Gokulapriyan's picture
End of training
4484406
{
"best_metric": 0.9481739412098146,
"best_model_checkpoint": "deit-tiny-patch16-224-finetuned-og-dataset-10e/checkpoint-2184",
"epoch": 5.998628257887518,
"global_step": 2184,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 2.2831050228310503e-06,
"loss": 1.4902,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 4.566210045662101e-06,
"loss": 1.3426,
"step": 20
},
{
"epoch": 0.08,
"learning_rate": 6.849315068493151e-06,
"loss": 1.1594,
"step": 30
},
{
"epoch": 0.11,
"learning_rate": 9.132420091324201e-06,
"loss": 0.9353,
"step": 40
},
{
"epoch": 0.14,
"learning_rate": 1.1415525114155251e-05,
"loss": 0.8424,
"step": 50
},
{
"epoch": 0.16,
"learning_rate": 1.3698630136986302e-05,
"loss": 0.8113,
"step": 60
},
{
"epoch": 0.19,
"learning_rate": 1.5981735159817352e-05,
"loss": 0.7902,
"step": 70
},
{
"epoch": 0.22,
"learning_rate": 1.8264840182648402e-05,
"loss": 0.7755,
"step": 80
},
{
"epoch": 0.25,
"learning_rate": 2.0547945205479453e-05,
"loss": 0.7586,
"step": 90
},
{
"epoch": 0.27,
"learning_rate": 2.2831050228310503e-05,
"loss": 0.7285,
"step": 100
},
{
"epoch": 0.3,
"learning_rate": 2.5114155251141553e-05,
"loss": 0.7206,
"step": 110
},
{
"epoch": 0.33,
"learning_rate": 2.7397260273972603e-05,
"loss": 0.6964,
"step": 120
},
{
"epoch": 0.36,
"learning_rate": 2.9680365296803654e-05,
"loss": 0.6705,
"step": 130
},
{
"epoch": 0.38,
"learning_rate": 3.1963470319634704e-05,
"loss": 0.6803,
"step": 140
},
{
"epoch": 0.41,
"learning_rate": 3.424657534246575e-05,
"loss": 0.6864,
"step": 150
},
{
"epoch": 0.44,
"learning_rate": 3.6529680365296805e-05,
"loss": 0.6818,
"step": 160
},
{
"epoch": 0.47,
"learning_rate": 3.881278538812785e-05,
"loss": 0.6484,
"step": 170
},
{
"epoch": 0.49,
"learning_rate": 4.1095890410958905e-05,
"loss": 0.6527,
"step": 180
},
{
"epoch": 0.52,
"learning_rate": 4.337899543378995e-05,
"loss": 0.632,
"step": 190
},
{
"epoch": 0.55,
"learning_rate": 4.5662100456621006e-05,
"loss": 0.6276,
"step": 200
},
{
"epoch": 0.58,
"learning_rate": 4.794520547945205e-05,
"loss": 0.6604,
"step": 210
},
{
"epoch": 0.6,
"learning_rate": 4.997455470737914e-05,
"loss": 0.6407,
"step": 220
},
{
"epoch": 0.63,
"learning_rate": 4.9720101781170486e-05,
"loss": 0.6526,
"step": 230
},
{
"epoch": 0.66,
"learning_rate": 4.9465648854961834e-05,
"loss": 0.6136,
"step": 240
},
{
"epoch": 0.69,
"learning_rate": 4.921119592875318e-05,
"loss": 0.5914,
"step": 250
},
{
"epoch": 0.71,
"learning_rate": 4.895674300254453e-05,
"loss": 0.6173,
"step": 260
},
{
"epoch": 0.74,
"learning_rate": 4.8702290076335885e-05,
"loss": 0.6036,
"step": 270
},
{
"epoch": 0.77,
"learning_rate": 4.844783715012723e-05,
"loss": 0.5949,
"step": 280
},
{
"epoch": 0.8,
"learning_rate": 4.8193384223918575e-05,
"loss": 0.5636,
"step": 290
},
{
"epoch": 0.82,
"learning_rate": 4.793893129770993e-05,
"loss": 0.557,
"step": 300
},
{
"epoch": 0.85,
"learning_rate": 4.768447837150127e-05,
"loss": 0.567,
"step": 310
},
{
"epoch": 0.88,
"learning_rate": 4.743002544529263e-05,
"loss": 0.5625,
"step": 320
},
{
"epoch": 0.91,
"learning_rate": 4.717557251908397e-05,
"loss": 0.5814,
"step": 330
},
{
"epoch": 0.93,
"learning_rate": 4.6921119592875317e-05,
"loss": 0.5825,
"step": 340
},
{
"epoch": 0.96,
"learning_rate": 4.666666666666667e-05,
"loss": 0.52,
"step": 350
},
{
"epoch": 0.99,
"learning_rate": 4.641221374045801e-05,
"loss": 0.5434,
"step": 360
},
{
"epoch": 1.0,
"eval_accuracy": 0.8003886954409264,
"eval_loss": 0.46485939621925354,
"eval_runtime": 145.162,
"eval_samples_per_second": 85.07,
"eval_steps_per_second": 1.777,
"step": 364
},
{
"epoch": 1.02,
"learning_rate": 4.615776081424937e-05,
"loss": 0.5464,
"step": 370
},
{
"epoch": 1.04,
"learning_rate": 4.5903307888040716e-05,
"loss": 0.5175,
"step": 380
},
{
"epoch": 1.07,
"learning_rate": 4.5648854961832065e-05,
"loss": 0.542,
"step": 390
},
{
"epoch": 1.1,
"learning_rate": 4.539440203562341e-05,
"loss": 0.5581,
"step": 400
},
{
"epoch": 1.13,
"learning_rate": 4.513994910941476e-05,
"loss": 0.5754,
"step": 410
},
{
"epoch": 1.15,
"learning_rate": 4.488549618320611e-05,
"loss": 0.5116,
"step": 420
},
{
"epoch": 1.18,
"learning_rate": 4.463104325699746e-05,
"loss": 0.5006,
"step": 430
},
{
"epoch": 1.21,
"learning_rate": 4.4376590330788806e-05,
"loss": 0.4939,
"step": 440
},
{
"epoch": 1.24,
"learning_rate": 4.4122137404580154e-05,
"loss": 0.5006,
"step": 450
},
{
"epoch": 1.26,
"learning_rate": 4.38676844783715e-05,
"loss": 0.4861,
"step": 460
},
{
"epoch": 1.29,
"learning_rate": 4.361323155216285e-05,
"loss": 0.4626,
"step": 470
},
{
"epoch": 1.32,
"learning_rate": 4.33587786259542e-05,
"loss": 0.4723,
"step": 480
},
{
"epoch": 1.35,
"learning_rate": 4.3104325699745554e-05,
"loss": 0.4499,
"step": 490
},
{
"epoch": 1.37,
"learning_rate": 4.2849872773536896e-05,
"loss": 0.477,
"step": 500
},
{
"epoch": 1.4,
"learning_rate": 4.2595419847328244e-05,
"loss": 0.4804,
"step": 510
},
{
"epoch": 1.43,
"learning_rate": 4.23409669211196e-05,
"loss": 0.4805,
"step": 520
},
{
"epoch": 1.46,
"learning_rate": 4.208651399491094e-05,
"loss": 0.4611,
"step": 530
},
{
"epoch": 1.48,
"learning_rate": 4.1832061068702296e-05,
"loss": 0.4573,
"step": 540
},
{
"epoch": 1.51,
"learning_rate": 4.157760814249364e-05,
"loss": 0.4532,
"step": 550
},
{
"epoch": 1.54,
"learning_rate": 4.1323155216284985e-05,
"loss": 0.4472,
"step": 560
},
{
"epoch": 1.57,
"learning_rate": 4.106870229007634e-05,
"loss": 0.4563,
"step": 570
},
{
"epoch": 1.59,
"learning_rate": 4.081424936386768e-05,
"loss": 0.4394,
"step": 580
},
{
"epoch": 1.62,
"learning_rate": 4.055979643765904e-05,
"loss": 0.4599,
"step": 590
},
{
"epoch": 1.65,
"learning_rate": 4.0305343511450385e-05,
"loss": 0.4466,
"step": 600
},
{
"epoch": 1.67,
"learning_rate": 4.0050890585241734e-05,
"loss": 0.443,
"step": 610
},
{
"epoch": 1.7,
"learning_rate": 3.979643765903308e-05,
"loss": 0.4413,
"step": 620
},
{
"epoch": 1.73,
"learning_rate": 3.954198473282443e-05,
"loss": 0.4168,
"step": 630
},
{
"epoch": 1.76,
"learning_rate": 3.928753180661578e-05,
"loss": 0.4134,
"step": 640
},
{
"epoch": 1.78,
"learning_rate": 3.903307888040713e-05,
"loss": 0.4401,
"step": 650
},
{
"epoch": 1.81,
"learning_rate": 3.8778625954198475e-05,
"loss": 0.4113,
"step": 660
},
{
"epoch": 1.84,
"learning_rate": 3.852417302798982e-05,
"loss": 0.4051,
"step": 670
},
{
"epoch": 1.87,
"learning_rate": 3.826972010178117e-05,
"loss": 0.435,
"step": 680
},
{
"epoch": 1.89,
"learning_rate": 3.801526717557252e-05,
"loss": 0.4313,
"step": 690
},
{
"epoch": 1.92,
"learning_rate": 3.776081424936387e-05,
"loss": 0.4097,
"step": 700
},
{
"epoch": 1.95,
"learning_rate": 3.750636132315522e-05,
"loss": 0.4292,
"step": 710
},
{
"epoch": 1.98,
"learning_rate": 3.7251908396946565e-05,
"loss": 0.3968,
"step": 720
},
{
"epoch": 2.0,
"eval_accuracy": 0.8713256134099927,
"eval_loss": 0.31458979845046997,
"eval_runtime": 148.1663,
"eval_samples_per_second": 83.346,
"eval_steps_per_second": 1.741,
"step": 728
},
{
"epoch": 2.01,
"learning_rate": 3.699745547073791e-05,
"loss": 0.4217,
"step": 730
},
{
"epoch": 2.03,
"learning_rate": 3.674300254452927e-05,
"loss": 0.404,
"step": 740
},
{
"epoch": 2.06,
"learning_rate": 3.648854961832061e-05,
"loss": 0.3986,
"step": 750
},
{
"epoch": 2.09,
"learning_rate": 3.6234096692111965e-05,
"loss": 0.3785,
"step": 760
},
{
"epoch": 2.12,
"learning_rate": 3.5979643765903306e-05,
"loss": 0.4032,
"step": 770
},
{
"epoch": 2.14,
"learning_rate": 3.5725190839694654e-05,
"loss": 0.3763,
"step": 780
},
{
"epoch": 2.17,
"learning_rate": 3.547073791348601e-05,
"loss": 0.3583,
"step": 790
},
{
"epoch": 2.2,
"learning_rate": 3.521628498727735e-05,
"loss": 0.4012,
"step": 800
},
{
"epoch": 2.22,
"learning_rate": 3.4961832061068706e-05,
"loss": 0.3448,
"step": 810
},
{
"epoch": 2.25,
"learning_rate": 3.4707379134860054e-05,
"loss": 0.398,
"step": 820
},
{
"epoch": 2.28,
"learning_rate": 3.44529262086514e-05,
"loss": 0.3806,
"step": 830
},
{
"epoch": 2.31,
"learning_rate": 3.419847328244275e-05,
"loss": 0.3674,
"step": 840
},
{
"epoch": 2.33,
"learning_rate": 3.39440203562341e-05,
"loss": 0.3559,
"step": 850
},
{
"epoch": 2.36,
"learning_rate": 3.368956743002545e-05,
"loss": 0.3825,
"step": 860
},
{
"epoch": 2.39,
"learning_rate": 3.3435114503816796e-05,
"loss": 0.375,
"step": 870
},
{
"epoch": 2.42,
"learning_rate": 3.3180661577608144e-05,
"loss": 0.3558,
"step": 880
},
{
"epoch": 2.44,
"learning_rate": 3.292620865139949e-05,
"loss": 0.3791,
"step": 890
},
{
"epoch": 2.47,
"learning_rate": 3.267175572519084e-05,
"loss": 0.3627,
"step": 900
},
{
"epoch": 2.5,
"learning_rate": 3.241730279898219e-05,
"loss": 0.3804,
"step": 910
},
{
"epoch": 2.53,
"learning_rate": 3.216284987277354e-05,
"loss": 0.3591,
"step": 920
},
{
"epoch": 2.55,
"learning_rate": 3.190839694656489e-05,
"loss": 0.3745,
"step": 930
},
{
"epoch": 2.58,
"learning_rate": 3.1653944020356234e-05,
"loss": 0.338,
"step": 940
},
{
"epoch": 2.61,
"learning_rate": 3.139949109414758e-05,
"loss": 0.343,
"step": 950
},
{
"epoch": 2.64,
"learning_rate": 3.114503816793894e-05,
"loss": 0.3537,
"step": 960
},
{
"epoch": 2.66,
"learning_rate": 3.089058524173028e-05,
"loss": 0.3347,
"step": 970
},
{
"epoch": 2.69,
"learning_rate": 3.0636132315521633e-05,
"loss": 0.3517,
"step": 980
},
{
"epoch": 2.72,
"learning_rate": 3.038167938931298e-05,
"loss": 0.336,
"step": 990
},
{
"epoch": 2.75,
"learning_rate": 3.0127226463104323e-05,
"loss": 0.3813,
"step": 1000
},
{
"epoch": 2.77,
"learning_rate": 2.9872773536895675e-05,
"loss": 0.3449,
"step": 1010
},
{
"epoch": 2.8,
"learning_rate": 2.9618320610687023e-05,
"loss": 0.3342,
"step": 1020
},
{
"epoch": 2.83,
"learning_rate": 2.9363867684478375e-05,
"loss": 0.3299,
"step": 1030
},
{
"epoch": 2.86,
"learning_rate": 2.910941475826972e-05,
"loss": 0.3376,
"step": 1040
},
{
"epoch": 2.88,
"learning_rate": 2.885496183206107e-05,
"loss": 0.3359,
"step": 1050
},
{
"epoch": 2.91,
"learning_rate": 2.860050890585242e-05,
"loss": 0.3321,
"step": 1060
},
{
"epoch": 2.94,
"learning_rate": 2.8346055979643765e-05,
"loss": 0.3126,
"step": 1070
},
{
"epoch": 2.97,
"learning_rate": 2.8091603053435116e-05,
"loss": 0.3352,
"step": 1080
},
{
"epoch": 2.99,
"learning_rate": 2.7837150127226465e-05,
"loss": 0.3075,
"step": 1090
},
{
"epoch": 3.0,
"eval_accuracy": 0.901206575431209,
"eval_loss": 0.24771326780319214,
"eval_runtime": 151.6412,
"eval_samples_per_second": 81.436,
"eval_steps_per_second": 1.701,
"step": 1092
},
{
"epoch": 3.02,
"learning_rate": 2.7582697201017816e-05,
"loss": 0.3368,
"step": 1100
},
{
"epoch": 3.05,
"learning_rate": 2.732824427480916e-05,
"loss": 0.2966,
"step": 1110
},
{
"epoch": 3.08,
"learning_rate": 2.707379134860051e-05,
"loss": 0.332,
"step": 1120
},
{
"epoch": 3.1,
"learning_rate": 2.681933842239186e-05,
"loss": 0.3006,
"step": 1130
},
{
"epoch": 3.13,
"learning_rate": 2.6564885496183206e-05,
"loss": 0.2954,
"step": 1140
},
{
"epoch": 3.16,
"learning_rate": 2.6310432569974558e-05,
"loss": 0.3323,
"step": 1150
},
{
"epoch": 3.19,
"learning_rate": 2.6055979643765906e-05,
"loss": 0.3164,
"step": 1160
},
{
"epoch": 3.21,
"learning_rate": 2.580152671755725e-05,
"loss": 0.3114,
"step": 1170
},
{
"epoch": 3.24,
"learning_rate": 2.5547073791348602e-05,
"loss": 0.3139,
"step": 1180
},
{
"epoch": 3.27,
"learning_rate": 2.5292620865139947e-05,
"loss": 0.322,
"step": 1190
},
{
"epoch": 3.3,
"learning_rate": 2.50381679389313e-05,
"loss": 0.2801,
"step": 1200
},
{
"epoch": 3.32,
"learning_rate": 2.4783715012722647e-05,
"loss": 0.3153,
"step": 1210
},
{
"epoch": 3.35,
"learning_rate": 2.4529262086513996e-05,
"loss": 0.2958,
"step": 1220
},
{
"epoch": 3.38,
"learning_rate": 2.4274809160305344e-05,
"loss": 0.295,
"step": 1230
},
{
"epoch": 3.41,
"learning_rate": 2.4020356234096695e-05,
"loss": 0.2996,
"step": 1240
},
{
"epoch": 3.43,
"learning_rate": 2.376590330788804e-05,
"loss": 0.3155,
"step": 1250
},
{
"epoch": 3.46,
"learning_rate": 2.351145038167939e-05,
"loss": 0.3116,
"step": 1260
},
{
"epoch": 3.49,
"learning_rate": 2.325699745547074e-05,
"loss": 0.2996,
"step": 1270
},
{
"epoch": 3.52,
"learning_rate": 2.300254452926209e-05,
"loss": 0.3183,
"step": 1280
},
{
"epoch": 3.54,
"learning_rate": 2.2748091603053437e-05,
"loss": 0.2928,
"step": 1290
},
{
"epoch": 3.57,
"learning_rate": 2.2493638676844785e-05,
"loss": 0.3158,
"step": 1300
},
{
"epoch": 3.6,
"learning_rate": 2.2239185750636133e-05,
"loss": 0.2972,
"step": 1310
},
{
"epoch": 3.63,
"learning_rate": 2.198473282442748e-05,
"loss": 0.2891,
"step": 1320
},
{
"epoch": 3.65,
"learning_rate": 2.173027989821883e-05,
"loss": 0.2935,
"step": 1330
},
{
"epoch": 3.68,
"learning_rate": 2.1475826972010178e-05,
"loss": 0.2984,
"step": 1340
},
{
"epoch": 3.71,
"learning_rate": 2.122137404580153e-05,
"loss": 0.2867,
"step": 1350
},
{
"epoch": 3.74,
"learning_rate": 2.0966921119592875e-05,
"loss": 0.2849,
"step": 1360
},
{
"epoch": 3.76,
"learning_rate": 2.0712468193384223e-05,
"loss": 0.2478,
"step": 1370
},
{
"epoch": 3.79,
"learning_rate": 2.0458015267175575e-05,
"loss": 0.2982,
"step": 1380
},
{
"epoch": 3.82,
"learning_rate": 2.0203562340966923e-05,
"loss": 0.2891,
"step": 1390
},
{
"epoch": 3.84,
"learning_rate": 1.994910941475827e-05,
"loss": 0.3038,
"step": 1400
},
{
"epoch": 3.87,
"learning_rate": 1.969465648854962e-05,
"loss": 0.3008,
"step": 1410
},
{
"epoch": 3.9,
"learning_rate": 1.9440203562340968e-05,
"loss": 0.2778,
"step": 1420
},
{
"epoch": 3.93,
"learning_rate": 1.9185750636132316e-05,
"loss": 0.2744,
"step": 1430
},
{
"epoch": 3.95,
"learning_rate": 1.8931297709923664e-05,
"loss": 0.2691,
"step": 1440
},
{
"epoch": 3.98,
"learning_rate": 1.8676844783715013e-05,
"loss": 0.2961,
"step": 1450
},
{
"epoch": 4.0,
"eval_accuracy": 0.9335168839582152,
"eval_loss": 0.17737890779972076,
"eval_runtime": 142.2521,
"eval_samples_per_second": 86.811,
"eval_steps_per_second": 1.814,
"step": 1456
},
{
"epoch": 4.01,
"learning_rate": 1.8422391857506364e-05,
"loss": 0.2954,
"step": 1460
},
{
"epoch": 4.04,
"learning_rate": 1.816793893129771e-05,
"loss": 0.2703,
"step": 1470
},
{
"epoch": 4.07,
"learning_rate": 1.7913486005089058e-05,
"loss": 0.2547,
"step": 1480
},
{
"epoch": 4.09,
"learning_rate": 1.765903307888041e-05,
"loss": 0.2583,
"step": 1490
},
{
"epoch": 4.12,
"learning_rate": 1.7404580152671757e-05,
"loss": 0.2686,
"step": 1500
},
{
"epoch": 4.15,
"learning_rate": 1.7150127226463106e-05,
"loss": 0.2774,
"step": 1510
},
{
"epoch": 4.18,
"learning_rate": 1.6895674300254454e-05,
"loss": 0.2708,
"step": 1520
},
{
"epoch": 4.2,
"learning_rate": 1.6641221374045802e-05,
"loss": 0.256,
"step": 1530
},
{
"epoch": 4.23,
"learning_rate": 1.638676844783715e-05,
"loss": 0.2766,
"step": 1540
},
{
"epoch": 4.26,
"learning_rate": 1.61323155216285e-05,
"loss": 0.263,
"step": 1550
},
{
"epoch": 4.29,
"learning_rate": 1.5877862595419847e-05,
"loss": 0.2478,
"step": 1560
},
{
"epoch": 4.31,
"learning_rate": 1.56234096692112e-05,
"loss": 0.2548,
"step": 1570
},
{
"epoch": 4.34,
"learning_rate": 1.5368956743002547e-05,
"loss": 0.2878,
"step": 1580
},
{
"epoch": 4.37,
"learning_rate": 1.5114503816793894e-05,
"loss": 0.2646,
"step": 1590
},
{
"epoch": 4.4,
"learning_rate": 1.4860050890585242e-05,
"loss": 0.2616,
"step": 1600
},
{
"epoch": 4.42,
"learning_rate": 1.4605597964376592e-05,
"loss": 0.2469,
"step": 1610
},
{
"epoch": 4.45,
"learning_rate": 1.435114503816794e-05,
"loss": 0.2539,
"step": 1620
},
{
"epoch": 4.48,
"learning_rate": 1.4096692111959288e-05,
"loss": 0.2536,
"step": 1630
},
{
"epoch": 4.5,
"learning_rate": 1.3842239185750635e-05,
"loss": 0.2763,
"step": 1640
},
{
"epoch": 4.53,
"learning_rate": 1.3587786259541985e-05,
"loss": 0.2681,
"step": 1650
},
{
"epoch": 4.56,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.2618,
"step": 1660
},
{
"epoch": 4.59,
"learning_rate": 1.3078880407124683e-05,
"loss": 0.2802,
"step": 1670
},
{
"epoch": 4.61,
"learning_rate": 1.2824427480916032e-05,
"loss": 0.2462,
"step": 1680
},
{
"epoch": 4.64,
"learning_rate": 1.2569974554707382e-05,
"loss": 0.2621,
"step": 1690
},
{
"epoch": 4.67,
"learning_rate": 1.2315521628498728e-05,
"loss": 0.2587,
"step": 1700
},
{
"epoch": 4.7,
"learning_rate": 1.2061068702290076e-05,
"loss": 0.2762,
"step": 1710
},
{
"epoch": 4.72,
"learning_rate": 1.1806615776081426e-05,
"loss": 0.2635,
"step": 1720
},
{
"epoch": 4.75,
"learning_rate": 1.1552162849872775e-05,
"loss": 0.265,
"step": 1730
},
{
"epoch": 4.78,
"learning_rate": 1.1297709923664123e-05,
"loss": 0.2712,
"step": 1740
},
{
"epoch": 4.81,
"learning_rate": 1.1043256997455471e-05,
"loss": 0.2392,
"step": 1750
},
{
"epoch": 4.83,
"learning_rate": 1.0788804071246821e-05,
"loss": 0.263,
"step": 1760
},
{
"epoch": 4.86,
"learning_rate": 1.0534351145038168e-05,
"loss": 0.2365,
"step": 1770
},
{
"epoch": 4.89,
"learning_rate": 1.0279898218829518e-05,
"loss": 0.2504,
"step": 1780
},
{
"epoch": 4.92,
"learning_rate": 1.0025445292620864e-05,
"loss": 0.2498,
"step": 1790
},
{
"epoch": 4.94,
"learning_rate": 9.770992366412214e-06,
"loss": 0.2449,
"step": 1800
},
{
"epoch": 4.97,
"learning_rate": 9.516539440203563e-06,
"loss": 0.2531,
"step": 1810
},
{
"epoch": 5.0,
"learning_rate": 9.26208651399491e-06,
"loss": 0.2523,
"step": 1820
},
{
"epoch": 5.0,
"eval_accuracy": 0.9421815531621993,
"eval_loss": 0.15593743324279785,
"eval_runtime": 137.5508,
"eval_samples_per_second": 89.778,
"eval_steps_per_second": 1.876,
"step": 1820
},
{
"epoch": 5.03,
"learning_rate": 9.00763358778626e-06,
"loss": 0.2562,
"step": 1830
},
{
"epoch": 5.05,
"learning_rate": 8.753180661577609e-06,
"loss": 0.22,
"step": 1840
},
{
"epoch": 5.08,
"learning_rate": 8.498727735368957e-06,
"loss": 0.2439,
"step": 1850
},
{
"epoch": 5.11,
"learning_rate": 8.244274809160306e-06,
"loss": 0.2483,
"step": 1860
},
{
"epoch": 5.14,
"learning_rate": 7.989821882951656e-06,
"loss": 0.2437,
"step": 1870
},
{
"epoch": 5.16,
"learning_rate": 7.735368956743002e-06,
"loss": 0.2555,
"step": 1880
},
{
"epoch": 5.19,
"learning_rate": 7.480916030534352e-06,
"loss": 0.2282,
"step": 1890
},
{
"epoch": 5.22,
"learning_rate": 7.2264631043257e-06,
"loss": 0.243,
"step": 1900
},
{
"epoch": 5.25,
"learning_rate": 6.972010178117049e-06,
"loss": 0.2138,
"step": 1910
},
{
"epoch": 5.27,
"learning_rate": 6.717557251908398e-06,
"loss": 0.2263,
"step": 1920
},
{
"epoch": 5.3,
"learning_rate": 6.463104325699745e-06,
"loss": 0.2305,
"step": 1930
},
{
"epoch": 5.33,
"learning_rate": 6.208651399491094e-06,
"loss": 0.2165,
"step": 1940
},
{
"epoch": 5.36,
"learning_rate": 5.954198473282443e-06,
"loss": 0.2327,
"step": 1950
},
{
"epoch": 5.38,
"learning_rate": 5.699745547073792e-06,
"loss": 0.253,
"step": 1960
},
{
"epoch": 5.41,
"learning_rate": 5.44529262086514e-06,
"loss": 0.2206,
"step": 1970
},
{
"epoch": 5.44,
"learning_rate": 5.190839694656488e-06,
"loss": 0.2571,
"step": 1980
},
{
"epoch": 5.47,
"learning_rate": 4.9363867684478375e-06,
"loss": 0.2242,
"step": 1990
},
{
"epoch": 5.49,
"learning_rate": 4.681933842239187e-06,
"loss": 0.2402,
"step": 2000
},
{
"epoch": 5.52,
"learning_rate": 4.427480916030535e-06,
"loss": 0.2462,
"step": 2010
},
{
"epoch": 5.55,
"learning_rate": 4.173027989821883e-06,
"loss": 0.217,
"step": 2020
},
{
"epoch": 5.58,
"learning_rate": 3.918575063613232e-06,
"loss": 0.2338,
"step": 2030
},
{
"epoch": 5.6,
"learning_rate": 3.6641221374045806e-06,
"loss": 0.2559,
"step": 2040
},
{
"epoch": 5.63,
"learning_rate": 3.409669211195929e-06,
"loss": 0.2408,
"step": 2050
},
{
"epoch": 5.66,
"learning_rate": 3.155216284987277e-06,
"loss": 0.2546,
"step": 2060
},
{
"epoch": 5.69,
"learning_rate": 2.900763358778626e-06,
"loss": 0.2327,
"step": 2070
},
{
"epoch": 5.71,
"learning_rate": 2.646310432569975e-06,
"loss": 0.2258,
"step": 2080
},
{
"epoch": 5.74,
"learning_rate": 2.3918575063613232e-06,
"loss": 0.2406,
"step": 2090
},
{
"epoch": 5.77,
"learning_rate": 2.137404580152672e-06,
"loss": 0.2117,
"step": 2100
},
{
"epoch": 5.8,
"learning_rate": 1.8829516539440202e-06,
"loss": 0.2513,
"step": 2110
},
{
"epoch": 5.82,
"learning_rate": 1.6284987277353691e-06,
"loss": 0.2285,
"step": 2120
},
{
"epoch": 5.85,
"learning_rate": 1.3740458015267176e-06,
"loss": 0.2422,
"step": 2130
},
{
"epoch": 5.88,
"learning_rate": 1.119592875318066e-06,
"loss": 0.2333,
"step": 2140
},
{
"epoch": 5.91,
"learning_rate": 8.651399491094147e-07,
"loss": 0.2206,
"step": 2150
},
{
"epoch": 5.93,
"learning_rate": 6.106870229007634e-07,
"loss": 0.2436,
"step": 2160
},
{
"epoch": 5.96,
"learning_rate": 3.56234096692112e-07,
"loss": 0.22,
"step": 2170
},
{
"epoch": 5.99,
"learning_rate": 1.0178117048346057e-07,
"loss": 0.2304,
"step": 2180
},
{
"epoch": 6.0,
"eval_accuracy": 0.9481739412098146,
"eval_loss": 0.14020109176635742,
"eval_runtime": 136.7445,
"eval_samples_per_second": 90.307,
"eval_steps_per_second": 1.887,
"step": 2184
},
{
"epoch": 6.0,
"step": 2184,
"total_flos": 2.0946151345503928e+18,
"train_loss": 0.3889721456519413,
"train_runtime": 6320.4879,
"train_samples_per_second": 66.424,
"train_steps_per_second": 0.346
}
],
"max_steps": 2184,
"num_train_epochs": 6,
"total_flos": 2.0946151345503928e+18,
"trial_name": null,
"trial_params": null
}