mansee's picture
Training in progress, epoch 1
867de38 verified
{
"best_metric": 0.8009728415079044,
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-2082",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 2082,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 2.3923444976076554e-06,
"loss": 1.4479,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 4.784688995215311e-06,
"loss": 1.4139,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 7.177033492822967e-06,
"loss": 1.4006,
"step": 30
},
{
"epoch": 0.06,
"learning_rate": 9.569377990430622e-06,
"loss": 1.3654,
"step": 40
},
{
"epoch": 0.07,
"learning_rate": 1.1961722488038278e-05,
"loss": 1.3395,
"step": 50
},
{
"epoch": 0.09,
"learning_rate": 1.4354066985645934e-05,
"loss": 1.2985,
"step": 60
},
{
"epoch": 0.1,
"learning_rate": 1.674641148325359e-05,
"loss": 1.2354,
"step": 70
},
{
"epoch": 0.12,
"learning_rate": 1.9138755980861243e-05,
"loss": 1.1581,
"step": 80
},
{
"epoch": 0.13,
"learning_rate": 2.1531100478468903e-05,
"loss": 1.0563,
"step": 90
},
{
"epoch": 0.14,
"learning_rate": 2.3923444976076556e-05,
"loss": 0.9842,
"step": 100
},
{
"epoch": 0.16,
"learning_rate": 2.6315789473684212e-05,
"loss": 0.9439,
"step": 110
},
{
"epoch": 0.17,
"learning_rate": 2.8708133971291868e-05,
"loss": 0.9081,
"step": 120
},
{
"epoch": 0.19,
"learning_rate": 3.110047846889952e-05,
"loss": 0.8584,
"step": 130
},
{
"epoch": 0.2,
"learning_rate": 3.349282296650718e-05,
"loss": 0.8333,
"step": 140
},
{
"epoch": 0.22,
"learning_rate": 3.5885167464114834e-05,
"loss": 0.8098,
"step": 150
},
{
"epoch": 0.23,
"learning_rate": 3.8277511961722486e-05,
"loss": 0.812,
"step": 160
},
{
"epoch": 0.24,
"learning_rate": 4.0669856459330146e-05,
"loss": 0.7806,
"step": 170
},
{
"epoch": 0.26,
"learning_rate": 4.3062200956937806e-05,
"loss": 0.8163,
"step": 180
},
{
"epoch": 0.27,
"learning_rate": 4.545454545454546e-05,
"loss": 0.7505,
"step": 190
},
{
"epoch": 0.29,
"learning_rate": 4.784688995215311e-05,
"loss": 0.744,
"step": 200
},
{
"epoch": 0.3,
"learning_rate": 4.997330485851575e-05,
"loss": 0.7064,
"step": 210
},
{
"epoch": 0.32,
"learning_rate": 4.9706353443673256e-05,
"loss": 0.7661,
"step": 220
},
{
"epoch": 0.33,
"learning_rate": 4.943940202883076e-05,
"loss": 0.738,
"step": 230
},
{
"epoch": 0.35,
"learning_rate": 4.917245061398826e-05,
"loss": 0.7195,
"step": 240
},
{
"epoch": 0.36,
"learning_rate": 4.890549919914576e-05,
"loss": 0.7131,
"step": 250
},
{
"epoch": 0.37,
"learning_rate": 4.863854778430326e-05,
"loss": 0.7106,
"step": 260
},
{
"epoch": 0.39,
"learning_rate": 4.837159636946076e-05,
"loss": 0.7293,
"step": 270
},
{
"epoch": 0.4,
"learning_rate": 4.810464495461826e-05,
"loss": 0.6959,
"step": 280
},
{
"epoch": 0.42,
"learning_rate": 4.783769353977576e-05,
"loss": 0.6844,
"step": 290
},
{
"epoch": 0.43,
"learning_rate": 4.7570742124933263e-05,
"loss": 0.6965,
"step": 300
},
{
"epoch": 0.45,
"learning_rate": 4.7303790710090764e-05,
"loss": 0.6807,
"step": 310
},
{
"epoch": 0.46,
"learning_rate": 4.703683929524827e-05,
"loss": 0.6954,
"step": 320
},
{
"epoch": 0.48,
"learning_rate": 4.6769887880405766e-05,
"loss": 0.6814,
"step": 330
},
{
"epoch": 0.49,
"learning_rate": 4.650293646556327e-05,
"loss": 0.6482,
"step": 340
},
{
"epoch": 0.5,
"learning_rate": 4.623598505072077e-05,
"loss": 0.6268,
"step": 350
},
{
"epoch": 0.52,
"learning_rate": 4.5969033635878276e-05,
"loss": 0.6598,
"step": 360
},
{
"epoch": 0.53,
"learning_rate": 4.570208222103578e-05,
"loss": 0.6507,
"step": 370
},
{
"epoch": 0.55,
"learning_rate": 4.543513080619328e-05,
"loss": 0.6453,
"step": 380
},
{
"epoch": 0.56,
"learning_rate": 4.516817939135078e-05,
"loss": 0.6599,
"step": 390
},
{
"epoch": 0.58,
"learning_rate": 4.490122797650827e-05,
"loss": 0.6673,
"step": 400
},
{
"epoch": 0.59,
"learning_rate": 4.463427656166578e-05,
"loss": 0.6551,
"step": 410
},
{
"epoch": 0.61,
"learning_rate": 4.436732514682328e-05,
"loss": 0.6788,
"step": 420
},
{
"epoch": 0.62,
"learning_rate": 4.410037373198078e-05,
"loss": 0.6611,
"step": 430
},
{
"epoch": 0.63,
"learning_rate": 4.383342231713828e-05,
"loss": 0.6666,
"step": 440
},
{
"epoch": 0.65,
"learning_rate": 4.3566470902295784e-05,
"loss": 0.6465,
"step": 450
},
{
"epoch": 0.66,
"learning_rate": 4.329951948745329e-05,
"loss": 0.6702,
"step": 460
},
{
"epoch": 0.68,
"learning_rate": 4.3032568072610786e-05,
"loss": 0.6287,
"step": 470
},
{
"epoch": 0.69,
"learning_rate": 4.276561665776829e-05,
"loss": 0.6588,
"step": 480
},
{
"epoch": 0.71,
"learning_rate": 4.249866524292579e-05,
"loss": 0.6607,
"step": 490
},
{
"epoch": 0.72,
"learning_rate": 4.223171382808329e-05,
"loss": 0.6183,
"step": 500
},
{
"epoch": 0.73,
"learning_rate": 4.1964762413240796e-05,
"loss": 0.6261,
"step": 510
},
{
"epoch": 0.75,
"learning_rate": 4.16978109983983e-05,
"loss": 0.6595,
"step": 520
},
{
"epoch": 0.76,
"learning_rate": 4.143085958355579e-05,
"loss": 0.6274,
"step": 530
},
{
"epoch": 0.78,
"learning_rate": 4.116390816871329e-05,
"loss": 0.6195,
"step": 540
},
{
"epoch": 0.79,
"learning_rate": 4.089695675387079e-05,
"loss": 0.6537,
"step": 550
},
{
"epoch": 0.81,
"learning_rate": 4.06300053390283e-05,
"loss": 0.607,
"step": 560
},
{
"epoch": 0.82,
"learning_rate": 4.03630539241858e-05,
"loss": 0.622,
"step": 570
},
{
"epoch": 0.84,
"learning_rate": 4.00961025093433e-05,
"loss": 0.6408,
"step": 580
},
{
"epoch": 0.85,
"learning_rate": 3.9829151094500804e-05,
"loss": 0.6265,
"step": 590
},
{
"epoch": 0.86,
"learning_rate": 3.9562199679658305e-05,
"loss": 0.6149,
"step": 600
},
{
"epoch": 0.88,
"learning_rate": 3.9295248264815805e-05,
"loss": 0.6153,
"step": 610
},
{
"epoch": 0.89,
"learning_rate": 3.9028296849973306e-05,
"loss": 0.5777,
"step": 620
},
{
"epoch": 0.91,
"learning_rate": 3.876134543513081e-05,
"loss": 0.6042,
"step": 630
},
{
"epoch": 0.92,
"learning_rate": 3.849439402028831e-05,
"loss": 0.5802,
"step": 640
},
{
"epoch": 0.94,
"learning_rate": 3.822744260544581e-05,
"loss": 0.617,
"step": 650
},
{
"epoch": 0.95,
"learning_rate": 3.796049119060332e-05,
"loss": 0.5741,
"step": 660
},
{
"epoch": 0.97,
"learning_rate": 3.769353977576081e-05,
"loss": 0.5801,
"step": 670
},
{
"epoch": 0.98,
"learning_rate": 3.742658836091831e-05,
"loss": 0.5933,
"step": 680
},
{
"epoch": 0.99,
"learning_rate": 3.715963694607581e-05,
"loss": 0.5941,
"step": 690
},
{
"epoch": 1.0,
"eval_accuracy": 0.7458451560599919,
"eval_loss": 0.46203261613845825,
"eval_runtime": 104.9031,
"eval_samples_per_second": 94.068,
"eval_steps_per_second": 2.946,
"step": 694
},
{
"epoch": 1.01,
"learning_rate": 3.689268553123332e-05,
"loss": 0.592,
"step": 700
},
{
"epoch": 1.02,
"learning_rate": 3.662573411639082e-05,
"loss": 0.5486,
"step": 710
},
{
"epoch": 1.04,
"learning_rate": 3.635878270154832e-05,
"loss": 0.5445,
"step": 720
},
{
"epoch": 1.05,
"learning_rate": 3.609183128670582e-05,
"loss": 0.5543,
"step": 730
},
{
"epoch": 1.07,
"learning_rate": 3.582487987186332e-05,
"loss": 0.5438,
"step": 740
},
{
"epoch": 1.08,
"learning_rate": 3.5557928457020825e-05,
"loss": 0.557,
"step": 750
},
{
"epoch": 1.1,
"learning_rate": 3.5290977042178326e-05,
"loss": 0.5419,
"step": 760
},
{
"epoch": 1.11,
"learning_rate": 3.502402562733583e-05,
"loss": 0.5643,
"step": 770
},
{
"epoch": 1.12,
"learning_rate": 3.475707421249333e-05,
"loss": 0.584,
"step": 780
},
{
"epoch": 1.14,
"learning_rate": 3.449012279765083e-05,
"loss": 0.5938,
"step": 790
},
{
"epoch": 1.15,
"learning_rate": 3.422317138280833e-05,
"loss": 0.5766,
"step": 800
},
{
"epoch": 1.17,
"learning_rate": 3.395621996796583e-05,
"loss": 0.574,
"step": 810
},
{
"epoch": 1.18,
"learning_rate": 3.368926855312333e-05,
"loss": 0.5888,
"step": 820
},
{
"epoch": 1.2,
"learning_rate": 3.342231713828083e-05,
"loss": 0.5593,
"step": 830
},
{
"epoch": 1.21,
"learning_rate": 3.315536572343833e-05,
"loss": 0.56,
"step": 840
},
{
"epoch": 1.22,
"learning_rate": 3.288841430859584e-05,
"loss": 0.5459,
"step": 850
},
{
"epoch": 1.24,
"learning_rate": 3.262146289375334e-05,
"loss": 0.546,
"step": 860
},
{
"epoch": 1.25,
"learning_rate": 3.2354511478910836e-05,
"loss": 0.5236,
"step": 870
},
{
"epoch": 1.27,
"learning_rate": 3.208756006406834e-05,
"loss": 0.5608,
"step": 880
},
{
"epoch": 1.28,
"learning_rate": 3.1820608649225845e-05,
"loss": 0.5749,
"step": 890
},
{
"epoch": 1.3,
"learning_rate": 3.1553657234383346e-05,
"loss": 0.5551,
"step": 900
},
{
"epoch": 1.31,
"learning_rate": 3.1286705819540846e-05,
"loss": 0.5638,
"step": 910
},
{
"epoch": 1.33,
"learning_rate": 3.101975440469835e-05,
"loss": 0.5491,
"step": 920
},
{
"epoch": 1.34,
"learning_rate": 3.075280298985585e-05,
"loss": 0.5183,
"step": 930
},
{
"epoch": 1.35,
"learning_rate": 3.0485851575013346e-05,
"loss": 0.5334,
"step": 940
},
{
"epoch": 1.37,
"learning_rate": 3.021890016017085e-05,
"loss": 0.5396,
"step": 950
},
{
"epoch": 1.38,
"learning_rate": 2.995194874532835e-05,
"loss": 0.5919,
"step": 960
},
{
"epoch": 1.4,
"learning_rate": 2.9684997330485852e-05,
"loss": 0.5492,
"step": 970
},
{
"epoch": 1.41,
"learning_rate": 2.9418045915643356e-05,
"loss": 0.54,
"step": 980
},
{
"epoch": 1.43,
"learning_rate": 2.9151094500800857e-05,
"loss": 0.5464,
"step": 990
},
{
"epoch": 1.44,
"learning_rate": 2.8884143085958358e-05,
"loss": 0.5424,
"step": 1000
},
{
"epoch": 1.46,
"learning_rate": 2.8617191671115856e-05,
"loss": 0.5649,
"step": 1010
},
{
"epoch": 1.47,
"learning_rate": 2.8350240256273357e-05,
"loss": 0.5231,
"step": 1020
},
{
"epoch": 1.48,
"learning_rate": 2.808328884143086e-05,
"loss": 0.5286,
"step": 1030
},
{
"epoch": 1.5,
"learning_rate": 2.7816337426588362e-05,
"loss": 0.5373,
"step": 1040
},
{
"epoch": 1.51,
"learning_rate": 2.7549386011745866e-05,
"loss": 0.5611,
"step": 1050
},
{
"epoch": 1.53,
"learning_rate": 2.7282434596903367e-05,
"loss": 0.5209,
"step": 1060
},
{
"epoch": 1.54,
"learning_rate": 2.7015483182060868e-05,
"loss": 0.5659,
"step": 1070
},
{
"epoch": 1.56,
"learning_rate": 2.6748531767218365e-05,
"loss": 0.5597,
"step": 1080
},
{
"epoch": 1.57,
"learning_rate": 2.6481580352375866e-05,
"loss": 0.5446,
"step": 1090
},
{
"epoch": 1.59,
"learning_rate": 2.621462893753337e-05,
"loss": 0.5282,
"step": 1100
},
{
"epoch": 1.6,
"learning_rate": 2.594767752269087e-05,
"loss": 0.5635,
"step": 1110
},
{
"epoch": 1.61,
"learning_rate": 2.5680726107848373e-05,
"loss": 0.5449,
"step": 1120
},
{
"epoch": 1.63,
"learning_rate": 2.5413774693005877e-05,
"loss": 0.5426,
"step": 1130
},
{
"epoch": 1.64,
"learning_rate": 2.5146823278163374e-05,
"loss": 0.4938,
"step": 1140
},
{
"epoch": 1.66,
"learning_rate": 2.487987186332088e-05,
"loss": 0.532,
"step": 1150
},
{
"epoch": 1.67,
"learning_rate": 2.4612920448478376e-05,
"loss": 0.552,
"step": 1160
},
{
"epoch": 1.69,
"learning_rate": 2.434596903363588e-05,
"loss": 0.5506,
"step": 1170
},
{
"epoch": 1.7,
"learning_rate": 2.407901761879338e-05,
"loss": 0.5466,
"step": 1180
},
{
"epoch": 1.71,
"learning_rate": 2.3812066203950882e-05,
"loss": 0.5244,
"step": 1190
},
{
"epoch": 1.73,
"learning_rate": 2.3545114789108383e-05,
"loss": 0.5397,
"step": 1200
},
{
"epoch": 1.74,
"learning_rate": 2.3278163374265884e-05,
"loss": 0.5262,
"step": 1210
},
{
"epoch": 1.76,
"learning_rate": 2.301121195942339e-05,
"loss": 0.5458,
"step": 1220
},
{
"epoch": 1.77,
"learning_rate": 2.2744260544580886e-05,
"loss": 0.5445,
"step": 1230
},
{
"epoch": 1.79,
"learning_rate": 2.247730912973839e-05,
"loss": 0.5246,
"step": 1240
},
{
"epoch": 1.8,
"learning_rate": 2.221035771489589e-05,
"loss": 0.5366,
"step": 1250
},
{
"epoch": 1.82,
"learning_rate": 2.194340630005339e-05,
"loss": 0.5158,
"step": 1260
},
{
"epoch": 1.83,
"learning_rate": 2.1676454885210893e-05,
"loss": 0.5354,
"step": 1270
},
{
"epoch": 1.84,
"learning_rate": 2.1409503470368394e-05,
"loss": 0.5365,
"step": 1280
},
{
"epoch": 1.86,
"learning_rate": 2.1142552055525898e-05,
"loss": 0.5094,
"step": 1290
},
{
"epoch": 1.87,
"learning_rate": 2.0875600640683396e-05,
"loss": 0.5393,
"step": 1300
},
{
"epoch": 1.89,
"learning_rate": 2.0608649225840897e-05,
"loss": 0.4804,
"step": 1310
},
{
"epoch": 1.9,
"learning_rate": 2.03416978109984e-05,
"loss": 0.4944,
"step": 1320
},
{
"epoch": 1.92,
"learning_rate": 2.00747463961559e-05,
"loss": 0.5167,
"step": 1330
},
{
"epoch": 1.93,
"learning_rate": 1.9807794981313403e-05,
"loss": 0.5164,
"step": 1340
},
{
"epoch": 1.95,
"learning_rate": 1.9540843566470904e-05,
"loss": 0.522,
"step": 1350
},
{
"epoch": 1.96,
"learning_rate": 1.9273892151628405e-05,
"loss": 0.5077,
"step": 1360
},
{
"epoch": 1.97,
"learning_rate": 1.9006940736785906e-05,
"loss": 0.5311,
"step": 1370
},
{
"epoch": 1.99,
"learning_rate": 1.8739989321943407e-05,
"loss": 0.4836,
"step": 1380
},
{
"epoch": 2.0,
"eval_accuracy": 0.792359140656668,
"eval_loss": 0.38869696855545044,
"eval_runtime": 102.7122,
"eval_samples_per_second": 96.074,
"eval_steps_per_second": 3.008,
"step": 1388
},
{
"epoch": 2.0,
"learning_rate": 1.847303790710091e-05,
"loss": 0.4986,
"step": 1390
},
{
"epoch": 2.02,
"learning_rate": 1.820608649225841e-05,
"loss": 0.5246,
"step": 1400
},
{
"epoch": 2.03,
"learning_rate": 1.7939135077415913e-05,
"loss": 0.5002,
"step": 1410
},
{
"epoch": 2.05,
"learning_rate": 1.7672183662573414e-05,
"loss": 0.4831,
"step": 1420
},
{
"epoch": 2.06,
"learning_rate": 1.740523224773091e-05,
"loss": 0.516,
"step": 1430
},
{
"epoch": 2.07,
"learning_rate": 1.7138280832888415e-05,
"loss": 0.491,
"step": 1440
},
{
"epoch": 2.09,
"learning_rate": 1.6871329418045916e-05,
"loss": 0.5351,
"step": 1450
},
{
"epoch": 2.1,
"learning_rate": 1.660437800320342e-05,
"loss": 0.5093,
"step": 1460
},
{
"epoch": 2.12,
"learning_rate": 1.6337426588360918e-05,
"loss": 0.5097,
"step": 1470
},
{
"epoch": 2.13,
"learning_rate": 1.607047517351842e-05,
"loss": 0.4834,
"step": 1480
},
{
"epoch": 2.15,
"learning_rate": 1.5803523758675923e-05,
"loss": 0.4861,
"step": 1490
},
{
"epoch": 2.16,
"learning_rate": 1.553657234383342e-05,
"loss": 0.4907,
"step": 1500
},
{
"epoch": 2.18,
"learning_rate": 1.5269620928990925e-05,
"loss": 0.5012,
"step": 1510
},
{
"epoch": 2.19,
"learning_rate": 1.5002669514148426e-05,
"loss": 0.448,
"step": 1520
},
{
"epoch": 2.2,
"learning_rate": 1.4735718099305925e-05,
"loss": 0.4973,
"step": 1530
},
{
"epoch": 2.22,
"learning_rate": 1.4468766684463428e-05,
"loss": 0.506,
"step": 1540
},
{
"epoch": 2.23,
"learning_rate": 1.420181526962093e-05,
"loss": 0.4568,
"step": 1550
},
{
"epoch": 2.25,
"learning_rate": 1.3934863854778431e-05,
"loss": 0.489,
"step": 1560
},
{
"epoch": 2.26,
"learning_rate": 1.366791243993593e-05,
"loss": 0.4819,
"step": 1570
},
{
"epoch": 2.28,
"learning_rate": 1.3400961025093433e-05,
"loss": 0.516,
"step": 1580
},
{
"epoch": 2.29,
"learning_rate": 1.3134009610250936e-05,
"loss": 0.494,
"step": 1590
},
{
"epoch": 2.31,
"learning_rate": 1.2867058195408435e-05,
"loss": 0.4747,
"step": 1600
},
{
"epoch": 2.32,
"learning_rate": 1.2600106780565938e-05,
"loss": 0.4525,
"step": 1610
},
{
"epoch": 2.33,
"learning_rate": 1.2333155365723439e-05,
"loss": 0.4705,
"step": 1620
},
{
"epoch": 2.35,
"learning_rate": 1.206620395088094e-05,
"loss": 0.5065,
"step": 1630
},
{
"epoch": 2.36,
"learning_rate": 1.179925253603844e-05,
"loss": 0.469,
"step": 1640
},
{
"epoch": 2.38,
"learning_rate": 1.1532301121195943e-05,
"loss": 0.4831,
"step": 1650
},
{
"epoch": 2.39,
"learning_rate": 1.1265349706353444e-05,
"loss": 0.4784,
"step": 1660
},
{
"epoch": 2.41,
"learning_rate": 1.0998398291510947e-05,
"loss": 0.4768,
"step": 1670
},
{
"epoch": 2.42,
"learning_rate": 1.0731446876668448e-05,
"loss": 0.4718,
"step": 1680
},
{
"epoch": 2.44,
"learning_rate": 1.0464495461825948e-05,
"loss": 0.4492,
"step": 1690
},
{
"epoch": 2.45,
"learning_rate": 1.019754404698345e-05,
"loss": 0.4921,
"step": 1700
},
{
"epoch": 2.46,
"learning_rate": 9.93059263214095e-06,
"loss": 0.4963,
"step": 1710
},
{
"epoch": 2.48,
"learning_rate": 9.663641217298453e-06,
"loss": 0.5026,
"step": 1720
},
{
"epoch": 2.49,
"learning_rate": 9.396689802455954e-06,
"loss": 0.4952,
"step": 1730
},
{
"epoch": 2.51,
"learning_rate": 9.129738387613455e-06,
"loss": 0.4896,
"step": 1740
},
{
"epoch": 2.52,
"learning_rate": 8.862786972770956e-06,
"loss": 0.4523,
"step": 1750
},
{
"epoch": 2.54,
"learning_rate": 8.595835557928457e-06,
"loss": 0.4524,
"step": 1760
},
{
"epoch": 2.55,
"learning_rate": 8.32888414308596e-06,
"loss": 0.5124,
"step": 1770
},
{
"epoch": 2.56,
"learning_rate": 8.06193272824346e-06,
"loss": 0.5054,
"step": 1780
},
{
"epoch": 2.58,
"learning_rate": 7.794981313400963e-06,
"loss": 0.5123,
"step": 1790
},
{
"epoch": 2.59,
"learning_rate": 7.528029898558463e-06,
"loss": 0.4805,
"step": 1800
},
{
"epoch": 2.61,
"learning_rate": 7.261078483715964e-06,
"loss": 0.511,
"step": 1810
},
{
"epoch": 2.62,
"learning_rate": 6.9941270688734655e-06,
"loss": 0.4488,
"step": 1820
},
{
"epoch": 2.64,
"learning_rate": 6.727175654030966e-06,
"loss": 0.491,
"step": 1830
},
{
"epoch": 2.65,
"learning_rate": 6.460224239188468e-06,
"loss": 0.5166,
"step": 1840
},
{
"epoch": 2.67,
"learning_rate": 6.193272824345969e-06,
"loss": 0.4727,
"step": 1850
},
{
"epoch": 2.68,
"learning_rate": 5.926321409503471e-06,
"loss": 0.4733,
"step": 1860
},
{
"epoch": 2.69,
"learning_rate": 5.659369994660972e-06,
"loss": 0.4678,
"step": 1870
},
{
"epoch": 2.71,
"learning_rate": 5.3924185798184735e-06,
"loss": 0.4781,
"step": 1880
},
{
"epoch": 2.72,
"learning_rate": 5.1254671649759744e-06,
"loss": 0.4796,
"step": 1890
},
{
"epoch": 2.74,
"learning_rate": 4.858515750133475e-06,
"loss": 0.4743,
"step": 1900
},
{
"epoch": 2.75,
"learning_rate": 4.591564335290977e-06,
"loss": 0.4762,
"step": 1910
},
{
"epoch": 2.77,
"learning_rate": 4.324612920448479e-06,
"loss": 0.4579,
"step": 1920
},
{
"epoch": 2.78,
"learning_rate": 4.05766150560598e-06,
"loss": 0.4649,
"step": 1930
},
{
"epoch": 2.8,
"learning_rate": 3.7907100907634816e-06,
"loss": 0.4576,
"step": 1940
},
{
"epoch": 2.81,
"learning_rate": 3.5237586759209825e-06,
"loss": 0.4711,
"step": 1950
},
{
"epoch": 2.82,
"learning_rate": 3.256807261078484e-06,
"loss": 0.4942,
"step": 1960
},
{
"epoch": 2.84,
"learning_rate": 2.989855846235985e-06,
"loss": 0.4716,
"step": 1970
},
{
"epoch": 2.85,
"learning_rate": 2.7229044313934865e-06,
"loss": 0.4874,
"step": 1980
},
{
"epoch": 2.87,
"learning_rate": 2.455953016550988e-06,
"loss": 0.4933,
"step": 1990
},
{
"epoch": 2.88,
"learning_rate": 2.189001601708489e-06,
"loss": 0.4802,
"step": 2000
},
{
"epoch": 2.9,
"learning_rate": 1.9220501868659905e-06,
"loss": 0.4897,
"step": 2010
},
{
"epoch": 2.91,
"learning_rate": 1.6550987720234916e-06,
"loss": 0.4512,
"step": 2020
},
{
"epoch": 2.93,
"learning_rate": 1.3881473571809932e-06,
"loss": 0.4543,
"step": 2030
},
{
"epoch": 2.94,
"learning_rate": 1.1211959423384945e-06,
"loss": 0.48,
"step": 2040
},
{
"epoch": 2.95,
"learning_rate": 8.542445274959957e-07,
"loss": 0.4739,
"step": 2050
},
{
"epoch": 2.97,
"learning_rate": 5.872931126534971e-07,
"loss": 0.4669,
"step": 2060
},
{
"epoch": 2.98,
"learning_rate": 3.203416978109984e-07,
"loss": 0.4674,
"step": 2070
},
{
"epoch": 3.0,
"learning_rate": 5.339028296849973e-08,
"loss": 0.4672,
"step": 2080
},
{
"epoch": 3.0,
"eval_accuracy": 0.8009728415079044,
"eval_loss": 0.3678824007511139,
"eval_runtime": 102.7271,
"eval_samples_per_second": 96.06,
"eval_steps_per_second": 3.008,
"step": 2082
},
{
"epoch": 3.0,
"step": 2082,
"total_flos": 6.622303803251835e+18,
"train_loss": 0.5971084463836824,
"train_runtime": 3243.1106,
"train_samples_per_second": 82.147,
"train_steps_per_second": 0.642
}
],
"logging_steps": 10,
"max_steps": 2082,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 6.622303803251835e+18,
"trial_name": null,
"trial_params": null
}