Oanhha9898's picture
End of training
53a806f
{
"best_metric": 0.6655629139072847,
"best_model_checkpoint": "videomae-base-finetuned-fight-dataset/checkpoint-1000",
"epoch": 3.25,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 2.5e-06,
"loss": 0.7569,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 5e-06,
"loss": 0.6872,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 7.5e-06,
"loss": 0.7042,
"step": 30
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 0.6789,
"step": 40
},
{
"epoch": 0.03,
"learning_rate": 1.25e-05,
"loss": 0.6225,
"step": 50
},
{
"epoch": 0.03,
"learning_rate": 1.5e-05,
"loss": 0.6309,
"step": 60
},
{
"epoch": 0.04,
"learning_rate": 1.75e-05,
"loss": 0.5263,
"step": 70
},
{
"epoch": 0.04,
"learning_rate": 2e-05,
"loss": 0.5395,
"step": 80
},
{
"epoch": 0.04,
"learning_rate": 2.25e-05,
"loss": 0.4395,
"step": 90
},
{
"epoch": 0.05,
"learning_rate": 2.5e-05,
"loss": 0.5052,
"step": 100
},
{
"epoch": 0.06,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.4392,
"step": 110
},
{
"epoch": 0.06,
"learning_rate": 3e-05,
"loss": 0.3282,
"step": 120
},
{
"epoch": 0.07,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.8817,
"step": 130
},
{
"epoch": 0.07,
"learning_rate": 3.5e-05,
"loss": 0.5713,
"step": 140
},
{
"epoch": 0.07,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.3963,
"step": 150
},
{
"epoch": 0.08,
"learning_rate": 4e-05,
"loss": 0.605,
"step": 160
},
{
"epoch": 0.09,
"learning_rate": 4.25e-05,
"loss": 0.5869,
"step": 170
},
{
"epoch": 0.09,
"learning_rate": 4.5e-05,
"loss": 0.5014,
"step": 180
},
{
"epoch": 0.1,
"learning_rate": 4.75e-05,
"loss": 0.1599,
"step": 190
},
{
"epoch": 0.1,
"learning_rate": 5e-05,
"loss": 0.3478,
"step": 200
},
{
"epoch": 0.1,
"learning_rate": 4.972222222222223e-05,
"loss": 0.5816,
"step": 210
},
{
"epoch": 0.11,
"learning_rate": 4.9444444444444446e-05,
"loss": 0.2589,
"step": 220
},
{
"epoch": 0.12,
"learning_rate": 4.9166666666666665e-05,
"loss": 0.2452,
"step": 230
},
{
"epoch": 0.12,
"learning_rate": 4.888888888888889e-05,
"loss": 0.6197,
"step": 240
},
{
"epoch": 0.12,
"learning_rate": 4.8611111111111115e-05,
"loss": 0.1213,
"step": 250
},
{
"epoch": 0.13,
"learning_rate": 4.8333333333333334e-05,
"loss": 0.8634,
"step": 260
},
{
"epoch": 0.14,
"learning_rate": 4.805555555555556e-05,
"loss": 0.5417,
"step": 270
},
{
"epoch": 0.14,
"learning_rate": 4.7777777777777784e-05,
"loss": 0.2182,
"step": 280
},
{
"epoch": 0.14,
"learning_rate": 4.75e-05,
"loss": 0.7483,
"step": 290
},
{
"epoch": 0.15,
"learning_rate": 4.722222222222222e-05,
"loss": 0.1573,
"step": 300
},
{
"epoch": 0.15,
"learning_rate": 4.6944444444444446e-05,
"loss": 0.1428,
"step": 310
},
{
"epoch": 0.16,
"learning_rate": 4.666666666666667e-05,
"loss": 0.494,
"step": 320
},
{
"epoch": 0.17,
"learning_rate": 4.638888888888889e-05,
"loss": 0.6205,
"step": 330
},
{
"epoch": 0.17,
"learning_rate": 4.6111111111111115e-05,
"loss": 0.0656,
"step": 340
},
{
"epoch": 0.17,
"learning_rate": 4.5833333333333334e-05,
"loss": 0.1562,
"step": 350
},
{
"epoch": 0.18,
"learning_rate": 4.555555555555556e-05,
"loss": 0.7243,
"step": 360
},
{
"epoch": 0.18,
"learning_rate": 4.527777777777778e-05,
"loss": 0.3633,
"step": 370
},
{
"epoch": 0.19,
"learning_rate": 4.5e-05,
"loss": 0.4622,
"step": 380
},
{
"epoch": 0.2,
"learning_rate": 4.472222222222223e-05,
"loss": 0.3835,
"step": 390
},
{
"epoch": 0.2,
"learning_rate": 4.4444444444444447e-05,
"loss": 0.1294,
"step": 400
},
{
"epoch": 0.2,
"learning_rate": 4.4166666666666665e-05,
"loss": 0.326,
"step": 410
},
{
"epoch": 0.21,
"learning_rate": 4.388888888888889e-05,
"loss": 0.6442,
"step": 420
},
{
"epoch": 0.21,
"learning_rate": 4.3611111111111116e-05,
"loss": 0.3621,
"step": 430
},
{
"epoch": 0.22,
"learning_rate": 4.3333333333333334e-05,
"loss": 0.3675,
"step": 440
},
{
"epoch": 0.23,
"learning_rate": 4.305555555555556e-05,
"loss": 0.5039,
"step": 450
},
{
"epoch": 0.23,
"learning_rate": 4.277777777777778e-05,
"loss": 0.3871,
"step": 460
},
{
"epoch": 0.23,
"learning_rate": 4.25e-05,
"loss": 0.3963,
"step": 470
},
{
"epoch": 0.24,
"learning_rate": 4.222222222222222e-05,
"loss": 0.381,
"step": 480
},
{
"epoch": 0.24,
"learning_rate": 4.194444444444445e-05,
"loss": 0.1636,
"step": 490
},
{
"epoch": 0.25,
"learning_rate": 4.166666666666667e-05,
"loss": 0.302,
"step": 500
},
{
"epoch": 0.25,
"eval_accuracy": 0.5066225165562914,
"eval_loss": 3.079164743423462,
"eval_runtime": 156.3566,
"eval_samples_per_second": 1.931,
"eval_steps_per_second": 0.486,
"step": 500
},
{
"epoch": 1.0,
"learning_rate": 4.138888888888889e-05,
"loss": 0.2551,
"step": 510
},
{
"epoch": 1.01,
"learning_rate": 4.111111111111111e-05,
"loss": 0.6533,
"step": 520
},
{
"epoch": 1.01,
"learning_rate": 4.0833333333333334e-05,
"loss": 0.1168,
"step": 530
},
{
"epoch": 1.02,
"learning_rate": 4.055555555555556e-05,
"loss": 0.266,
"step": 540
},
{
"epoch": 1.02,
"learning_rate": 4.027777777777778e-05,
"loss": 0.2043,
"step": 550
},
{
"epoch": 1.03,
"learning_rate": 4e-05,
"loss": 0.2738,
"step": 560
},
{
"epoch": 1.03,
"learning_rate": 3.972222222222222e-05,
"loss": 0.1246,
"step": 570
},
{
"epoch": 1.04,
"learning_rate": 3.944444444444445e-05,
"loss": 0.2619,
"step": 580
},
{
"epoch": 1.04,
"learning_rate": 3.9166666666666665e-05,
"loss": 0.2557,
"step": 590
},
{
"epoch": 1.05,
"learning_rate": 3.888888888888889e-05,
"loss": 0.4214,
"step": 600
},
{
"epoch": 1.05,
"learning_rate": 3.8611111111111116e-05,
"loss": 0.0059,
"step": 610
},
{
"epoch": 1.06,
"learning_rate": 3.8333333333333334e-05,
"loss": 0.239,
"step": 620
},
{
"epoch": 1.06,
"learning_rate": 3.805555555555555e-05,
"loss": 1.0615,
"step": 630
},
{
"epoch": 1.07,
"learning_rate": 3.777777777777778e-05,
"loss": 0.0295,
"step": 640
},
{
"epoch": 1.07,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.3288,
"step": 650
},
{
"epoch": 1.08,
"learning_rate": 3.722222222222222e-05,
"loss": 0.3106,
"step": 660
},
{
"epoch": 1.08,
"learning_rate": 3.694444444444445e-05,
"loss": 0.2169,
"step": 670
},
{
"epoch": 1.09,
"learning_rate": 3.6666666666666666e-05,
"loss": 0.0814,
"step": 680
},
{
"epoch": 1.09,
"learning_rate": 3.638888888888889e-05,
"loss": 0.2151,
"step": 690
},
{
"epoch": 1.1,
"learning_rate": 3.611111111111111e-05,
"loss": 0.2173,
"step": 700
},
{
"epoch": 1.1,
"learning_rate": 3.5833333333333335e-05,
"loss": 0.2315,
"step": 710
},
{
"epoch": 1.11,
"learning_rate": 3.555555555555556e-05,
"loss": 0.6835,
"step": 720
},
{
"epoch": 1.11,
"learning_rate": 3.527777777777778e-05,
"loss": 0.1302,
"step": 730
},
{
"epoch": 1.12,
"learning_rate": 3.5e-05,
"loss": 0.2809,
"step": 740
},
{
"epoch": 1.12,
"learning_rate": 3.472222222222222e-05,
"loss": 0.1918,
"step": 750
},
{
"epoch": 1.13,
"learning_rate": 3.444444444444445e-05,
"loss": 0.0079,
"step": 760
},
{
"epoch": 1.14,
"learning_rate": 3.4166666666666666e-05,
"loss": 0.3089,
"step": 770
},
{
"epoch": 1.14,
"learning_rate": 3.388888888888889e-05,
"loss": 0.3032,
"step": 780
},
{
"epoch": 1.15,
"learning_rate": 3.3611111111111116e-05,
"loss": 0.3509,
"step": 790
},
{
"epoch": 1.15,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.2107,
"step": 800
},
{
"epoch": 1.16,
"learning_rate": 3.3055555555555553e-05,
"loss": 0.4484,
"step": 810
},
{
"epoch": 1.16,
"learning_rate": 3.277777777777778e-05,
"loss": 0.9292,
"step": 820
},
{
"epoch": 1.17,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.2456,
"step": 830
},
{
"epoch": 1.17,
"learning_rate": 3.222222222222223e-05,
"loss": 0.0648,
"step": 840
},
{
"epoch": 1.18,
"learning_rate": 3.194444444444444e-05,
"loss": 0.1819,
"step": 850
},
{
"epoch": 1.18,
"learning_rate": 3.1666666666666666e-05,
"loss": 0.0518,
"step": 860
},
{
"epoch": 1.19,
"learning_rate": 3.138888888888889e-05,
"loss": 0.0573,
"step": 870
},
{
"epoch": 1.19,
"learning_rate": 3.111111111111111e-05,
"loss": 0.0964,
"step": 880
},
{
"epoch": 1.2,
"learning_rate": 3.0833333333333335e-05,
"loss": 0.3063,
"step": 890
},
{
"epoch": 1.2,
"learning_rate": 3.055555555555556e-05,
"loss": 0.124,
"step": 900
},
{
"epoch": 1.21,
"learning_rate": 3.0277777777777776e-05,
"loss": 0.3151,
"step": 910
},
{
"epoch": 1.21,
"learning_rate": 3e-05,
"loss": 0.5211,
"step": 920
},
{
"epoch": 1.22,
"learning_rate": 2.9722222222222223e-05,
"loss": 0.0203,
"step": 930
},
{
"epoch": 1.22,
"learning_rate": 2.9444444444444448e-05,
"loss": 0.0847,
"step": 940
},
{
"epoch": 1.23,
"learning_rate": 2.916666666666667e-05,
"loss": 0.3277,
"step": 950
},
{
"epoch": 1.23,
"learning_rate": 2.8888888888888888e-05,
"loss": 0.218,
"step": 960
},
{
"epoch": 1.23,
"learning_rate": 2.861111111111111e-05,
"loss": 0.1086,
"step": 970
},
{
"epoch": 1.24,
"learning_rate": 2.8333333333333335e-05,
"loss": 0.4176,
"step": 980
},
{
"epoch": 1.25,
"learning_rate": 2.8055555555555557e-05,
"loss": 0.0344,
"step": 990
},
{
"epoch": 1.25,
"learning_rate": 2.777777777777778e-05,
"loss": 0.0239,
"step": 1000
},
{
"epoch": 1.25,
"eval_accuracy": 0.6655629139072847,
"eval_loss": 1.7202953100204468,
"eval_runtime": 159.3334,
"eval_samples_per_second": 1.895,
"eval_steps_per_second": 0.477,
"step": 1000
},
{
"epoch": 2.0,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.4078,
"step": 1010
},
{
"epoch": 2.01,
"learning_rate": 2.7222222222222223e-05,
"loss": 0.0143,
"step": 1020
},
{
"epoch": 2.02,
"learning_rate": 2.6944444444444445e-05,
"loss": 0.1438,
"step": 1030
},
{
"epoch": 2.02,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.0026,
"step": 1040
},
{
"epoch": 2.02,
"learning_rate": 2.6388888888888892e-05,
"loss": 0.0379,
"step": 1050
},
{
"epoch": 2.03,
"learning_rate": 2.6111111111111114e-05,
"loss": 0.2624,
"step": 1060
},
{
"epoch": 2.04,
"learning_rate": 2.5833333333333336e-05,
"loss": 0.0402,
"step": 1070
},
{
"epoch": 2.04,
"learning_rate": 2.5555555555555554e-05,
"loss": 0.0015,
"step": 1080
},
{
"epoch": 2.04,
"learning_rate": 2.527777777777778e-05,
"loss": 0.3487,
"step": 1090
},
{
"epoch": 2.05,
"learning_rate": 2.5e-05,
"loss": 0.07,
"step": 1100
},
{
"epoch": 2.06,
"learning_rate": 2.4722222222222223e-05,
"loss": 0.0026,
"step": 1110
},
{
"epoch": 2.06,
"learning_rate": 2.4444444444444445e-05,
"loss": 0.0043,
"step": 1120
},
{
"epoch": 2.06,
"learning_rate": 2.4166666666666667e-05,
"loss": 0.3279,
"step": 1130
},
{
"epoch": 2.07,
"learning_rate": 2.3888888888888892e-05,
"loss": 0.0013,
"step": 1140
},
{
"epoch": 2.08,
"learning_rate": 2.361111111111111e-05,
"loss": 0.1997,
"step": 1150
},
{
"epoch": 2.08,
"learning_rate": 2.3333333333333336e-05,
"loss": 0.2843,
"step": 1160
},
{
"epoch": 2.08,
"learning_rate": 2.3055555555555558e-05,
"loss": 0.1788,
"step": 1170
},
{
"epoch": 2.09,
"learning_rate": 2.277777777777778e-05,
"loss": 0.2823,
"step": 1180
},
{
"epoch": 2.1,
"learning_rate": 2.25e-05,
"loss": 0.1454,
"step": 1190
},
{
"epoch": 2.1,
"learning_rate": 2.2222222222222223e-05,
"loss": 0.2271,
"step": 1200
},
{
"epoch": 2.1,
"learning_rate": 2.1944444444444445e-05,
"loss": 0.2382,
"step": 1210
},
{
"epoch": 2.11,
"learning_rate": 2.1666666666666667e-05,
"loss": 0.2126,
"step": 1220
},
{
"epoch": 2.12,
"learning_rate": 2.138888888888889e-05,
"loss": 0.1598,
"step": 1230
},
{
"epoch": 2.12,
"learning_rate": 2.111111111111111e-05,
"loss": 0.1449,
"step": 1240
},
{
"epoch": 2.12,
"learning_rate": 2.0833333333333336e-05,
"loss": 0.1044,
"step": 1250
},
{
"epoch": 2.13,
"learning_rate": 2.0555555555555555e-05,
"loss": 0.1336,
"step": 1260
},
{
"epoch": 2.13,
"learning_rate": 2.027777777777778e-05,
"loss": 0.1929,
"step": 1270
},
{
"epoch": 2.14,
"learning_rate": 2e-05,
"loss": 0.2308,
"step": 1280
},
{
"epoch": 2.15,
"learning_rate": 1.9722222222222224e-05,
"loss": 0.2783,
"step": 1290
},
{
"epoch": 2.15,
"learning_rate": 1.9444444444444445e-05,
"loss": 0.0015,
"step": 1300
},
{
"epoch": 2.15,
"learning_rate": 1.9166666666666667e-05,
"loss": 0.0012,
"step": 1310
},
{
"epoch": 2.16,
"learning_rate": 1.888888888888889e-05,
"loss": 0.1149,
"step": 1320
},
{
"epoch": 2.17,
"learning_rate": 1.861111111111111e-05,
"loss": 0.2485,
"step": 1330
},
{
"epoch": 2.17,
"learning_rate": 1.8333333333333333e-05,
"loss": 0.2186,
"step": 1340
},
{
"epoch": 2.17,
"learning_rate": 1.8055555555555555e-05,
"loss": 0.0037,
"step": 1350
},
{
"epoch": 2.18,
"learning_rate": 1.777777777777778e-05,
"loss": 0.1625,
"step": 1360
},
{
"epoch": 2.19,
"learning_rate": 1.75e-05,
"loss": 0.0012,
"step": 1370
},
{
"epoch": 2.19,
"learning_rate": 1.7222222222222224e-05,
"loss": 0.1512,
"step": 1380
},
{
"epoch": 2.19,
"learning_rate": 1.6944444444444446e-05,
"loss": 0.4087,
"step": 1390
},
{
"epoch": 2.2,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.202,
"step": 1400
},
{
"epoch": 2.21,
"learning_rate": 1.638888888888889e-05,
"loss": 0.0017,
"step": 1410
},
{
"epoch": 2.21,
"learning_rate": 1.6111111111111115e-05,
"loss": 0.0014,
"step": 1420
},
{
"epoch": 2.21,
"learning_rate": 1.5833333333333333e-05,
"loss": 0.2225,
"step": 1430
},
{
"epoch": 2.22,
"learning_rate": 1.5555555555555555e-05,
"loss": 0.1513,
"step": 1440
},
{
"epoch": 2.23,
"learning_rate": 1.527777777777778e-05,
"loss": 0.0076,
"step": 1450
},
{
"epoch": 2.23,
"learning_rate": 1.5e-05,
"loss": 0.1032,
"step": 1460
},
{
"epoch": 2.23,
"learning_rate": 1.4722222222222224e-05,
"loss": 0.2871,
"step": 1470
},
{
"epoch": 2.24,
"learning_rate": 1.4444444444444444e-05,
"loss": 0.0019,
"step": 1480
},
{
"epoch": 2.25,
"learning_rate": 1.4166666666666668e-05,
"loss": 0.2831,
"step": 1490
},
{
"epoch": 2.25,
"learning_rate": 1.388888888888889e-05,
"loss": 0.0083,
"step": 1500
},
{
"epoch": 2.25,
"eval_accuracy": 0.5529801324503312,
"eval_loss": 2.5333240032196045,
"eval_runtime": 159.2778,
"eval_samples_per_second": 1.896,
"eval_steps_per_second": 0.477,
"step": 1500
},
{
"epoch": 3.0,
"learning_rate": 1.3611111111111111e-05,
"loss": 0.0368,
"step": 1510
},
{
"epoch": 3.01,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.1345,
"step": 1520
},
{
"epoch": 3.02,
"learning_rate": 1.3055555555555557e-05,
"loss": 0.0029,
"step": 1530
},
{
"epoch": 3.02,
"learning_rate": 1.2777777777777777e-05,
"loss": 0.0027,
"step": 1540
},
{
"epoch": 3.02,
"learning_rate": 1.25e-05,
"loss": 0.0034,
"step": 1550
},
{
"epoch": 3.03,
"learning_rate": 1.2222222222222222e-05,
"loss": 0.2249,
"step": 1560
},
{
"epoch": 3.04,
"learning_rate": 1.1944444444444446e-05,
"loss": 0.0012,
"step": 1570
},
{
"epoch": 3.04,
"learning_rate": 1.1666666666666668e-05,
"loss": 0.0011,
"step": 1580
},
{
"epoch": 3.04,
"learning_rate": 1.138888888888889e-05,
"loss": 0.0007,
"step": 1590
},
{
"epoch": 3.05,
"learning_rate": 1.1111111111111112e-05,
"loss": 0.001,
"step": 1600
},
{
"epoch": 3.06,
"learning_rate": 1.0833333333333334e-05,
"loss": 0.0015,
"step": 1610
},
{
"epoch": 3.06,
"learning_rate": 1.0555555555555555e-05,
"loss": 0.0253,
"step": 1620
},
{
"epoch": 3.06,
"learning_rate": 1.0277777777777777e-05,
"loss": 0.1231,
"step": 1630
},
{
"epoch": 3.07,
"learning_rate": 1e-05,
"loss": 0.1413,
"step": 1640
},
{
"epoch": 3.08,
"learning_rate": 9.722222222222223e-06,
"loss": 0.1219,
"step": 1650
},
{
"epoch": 3.08,
"learning_rate": 9.444444444444445e-06,
"loss": 0.0017,
"step": 1660
},
{
"epoch": 3.08,
"learning_rate": 9.166666666666666e-06,
"loss": 0.2959,
"step": 1670
},
{
"epoch": 3.09,
"learning_rate": 8.88888888888889e-06,
"loss": 0.0012,
"step": 1680
},
{
"epoch": 3.1,
"learning_rate": 8.611111111111112e-06,
"loss": 0.1811,
"step": 1690
},
{
"epoch": 3.1,
"learning_rate": 8.333333333333334e-06,
"loss": 0.0073,
"step": 1700
},
{
"epoch": 3.1,
"learning_rate": 8.055555555555557e-06,
"loss": 0.0872,
"step": 1710
},
{
"epoch": 3.11,
"learning_rate": 7.777777777777777e-06,
"loss": 0.0008,
"step": 1720
},
{
"epoch": 3.12,
"learning_rate": 7.5e-06,
"loss": 0.001,
"step": 1730
},
{
"epoch": 3.12,
"learning_rate": 7.222222222222222e-06,
"loss": 0.2962,
"step": 1740
},
{
"epoch": 3.12,
"learning_rate": 6.944444444444445e-06,
"loss": 0.0876,
"step": 1750
},
{
"epoch": 3.13,
"learning_rate": 6.666666666666667e-06,
"loss": 0.0923,
"step": 1760
},
{
"epoch": 3.13,
"learning_rate": 6.3888888888888885e-06,
"loss": 0.0024,
"step": 1770
},
{
"epoch": 3.14,
"learning_rate": 6.111111111111111e-06,
"loss": 0.0018,
"step": 1780
},
{
"epoch": 3.15,
"learning_rate": 5.833333333333334e-06,
"loss": 0.0008,
"step": 1790
},
{
"epoch": 3.15,
"learning_rate": 5.555555555555556e-06,
"loss": 0.1655,
"step": 1800
},
{
"epoch": 3.15,
"learning_rate": 5.277777777777778e-06,
"loss": 0.0009,
"step": 1810
},
{
"epoch": 3.16,
"learning_rate": 5e-06,
"loss": 0.0271,
"step": 1820
},
{
"epoch": 3.17,
"learning_rate": 4.722222222222222e-06,
"loss": 0.0825,
"step": 1830
},
{
"epoch": 3.17,
"learning_rate": 4.444444444444445e-06,
"loss": 0.0915,
"step": 1840
},
{
"epoch": 3.17,
"learning_rate": 4.166666666666667e-06,
"loss": 0.0011,
"step": 1850
},
{
"epoch": 3.18,
"learning_rate": 3.888888888888889e-06,
"loss": 0.2249,
"step": 1860
},
{
"epoch": 3.19,
"learning_rate": 3.611111111111111e-06,
"loss": 0.001,
"step": 1870
},
{
"epoch": 3.19,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.1616,
"step": 1880
},
{
"epoch": 3.19,
"learning_rate": 3.0555555555555556e-06,
"loss": 0.0009,
"step": 1890
},
{
"epoch": 3.2,
"learning_rate": 2.777777777777778e-06,
"loss": 0.0009,
"step": 1900
},
{
"epoch": 3.21,
"learning_rate": 2.5e-06,
"loss": 0.0008,
"step": 1910
},
{
"epoch": 3.21,
"learning_rate": 2.2222222222222225e-06,
"loss": 0.0007,
"step": 1920
},
{
"epoch": 3.21,
"learning_rate": 1.9444444444444444e-06,
"loss": 0.1779,
"step": 1930
},
{
"epoch": 3.22,
"learning_rate": 1.6666666666666667e-06,
"loss": 0.1649,
"step": 1940
},
{
"epoch": 3.23,
"learning_rate": 1.388888888888889e-06,
"loss": 0.0008,
"step": 1950
},
{
"epoch": 3.23,
"learning_rate": 1.1111111111111112e-06,
"loss": 0.0026,
"step": 1960
},
{
"epoch": 3.23,
"learning_rate": 8.333333333333333e-07,
"loss": 0.0032,
"step": 1970
},
{
"epoch": 3.24,
"learning_rate": 5.555555555555556e-07,
"loss": 0.1384,
"step": 1980
},
{
"epoch": 3.25,
"learning_rate": 2.777777777777778e-07,
"loss": 0.0061,
"step": 1990
},
{
"epoch": 3.25,
"learning_rate": 0.0,
"loss": 0.0009,
"step": 2000
},
{
"epoch": 3.25,
"eval_accuracy": 0.6556291390728477,
"eval_loss": 2.1635005474090576,
"eval_runtime": 157.8089,
"eval_samples_per_second": 1.914,
"eval_steps_per_second": 0.482,
"step": 2000
},
{
"epoch": 3.25,
"step": 2000,
"total_flos": 9.968516715773952e+18,
"train_loss": 0.22924756015650927,
"train_runtime": 6295.3826,
"train_samples_per_second": 1.271,
"train_steps_per_second": 0.318
},
{
"epoch": 3.25,
"eval_accuracy": 0.6655629139072847,
"eval_loss": 1.7202953100204468,
"eval_runtime": 161.3009,
"eval_samples_per_second": 1.872,
"eval_steps_per_second": 0.471,
"step": 2000
},
{
"epoch": 3.25,
"eval_accuracy": 0.6655629139072847,
"eval_loss": 1.7202953100204468,
"eval_runtime": 156.137,
"eval_samples_per_second": 1.934,
"eval_steps_per_second": 0.487,
"step": 2000
}
],
"logging_steps": 10,
"max_steps": 2000,
"num_train_epochs": 9223372036854775807,
"save_steps": 500,
"total_flos": 9.968516715773952e+18,
"trial_name": null,
"trial_params": null
}