Jayanth2002's picture
End of training
0562c92
{
"best_metric": 0.9342629482071713,
"best_model_checkpoint": "vit_base_patch16_224-finetuned-SkinDisease/checkpoint-2820",
"epoch": 9.982300884955752,
"eval_steps": 500,
"global_step": 2820,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 1.7730496453900712e-06,
"loss": 3.5665,
"step": 10
},
{
"epoch": 0.07,
"learning_rate": 3.5460992907801423e-06,
"loss": 3.539,
"step": 20
},
{
"epoch": 0.11,
"learning_rate": 5.319148936170213e-06,
"loss": 3.4681,
"step": 30
},
{
"epoch": 0.14,
"learning_rate": 7.092198581560285e-06,
"loss": 3.3703,
"step": 40
},
{
"epoch": 0.18,
"learning_rate": 8.865248226950355e-06,
"loss": 3.22,
"step": 50
},
{
"epoch": 0.21,
"learning_rate": 1.0638297872340426e-05,
"loss": 3.1027,
"step": 60
},
{
"epoch": 0.25,
"learning_rate": 1.2411347517730498e-05,
"loss": 2.9537,
"step": 70
},
{
"epoch": 0.28,
"learning_rate": 1.418439716312057e-05,
"loss": 2.7977,
"step": 80
},
{
"epoch": 0.32,
"learning_rate": 1.595744680851064e-05,
"loss": 2.5979,
"step": 90
},
{
"epoch": 0.35,
"learning_rate": 1.773049645390071e-05,
"loss": 2.5062,
"step": 100
},
{
"epoch": 0.39,
"learning_rate": 1.950354609929078e-05,
"loss": 2.2981,
"step": 110
},
{
"epoch": 0.42,
"learning_rate": 2.1276595744680852e-05,
"loss": 2.1816,
"step": 120
},
{
"epoch": 0.46,
"learning_rate": 2.3049645390070924e-05,
"loss": 2.0612,
"step": 130
},
{
"epoch": 0.5,
"learning_rate": 2.4822695035460995e-05,
"loss": 1.9642,
"step": 140
},
{
"epoch": 0.53,
"learning_rate": 2.6595744680851064e-05,
"loss": 1.7489,
"step": 150
},
{
"epoch": 0.57,
"learning_rate": 2.836879432624114e-05,
"loss": 1.7245,
"step": 160
},
{
"epoch": 0.6,
"learning_rate": 3.0141843971631207e-05,
"loss": 1.6003,
"step": 170
},
{
"epoch": 0.64,
"learning_rate": 3.191489361702128e-05,
"loss": 1.5055,
"step": 180
},
{
"epoch": 0.67,
"learning_rate": 3.3687943262411347e-05,
"loss": 1.3892,
"step": 190
},
{
"epoch": 0.71,
"learning_rate": 3.546099290780142e-05,
"loss": 1.2483,
"step": 200
},
{
"epoch": 0.74,
"learning_rate": 3.723404255319149e-05,
"loss": 1.2776,
"step": 210
},
{
"epoch": 0.78,
"learning_rate": 3.900709219858156e-05,
"loss": 1.1794,
"step": 220
},
{
"epoch": 0.81,
"learning_rate": 4.078014184397163e-05,
"loss": 1.1382,
"step": 230
},
{
"epoch": 0.85,
"learning_rate": 4.2553191489361704e-05,
"loss": 1.1257,
"step": 240
},
{
"epoch": 0.88,
"learning_rate": 4.432624113475177e-05,
"loss": 1.1178,
"step": 250
},
{
"epoch": 0.92,
"learning_rate": 4.609929078014185e-05,
"loss": 0.9985,
"step": 260
},
{
"epoch": 0.96,
"learning_rate": 4.787234042553192e-05,
"loss": 1.0547,
"step": 270
},
{
"epoch": 0.99,
"learning_rate": 4.964539007092199e-05,
"loss": 0.9099,
"step": 280
},
{
"epoch": 1.0,
"eval_accuracy": 0.764691235059761,
"eval_loss": 0.8247547149658203,
"eval_runtime": 88.9587,
"eval_samples_per_second": 45.145,
"eval_steps_per_second": 1.416,
"step": 282
},
{
"epoch": 1.03,
"learning_rate": 4.984239558707644e-05,
"loss": 0.9566,
"step": 290
},
{
"epoch": 1.06,
"learning_rate": 4.964539007092199e-05,
"loss": 0.8344,
"step": 300
},
{
"epoch": 1.1,
"learning_rate": 4.944838455476754e-05,
"loss": 0.8723,
"step": 310
},
{
"epoch": 1.13,
"learning_rate": 4.9251379038613084e-05,
"loss": 0.8365,
"step": 320
},
{
"epoch": 1.17,
"learning_rate": 4.905437352245863e-05,
"loss": 0.7845,
"step": 330
},
{
"epoch": 1.2,
"learning_rate": 4.885736800630418e-05,
"loss": 0.7433,
"step": 340
},
{
"epoch": 1.24,
"learning_rate": 4.8660362490149725e-05,
"loss": 0.7748,
"step": 350
},
{
"epoch": 1.27,
"learning_rate": 4.846335697399527e-05,
"loss": 0.7358,
"step": 360
},
{
"epoch": 1.31,
"learning_rate": 4.826635145784082e-05,
"loss": 0.7416,
"step": 370
},
{
"epoch": 1.35,
"learning_rate": 4.806934594168637e-05,
"loss": 0.713,
"step": 380
},
{
"epoch": 1.38,
"learning_rate": 4.787234042553192e-05,
"loss": 0.7054,
"step": 390
},
{
"epoch": 1.42,
"learning_rate": 4.7675334909377466e-05,
"loss": 0.628,
"step": 400
},
{
"epoch": 1.45,
"learning_rate": 4.747832939322301e-05,
"loss": 0.6797,
"step": 410
},
{
"epoch": 1.49,
"learning_rate": 4.728132387706856e-05,
"loss": 0.6752,
"step": 420
},
{
"epoch": 1.52,
"learning_rate": 4.7084318360914107e-05,
"loss": 0.6186,
"step": 430
},
{
"epoch": 1.56,
"learning_rate": 4.6887312844759653e-05,
"loss": 0.6372,
"step": 440
},
{
"epoch": 1.59,
"learning_rate": 4.669030732860521e-05,
"loss": 0.6946,
"step": 450
},
{
"epoch": 1.63,
"learning_rate": 4.6493301812450754e-05,
"loss": 0.5847,
"step": 460
},
{
"epoch": 1.66,
"learning_rate": 4.62962962962963e-05,
"loss": 0.5871,
"step": 470
},
{
"epoch": 1.7,
"learning_rate": 4.609929078014185e-05,
"loss": 0.627,
"step": 480
},
{
"epoch": 1.73,
"learning_rate": 4.5902285263987394e-05,
"loss": 0.5451,
"step": 490
},
{
"epoch": 1.77,
"learning_rate": 4.570527974783294e-05,
"loss": 0.608,
"step": 500
},
{
"epoch": 1.81,
"learning_rate": 4.550827423167849e-05,
"loss": 0.666,
"step": 510
},
{
"epoch": 1.84,
"learning_rate": 4.5311268715524035e-05,
"loss": 0.5734,
"step": 520
},
{
"epoch": 1.88,
"learning_rate": 4.511426319936958e-05,
"loss": 0.5667,
"step": 530
},
{
"epoch": 1.91,
"learning_rate": 4.491725768321513e-05,
"loss": 0.5508,
"step": 540
},
{
"epoch": 1.95,
"learning_rate": 4.4720252167060676e-05,
"loss": 0.5871,
"step": 550
},
{
"epoch": 1.98,
"learning_rate": 4.452324665090622e-05,
"loss": 0.5848,
"step": 560
},
{
"epoch": 2.0,
"eval_accuracy": 0.8747509960159362,
"eval_loss": 0.42364752292633057,
"eval_runtime": 85.8744,
"eval_samples_per_second": 46.766,
"eval_steps_per_second": 1.467,
"step": 565
},
{
"epoch": 2.02,
"learning_rate": 4.432624113475177e-05,
"loss": 0.5252,
"step": 570
},
{
"epoch": 2.05,
"learning_rate": 4.412923561859732e-05,
"loss": 0.4713,
"step": 580
},
{
"epoch": 2.09,
"learning_rate": 4.393223010244287e-05,
"loss": 0.4634,
"step": 590
},
{
"epoch": 2.12,
"learning_rate": 4.373522458628842e-05,
"loss": 0.5289,
"step": 600
},
{
"epoch": 2.16,
"learning_rate": 4.353821907013397e-05,
"loss": 0.4863,
"step": 610
},
{
"epoch": 2.19,
"learning_rate": 4.334121355397952e-05,
"loss": 0.4758,
"step": 620
},
{
"epoch": 2.23,
"learning_rate": 4.3144208037825064e-05,
"loss": 0.4495,
"step": 630
},
{
"epoch": 2.27,
"learning_rate": 4.294720252167061e-05,
"loss": 0.4246,
"step": 640
},
{
"epoch": 2.3,
"learning_rate": 4.275019700551616e-05,
"loss": 0.4965,
"step": 650
},
{
"epoch": 2.34,
"learning_rate": 4.2553191489361704e-05,
"loss": 0.4253,
"step": 660
},
{
"epoch": 2.37,
"learning_rate": 4.235618597320725e-05,
"loss": 0.4851,
"step": 670
},
{
"epoch": 2.41,
"learning_rate": 4.21591804570528e-05,
"loss": 0.4589,
"step": 680
},
{
"epoch": 2.44,
"learning_rate": 4.1962174940898345e-05,
"loss": 0.4366,
"step": 690
},
{
"epoch": 2.48,
"learning_rate": 4.176516942474389e-05,
"loss": 0.4655,
"step": 700
},
{
"epoch": 2.51,
"learning_rate": 4.156816390858944e-05,
"loss": 0.4857,
"step": 710
},
{
"epoch": 2.55,
"learning_rate": 4.1371158392434986e-05,
"loss": 0.4506,
"step": 720
},
{
"epoch": 2.58,
"learning_rate": 4.117415287628054e-05,
"loss": 0.4374,
"step": 730
},
{
"epoch": 2.62,
"learning_rate": 4.0977147360126086e-05,
"loss": 0.4443,
"step": 740
},
{
"epoch": 2.65,
"learning_rate": 4.078014184397163e-05,
"loss": 0.4467,
"step": 750
},
{
"epoch": 2.69,
"learning_rate": 4.058313632781718e-05,
"loss": 0.4704,
"step": 760
},
{
"epoch": 2.73,
"learning_rate": 4.0386130811662727e-05,
"loss": 0.425,
"step": 770
},
{
"epoch": 2.76,
"learning_rate": 4.018912529550828e-05,
"loss": 0.4493,
"step": 780
},
{
"epoch": 2.8,
"learning_rate": 3.999211977935383e-05,
"loss": 0.4149,
"step": 790
},
{
"epoch": 2.83,
"learning_rate": 3.9795114263199374e-05,
"loss": 0.4443,
"step": 800
},
{
"epoch": 2.87,
"learning_rate": 3.959810874704492e-05,
"loss": 0.4401,
"step": 810
},
{
"epoch": 2.9,
"learning_rate": 3.940110323089047e-05,
"loss": 0.4113,
"step": 820
},
{
"epoch": 2.94,
"learning_rate": 3.9204097714736014e-05,
"loss": 0.4106,
"step": 830
},
{
"epoch": 2.97,
"learning_rate": 3.900709219858156e-05,
"loss": 0.3952,
"step": 840
},
{
"epoch": 3.0,
"eval_accuracy": 0.9021414342629482,
"eval_loss": 0.3154027462005615,
"eval_runtime": 72.9456,
"eval_samples_per_second": 55.055,
"eval_steps_per_second": 1.727,
"step": 847
},
{
"epoch": 3.01,
"learning_rate": 3.881008668242711e-05,
"loss": 0.3375,
"step": 850
},
{
"epoch": 3.04,
"learning_rate": 3.8613081166272655e-05,
"loss": 0.3709,
"step": 860
},
{
"epoch": 3.08,
"learning_rate": 3.84160756501182e-05,
"loss": 0.3932,
"step": 870
},
{
"epoch": 3.12,
"learning_rate": 3.8219070133963755e-05,
"loss": 0.4064,
"step": 880
},
{
"epoch": 3.15,
"learning_rate": 3.80220646178093e-05,
"loss": 0.3827,
"step": 890
},
{
"epoch": 3.19,
"learning_rate": 3.782505910165485e-05,
"loss": 0.3432,
"step": 900
},
{
"epoch": 3.22,
"learning_rate": 3.7628053585500396e-05,
"loss": 0.3915,
"step": 910
},
{
"epoch": 3.26,
"learning_rate": 3.743104806934594e-05,
"loss": 0.3692,
"step": 920
},
{
"epoch": 3.29,
"learning_rate": 3.723404255319149e-05,
"loss": 0.4126,
"step": 930
},
{
"epoch": 3.33,
"learning_rate": 3.7037037037037037e-05,
"loss": 0.3977,
"step": 940
},
{
"epoch": 3.36,
"learning_rate": 3.6840031520882583e-05,
"loss": 0.3758,
"step": 950
},
{
"epoch": 3.4,
"learning_rate": 3.664302600472813e-05,
"loss": 0.4129,
"step": 960
},
{
"epoch": 3.43,
"learning_rate": 3.6446020488573684e-05,
"loss": 0.3527,
"step": 970
},
{
"epoch": 3.47,
"learning_rate": 3.624901497241923e-05,
"loss": 0.3177,
"step": 980
},
{
"epoch": 3.5,
"learning_rate": 3.605200945626478e-05,
"loss": 0.3571,
"step": 990
},
{
"epoch": 3.54,
"learning_rate": 3.5855003940110324e-05,
"loss": 0.359,
"step": 1000
},
{
"epoch": 3.58,
"learning_rate": 3.565799842395587e-05,
"loss": 0.3537,
"step": 1010
},
{
"epoch": 3.61,
"learning_rate": 3.546099290780142e-05,
"loss": 0.3786,
"step": 1020
},
{
"epoch": 3.65,
"learning_rate": 3.526398739164697e-05,
"loss": 0.3314,
"step": 1030
},
{
"epoch": 3.68,
"learning_rate": 3.506698187549252e-05,
"loss": 0.3432,
"step": 1040
},
{
"epoch": 3.72,
"learning_rate": 3.4869976359338065e-05,
"loss": 0.3584,
"step": 1050
},
{
"epoch": 3.75,
"learning_rate": 3.467297084318361e-05,
"loss": 0.3607,
"step": 1060
},
{
"epoch": 3.79,
"learning_rate": 3.447596532702916e-05,
"loss": 0.3257,
"step": 1070
},
{
"epoch": 3.82,
"learning_rate": 3.4278959810874706e-05,
"loss": 0.3938,
"step": 1080
},
{
"epoch": 3.86,
"learning_rate": 3.408195429472025e-05,
"loss": 0.3557,
"step": 1090
},
{
"epoch": 3.89,
"learning_rate": 3.38849487785658e-05,
"loss": 0.3264,
"step": 1100
},
{
"epoch": 3.93,
"learning_rate": 3.3687943262411347e-05,
"loss": 0.35,
"step": 1110
},
{
"epoch": 3.96,
"learning_rate": 3.349093774625689e-05,
"loss": 0.3431,
"step": 1120
},
{
"epoch": 4.0,
"learning_rate": 3.329393223010244e-05,
"loss": 0.3957,
"step": 1130
},
{
"epoch": 4.0,
"eval_accuracy": 0.9106075697211156,
"eval_loss": 0.2695058584213257,
"eval_runtime": 79.261,
"eval_samples_per_second": 50.668,
"eval_steps_per_second": 1.59,
"step": 1130
},
{
"epoch": 4.04,
"learning_rate": 3.309692671394799e-05,
"loss": 0.3067,
"step": 1140
},
{
"epoch": 4.07,
"learning_rate": 3.2899921197793534e-05,
"loss": 0.2966,
"step": 1150
},
{
"epoch": 4.11,
"learning_rate": 3.270291568163909e-05,
"loss": 0.2977,
"step": 1160
},
{
"epoch": 4.14,
"learning_rate": 3.2505910165484634e-05,
"loss": 0.3108,
"step": 1170
},
{
"epoch": 4.18,
"learning_rate": 3.230890464933019e-05,
"loss": 0.3401,
"step": 1180
},
{
"epoch": 4.21,
"learning_rate": 3.2111899133175735e-05,
"loss": 0.3415,
"step": 1190
},
{
"epoch": 4.25,
"learning_rate": 3.191489361702128e-05,
"loss": 0.3297,
"step": 1200
},
{
"epoch": 4.28,
"learning_rate": 3.171788810086683e-05,
"loss": 0.3289,
"step": 1210
},
{
"epoch": 4.32,
"learning_rate": 3.1520882584712375e-05,
"loss": 0.3149,
"step": 1220
},
{
"epoch": 4.35,
"learning_rate": 3.132387706855792e-05,
"loss": 0.3181,
"step": 1230
},
{
"epoch": 4.39,
"learning_rate": 3.112687155240347e-05,
"loss": 0.2779,
"step": 1240
},
{
"epoch": 4.42,
"learning_rate": 3.0929866036249016e-05,
"loss": 0.3016,
"step": 1250
},
{
"epoch": 4.46,
"learning_rate": 3.073286052009456e-05,
"loss": 0.2998,
"step": 1260
},
{
"epoch": 4.5,
"learning_rate": 3.053585500394011e-05,
"loss": 0.3195,
"step": 1270
},
{
"epoch": 4.53,
"learning_rate": 3.033884948778566e-05,
"loss": 0.3305,
"step": 1280
},
{
"epoch": 4.57,
"learning_rate": 3.0141843971631207e-05,
"loss": 0.3228,
"step": 1290
},
{
"epoch": 4.6,
"learning_rate": 2.9944838455476754e-05,
"loss": 0.3396,
"step": 1300
},
{
"epoch": 4.64,
"learning_rate": 2.97478329393223e-05,
"loss": 0.3228,
"step": 1310
},
{
"epoch": 4.67,
"learning_rate": 2.9550827423167847e-05,
"loss": 0.328,
"step": 1320
},
{
"epoch": 4.71,
"learning_rate": 2.9353821907013394e-05,
"loss": 0.2817,
"step": 1330
},
{
"epoch": 4.74,
"learning_rate": 2.9156816390858944e-05,
"loss": 0.3395,
"step": 1340
},
{
"epoch": 4.78,
"learning_rate": 2.895981087470449e-05,
"loss": 0.3263,
"step": 1350
},
{
"epoch": 4.81,
"learning_rate": 2.8762805358550045e-05,
"loss": 0.3101,
"step": 1360
},
{
"epoch": 4.85,
"learning_rate": 2.8565799842395592e-05,
"loss": 0.2777,
"step": 1370
},
{
"epoch": 4.88,
"learning_rate": 2.836879432624114e-05,
"loss": 0.305,
"step": 1380
},
{
"epoch": 4.92,
"learning_rate": 2.8171788810086685e-05,
"loss": 0.3065,
"step": 1390
},
{
"epoch": 4.96,
"learning_rate": 2.7974783293932232e-05,
"loss": 0.311,
"step": 1400
},
{
"epoch": 4.99,
"learning_rate": 2.777777777777778e-05,
"loss": 0.3146,
"step": 1410
},
{
"epoch": 5.0,
"eval_accuracy": 0.9198207171314741,
"eval_loss": 0.23812231421470642,
"eval_runtime": 71.133,
"eval_samples_per_second": 56.458,
"eval_steps_per_second": 1.771,
"step": 1412
},
{
"epoch": 5.03,
"learning_rate": 2.758077226162333e-05,
"loss": 0.2598,
"step": 1420
},
{
"epoch": 5.06,
"learning_rate": 2.7383766745468876e-05,
"loss": 0.2723,
"step": 1430
},
{
"epoch": 5.1,
"learning_rate": 2.7186761229314423e-05,
"loss": 0.2936,
"step": 1440
},
{
"epoch": 5.13,
"learning_rate": 2.698975571315997e-05,
"loss": 0.3201,
"step": 1450
},
{
"epoch": 5.17,
"learning_rate": 2.6792750197005517e-05,
"loss": 0.2537,
"step": 1460
},
{
"epoch": 5.2,
"learning_rate": 2.6595744680851064e-05,
"loss": 0.327,
"step": 1470
},
{
"epoch": 5.24,
"learning_rate": 2.639873916469661e-05,
"loss": 0.2937,
"step": 1480
},
{
"epoch": 5.27,
"learning_rate": 2.620173364854216e-05,
"loss": 0.2968,
"step": 1490
},
{
"epoch": 5.31,
"learning_rate": 2.6004728132387708e-05,
"loss": 0.2921,
"step": 1500
},
{
"epoch": 5.35,
"learning_rate": 2.5807722616233254e-05,
"loss": 0.3074,
"step": 1510
},
{
"epoch": 5.38,
"learning_rate": 2.56107171000788e-05,
"loss": 0.3168,
"step": 1520
},
{
"epoch": 5.42,
"learning_rate": 2.5413711583924348e-05,
"loss": 0.2683,
"step": 1530
},
{
"epoch": 5.45,
"learning_rate": 2.5216706067769895e-05,
"loss": 0.2985,
"step": 1540
},
{
"epoch": 5.49,
"learning_rate": 2.5019700551615445e-05,
"loss": 0.2838,
"step": 1550
},
{
"epoch": 5.52,
"learning_rate": 2.4822695035460995e-05,
"loss": 0.2936,
"step": 1560
},
{
"epoch": 5.56,
"learning_rate": 2.4625689519306542e-05,
"loss": 0.3081,
"step": 1570
},
{
"epoch": 5.59,
"learning_rate": 2.442868400315209e-05,
"loss": 0.2373,
"step": 1580
},
{
"epoch": 5.63,
"learning_rate": 2.4231678486997636e-05,
"loss": 0.2953,
"step": 1590
},
{
"epoch": 5.66,
"learning_rate": 2.4034672970843186e-05,
"loss": 0.2781,
"step": 1600
},
{
"epoch": 5.7,
"learning_rate": 2.3837667454688733e-05,
"loss": 0.277,
"step": 1610
},
{
"epoch": 5.73,
"learning_rate": 2.364066193853428e-05,
"loss": 0.2925,
"step": 1620
},
{
"epoch": 5.77,
"learning_rate": 2.3443656422379827e-05,
"loss": 0.2578,
"step": 1630
},
{
"epoch": 5.81,
"learning_rate": 2.3246650906225377e-05,
"loss": 0.2808,
"step": 1640
},
{
"epoch": 5.84,
"learning_rate": 2.3049645390070924e-05,
"loss": 0.3181,
"step": 1650
},
{
"epoch": 5.88,
"learning_rate": 2.285263987391647e-05,
"loss": 0.302,
"step": 1660
},
{
"epoch": 5.91,
"learning_rate": 2.2655634357762018e-05,
"loss": 0.2724,
"step": 1670
},
{
"epoch": 5.95,
"learning_rate": 2.2458628841607564e-05,
"loss": 0.2614,
"step": 1680
},
{
"epoch": 5.98,
"learning_rate": 2.226162332545311e-05,
"loss": 0.2883,
"step": 1690
},
{
"epoch": 6.0,
"eval_accuracy": 0.921812749003984,
"eval_loss": 0.24074074625968933,
"eval_runtime": 81.9182,
"eval_samples_per_second": 49.025,
"eval_steps_per_second": 1.538,
"step": 1695
},
{
"epoch": 6.02,
"learning_rate": 2.206461780929866e-05,
"loss": 0.2695,
"step": 1700
},
{
"epoch": 6.05,
"learning_rate": 2.186761229314421e-05,
"loss": 0.31,
"step": 1710
},
{
"epoch": 6.09,
"learning_rate": 2.167060677698976e-05,
"loss": 0.2598,
"step": 1720
},
{
"epoch": 6.12,
"learning_rate": 2.1473601260835305e-05,
"loss": 0.26,
"step": 1730
},
{
"epoch": 6.16,
"learning_rate": 2.1276595744680852e-05,
"loss": 0.2491,
"step": 1740
},
{
"epoch": 6.19,
"learning_rate": 2.10795902285264e-05,
"loss": 0.2479,
"step": 1750
},
{
"epoch": 6.23,
"learning_rate": 2.0882584712371946e-05,
"loss": 0.2387,
"step": 1760
},
{
"epoch": 6.27,
"learning_rate": 2.0685579196217493e-05,
"loss": 0.2686,
"step": 1770
},
{
"epoch": 6.3,
"learning_rate": 2.0488573680063043e-05,
"loss": 0.2302,
"step": 1780
},
{
"epoch": 6.34,
"learning_rate": 2.029156816390859e-05,
"loss": 0.2592,
"step": 1790
},
{
"epoch": 6.37,
"learning_rate": 2.009456264775414e-05,
"loss": 0.2857,
"step": 1800
},
{
"epoch": 6.41,
"learning_rate": 1.9897557131599687e-05,
"loss": 0.2666,
"step": 1810
},
{
"epoch": 6.44,
"learning_rate": 1.9700551615445234e-05,
"loss": 0.2332,
"step": 1820
},
{
"epoch": 6.48,
"learning_rate": 1.950354609929078e-05,
"loss": 0.2552,
"step": 1830
},
{
"epoch": 6.51,
"learning_rate": 1.9306540583136327e-05,
"loss": 0.2688,
"step": 1840
},
{
"epoch": 6.55,
"learning_rate": 1.9109535066981878e-05,
"loss": 0.2424,
"step": 1850
},
{
"epoch": 6.58,
"learning_rate": 1.8912529550827425e-05,
"loss": 0.2981,
"step": 1860
},
{
"epoch": 6.62,
"learning_rate": 1.871552403467297e-05,
"loss": 0.2247,
"step": 1870
},
{
"epoch": 6.65,
"learning_rate": 1.8518518518518518e-05,
"loss": 0.2652,
"step": 1880
},
{
"epoch": 6.69,
"learning_rate": 1.8321513002364065e-05,
"loss": 0.2303,
"step": 1890
},
{
"epoch": 6.73,
"learning_rate": 1.8124507486209615e-05,
"loss": 0.2841,
"step": 1900
},
{
"epoch": 6.76,
"learning_rate": 1.7927501970055162e-05,
"loss": 0.2634,
"step": 1910
},
{
"epoch": 6.8,
"learning_rate": 1.773049645390071e-05,
"loss": 0.2628,
"step": 1920
},
{
"epoch": 6.83,
"learning_rate": 1.753349093774626e-05,
"loss": 0.2686,
"step": 1930
},
{
"epoch": 6.87,
"learning_rate": 1.7336485421591806e-05,
"loss": 0.2289,
"step": 1940
},
{
"epoch": 6.9,
"learning_rate": 1.7139479905437353e-05,
"loss": 0.2754,
"step": 1950
},
{
"epoch": 6.94,
"learning_rate": 1.69424743892829e-05,
"loss": 0.3029,
"step": 1960
},
{
"epoch": 6.97,
"learning_rate": 1.6745468873128447e-05,
"loss": 0.2264,
"step": 1970
},
{
"epoch": 7.0,
"eval_accuracy": 0.9277888446215139,
"eval_loss": 0.21604356169700623,
"eval_runtime": 81.708,
"eval_samples_per_second": 49.151,
"eval_steps_per_second": 1.542,
"step": 1977
},
{
"epoch": 7.01,
"learning_rate": 1.6548463356973994e-05,
"loss": 0.2146,
"step": 1980
},
{
"epoch": 7.04,
"learning_rate": 1.6351457840819544e-05,
"loss": 0.246,
"step": 1990
},
{
"epoch": 7.08,
"learning_rate": 1.6154452324665094e-05,
"loss": 0.2321,
"step": 2000
},
{
"epoch": 7.12,
"learning_rate": 1.595744680851064e-05,
"loss": 0.2116,
"step": 2010
},
{
"epoch": 7.15,
"learning_rate": 1.5760441292356188e-05,
"loss": 0.2548,
"step": 2020
},
{
"epoch": 7.19,
"learning_rate": 1.5563435776201735e-05,
"loss": 0.2535,
"step": 2030
},
{
"epoch": 7.22,
"learning_rate": 1.536643026004728e-05,
"loss": 0.2411,
"step": 2040
},
{
"epoch": 7.26,
"learning_rate": 1.516942474389283e-05,
"loss": 0.2832,
"step": 2050
},
{
"epoch": 7.29,
"learning_rate": 1.4972419227738377e-05,
"loss": 0.2626,
"step": 2060
},
{
"epoch": 7.33,
"learning_rate": 1.4775413711583924e-05,
"loss": 0.2454,
"step": 2070
},
{
"epoch": 7.36,
"learning_rate": 1.4578408195429472e-05,
"loss": 0.2343,
"step": 2080
},
{
"epoch": 7.4,
"learning_rate": 1.4381402679275022e-05,
"loss": 0.235,
"step": 2090
},
{
"epoch": 7.43,
"learning_rate": 1.418439716312057e-05,
"loss": 0.22,
"step": 2100
},
{
"epoch": 7.47,
"learning_rate": 1.3987391646966116e-05,
"loss": 0.2518,
"step": 2110
},
{
"epoch": 7.5,
"learning_rate": 1.3790386130811665e-05,
"loss": 0.2151,
"step": 2120
},
{
"epoch": 7.54,
"learning_rate": 1.3593380614657212e-05,
"loss": 0.2332,
"step": 2130
},
{
"epoch": 7.58,
"learning_rate": 1.3396375098502758e-05,
"loss": 0.1913,
"step": 2140
},
{
"epoch": 7.61,
"learning_rate": 1.3199369582348305e-05,
"loss": 0.2233,
"step": 2150
},
{
"epoch": 7.65,
"learning_rate": 1.3002364066193854e-05,
"loss": 0.2342,
"step": 2160
},
{
"epoch": 7.68,
"learning_rate": 1.28053585500394e-05,
"loss": 0.221,
"step": 2170
},
{
"epoch": 7.72,
"learning_rate": 1.2608353033884947e-05,
"loss": 0.2295,
"step": 2180
},
{
"epoch": 7.75,
"learning_rate": 1.2411347517730498e-05,
"loss": 0.2108,
"step": 2190
},
{
"epoch": 7.79,
"learning_rate": 1.2214342001576045e-05,
"loss": 0.2356,
"step": 2200
},
{
"epoch": 7.82,
"learning_rate": 1.2017336485421593e-05,
"loss": 0.255,
"step": 2210
},
{
"epoch": 7.86,
"learning_rate": 1.182033096926714e-05,
"loss": 0.2301,
"step": 2220
},
{
"epoch": 7.89,
"learning_rate": 1.1623325453112688e-05,
"loss": 0.2541,
"step": 2230
},
{
"epoch": 7.93,
"learning_rate": 1.1426319936958235e-05,
"loss": 0.2411,
"step": 2240
},
{
"epoch": 7.96,
"learning_rate": 1.1229314420803782e-05,
"loss": 0.2147,
"step": 2250
},
{
"epoch": 8.0,
"learning_rate": 1.103230890464933e-05,
"loss": 0.2339,
"step": 2260
},
{
"epoch": 8.0,
"eval_accuracy": 0.9282868525896414,
"eval_loss": 0.21214231848716736,
"eval_runtime": 78.6901,
"eval_samples_per_second": 51.036,
"eval_steps_per_second": 1.601,
"step": 2260
},
{
"epoch": 8.04,
"learning_rate": 1.083530338849488e-05,
"loss": 0.1966,
"step": 2270
},
{
"epoch": 8.07,
"learning_rate": 1.0638297872340426e-05,
"loss": 0.1993,
"step": 2280
},
{
"epoch": 8.11,
"learning_rate": 1.0441292356185973e-05,
"loss": 0.2137,
"step": 2290
},
{
"epoch": 8.14,
"learning_rate": 1.0244286840031522e-05,
"loss": 0.2221,
"step": 2300
},
{
"epoch": 8.18,
"learning_rate": 1.004728132387707e-05,
"loss": 0.2274,
"step": 2310
},
{
"epoch": 8.21,
"learning_rate": 9.850275807722617e-06,
"loss": 0.2008,
"step": 2320
},
{
"epoch": 8.25,
"learning_rate": 9.653270291568164e-06,
"loss": 0.244,
"step": 2330
},
{
"epoch": 8.28,
"learning_rate": 9.456264775413712e-06,
"loss": 0.207,
"step": 2340
},
{
"epoch": 8.32,
"learning_rate": 9.259259259259259e-06,
"loss": 0.2319,
"step": 2350
},
{
"epoch": 8.35,
"learning_rate": 9.062253743104808e-06,
"loss": 0.2151,
"step": 2360
},
{
"epoch": 8.39,
"learning_rate": 8.865248226950355e-06,
"loss": 0.2118,
"step": 2370
},
{
"epoch": 8.42,
"learning_rate": 8.668242710795903e-06,
"loss": 0.2449,
"step": 2380
},
{
"epoch": 8.46,
"learning_rate": 8.47123719464145e-06,
"loss": 0.2707,
"step": 2390
},
{
"epoch": 8.5,
"learning_rate": 8.274231678486997e-06,
"loss": 0.2238,
"step": 2400
},
{
"epoch": 8.53,
"learning_rate": 8.077226162332547e-06,
"loss": 0.2197,
"step": 2410
},
{
"epoch": 8.57,
"learning_rate": 7.880220646178094e-06,
"loss": 0.2109,
"step": 2420
},
{
"epoch": 8.6,
"learning_rate": 7.68321513002364e-06,
"loss": 0.2258,
"step": 2430
},
{
"epoch": 8.64,
"learning_rate": 7.486209613869188e-06,
"loss": 0.1806,
"step": 2440
},
{
"epoch": 8.67,
"learning_rate": 7.289204097714736e-06,
"loss": 0.2156,
"step": 2450
},
{
"epoch": 8.71,
"learning_rate": 7.092198581560285e-06,
"loss": 0.2298,
"step": 2460
},
{
"epoch": 8.74,
"learning_rate": 6.895193065405832e-06,
"loss": 0.1984,
"step": 2470
},
{
"epoch": 8.78,
"learning_rate": 6.698187549251379e-06,
"loss": 0.1997,
"step": 2480
},
{
"epoch": 8.81,
"learning_rate": 6.501182033096927e-06,
"loss": 0.2346,
"step": 2490
},
{
"epoch": 8.85,
"learning_rate": 6.304176516942474e-06,
"loss": 0.1982,
"step": 2500
},
{
"epoch": 8.88,
"learning_rate": 6.107171000788022e-06,
"loss": 0.2262,
"step": 2510
},
{
"epoch": 8.92,
"learning_rate": 5.91016548463357e-06,
"loss": 0.195,
"step": 2520
},
{
"epoch": 8.96,
"learning_rate": 5.713159968479118e-06,
"loss": 0.2519,
"step": 2530
},
{
"epoch": 8.99,
"learning_rate": 5.516154452324665e-06,
"loss": 0.1966,
"step": 2540
},
{
"epoch": 9.0,
"eval_accuracy": 0.9302788844621513,
"eval_loss": 0.20438914000988007,
"eval_runtime": 93.0501,
"eval_samples_per_second": 43.16,
"eval_steps_per_second": 1.354,
"step": 2542
},
{
"epoch": 9.03,
"learning_rate": 5.319148936170213e-06,
"loss": 0.2231,
"step": 2550
},
{
"epoch": 9.06,
"learning_rate": 5.122143420015761e-06,
"loss": 0.2259,
"step": 2560
},
{
"epoch": 9.1,
"learning_rate": 4.9251379038613084e-06,
"loss": 0.2053,
"step": 2570
},
{
"epoch": 9.13,
"learning_rate": 4.728132387706856e-06,
"loss": 0.1838,
"step": 2580
},
{
"epoch": 9.17,
"learning_rate": 4.531126871552404e-06,
"loss": 0.2209,
"step": 2590
},
{
"epoch": 9.2,
"learning_rate": 4.3341213553979515e-06,
"loss": 0.2122,
"step": 2600
},
{
"epoch": 9.24,
"learning_rate": 4.137115839243498e-06,
"loss": 0.1958,
"step": 2610
},
{
"epoch": 9.27,
"learning_rate": 3.940110323089047e-06,
"loss": 0.1875,
"step": 2620
},
{
"epoch": 9.31,
"learning_rate": 3.743104806934594e-06,
"loss": 0.2083,
"step": 2630
},
{
"epoch": 9.35,
"learning_rate": 3.5460992907801423e-06,
"loss": 0.2043,
"step": 2640
},
{
"epoch": 9.38,
"learning_rate": 3.3490937746256896e-06,
"loss": 0.1946,
"step": 2650
},
{
"epoch": 9.42,
"learning_rate": 3.152088258471237e-06,
"loss": 0.194,
"step": 2660
},
{
"epoch": 9.45,
"learning_rate": 2.955082742316785e-06,
"loss": 0.209,
"step": 2670
},
{
"epoch": 9.49,
"learning_rate": 2.7580772261623327e-06,
"loss": 0.2092,
"step": 2680
},
{
"epoch": 9.52,
"learning_rate": 2.5610717100078804e-06,
"loss": 0.2246,
"step": 2690
},
{
"epoch": 9.56,
"learning_rate": 2.364066193853428e-06,
"loss": 0.2011,
"step": 2700
},
{
"epoch": 9.59,
"learning_rate": 2.1670606776989758e-06,
"loss": 0.1963,
"step": 2710
},
{
"epoch": 9.63,
"learning_rate": 1.9700551615445235e-06,
"loss": 0.2212,
"step": 2720
},
{
"epoch": 9.66,
"learning_rate": 1.7730496453900712e-06,
"loss": 0.214,
"step": 2730
},
{
"epoch": 9.7,
"learning_rate": 1.5760441292356184e-06,
"loss": 0.18,
"step": 2740
},
{
"epoch": 9.73,
"learning_rate": 1.3790386130811663e-06,
"loss": 0.183,
"step": 2750
},
{
"epoch": 9.77,
"learning_rate": 1.182033096926714e-06,
"loss": 0.2138,
"step": 2760
},
{
"epoch": 9.81,
"learning_rate": 9.850275807722617e-07,
"loss": 0.206,
"step": 2770
},
{
"epoch": 9.84,
"learning_rate": 7.880220646178092e-07,
"loss": 0.1992,
"step": 2780
},
{
"epoch": 9.88,
"learning_rate": 5.91016548463357e-07,
"loss": 0.2199,
"step": 2790
},
{
"epoch": 9.91,
"learning_rate": 3.940110323089046e-07,
"loss": 0.195,
"step": 2800
},
{
"epoch": 9.95,
"learning_rate": 1.970055161544523e-07,
"loss": 0.2096,
"step": 2810
},
{
"epoch": 9.98,
"learning_rate": 0.0,
"loss": 0.2366,
"step": 2820
},
{
"epoch": 9.98,
"eval_accuracy": 0.9342629482071713,
"eval_loss": 0.19922704994678497,
"eval_runtime": 78.2576,
"eval_samples_per_second": 51.318,
"eval_steps_per_second": 1.61,
"step": 2820
},
{
"epoch": 9.98,
"step": 2820,
"total_flos": 2.796343146304469e+19,
"train_loss": 0.5066332549913555,
"train_runtime": 12045.0104,
"train_samples_per_second": 30.002,
"train_steps_per_second": 0.234
}
],
"logging_steps": 10,
"max_steps": 2820,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 2.796343146304469e+19,
"trial_name": null,
"trial_params": null
}