Gokulapriyan's picture
End of training
31ba05f
{
"best_metric": 0.9741915422885572,
"best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-2635",
"epoch": 4.99857887257224,
"global_step": 2635,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 1.8939393939393941e-06,
"loss": 1.4619,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 3.7878787878787882e-06,
"loss": 1.3888,
"step": 20
},
{
"epoch": 0.06,
"learning_rate": 5.681818181818182e-06,
"loss": 1.2545,
"step": 30
},
{
"epoch": 0.08,
"learning_rate": 7.5757575757575764e-06,
"loss": 1.1428,
"step": 40
},
{
"epoch": 0.09,
"learning_rate": 9.46969696969697e-06,
"loss": 0.9846,
"step": 50
},
{
"epoch": 0.11,
"learning_rate": 1.1363636363636365e-05,
"loss": 0.8566,
"step": 60
},
{
"epoch": 0.13,
"learning_rate": 1.3257575757575758e-05,
"loss": 0.8184,
"step": 70
},
{
"epoch": 0.15,
"learning_rate": 1.5151515151515153e-05,
"loss": 0.8055,
"step": 80
},
{
"epoch": 0.17,
"learning_rate": 1.7045454545454546e-05,
"loss": 0.7846,
"step": 90
},
{
"epoch": 0.19,
"learning_rate": 1.893939393939394e-05,
"loss": 0.7953,
"step": 100
},
{
"epoch": 0.21,
"learning_rate": 2.0833333333333336e-05,
"loss": 0.7205,
"step": 110
},
{
"epoch": 0.23,
"learning_rate": 2.272727272727273e-05,
"loss": 0.699,
"step": 120
},
{
"epoch": 0.25,
"learning_rate": 2.4621212121212123e-05,
"loss": 0.698,
"step": 130
},
{
"epoch": 0.27,
"learning_rate": 2.6515151515151516e-05,
"loss": 0.7095,
"step": 140
},
{
"epoch": 0.28,
"learning_rate": 2.8409090909090912e-05,
"loss": 0.6753,
"step": 150
},
{
"epoch": 0.3,
"learning_rate": 3.0303030303030306e-05,
"loss": 0.6655,
"step": 160
},
{
"epoch": 0.32,
"learning_rate": 3.2196969696969696e-05,
"loss": 0.6625,
"step": 170
},
{
"epoch": 0.34,
"learning_rate": 3.409090909090909e-05,
"loss": 0.6881,
"step": 180
},
{
"epoch": 0.36,
"learning_rate": 3.598484848484849e-05,
"loss": 0.6698,
"step": 190
},
{
"epoch": 0.38,
"learning_rate": 3.787878787878788e-05,
"loss": 0.6548,
"step": 200
},
{
"epoch": 0.4,
"learning_rate": 3.9772727272727275e-05,
"loss": 0.6373,
"step": 210
},
{
"epoch": 0.42,
"learning_rate": 4.166666666666667e-05,
"loss": 0.6437,
"step": 220
},
{
"epoch": 0.44,
"learning_rate": 4.356060606060606e-05,
"loss": 0.6308,
"step": 230
},
{
"epoch": 0.45,
"learning_rate": 4.545454545454546e-05,
"loss": 0.6119,
"step": 240
},
{
"epoch": 0.47,
"learning_rate": 4.7348484848484855e-05,
"loss": 0.5998,
"step": 250
},
{
"epoch": 0.49,
"learning_rate": 4.9242424242424245e-05,
"loss": 0.6188,
"step": 260
},
{
"epoch": 0.51,
"learning_rate": 4.987347110923661e-05,
"loss": 0.5837,
"step": 270
},
{
"epoch": 0.53,
"learning_rate": 4.966258962463096e-05,
"loss": 0.585,
"step": 280
},
{
"epoch": 0.55,
"learning_rate": 4.945170814002531e-05,
"loss": 0.6001,
"step": 290
},
{
"epoch": 0.57,
"learning_rate": 4.924082665541966e-05,
"loss": 0.5664,
"step": 300
},
{
"epoch": 0.59,
"learning_rate": 4.9029945170814005e-05,
"loss": 0.5603,
"step": 310
},
{
"epoch": 0.61,
"learning_rate": 4.8819063686208354e-05,
"loss": 0.601,
"step": 320
},
{
"epoch": 0.63,
"learning_rate": 4.86081822016027e-05,
"loss": 0.5489,
"step": 330
},
{
"epoch": 0.64,
"learning_rate": 4.839730071699705e-05,
"loss": 0.5525,
"step": 340
},
{
"epoch": 0.66,
"learning_rate": 4.81864192323914e-05,
"loss": 0.5451,
"step": 350
},
{
"epoch": 0.68,
"learning_rate": 4.797553774778575e-05,
"loss": 0.5515,
"step": 360
},
{
"epoch": 0.7,
"learning_rate": 4.7764656263180096e-05,
"loss": 0.4817,
"step": 370
},
{
"epoch": 0.72,
"learning_rate": 4.7553774778574444e-05,
"loss": 0.5398,
"step": 380
},
{
"epoch": 0.74,
"learning_rate": 4.734289329396879e-05,
"loss": 0.4987,
"step": 390
},
{
"epoch": 0.76,
"learning_rate": 4.713201180936314e-05,
"loss": 0.5202,
"step": 400
},
{
"epoch": 0.78,
"learning_rate": 4.692113032475749e-05,
"loss": 0.5143,
"step": 410
},
{
"epoch": 0.8,
"learning_rate": 4.671024884015184e-05,
"loss": 0.4946,
"step": 420
},
{
"epoch": 0.81,
"learning_rate": 4.6499367355546186e-05,
"loss": 0.5009,
"step": 430
},
{
"epoch": 0.83,
"learning_rate": 4.6288485870940535e-05,
"loss": 0.5015,
"step": 440
},
{
"epoch": 0.85,
"learning_rate": 4.607760438633488e-05,
"loss": 0.4837,
"step": 450
},
{
"epoch": 0.87,
"learning_rate": 4.586672290172923e-05,
"loss": 0.4814,
"step": 460
},
{
"epoch": 0.89,
"learning_rate": 4.565584141712358e-05,
"loss": 0.4827,
"step": 470
},
{
"epoch": 0.91,
"learning_rate": 4.544495993251793e-05,
"loss": 0.5304,
"step": 480
},
{
"epoch": 0.93,
"learning_rate": 4.523407844791228e-05,
"loss": 0.4592,
"step": 490
},
{
"epoch": 0.95,
"learning_rate": 4.5023196963306626e-05,
"loss": 0.4759,
"step": 500
},
{
"epoch": 0.97,
"learning_rate": 4.4812315478700974e-05,
"loss": 0.4431,
"step": 510
},
{
"epoch": 0.99,
"learning_rate": 4.460143399409532e-05,
"loss": 0.4378,
"step": 520
},
{
"epoch": 1.0,
"eval_accuracy": 0.8507462686567164,
"eval_loss": 0.36681434512138367,
"eval_runtime": 136.5295,
"eval_samples_per_second": 70.666,
"eval_steps_per_second": 2.212,
"step": 527
},
{
"epoch": 1.01,
"learning_rate": 4.439055250948967e-05,
"loss": 0.486,
"step": 530
},
{
"epoch": 1.02,
"learning_rate": 4.417967102488402e-05,
"loss": 0.4533,
"step": 540
},
{
"epoch": 1.04,
"learning_rate": 4.396878954027837e-05,
"loss": 0.4119,
"step": 550
},
{
"epoch": 1.06,
"learning_rate": 4.3757908055672716e-05,
"loss": 0.4279,
"step": 560
},
{
"epoch": 1.08,
"learning_rate": 4.3547026571067065e-05,
"loss": 0.4389,
"step": 570
},
{
"epoch": 1.1,
"learning_rate": 4.333614508646141e-05,
"loss": 0.4344,
"step": 580
},
{
"epoch": 1.12,
"learning_rate": 4.312526360185576e-05,
"loss": 0.3977,
"step": 590
},
{
"epoch": 1.14,
"learning_rate": 4.291438211725011e-05,
"loss": 0.413,
"step": 600
},
{
"epoch": 1.16,
"learning_rate": 4.270350063264446e-05,
"loss": 0.4302,
"step": 610
},
{
"epoch": 1.18,
"learning_rate": 4.249261914803881e-05,
"loss": 0.4229,
"step": 620
},
{
"epoch": 1.2,
"learning_rate": 4.2281737663433155e-05,
"loss": 0.4015,
"step": 630
},
{
"epoch": 1.21,
"learning_rate": 4.20708561788275e-05,
"loss": 0.3929,
"step": 640
},
{
"epoch": 1.23,
"learning_rate": 4.1859974694221845e-05,
"loss": 0.4133,
"step": 650
},
{
"epoch": 1.25,
"learning_rate": 4.1649093209616194e-05,
"loss": 0.384,
"step": 660
},
{
"epoch": 1.27,
"learning_rate": 4.143821172501054e-05,
"loss": 0.4043,
"step": 670
},
{
"epoch": 1.29,
"learning_rate": 4.122733024040489e-05,
"loss": 0.3696,
"step": 680
},
{
"epoch": 1.31,
"learning_rate": 4.101644875579924e-05,
"loss": 0.3942,
"step": 690
},
{
"epoch": 1.33,
"learning_rate": 4.080556727119359e-05,
"loss": 0.3915,
"step": 700
},
{
"epoch": 1.35,
"learning_rate": 4.0594685786587936e-05,
"loss": 0.3431,
"step": 710
},
{
"epoch": 1.37,
"learning_rate": 4.0383804301982284e-05,
"loss": 0.352,
"step": 720
},
{
"epoch": 1.38,
"learning_rate": 4.017292281737663e-05,
"loss": 0.3876,
"step": 730
},
{
"epoch": 1.4,
"learning_rate": 3.996204133277098e-05,
"loss": 0.3589,
"step": 740
},
{
"epoch": 1.42,
"learning_rate": 3.975115984816533e-05,
"loss": 0.3519,
"step": 750
},
{
"epoch": 1.44,
"learning_rate": 3.954027836355968e-05,
"loss": 0.3908,
"step": 760
},
{
"epoch": 1.46,
"learning_rate": 3.9329396878954027e-05,
"loss": 0.3677,
"step": 770
},
{
"epoch": 1.48,
"learning_rate": 3.9118515394348375e-05,
"loss": 0.3549,
"step": 780
},
{
"epoch": 1.5,
"learning_rate": 3.8907633909742723e-05,
"loss": 0.3453,
"step": 790
},
{
"epoch": 1.52,
"learning_rate": 3.869675242513707e-05,
"loss": 0.3366,
"step": 800
},
{
"epoch": 1.54,
"learning_rate": 3.848587094053142e-05,
"loss": 0.3553,
"step": 810
},
{
"epoch": 1.56,
"learning_rate": 3.827498945592577e-05,
"loss": 0.3224,
"step": 820
},
{
"epoch": 1.57,
"learning_rate": 3.806410797132012e-05,
"loss": 0.345,
"step": 830
},
{
"epoch": 1.59,
"learning_rate": 3.7853226486714466e-05,
"loss": 0.3298,
"step": 840
},
{
"epoch": 1.61,
"learning_rate": 3.7642345002108814e-05,
"loss": 0.3417,
"step": 850
},
{
"epoch": 1.63,
"learning_rate": 3.743146351750316e-05,
"loss": 0.3832,
"step": 860
},
{
"epoch": 1.65,
"learning_rate": 3.722058203289751e-05,
"loss": 0.3343,
"step": 870
},
{
"epoch": 1.67,
"learning_rate": 3.700970054829186e-05,
"loss": 0.3112,
"step": 880
},
{
"epoch": 1.69,
"learning_rate": 3.679881906368621e-05,
"loss": 0.3355,
"step": 890
},
{
"epoch": 1.71,
"learning_rate": 3.658793757908056e-05,
"loss": 0.3223,
"step": 900
},
{
"epoch": 1.73,
"learning_rate": 3.637705609447491e-05,
"loss": 0.3229,
"step": 910
},
{
"epoch": 1.74,
"learning_rate": 3.616617460986926e-05,
"loss": 0.3395,
"step": 920
},
{
"epoch": 1.76,
"learning_rate": 3.595529312526361e-05,
"loss": 0.3092,
"step": 930
},
{
"epoch": 1.78,
"learning_rate": 3.574441164065796e-05,
"loss": 0.3006,
"step": 940
},
{
"epoch": 1.8,
"learning_rate": 3.5533530156052305e-05,
"loss": 0.3557,
"step": 950
},
{
"epoch": 1.82,
"learning_rate": 3.5322648671446654e-05,
"loss": 0.325,
"step": 960
},
{
"epoch": 1.84,
"learning_rate": 3.5111767186841e-05,
"loss": 0.3039,
"step": 970
},
{
"epoch": 1.86,
"learning_rate": 3.490088570223535e-05,
"loss": 0.3506,
"step": 980
},
{
"epoch": 1.88,
"learning_rate": 3.46900042176297e-05,
"loss": 0.3268,
"step": 990
},
{
"epoch": 1.9,
"learning_rate": 3.447912273302405e-05,
"loss": 0.3007,
"step": 1000
},
{
"epoch": 1.92,
"learning_rate": 3.426824124841839e-05,
"loss": 0.3202,
"step": 1010
},
{
"epoch": 1.93,
"learning_rate": 3.405735976381274e-05,
"loss": 0.3118,
"step": 1020
},
{
"epoch": 1.95,
"learning_rate": 3.3846478279207086e-05,
"loss": 0.3278,
"step": 1030
},
{
"epoch": 1.97,
"learning_rate": 3.3635596794601434e-05,
"loss": 0.292,
"step": 1040
},
{
"epoch": 1.99,
"learning_rate": 3.342471530999578e-05,
"loss": 0.3133,
"step": 1050
},
{
"epoch": 2.0,
"eval_accuracy": 0.9429933665008292,
"eval_loss": 0.15862515568733215,
"eval_runtime": 141.8451,
"eval_samples_per_second": 68.018,
"eval_steps_per_second": 2.129,
"step": 1054
},
{
"epoch": 2.01,
"learning_rate": 3.321383382539013e-05,
"loss": 0.3435,
"step": 1060
},
{
"epoch": 2.03,
"learning_rate": 3.300295234078448e-05,
"loss": 0.31,
"step": 1070
},
{
"epoch": 2.05,
"learning_rate": 3.279207085617883e-05,
"loss": 0.3035,
"step": 1080
},
{
"epoch": 2.07,
"learning_rate": 3.2581189371573177e-05,
"loss": 0.3138,
"step": 1090
},
{
"epoch": 2.09,
"learning_rate": 3.2370307886967525e-05,
"loss": 0.309,
"step": 1100
},
{
"epoch": 2.11,
"learning_rate": 3.2159426402361873e-05,
"loss": 0.3034,
"step": 1110
},
{
"epoch": 2.13,
"learning_rate": 3.194854491775622e-05,
"loss": 0.2805,
"step": 1120
},
{
"epoch": 2.14,
"learning_rate": 3.173766343315057e-05,
"loss": 0.2889,
"step": 1130
},
{
"epoch": 2.16,
"learning_rate": 3.152678194854492e-05,
"loss": 0.2864,
"step": 1140
},
{
"epoch": 2.18,
"learning_rate": 3.131590046393927e-05,
"loss": 0.2723,
"step": 1150
},
{
"epoch": 2.2,
"learning_rate": 3.1105018979333616e-05,
"loss": 0.2763,
"step": 1160
},
{
"epoch": 2.22,
"learning_rate": 3.0894137494727964e-05,
"loss": 0.2561,
"step": 1170
},
{
"epoch": 2.24,
"learning_rate": 3.068325601012231e-05,
"loss": 0.2732,
"step": 1180
},
{
"epoch": 2.26,
"learning_rate": 3.047237452551666e-05,
"loss": 0.2458,
"step": 1190
},
{
"epoch": 2.28,
"learning_rate": 3.026149304091101e-05,
"loss": 0.2632,
"step": 1200
},
{
"epoch": 2.3,
"learning_rate": 3.0050611556305358e-05,
"loss": 0.2889,
"step": 1210
},
{
"epoch": 2.31,
"learning_rate": 2.9839730071699706e-05,
"loss": 0.2406,
"step": 1220
},
{
"epoch": 2.33,
"learning_rate": 2.9628848587094055e-05,
"loss": 0.2566,
"step": 1230
},
{
"epoch": 2.35,
"learning_rate": 2.9417967102488403e-05,
"loss": 0.2576,
"step": 1240
},
{
"epoch": 2.37,
"learning_rate": 2.920708561788275e-05,
"loss": 0.268,
"step": 1250
},
{
"epoch": 2.39,
"learning_rate": 2.89962041332771e-05,
"loss": 0.2556,
"step": 1260
},
{
"epoch": 2.41,
"learning_rate": 2.878532264867145e-05,
"loss": 0.2577,
"step": 1270
},
{
"epoch": 2.43,
"learning_rate": 2.8574441164065797e-05,
"loss": 0.2507,
"step": 1280
},
{
"epoch": 2.45,
"learning_rate": 2.8363559679460145e-05,
"loss": 0.2271,
"step": 1290
},
{
"epoch": 2.47,
"learning_rate": 2.8152678194854494e-05,
"loss": 0.2792,
"step": 1300
},
{
"epoch": 2.49,
"learning_rate": 2.7941796710248842e-05,
"loss": 0.2755,
"step": 1310
},
{
"epoch": 2.5,
"learning_rate": 2.773091522564319e-05,
"loss": 0.2456,
"step": 1320
},
{
"epoch": 2.52,
"learning_rate": 2.752003374103754e-05,
"loss": 0.2463,
"step": 1330
},
{
"epoch": 2.54,
"learning_rate": 2.7309152256431884e-05,
"loss": 0.2569,
"step": 1340
},
{
"epoch": 2.56,
"learning_rate": 2.7098270771826233e-05,
"loss": 0.2609,
"step": 1350
},
{
"epoch": 2.58,
"learning_rate": 2.688738928722058e-05,
"loss": 0.2437,
"step": 1360
},
{
"epoch": 2.6,
"learning_rate": 2.667650780261493e-05,
"loss": 0.2491,
"step": 1370
},
{
"epoch": 2.62,
"learning_rate": 2.6465626318009278e-05,
"loss": 0.1923,
"step": 1380
},
{
"epoch": 2.64,
"learning_rate": 2.6254744833403626e-05,
"loss": 0.2435,
"step": 1390
},
{
"epoch": 2.66,
"learning_rate": 2.6043863348797975e-05,
"loss": 0.2382,
"step": 1400
},
{
"epoch": 2.67,
"learning_rate": 2.5832981864192323e-05,
"loss": 0.2316,
"step": 1410
},
{
"epoch": 2.69,
"learning_rate": 2.562210037958667e-05,
"loss": 0.2294,
"step": 1420
},
{
"epoch": 2.71,
"learning_rate": 2.541121889498102e-05,
"loss": 0.2187,
"step": 1430
},
{
"epoch": 2.73,
"learning_rate": 2.520033741037537e-05,
"loss": 0.2595,
"step": 1440
},
{
"epoch": 2.75,
"learning_rate": 2.498945592576972e-05,
"loss": 0.2401,
"step": 1450
},
{
"epoch": 2.77,
"learning_rate": 2.477857444116407e-05,
"loss": 0.2344,
"step": 1460
},
{
"epoch": 2.79,
"learning_rate": 2.4567692956558417e-05,
"loss": 0.2334,
"step": 1470
},
{
"epoch": 2.81,
"learning_rate": 2.4356811471952766e-05,
"loss": 0.2697,
"step": 1480
},
{
"epoch": 2.83,
"learning_rate": 2.4145929987347114e-05,
"loss": 0.2407,
"step": 1490
},
{
"epoch": 2.85,
"learning_rate": 2.3935048502741463e-05,
"loss": 0.2434,
"step": 1500
},
{
"epoch": 2.86,
"learning_rate": 2.372416701813581e-05,
"loss": 0.2781,
"step": 1510
},
{
"epoch": 2.88,
"learning_rate": 2.351328553353016e-05,
"loss": 0.2377,
"step": 1520
},
{
"epoch": 2.9,
"learning_rate": 2.3302404048924504e-05,
"loss": 0.2478,
"step": 1530
},
{
"epoch": 2.92,
"learning_rate": 2.3091522564318853e-05,
"loss": 0.2558,
"step": 1540
},
{
"epoch": 2.94,
"learning_rate": 2.28806410797132e-05,
"loss": 0.2378,
"step": 1550
},
{
"epoch": 2.96,
"learning_rate": 2.266975959510755e-05,
"loss": 0.2303,
"step": 1560
},
{
"epoch": 2.98,
"learning_rate": 2.2458878110501898e-05,
"loss": 0.271,
"step": 1570
},
{
"epoch": 3.0,
"learning_rate": 2.2247996625896247e-05,
"loss": 0.2065,
"step": 1580
},
{
"epoch": 3.0,
"eval_accuracy": 0.9607172470978441,
"eval_loss": 0.1048618033528328,
"eval_runtime": 131.6181,
"eval_samples_per_second": 73.303,
"eval_steps_per_second": 2.295,
"step": 1581
},
{
"epoch": 3.02,
"learning_rate": 2.2037115141290595e-05,
"loss": 0.211,
"step": 1590
},
{
"epoch": 3.04,
"learning_rate": 2.1826233656684943e-05,
"loss": 0.2139,
"step": 1600
},
{
"epoch": 3.05,
"learning_rate": 2.1615352172079292e-05,
"loss": 0.226,
"step": 1610
},
{
"epoch": 3.07,
"learning_rate": 2.140447068747364e-05,
"loss": 0.2295,
"step": 1620
},
{
"epoch": 3.09,
"learning_rate": 2.119358920286799e-05,
"loss": 0.2284,
"step": 1630
},
{
"epoch": 3.11,
"learning_rate": 2.0982707718262337e-05,
"loss": 0.2181,
"step": 1640
},
{
"epoch": 3.13,
"learning_rate": 2.0771826233656686e-05,
"loss": 0.2174,
"step": 1650
},
{
"epoch": 3.15,
"learning_rate": 2.0560944749051034e-05,
"loss": 0.2301,
"step": 1660
},
{
"epoch": 3.17,
"learning_rate": 2.0350063264445383e-05,
"loss": 0.2078,
"step": 1670
},
{
"epoch": 3.19,
"learning_rate": 2.013918177983973e-05,
"loss": 0.2338,
"step": 1680
},
{
"epoch": 3.21,
"learning_rate": 1.992830029523408e-05,
"loss": 0.235,
"step": 1690
},
{
"epoch": 3.23,
"learning_rate": 1.9717418810628428e-05,
"loss": 0.2152,
"step": 1700
},
{
"epoch": 3.24,
"learning_rate": 1.9506537326022776e-05,
"loss": 0.2154,
"step": 1710
},
{
"epoch": 3.26,
"learning_rate": 1.9295655841417125e-05,
"loss": 0.2146,
"step": 1720
},
{
"epoch": 3.28,
"learning_rate": 1.9084774356811473e-05,
"loss": 0.2279,
"step": 1730
},
{
"epoch": 3.3,
"learning_rate": 1.887389287220582e-05,
"loss": 0.2176,
"step": 1740
},
{
"epoch": 3.32,
"learning_rate": 1.8663011387600167e-05,
"loss": 0.2409,
"step": 1750
},
{
"epoch": 3.34,
"learning_rate": 1.8452129902994515e-05,
"loss": 0.2294,
"step": 1760
},
{
"epoch": 3.36,
"learning_rate": 1.8241248418388867e-05,
"loss": 0.2118,
"step": 1770
},
{
"epoch": 3.38,
"learning_rate": 1.8030366933783215e-05,
"loss": 0.2141,
"step": 1780
},
{
"epoch": 3.4,
"learning_rate": 1.7819485449177564e-05,
"loss": 0.1921,
"step": 1790
},
{
"epoch": 3.41,
"learning_rate": 1.7608603964571912e-05,
"loss": 0.184,
"step": 1800
},
{
"epoch": 3.43,
"learning_rate": 1.739772247996626e-05,
"loss": 0.2109,
"step": 1810
},
{
"epoch": 3.45,
"learning_rate": 1.718684099536061e-05,
"loss": 0.2119,
"step": 1820
},
{
"epoch": 3.47,
"learning_rate": 1.6975959510754958e-05,
"loss": 0.2294,
"step": 1830
},
{
"epoch": 3.49,
"learning_rate": 1.6765078026149306e-05,
"loss": 0.234,
"step": 1840
},
{
"epoch": 3.51,
"learning_rate": 1.6554196541543654e-05,
"loss": 0.1865,
"step": 1850
},
{
"epoch": 3.53,
"learning_rate": 1.6343315056938003e-05,
"loss": 0.22,
"step": 1860
},
{
"epoch": 3.55,
"learning_rate": 1.613243357233235e-05,
"loss": 0.2034,
"step": 1870
},
{
"epoch": 3.57,
"learning_rate": 1.59215520877267e-05,
"loss": 0.2088,
"step": 1880
},
{
"epoch": 3.59,
"learning_rate": 1.5710670603121048e-05,
"loss": 0.1922,
"step": 1890
},
{
"epoch": 3.6,
"learning_rate": 1.5499789118515397e-05,
"loss": 0.2146,
"step": 1900
},
{
"epoch": 3.62,
"learning_rate": 1.5288907633909745e-05,
"loss": 0.2198,
"step": 1910
},
{
"epoch": 3.64,
"learning_rate": 1.5078026149304092e-05,
"loss": 0.2008,
"step": 1920
},
{
"epoch": 3.66,
"learning_rate": 1.486714466469844e-05,
"loss": 0.204,
"step": 1930
},
{
"epoch": 3.68,
"learning_rate": 1.4656263180092789e-05,
"loss": 0.2053,
"step": 1940
},
{
"epoch": 3.7,
"learning_rate": 1.4445381695487137e-05,
"loss": 0.2194,
"step": 1950
},
{
"epoch": 3.72,
"learning_rate": 1.4234500210881486e-05,
"loss": 0.1869,
"step": 1960
},
{
"epoch": 3.74,
"learning_rate": 1.4023618726275834e-05,
"loss": 0.2008,
"step": 1970
},
{
"epoch": 3.76,
"learning_rate": 1.3812737241670182e-05,
"loss": 0.2011,
"step": 1980
},
{
"epoch": 3.77,
"learning_rate": 1.360185575706453e-05,
"loss": 0.1867,
"step": 1990
},
{
"epoch": 3.79,
"learning_rate": 1.3390974272458878e-05,
"loss": 0.1892,
"step": 2000
},
{
"epoch": 3.81,
"learning_rate": 1.3180092787853226e-05,
"loss": 0.1646,
"step": 2010
},
{
"epoch": 3.83,
"learning_rate": 1.2969211303247574e-05,
"loss": 0.2096,
"step": 2020
},
{
"epoch": 3.85,
"learning_rate": 1.2758329818641923e-05,
"loss": 0.1834,
"step": 2030
},
{
"epoch": 3.87,
"learning_rate": 1.2547448334036271e-05,
"loss": 0.1909,
"step": 2040
},
{
"epoch": 3.89,
"learning_rate": 1.2336566849430621e-05,
"loss": 0.1867,
"step": 2050
},
{
"epoch": 3.91,
"learning_rate": 1.212568536482497e-05,
"loss": 0.197,
"step": 2060
},
{
"epoch": 3.93,
"learning_rate": 1.1914803880219318e-05,
"loss": 0.2021,
"step": 2070
},
{
"epoch": 3.95,
"learning_rate": 1.1703922395613665e-05,
"loss": 0.1906,
"step": 2080
},
{
"epoch": 3.96,
"learning_rate": 1.1493040911008014e-05,
"loss": 0.1851,
"step": 2090
},
{
"epoch": 3.98,
"learning_rate": 1.1282159426402362e-05,
"loss": 0.22,
"step": 2100
},
{
"epoch": 4.0,
"eval_accuracy": 0.9701492537313433,
"eval_loss": 0.08384203910827637,
"eval_runtime": 131.303,
"eval_samples_per_second": 73.479,
"eval_steps_per_second": 2.3,
"step": 2108
},
{
"epoch": 4.0,
"learning_rate": 1.107127794179671e-05,
"loss": 0.2109,
"step": 2110
},
{
"epoch": 4.02,
"learning_rate": 1.0860396457191059e-05,
"loss": 0.1934,
"step": 2120
},
{
"epoch": 4.04,
"learning_rate": 1.0649514972585407e-05,
"loss": 0.1984,
"step": 2130
},
{
"epoch": 4.06,
"learning_rate": 1.0438633487979756e-05,
"loss": 0.2011,
"step": 2140
},
{
"epoch": 4.08,
"learning_rate": 1.0227752003374104e-05,
"loss": 0.1784,
"step": 2150
},
{
"epoch": 4.1,
"learning_rate": 1.0016870518768453e-05,
"loss": 0.2025,
"step": 2160
},
{
"epoch": 4.12,
"learning_rate": 9.805989034162801e-06,
"loss": 0.1766,
"step": 2170
},
{
"epoch": 4.14,
"learning_rate": 9.59510754955715e-06,
"loss": 0.1866,
"step": 2180
},
{
"epoch": 4.16,
"learning_rate": 9.384226064951498e-06,
"loss": 0.1985,
"step": 2190
},
{
"epoch": 4.17,
"learning_rate": 9.173344580345846e-06,
"loss": 0.174,
"step": 2200
},
{
"epoch": 4.19,
"learning_rate": 8.962463095740195e-06,
"loss": 0.2045,
"step": 2210
},
{
"epoch": 4.21,
"learning_rate": 8.751581611134543e-06,
"loss": 0.1847,
"step": 2220
},
{
"epoch": 4.23,
"learning_rate": 8.540700126528892e-06,
"loss": 0.1785,
"step": 2230
},
{
"epoch": 4.25,
"learning_rate": 8.32981864192324e-06,
"loss": 0.1421,
"step": 2240
},
{
"epoch": 4.27,
"learning_rate": 8.118937157317589e-06,
"loss": 0.162,
"step": 2250
},
{
"epoch": 4.29,
"learning_rate": 7.908055672711937e-06,
"loss": 0.1989,
"step": 2260
},
{
"epoch": 4.31,
"learning_rate": 7.697174188106285e-06,
"loss": 0.1748,
"step": 2270
},
{
"epoch": 4.33,
"learning_rate": 7.486292703500633e-06,
"loss": 0.1702,
"step": 2280
},
{
"epoch": 4.34,
"learning_rate": 7.2754112188949814e-06,
"loss": 0.1721,
"step": 2290
},
{
"epoch": 4.36,
"learning_rate": 7.06452973428933e-06,
"loss": 0.1754,
"step": 2300
},
{
"epoch": 4.38,
"learning_rate": 6.853648249683678e-06,
"loss": 0.175,
"step": 2310
},
{
"epoch": 4.4,
"learning_rate": 6.642766765078026e-06,
"loss": 0.1906,
"step": 2320
},
{
"epoch": 4.42,
"learning_rate": 6.431885280472374e-06,
"loss": 0.1789,
"step": 2330
},
{
"epoch": 4.44,
"learning_rate": 6.221003795866724e-06,
"loss": 0.1607,
"step": 2340
},
{
"epoch": 4.46,
"learning_rate": 6.010122311261072e-06,
"loss": 0.1747,
"step": 2350
},
{
"epoch": 4.48,
"learning_rate": 5.79924082665542e-06,
"loss": 0.1611,
"step": 2360
},
{
"epoch": 4.5,
"learning_rate": 5.588359342049768e-06,
"loss": 0.1611,
"step": 2370
},
{
"epoch": 4.52,
"learning_rate": 5.3774778574441165e-06,
"loss": 0.1674,
"step": 2380
},
{
"epoch": 4.53,
"learning_rate": 5.166596372838465e-06,
"loss": 0.1797,
"step": 2390
},
{
"epoch": 4.55,
"learning_rate": 4.955714888232813e-06,
"loss": 0.2051,
"step": 2400
},
{
"epoch": 4.57,
"learning_rate": 4.744833403627162e-06,
"loss": 0.171,
"step": 2410
},
{
"epoch": 4.59,
"learning_rate": 4.53395191902151e-06,
"loss": 0.1622,
"step": 2420
},
{
"epoch": 4.61,
"learning_rate": 4.323070434415859e-06,
"loss": 0.1891,
"step": 2430
},
{
"epoch": 4.63,
"learning_rate": 4.112188949810207e-06,
"loss": 0.1884,
"step": 2440
},
{
"epoch": 4.65,
"learning_rate": 3.901307465204556e-06,
"loss": 0.1946,
"step": 2450
},
{
"epoch": 4.67,
"learning_rate": 3.6904259805989036e-06,
"loss": 0.1769,
"step": 2460
},
{
"epoch": 4.69,
"learning_rate": 3.479544495993252e-06,
"loss": 0.19,
"step": 2470
},
{
"epoch": 4.7,
"learning_rate": 3.2686630113876e-06,
"loss": 0.1741,
"step": 2480
},
{
"epoch": 4.72,
"learning_rate": 3.057781526781949e-06,
"loss": 0.1697,
"step": 2490
},
{
"epoch": 4.74,
"learning_rate": 2.846900042176297e-06,
"loss": 0.1901,
"step": 2500
},
{
"epoch": 4.76,
"learning_rate": 2.6360185575706454e-06,
"loss": 0.1794,
"step": 2510
},
{
"epoch": 4.78,
"learning_rate": 2.425137072964994e-06,
"loss": 0.1514,
"step": 2520
},
{
"epoch": 4.8,
"learning_rate": 2.2142555883593423e-06,
"loss": 0.1841,
"step": 2530
},
{
"epoch": 4.82,
"learning_rate": 2.0033741037536907e-06,
"loss": 0.1676,
"step": 2540
},
{
"epoch": 4.84,
"learning_rate": 1.792492619148039e-06,
"loss": 0.1723,
"step": 2550
},
{
"epoch": 4.86,
"learning_rate": 1.5816111345423871e-06,
"loss": 0.186,
"step": 2560
},
{
"epoch": 4.88,
"learning_rate": 1.3707296499367356e-06,
"loss": 0.1669,
"step": 2570
},
{
"epoch": 4.89,
"learning_rate": 1.1598481653310838e-06,
"loss": 0.1801,
"step": 2580
},
{
"epoch": 4.91,
"learning_rate": 9.489666807254323e-07,
"loss": 0.1469,
"step": 2590
},
{
"epoch": 4.93,
"learning_rate": 7.380851961197808e-07,
"loss": 0.1642,
"step": 2600
},
{
"epoch": 4.95,
"learning_rate": 5.272037115141291e-07,
"loss": 0.1691,
"step": 2610
},
{
"epoch": 4.97,
"learning_rate": 3.1632222690847745e-07,
"loss": 0.1644,
"step": 2620
},
{
"epoch": 4.99,
"learning_rate": 1.0544074230282581e-07,
"loss": 0.173,
"step": 2630
},
{
"epoch": 5.0,
"eval_accuracy": 0.9741915422885572,
"eval_loss": 0.06838314980268478,
"eval_runtime": 133.6073,
"eval_samples_per_second": 72.212,
"eval_steps_per_second": 2.26,
"step": 2635
},
{
"epoch": 5.0,
"step": 2635,
"total_flos": 8.391154825876193e+18,
"train_loss": 0.33317647269826234,
"train_runtime": 8035.3313,
"train_samples_per_second": 42.02,
"train_steps_per_second": 0.328
}
],
"max_steps": 2635,
"num_train_epochs": 5,
"total_flos": 8.391154825876193e+18,
"trial_name": null,
"trial_params": null
}