracy": 0.9694968553459119,
"eval_loss": 0.0823180079460144,
"eval_runtime": 2100.5651,
"eval_samples_per_second": 3.028,
"eval_steps_per_second": 0.095,
"step": 447
},
{
"epoch": 1.01,
"learning_rate": 3.6981757877280265e-05,
"loss": 0.0781,
"step": 450
},
{
"epoch": 1.03,
"learning_rate": 3.656716417910448e-05,
"loss": 0.039,
"step": 460
},
{
"epoch": 1.05,
"learning_rate": 3.6152570480928693e-05,
"loss": 0.0402,
"step": 470
},
{
"epoch": 1.07,
"learning_rate": 3.57379767827529e-05,
"loss": 0.0585,
"step": 480
},
{
"epoch": 1.1,
"learning_rate": 3.5323383084577115e-05,
"loss": 0.0524,
"step": 490
},
{
"epoch": 1.12,
"learning_rate": 3.490878938640133e-05,
"loss": 0.0344,
"step": 500
},
{
"epoch": 1.14,
"learning_rate": 3.449419568822554e-05,
"loss": 0.0346,
"step": 510
},
{
"epoch": 1.16,
"learning_rate": 3.407960199004975e-05,
"loss": 0.0474,
"step": 520
},
{
"epoch": 1.19,
"learning_rate": 3.3665008291873966e-05,
"loss": 0.0308,
"step": 530
},
{
"epoch": 1.21,
"learning_rate": 3.3250414593698174e-05,
"loss": 0.0323,
"step": 540
},
{
"epoch": 1.23,
"learning_rate": 3.283582089552239e-05,
"loss": 0.035,
"step": 550
},
{
"epoch": 1.25,
"learning_rate": 3.24212271973466e-05,
"loss": 0.0217,
"step": 560
},
{
"epoch": 1.28,
"learning_rate": 3.200663349917081e-05,
"loss": 0.0305,
"step": 570
},
{
"epoch": 1.3,
"learning_rate": 3.1592039800995024e-05,
"loss": 0.0524,
"step": 580
},
{
"epoch": 1.32,
"learning_rate": 3.117744610281924e-05,
"loss": 0.0368,
"step": 590
},
{
"epoch": 1.34,
"learning_rate": 3.0762852404643446e-05,
"loss": 0.0292,
"step": 600
},
{
"epoch": 1.36,
"learning_rate": 3.0348258706467664e-05,
"loss": 0.0304,
"step": 610
},
{
"epoch": 1.39,
"learning_rate": 2.993366500829188e-05,
"loss": 0.0391,
"step": 620
},
{
"epoch": 1.41,
"learning_rate": 2.9519071310116086e-05,
"loss": 0.0359,
"step": 630
},
{
"epoch": 1.43,
"learning_rate": 2.9145936981757878e-05,
"loss": 0.0689,
"step": 640
},
{
"epoch": 1.45,
"learning_rate": 2.8731343283582092e-05,
"loss": 0.0271,
"step": 650
},
{
"epoch": 1.48,
"learning_rate": 2.8316749585406303e-05,
"loss": 0.0333,
"step": 660
},
{
"epoch": 1.5,
"learning_rate": 2.7902155887230514e-05,
"loss": 0.044,
"step": 670
},
{
"epoch": 1.52,
"learning_rate": 2.748756218905473e-05,
"loss": 0.0326,
"step": 680
},
{
"epoch": 1.54,
"learning_rate": 2.7072968490878943e-05,
"loss": 0.0378,
"step": 690
},
{
"epoch": 1.57,
"learning_rate": 2.665837479270315e-05,
"loss": 0.0265,
"step": 700
},
{
"epoch": 1.59,
"learning_rate": 2.6243781094527365e-05,
"loss": 0.0289,
"step": 710
},
{
"epoch": 1.61,
"learning_rate": 2.582918739635158e-05,
"loss": 0.0232,
"step": 720
},
{
"epoch": 1.63,
"learning_rate": 2.5414593698175787e-05,
"loss": 0.0254,
"step": 730
},
{
"epoch": 1.66,
"learning_rate": 2.5e-05,
"loss": 0.033,
"step": 740
},
{
"epoch": 1.68,
"learning_rate": 2.4585406301824212e-05,
"loss": 0.0195,
"step": 750
},
{
"epoch": 1.7,
"learning_rate": 2.4170812603648427e-05,
"loss": 0.0252,
"step": 760
},
{
"epoch": 1.72,
"learning_rate": 2.3756218905472638e-05,
"loss": 0.0235,
"step": 770
},
{
"epoch": 1.74,
"learning_rate": 2.334162520729685e-05,
"loss": 0.0176,
"step": 780
},
{
"epoch": 1.77,
"learning_rate": 2.2927031509121063e-05,
"loss": 0.026,
"step": 790
},
{
"epoch": 1.79,
"learning_rate": 2.2512437810945274e-05,
"loss": 0.0224,
"step": 800
},
{
"epoch": 1.81,
"learning_rate": 2.2097844112769485e-05,
"loss": 0.0294,
"step": 810
},
{
"epoch": 1.83,
"learning_rate": 2.16832504145937e-05,
"loss": 0.0288,
"step": 820
},
{
"epoch": 1.86,
"learning_rate": 2.126865671641791e-05,
"loss": 0.0385,
"step": 830
},
{
"epoch": 1.88,
"learning_rate": 2.0854063018242125e-05,
"loss": 0.021,
"step": 840
},
{
"epoch": 1.9,
"learning_rate": 2.0439469320066336e-05,
"loss": 0.0235,
"step": 850
},
{
"epoch": 1.92,
"learning_rate": 2.002487562189055e-05,
"loss": 0.0249,
"step": 860
},
{
"epoch": 1.95,
"learning_rate": 1.961028192371476e-05,
"loss": 0.0222,
"step": 870
},
{
"epoch": 1.97,
"learning_rate": 1.9195688225538972e-05,
"loss": 0.0318,
"step": 880
},
{
"epoch": 1.99,
"learning_rate": 1.8781094527363186e-05,
"loss": 0.0196,
"step": 890
},
{
"epoch": 2.0,
"eval_accuracy": 0.9738993710691823,
"eval_loss": 0.07613054662942886,
"eval_runtime": 49.4856,
"eval_samples_per_second": 128.522,
"eval_steps_per_second": 4.021,
"step": 894
},
{
"epoch": 2.01,
"learning_rate": 1.8366500829187397e-05,
"loss": 0.0208,
"step": 900
},
{
"epoch": 2.04,
"learning_rate": 1.795190713101161e-05,
"loss": 0.013,
"step": 910
},
{
"epoch": 2.06,
"learning_rate": 1.7537313432835823e-05,
"loss": 0.0136,
"step": 920
},
{
"epoch": 2.08,
"learning_rate": 1.7122719734660034e-05,
"loss": 0.0072,
"step": 930
},
{
"epoch": 2.1,
"learning_rate": 1.6708126036484245e-05,
"loss": 0.0128,
"step": 940
},
{
"epoch": 2.13,
"learning_rate": 1.629353233830846e-05,
"loss": 0.0072,
"step": 950
},
{
"epoch": 2.15,
"learning_rate": 1.587893864013267e-05,
"loss": 0.0056,
"step": 960
},
{
"epoch": 2.17,
"learning_rate": 1.546434494195688e-05,
"loss": 0.0151,
"step": 970
},
{
"epoch": 2.19,
"learning_rate": 1.5049751243781095e-05,
"loss": 0.0124,
"step": 980
},
{
"epoch": 2.21,
"learning_rate": 1.4635157545605308e-05,
"loss": 0.0157,
"step": 990
},
{
"epoch": 2.24,
"learning_rate": 1.4220563847429519e-05,
"loss": 0.0095,
"step": 1000
},
{
"epoch": 2.26,
"learning_rate": 1.3805970149253733e-05,
"loss": 0.0107,
"step": 1010
},
{
"epoch": 2.28,
"learning_rate": 1.3391376451077944e-05,
"loss": 0.0131,
"step": 1020
},
{
"epoch": 2.3,
"learning_rate": 1.2976782752902155e-05,
"loss": 0.0072,
"step": 1030
},
{
"epoch": 2.33,
"learning_rate": 1.256218905472637e-05,
"loss": 0.0148,
"step": 1040
},
{
"epoch": 2.35,
"learning_rate": 1.214759535655058e-05,
"loss": 0.0086,
"step": 1050
},
{
"epoch": 2.37,
"learning_rate": 1.1733001658374792e-05,
"loss": 0.0129,
"step": 1060
},
{
"epoch": 2.39,
"learning_rate": 1.1318407960199006e-05,
"loss": 0.017,
"step": 1070
},
{
"epoch": 2.42,
"learning_rate": 1.0903814262023219e-05,
"loss": 0.013,
"step": 1080
},
{
"epoch": 2.44,
"learning_rate": 1.048922056384743e-05,
"loss": 0.0056,
"step": 1090
},
{
"epoch": 2.46,
"learning_rate": 1.0074626865671643e-05,
"loss": 0.0089,
"step": 1100
},
{
"epoch": 2.48,
"learning_rate": 9.660033167495855e-06,
"loss": 0.0072,
"step": 1110
},
{
"epoch": 2.51,
"learning_rate": 9.245439469320066e-06,
"loss": 0.0113,
"step": 1120
},
{
"epoch": 2.53,
"learning_rate": 8.830845771144279e-06,
"loss": 0.0068,
"step": 1130
},
{
"epoch": 2.55,
"learning_rate": 8.416252072968492e-06,
"loss": 0.0128,
"step": 1140
},
{
"epoch": 2.57,
"learning_rate": 8.001658374792703e-06,
"loss": 0.0061,
"step": 1150
},
{
"epoch": 2.59,
"learning_rate": 7.587064676616916e-06,
"loss": 0.0088,
"step": 1160
},
{
"epoch": 2.62,
"learning_rate": 7.172470978441129e-06,
"loss": 0.0037,
"step": 1170
},
{
"epoch": 2.64,
"learning_rate": 6.75787728026534e-06,
"loss": 0.0071,
"step": 1180
},
{
"epoch": 2.66,
"learning_rate": 6.343283582089552e-06,
"loss": 0.0038,
"step": 1190
},
{
"epoch": 2.68,
"learning_rate": 5.928689883913765e-06,
"loss": 0.0116,
"step": 1200
},
{
"epoch": 2.71,
"learning_rate": 5.514096185737977e-06,
"loss": 0.0089,
"step": 1210
},
{
"epoch": 2.73,
"learning_rate": 5.099502487562189e-06,
"loss": 0.0091,
"step": 1220
},
{
"epoch": 2.75,
"learning_rate": 4.6849087893864014e-06,
"loss": 0.0035,
"step": 1230
},
{
"epoch": 2.77,
"learning_rate": 4.270315091210614e-06,
"loss": 0.0066,
"step": 1240
},
{
"epoch": 2.8,
"learning_rate": 3.855721393034826e-06,
"loss": 0.0033,
"step": 1250
},
{
"epoch": 2.82,
"learning_rate": 3.4411276948590386e-06,
"loss": 0.0061,
"step": 1260
},
{
"epoch": 2.84,
"learning_rate": 3.0265339966832505e-06,
"loss": 0.0034,
"step": 1270
},
{
"epoch": 2.86,
"learning_rate": 2.6119402985074627e-06,
"loss": 0.0075,
"step": 1280
},
{
"epoch": 2.89,
"learning_rate": 2.197346600331675e-06,
"loss": 0.0094,
"step": 1290
},
{
"epoch": 2.91,
"learning_rate": 1.7827529021558872e-06,
"loss": 0.0098,
"step": 1300
},
{
"epoch": 2.93,
"learning_rate": 1.3681592039800995e-06,
"loss": 0.0067,
"step": 1310
},
{
"epoch": 2.95,
"learning_rate": 9.535655058043119e-07,
"loss": 0.0036,
"step": 1320
},
{
"epoch": 2.97,
"learning_rate": 5.38971807628524e-07,
"loss": 0.0045,
"step": 1330
},
{
"epoch": 3.0,
"learning_rate": 1.2437810945273633e-07,
"loss": 0.0058,
"step": 1340
},
{
"epoch": 3.0,
"eval_accuracy": 0.9806603773584905,
"eval_loss": 0.06080754101276398,
"eval_runtime": 49.2168,
"eval_samples_per_second": 129.224,
"eval_steps_per_second": 4.043,
"step": 1341
},
{
"epoch": 3.0,
"step": 1341,
"total_flos": 4.2672264771137864e+18,
"train_loss": 0.07098129998106373,
"train_runtime": 22089.0495,
"train_samples_per_second": 7.773,
"train_steps_per_second": 0.061
}
],
"max_steps": 1341,
"num_train_epochs": 3,
"total_flos": 4.2672264771137864e+18,
"trial_name": null,
"trial_params": null
}