DouglasBraga's picture
End of training
cd538d2 verified
{
"best_metric": 0.954,
"best_model_checkpoint": "swin-tiny-patch4-window7-224-swin-tiny-patch4-window7-224-finetuned-leukemia.v2.1/checkpoint-2810",
"epoch": 9.991111111111111,
"eval_steps": 500,
"global_step": 2810,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.035555555555555556,
"grad_norm": 6.782552719116211,
"learning_rate": 1.7793594306049826e-06,
"loss": 0.6998,
"step": 10
},
{
"epoch": 0.07111111111111111,
"grad_norm": 9.350823402404785,
"learning_rate": 3.558718861209965e-06,
"loss": 0.6905,
"step": 20
},
{
"epoch": 0.10666666666666667,
"grad_norm": 10.970987319946289,
"learning_rate": 5.338078291814947e-06,
"loss": 0.6829,
"step": 30
},
{
"epoch": 0.14222222222222222,
"grad_norm": 7.290198802947998,
"learning_rate": 7.11743772241993e-06,
"loss": 0.6713,
"step": 40
},
{
"epoch": 0.17777777777777778,
"grad_norm": 10.42104721069336,
"learning_rate": 8.896797153024912e-06,
"loss": 0.6545,
"step": 50
},
{
"epoch": 0.21333333333333335,
"grad_norm": 7.574017524719238,
"learning_rate": 1.0676156583629894e-05,
"loss": 0.6612,
"step": 60
},
{
"epoch": 0.24888888888888888,
"grad_norm": 4.902874946594238,
"learning_rate": 1.2455516014234877e-05,
"loss": 0.6571,
"step": 70
},
{
"epoch": 0.28444444444444444,
"grad_norm": 6.821291446685791,
"learning_rate": 1.423487544483986e-05,
"loss": 0.6425,
"step": 80
},
{
"epoch": 0.32,
"grad_norm": 5.546478271484375,
"learning_rate": 1.601423487544484e-05,
"loss": 0.6333,
"step": 90
},
{
"epoch": 0.35555555555555557,
"grad_norm": 8.954255104064941,
"learning_rate": 1.7793594306049825e-05,
"loss": 0.6294,
"step": 100
},
{
"epoch": 0.39111111111111113,
"grad_norm": 8.712015151977539,
"learning_rate": 1.9572953736654805e-05,
"loss": 0.6262,
"step": 110
},
{
"epoch": 0.4266666666666667,
"grad_norm": 8.461681365966797,
"learning_rate": 2.135231316725979e-05,
"loss": 0.594,
"step": 120
},
{
"epoch": 0.4622222222222222,
"grad_norm": 15.287362098693848,
"learning_rate": 2.313167259786477e-05,
"loss": 0.5622,
"step": 130
},
{
"epoch": 0.49777777777777776,
"grad_norm": 13.876784324645996,
"learning_rate": 2.4911032028469753e-05,
"loss": 0.5684,
"step": 140
},
{
"epoch": 0.5333333333333333,
"grad_norm": 8.108331680297852,
"learning_rate": 2.669039145907473e-05,
"loss": 0.5268,
"step": 150
},
{
"epoch": 0.5688888888888889,
"grad_norm": 10.684402465820312,
"learning_rate": 2.846975088967972e-05,
"loss": 0.5397,
"step": 160
},
{
"epoch": 0.6044444444444445,
"grad_norm": 6.989006042480469,
"learning_rate": 3.02491103202847e-05,
"loss": 0.5337,
"step": 170
},
{
"epoch": 0.64,
"grad_norm": 25.538442611694336,
"learning_rate": 3.202846975088968e-05,
"loss": 0.5013,
"step": 180
},
{
"epoch": 0.6755555555555556,
"grad_norm": 16.017742156982422,
"learning_rate": 3.380782918149467e-05,
"loss": 0.4775,
"step": 190
},
{
"epoch": 0.7111111111111111,
"grad_norm": 8.600865364074707,
"learning_rate": 3.558718861209965e-05,
"loss": 0.5052,
"step": 200
},
{
"epoch": 0.7466666666666667,
"grad_norm": 10.005355834960938,
"learning_rate": 3.736654804270463e-05,
"loss": 0.5027,
"step": 210
},
{
"epoch": 0.7822222222222223,
"grad_norm": 9.54813003540039,
"learning_rate": 3.914590747330961e-05,
"loss": 0.4906,
"step": 220
},
{
"epoch": 0.8177777777777778,
"grad_norm": 26.83182144165039,
"learning_rate": 4.09252669039146e-05,
"loss": 0.4725,
"step": 230
},
{
"epoch": 0.8533333333333334,
"grad_norm": 15.171409606933594,
"learning_rate": 4.270462633451958e-05,
"loss": 0.4698,
"step": 240
},
{
"epoch": 0.8888888888888888,
"grad_norm": 13.108918190002441,
"learning_rate": 4.448398576512456e-05,
"loss": 0.4294,
"step": 250
},
{
"epoch": 0.9244444444444444,
"grad_norm": 9.245574951171875,
"learning_rate": 4.626334519572954e-05,
"loss": 0.4691,
"step": 260
},
{
"epoch": 0.96,
"grad_norm": 24.02051544189453,
"learning_rate": 4.8042704626334526e-05,
"loss": 0.4528,
"step": 270
},
{
"epoch": 0.9955555555555555,
"grad_norm": 15.161036491394043,
"learning_rate": 4.9822064056939506e-05,
"loss": 0.4215,
"step": 280
},
{
"epoch": 0.9991111111111111,
"eval_accuracy": 0.82925,
"eval_loss": 0.3879869878292084,
"eval_runtime": 1523.0822,
"eval_samples_per_second": 2.626,
"eval_steps_per_second": 0.082,
"step": 281
},
{
"epoch": 1.031111111111111,
"grad_norm": 14.298422813415527,
"learning_rate": 4.9822064056939506e-05,
"loss": 0.4261,
"step": 290
},
{
"epoch": 1.0666666666666667,
"grad_norm": 25.5822696685791,
"learning_rate": 4.962435745353895e-05,
"loss": 0.4725,
"step": 300
},
{
"epoch": 1.1022222222222222,
"grad_norm": 6.261577606201172,
"learning_rate": 4.9426650850138396e-05,
"loss": 0.3882,
"step": 310
},
{
"epoch": 1.1377777777777778,
"grad_norm": 13.508868217468262,
"learning_rate": 4.9228944246737844e-05,
"loss": 0.4532,
"step": 320
},
{
"epoch": 1.1733333333333333,
"grad_norm": 15.246574401855469,
"learning_rate": 4.903123764333729e-05,
"loss": 0.4165,
"step": 330
},
{
"epoch": 1.208888888888889,
"grad_norm": 8.761860847473145,
"learning_rate": 4.8833531039936733e-05,
"loss": 0.3892,
"step": 340
},
{
"epoch": 1.2444444444444445,
"grad_norm": 14.988066673278809,
"learning_rate": 4.863582443653618e-05,
"loss": 0.4098,
"step": 350
},
{
"epoch": 1.28,
"grad_norm": 25.65663719177246,
"learning_rate": 4.843811783313563e-05,
"loss": 0.4069,
"step": 360
},
{
"epoch": 1.3155555555555556,
"grad_norm": 8.681095123291016,
"learning_rate": 4.824041122973508e-05,
"loss": 0.3701,
"step": 370
},
{
"epoch": 1.3511111111111112,
"grad_norm": 11.527020454406738,
"learning_rate": 4.8042704626334526e-05,
"loss": 0.3814,
"step": 380
},
{
"epoch": 1.3866666666666667,
"grad_norm": 20.192686080932617,
"learning_rate": 4.784499802293397e-05,
"loss": 0.3811,
"step": 390
},
{
"epoch": 1.4222222222222223,
"grad_norm": 31.64283561706543,
"learning_rate": 4.7647291419533415e-05,
"loss": 0.3792,
"step": 400
},
{
"epoch": 1.4577777777777778,
"grad_norm": 26.02726173400879,
"learning_rate": 4.7449584816132864e-05,
"loss": 0.3975,
"step": 410
},
{
"epoch": 1.4933333333333334,
"grad_norm": 19.982933044433594,
"learning_rate": 4.725187821273231e-05,
"loss": 0.3901,
"step": 420
},
{
"epoch": 1.528888888888889,
"grad_norm": 36.1695442199707,
"learning_rate": 4.705417160933175e-05,
"loss": 0.4053,
"step": 430
},
{
"epoch": 1.5644444444444443,
"grad_norm": 16.495031356811523,
"learning_rate": 4.68564650059312e-05,
"loss": 0.4005,
"step": 440
},
{
"epoch": 1.6,
"grad_norm": 31.459928512573242,
"learning_rate": 4.665875840253064e-05,
"loss": 0.3576,
"step": 450
},
{
"epoch": 1.6355555555555554,
"grad_norm": 6.371111869812012,
"learning_rate": 4.64610517991301e-05,
"loss": 0.3354,
"step": 460
},
{
"epoch": 1.6711111111111112,
"grad_norm": 7.015986919403076,
"learning_rate": 4.626334519572954e-05,
"loss": 0.3222,
"step": 470
},
{
"epoch": 1.7066666666666666,
"grad_norm": 30.189485549926758,
"learning_rate": 4.606563859232899e-05,
"loss": 0.3579,
"step": 480
},
{
"epoch": 1.7422222222222223,
"grad_norm": 15.577569007873535,
"learning_rate": 4.586793198892843e-05,
"loss": 0.3805,
"step": 490
},
{
"epoch": 1.7777777777777777,
"grad_norm": 30.020050048828125,
"learning_rate": 4.5670225385527876e-05,
"loss": 0.4028,
"step": 500
},
{
"epoch": 1.8133333333333335,
"grad_norm": 24.862821578979492,
"learning_rate": 4.5472518782127324e-05,
"loss": 0.3599,
"step": 510
},
{
"epoch": 1.8488888888888888,
"grad_norm": 36.88605880737305,
"learning_rate": 4.527481217872677e-05,
"loss": 0.3329,
"step": 520
},
{
"epoch": 1.8844444444444446,
"grad_norm": 32.23126983642578,
"learning_rate": 4.5077105575326214e-05,
"loss": 0.3715,
"step": 530
},
{
"epoch": 1.92,
"grad_norm": 9.027021408081055,
"learning_rate": 4.487939897192566e-05,
"loss": 0.3678,
"step": 540
},
{
"epoch": 1.9555555555555557,
"grad_norm": 16.631864547729492,
"learning_rate": 4.468169236852511e-05,
"loss": 0.3346,
"step": 550
},
{
"epoch": 1.991111111111111,
"grad_norm": 19.838829040527344,
"learning_rate": 4.448398576512456e-05,
"loss": 0.3137,
"step": 560
},
{
"epoch": 1.9982222222222221,
"eval_accuracy": 0.87875,
"eval_loss": 0.2897728383541107,
"eval_runtime": 1451.863,
"eval_samples_per_second": 2.755,
"eval_steps_per_second": 0.086,
"step": 562
},
{
"epoch": 2.026666666666667,
"grad_norm": 20.36936378479004,
"learning_rate": 4.4286279161724006e-05,
"loss": 0.3102,
"step": 570
},
{
"epoch": 2.062222222222222,
"grad_norm": 8.112001419067383,
"learning_rate": 4.408857255832345e-05,
"loss": 0.3337,
"step": 580
},
{
"epoch": 2.097777777777778,
"grad_norm": 27.735227584838867,
"learning_rate": 4.3890865954922896e-05,
"loss": 0.3596,
"step": 590
},
{
"epoch": 2.1333333333333333,
"grad_norm": 12.126736640930176,
"learning_rate": 4.3693159351522344e-05,
"loss": 0.4431,
"step": 600
},
{
"epoch": 2.168888888888889,
"grad_norm": 36.314876556396484,
"learning_rate": 4.349545274812179e-05,
"loss": 0.3472,
"step": 610
},
{
"epoch": 2.2044444444444444,
"grad_norm": 8.522990226745605,
"learning_rate": 4.3297746144721233e-05,
"loss": 0.3179,
"step": 620
},
{
"epoch": 2.24,
"grad_norm": 13.799488067626953,
"learning_rate": 4.310003954132068e-05,
"loss": 0.3166,
"step": 630
},
{
"epoch": 2.2755555555555556,
"grad_norm": 10.06682300567627,
"learning_rate": 4.290233293792013e-05,
"loss": 0.3291,
"step": 640
},
{
"epoch": 2.311111111111111,
"grad_norm": 45.33847427368164,
"learning_rate": 4.270462633451958e-05,
"loss": 0.3048,
"step": 650
},
{
"epoch": 2.3466666666666667,
"grad_norm": 19.919029235839844,
"learning_rate": 4.250691973111902e-05,
"loss": 0.3771,
"step": 660
},
{
"epoch": 2.3822222222222225,
"grad_norm": 13.33297348022461,
"learning_rate": 4.230921312771847e-05,
"loss": 0.2913,
"step": 670
},
{
"epoch": 2.417777777777778,
"grad_norm": 10.342403411865234,
"learning_rate": 4.211150652431791e-05,
"loss": 0.329,
"step": 680
},
{
"epoch": 2.453333333333333,
"grad_norm": 14.087092399597168,
"learning_rate": 4.1913799920917364e-05,
"loss": 0.2843,
"step": 690
},
{
"epoch": 2.488888888888889,
"grad_norm": 20.755348205566406,
"learning_rate": 4.1716093317516805e-05,
"loss": 0.3078,
"step": 700
},
{
"epoch": 2.5244444444444447,
"grad_norm": 23.535104751586914,
"learning_rate": 4.151838671411625e-05,
"loss": 0.3001,
"step": 710
},
{
"epoch": 2.56,
"grad_norm": 32.4664421081543,
"learning_rate": 4.13206801107157e-05,
"loss": 0.3346,
"step": 720
},
{
"epoch": 2.5955555555555554,
"grad_norm": 12.650872230529785,
"learning_rate": 4.112297350731515e-05,
"loss": 0.2884,
"step": 730
},
{
"epoch": 2.631111111111111,
"grad_norm": 11.952192306518555,
"learning_rate": 4.09252669039146e-05,
"loss": 0.2912,
"step": 740
},
{
"epoch": 2.6666666666666665,
"grad_norm": 9.068989753723145,
"learning_rate": 4.072756030051404e-05,
"loss": 0.2664,
"step": 750
},
{
"epoch": 2.7022222222222223,
"grad_norm": 47.9985466003418,
"learning_rate": 4.052985369711349e-05,
"loss": 0.2881,
"step": 760
},
{
"epoch": 2.7377777777777776,
"grad_norm": 23.085819244384766,
"learning_rate": 4.033214709371293e-05,
"loss": 0.3261,
"step": 770
},
{
"epoch": 2.7733333333333334,
"grad_norm": 9.50033950805664,
"learning_rate": 4.013444049031238e-05,
"loss": 0.3105,
"step": 780
},
{
"epoch": 2.8088888888888888,
"grad_norm": 13.149019241333008,
"learning_rate": 3.9936733886911825e-05,
"loss": 0.3034,
"step": 790
},
{
"epoch": 2.8444444444444446,
"grad_norm": 48.091148376464844,
"learning_rate": 3.973902728351127e-05,
"loss": 0.2799,
"step": 800
},
{
"epoch": 2.88,
"grad_norm": 11.447802543640137,
"learning_rate": 3.9541320680110714e-05,
"loss": 0.2979,
"step": 810
},
{
"epoch": 2.9155555555555557,
"grad_norm": 22.164430618286133,
"learning_rate": 3.934361407671016e-05,
"loss": 0.2732,
"step": 820
},
{
"epoch": 2.951111111111111,
"grad_norm": 9.461747169494629,
"learning_rate": 3.914590747330961e-05,
"loss": 0.284,
"step": 830
},
{
"epoch": 2.986666666666667,
"grad_norm": 9.027481079101562,
"learning_rate": 3.894820086990906e-05,
"loss": 0.2631,
"step": 840
},
{
"epoch": 2.997333333333333,
"eval_accuracy": 0.907,
"eval_loss": 0.2382480353116989,
"eval_runtime": 1544.9741,
"eval_samples_per_second": 2.589,
"eval_steps_per_second": 0.081,
"step": 843
},
{
"epoch": 3.022222222222222,
"grad_norm": 21.90301513671875,
"learning_rate": 3.87504942665085e-05,
"loss": 0.2526,
"step": 850
},
{
"epoch": 3.057777777777778,
"grad_norm": 17.74726104736328,
"learning_rate": 3.855278766310795e-05,
"loss": 0.2289,
"step": 860
},
{
"epoch": 3.0933333333333333,
"grad_norm": 5.85569953918457,
"learning_rate": 3.8355081059707396e-05,
"loss": 0.3025,
"step": 870
},
{
"epoch": 3.128888888888889,
"grad_norm": 24.68912124633789,
"learning_rate": 3.8157374456306844e-05,
"loss": 0.2638,
"step": 880
},
{
"epoch": 3.1644444444444444,
"grad_norm": 10.496946334838867,
"learning_rate": 3.7959667852906285e-05,
"loss": 0.2397,
"step": 890
},
{
"epoch": 3.2,
"grad_norm": 13.301694869995117,
"learning_rate": 3.7761961249505734e-05,
"loss": 0.2785,
"step": 900
},
{
"epoch": 3.2355555555555555,
"grad_norm": 21.722679138183594,
"learning_rate": 3.756425464610518e-05,
"loss": 0.2962,
"step": 910
},
{
"epoch": 3.2711111111111113,
"grad_norm": 20.864559173583984,
"learning_rate": 3.736654804270463e-05,
"loss": 0.2644,
"step": 920
},
{
"epoch": 3.3066666666666666,
"grad_norm": 7.889869689941406,
"learning_rate": 3.716884143930408e-05,
"loss": 0.2887,
"step": 930
},
{
"epoch": 3.3422222222222224,
"grad_norm": 9.892852783203125,
"learning_rate": 3.697113483590352e-05,
"loss": 0.2638,
"step": 940
},
{
"epoch": 3.3777777777777778,
"grad_norm": 9.880372047424316,
"learning_rate": 3.677342823250297e-05,
"loss": 0.2559,
"step": 950
},
{
"epoch": 3.413333333333333,
"grad_norm": 17.303327560424805,
"learning_rate": 3.6575721629102416e-05,
"loss": 0.246,
"step": 960
},
{
"epoch": 3.448888888888889,
"grad_norm": 25.565025329589844,
"learning_rate": 3.6378015025701864e-05,
"loss": 0.2475,
"step": 970
},
{
"epoch": 3.4844444444444447,
"grad_norm": 18.166460037231445,
"learning_rate": 3.6180308422301305e-05,
"loss": 0.2515,
"step": 980
},
{
"epoch": 3.52,
"grad_norm": 12.403401374816895,
"learning_rate": 3.598260181890075e-05,
"loss": 0.2545,
"step": 990
},
{
"epoch": 3.5555555555555554,
"grad_norm": 41.32758712768555,
"learning_rate": 3.5784895215500194e-05,
"loss": 0.2446,
"step": 1000
},
{
"epoch": 3.591111111111111,
"grad_norm": 20.999855041503906,
"learning_rate": 3.558718861209965e-05,
"loss": 0.2752,
"step": 1010
},
{
"epoch": 3.626666666666667,
"grad_norm": 10.489103317260742,
"learning_rate": 3.538948200869909e-05,
"loss": 0.2594,
"step": 1020
},
{
"epoch": 3.6622222222222223,
"grad_norm": 15.303348541259766,
"learning_rate": 3.519177540529854e-05,
"loss": 0.2784,
"step": 1030
},
{
"epoch": 3.6977777777777776,
"grad_norm": 28.007869720458984,
"learning_rate": 3.499406880189798e-05,
"loss": 0.249,
"step": 1040
},
{
"epoch": 3.7333333333333334,
"grad_norm": 11.705853462219238,
"learning_rate": 3.4796362198497435e-05,
"loss": 0.2441,
"step": 1050
},
{
"epoch": 3.7688888888888887,
"grad_norm": 10.978654861450195,
"learning_rate": 3.4598655595096876e-05,
"loss": 0.2476,
"step": 1060
},
{
"epoch": 3.8044444444444445,
"grad_norm": 21.1198787689209,
"learning_rate": 3.4400948991696325e-05,
"loss": 0.2498,
"step": 1070
},
{
"epoch": 3.84,
"grad_norm": 15.153464317321777,
"learning_rate": 3.420324238829577e-05,
"loss": 0.2599,
"step": 1080
},
{
"epoch": 3.8755555555555556,
"grad_norm": 13.55528450012207,
"learning_rate": 3.4005535784895214e-05,
"loss": 0.2381,
"step": 1090
},
{
"epoch": 3.911111111111111,
"grad_norm": 8.704148292541504,
"learning_rate": 3.380782918149467e-05,
"loss": 0.2108,
"step": 1100
},
{
"epoch": 3.9466666666666668,
"grad_norm": 9.983017921447754,
"learning_rate": 3.361012257809411e-05,
"loss": 0.2399,
"step": 1110
},
{
"epoch": 3.982222222222222,
"grad_norm": 7.5024003982543945,
"learning_rate": 3.341241597469356e-05,
"loss": 0.2338,
"step": 1120
},
{
"epoch": 4.0,
"eval_accuracy": 0.8575,
"eval_loss": 0.40904077887535095,
"eval_runtime": 1463.697,
"eval_samples_per_second": 2.733,
"eval_steps_per_second": 0.085,
"step": 1125
},
{
"epoch": 4.017777777777778,
"grad_norm": 16.46148109436035,
"learning_rate": 3.3214709371293e-05,
"loss": 0.2557,
"step": 1130
},
{
"epoch": 4.053333333333334,
"grad_norm": 7.5980939865112305,
"learning_rate": 3.301700276789245e-05,
"loss": 0.2543,
"step": 1140
},
{
"epoch": 4.088888888888889,
"grad_norm": 16.72043228149414,
"learning_rate": 3.2819296164491896e-05,
"loss": 0.2292,
"step": 1150
},
{
"epoch": 4.124444444444444,
"grad_norm": 26.61065101623535,
"learning_rate": 3.2621589561091344e-05,
"loss": 0.2954,
"step": 1160
},
{
"epoch": 4.16,
"grad_norm": 10.202407836914062,
"learning_rate": 3.2423882957690785e-05,
"loss": 0.2527,
"step": 1170
},
{
"epoch": 4.195555555555556,
"grad_norm": 25.287439346313477,
"learning_rate": 3.2226176354290234e-05,
"loss": 0.2308,
"step": 1180
},
{
"epoch": 4.231111111111111,
"grad_norm": 10.251760482788086,
"learning_rate": 3.202846975088968e-05,
"loss": 0.2262,
"step": 1190
},
{
"epoch": 4.266666666666667,
"grad_norm": 11.580595016479492,
"learning_rate": 3.183076314748913e-05,
"loss": 0.2135,
"step": 1200
},
{
"epoch": 4.302222222222222,
"grad_norm": 10.563607215881348,
"learning_rate": 3.163305654408857e-05,
"loss": 0.2226,
"step": 1210
},
{
"epoch": 4.337777777777778,
"grad_norm": 15.37928295135498,
"learning_rate": 3.143534994068802e-05,
"loss": 0.2237,
"step": 1220
},
{
"epoch": 4.373333333333333,
"grad_norm": 9.385284423828125,
"learning_rate": 3.123764333728747e-05,
"loss": 0.2696,
"step": 1230
},
{
"epoch": 4.408888888888889,
"grad_norm": 5.899435520172119,
"learning_rate": 3.1039936733886916e-05,
"loss": 0.2249,
"step": 1240
},
{
"epoch": 4.444444444444445,
"grad_norm": 9.673226356506348,
"learning_rate": 3.0842230130486364e-05,
"loss": 0.2159,
"step": 1250
},
{
"epoch": 4.48,
"grad_norm": 13.770596504211426,
"learning_rate": 3.0644523527085805e-05,
"loss": 0.2372,
"step": 1260
},
{
"epoch": 4.515555555555555,
"grad_norm": 7.797916412353516,
"learning_rate": 3.044681692368525e-05,
"loss": 0.206,
"step": 1270
},
{
"epoch": 4.551111111111111,
"grad_norm": 14.872694969177246,
"learning_rate": 3.02491103202847e-05,
"loss": 0.2215,
"step": 1280
},
{
"epoch": 4.586666666666667,
"grad_norm": 16.459089279174805,
"learning_rate": 3.0051403716884146e-05,
"loss": 0.1951,
"step": 1290
},
{
"epoch": 4.622222222222222,
"grad_norm": 19.72576141357422,
"learning_rate": 2.985369711348359e-05,
"loss": 0.2248,
"step": 1300
},
{
"epoch": 4.657777777777778,
"grad_norm": 11.154007911682129,
"learning_rate": 2.9655990510083035e-05,
"loss": 0.2112,
"step": 1310
},
{
"epoch": 4.693333333333333,
"grad_norm": 12.139333724975586,
"learning_rate": 2.9458283906682484e-05,
"loss": 0.1851,
"step": 1320
},
{
"epoch": 4.728888888888889,
"grad_norm": 20.61275863647461,
"learning_rate": 2.9260577303281932e-05,
"loss": 0.2017,
"step": 1330
},
{
"epoch": 4.764444444444445,
"grad_norm": 8.542513847351074,
"learning_rate": 2.906287069988138e-05,
"loss": 0.1957,
"step": 1340
},
{
"epoch": 4.8,
"grad_norm": 19.356861114501953,
"learning_rate": 2.8865164096480825e-05,
"loss": 0.2341,
"step": 1350
},
{
"epoch": 4.835555555555556,
"grad_norm": 14.768260955810547,
"learning_rate": 2.866745749308027e-05,
"loss": 0.1954,
"step": 1360
},
{
"epoch": 4.871111111111111,
"grad_norm": 9.00818157196045,
"learning_rate": 2.846975088967972e-05,
"loss": 0.2095,
"step": 1370
},
{
"epoch": 4.906666666666666,
"grad_norm": 27.53821563720703,
"learning_rate": 2.8272044286279166e-05,
"loss": 0.2237,
"step": 1380
},
{
"epoch": 4.942222222222222,
"grad_norm": 8.379549980163574,
"learning_rate": 2.807433768287861e-05,
"loss": 0.2137,
"step": 1390
},
{
"epoch": 4.977777777777778,
"grad_norm": 14.70921516418457,
"learning_rate": 2.7876631079478055e-05,
"loss": 0.1834,
"step": 1400
},
{
"epoch": 4.999111111111111,
"eval_accuracy": 0.8985,
"eval_loss": 0.2476767748594284,
"eval_runtime": 1541.9167,
"eval_samples_per_second": 2.594,
"eval_steps_per_second": 0.081,
"step": 1406
},
{
"epoch": 5.013333333333334,
"grad_norm": 4.798450469970703,
"learning_rate": 2.76789244760775e-05,
"loss": 0.2062,
"step": 1410
},
{
"epoch": 5.0488888888888885,
"grad_norm": 23.149574279785156,
"learning_rate": 2.748121787267695e-05,
"loss": 0.2002,
"step": 1420
},
{
"epoch": 5.084444444444444,
"grad_norm": 8.797248840332031,
"learning_rate": 2.7283511269276396e-05,
"loss": 0.2004,
"step": 1430
},
{
"epoch": 5.12,
"grad_norm": 11.881458282470703,
"learning_rate": 2.708580466587584e-05,
"loss": 0.1961,
"step": 1440
},
{
"epoch": 5.155555555555556,
"grad_norm": 12.706141471862793,
"learning_rate": 2.6888098062475286e-05,
"loss": 0.1797,
"step": 1450
},
{
"epoch": 5.191111111111111,
"grad_norm": 7.330083847045898,
"learning_rate": 2.669039145907473e-05,
"loss": 0.1711,
"step": 1460
},
{
"epoch": 5.226666666666667,
"grad_norm": 18.660188674926758,
"learning_rate": 2.6492684855674182e-05,
"loss": 0.1848,
"step": 1470
},
{
"epoch": 5.262222222222222,
"grad_norm": 7.45512056350708,
"learning_rate": 2.6294978252273626e-05,
"loss": 0.1827,
"step": 1480
},
{
"epoch": 5.297777777777778,
"grad_norm": 8.177336692810059,
"learning_rate": 2.609727164887307e-05,
"loss": 0.183,
"step": 1490
},
{
"epoch": 5.333333333333333,
"grad_norm": 14.408385276794434,
"learning_rate": 2.589956504547252e-05,
"loss": 0.1949,
"step": 1500
},
{
"epoch": 5.368888888888889,
"grad_norm": 7.131970405578613,
"learning_rate": 2.5701858442071967e-05,
"loss": 0.191,
"step": 1510
},
{
"epoch": 5.404444444444445,
"grad_norm": 14.019416809082031,
"learning_rate": 2.5504151838671416e-05,
"loss": 0.2121,
"step": 1520
},
{
"epoch": 5.44,
"grad_norm": 30.826915740966797,
"learning_rate": 2.530644523527086e-05,
"loss": 0.2317,
"step": 1530
},
{
"epoch": 5.475555555555555,
"grad_norm": 13.3015718460083,
"learning_rate": 2.5108738631870305e-05,
"loss": 0.2021,
"step": 1540
},
{
"epoch": 5.511111111111111,
"grad_norm": 24.24390983581543,
"learning_rate": 2.4911032028469753e-05,
"loss": 0.2085,
"step": 1550
},
{
"epoch": 5.546666666666667,
"grad_norm": 7.3809285163879395,
"learning_rate": 2.4713325425069198e-05,
"loss": 0.168,
"step": 1560
},
{
"epoch": 5.582222222222223,
"grad_norm": 17.8999080657959,
"learning_rate": 2.4515618821668646e-05,
"loss": 0.2103,
"step": 1570
},
{
"epoch": 5.6177777777777775,
"grad_norm": 19.31194305419922,
"learning_rate": 2.431791221826809e-05,
"loss": 0.1994,
"step": 1580
},
{
"epoch": 5.653333333333333,
"grad_norm": 6.58336067199707,
"learning_rate": 2.412020561486754e-05,
"loss": 0.1677,
"step": 1590
},
{
"epoch": 5.688888888888889,
"grad_norm": 12.235469818115234,
"learning_rate": 2.3922499011466984e-05,
"loss": 0.1707,
"step": 1600
},
{
"epoch": 5.724444444444444,
"grad_norm": 21.070587158203125,
"learning_rate": 2.3724792408066432e-05,
"loss": 0.1754,
"step": 1610
},
{
"epoch": 5.76,
"grad_norm": 20.813701629638672,
"learning_rate": 2.3527085804665877e-05,
"loss": 0.1576,
"step": 1620
},
{
"epoch": 5.795555555555556,
"grad_norm": 17.073057174682617,
"learning_rate": 2.332937920126532e-05,
"loss": 0.1631,
"step": 1630
},
{
"epoch": 5.831111111111111,
"grad_norm": 10.700809478759766,
"learning_rate": 2.313167259786477e-05,
"loss": 0.1854,
"step": 1640
},
{
"epoch": 5.866666666666667,
"grad_norm": 11.791812896728516,
"learning_rate": 2.2933965994464214e-05,
"loss": 0.187,
"step": 1650
},
{
"epoch": 5.902222222222222,
"grad_norm": 13.353257179260254,
"learning_rate": 2.2736259391063662e-05,
"loss": 0.1798,
"step": 1660
},
{
"epoch": 5.937777777777778,
"grad_norm": 13.19456672668457,
"learning_rate": 2.2538552787663107e-05,
"loss": 0.1817,
"step": 1670
},
{
"epoch": 5.973333333333334,
"grad_norm": 13.983536720275879,
"learning_rate": 2.2340846184262555e-05,
"loss": 0.2065,
"step": 1680
},
{
"epoch": 5.998222222222222,
"eval_accuracy": 0.95125,
"eval_loss": 0.13313554227352142,
"eval_runtime": 1541.5332,
"eval_samples_per_second": 2.595,
"eval_steps_per_second": 0.081,
"step": 1687
},
{
"epoch": 6.0088888888888885,
"grad_norm": 10.821728706359863,
"learning_rate": 2.2143139580862003e-05,
"loss": 0.1775,
"step": 1690
},
{
"epoch": 6.044444444444444,
"grad_norm": 16.398344039916992,
"learning_rate": 2.1945432977461448e-05,
"loss": 0.179,
"step": 1700
},
{
"epoch": 6.08,
"grad_norm": 18.149566650390625,
"learning_rate": 2.1747726374060896e-05,
"loss": 0.1822,
"step": 1710
},
{
"epoch": 6.115555555555556,
"grad_norm": 10.178900718688965,
"learning_rate": 2.155001977066034e-05,
"loss": 0.1779,
"step": 1720
},
{
"epoch": 6.151111111111111,
"grad_norm": 22.30776023864746,
"learning_rate": 2.135231316725979e-05,
"loss": 0.2134,
"step": 1730
},
{
"epoch": 6.1866666666666665,
"grad_norm": 10.142642974853516,
"learning_rate": 2.1154606563859234e-05,
"loss": 0.1676,
"step": 1740
},
{
"epoch": 6.222222222222222,
"grad_norm": 11.22693920135498,
"learning_rate": 2.0956899960458682e-05,
"loss": 0.153,
"step": 1750
},
{
"epoch": 6.257777777777778,
"grad_norm": 16.93440055847168,
"learning_rate": 2.0759193357058127e-05,
"loss": 0.1707,
"step": 1760
},
{
"epoch": 6.293333333333333,
"grad_norm": 15.217277526855469,
"learning_rate": 2.0561486753657575e-05,
"loss": 0.1661,
"step": 1770
},
{
"epoch": 6.328888888888889,
"grad_norm": 10.898624420166016,
"learning_rate": 2.036378015025702e-05,
"loss": 0.1621,
"step": 1780
},
{
"epoch": 6.364444444444445,
"grad_norm": 8.637317657470703,
"learning_rate": 2.0166073546856464e-05,
"loss": 0.1895,
"step": 1790
},
{
"epoch": 6.4,
"grad_norm": 9.220898628234863,
"learning_rate": 1.9968366943455912e-05,
"loss": 0.1598,
"step": 1800
},
{
"epoch": 6.435555555555555,
"grad_norm": 10.16035270690918,
"learning_rate": 1.9770660340055357e-05,
"loss": 0.1688,
"step": 1810
},
{
"epoch": 6.471111111111111,
"grad_norm": 12.095807075500488,
"learning_rate": 1.9572953736654805e-05,
"loss": 0.201,
"step": 1820
},
{
"epoch": 6.506666666666667,
"grad_norm": 23.264787673950195,
"learning_rate": 1.937524713325425e-05,
"loss": 0.1788,
"step": 1830
},
{
"epoch": 6.542222222222223,
"grad_norm": 14.32829475402832,
"learning_rate": 1.9177540529853698e-05,
"loss": 0.1723,
"step": 1840
},
{
"epoch": 6.5777777777777775,
"grad_norm": 6.539437770843506,
"learning_rate": 1.8979833926453143e-05,
"loss": 0.1761,
"step": 1850
},
{
"epoch": 6.613333333333333,
"grad_norm": 22.11655616760254,
"learning_rate": 1.878212732305259e-05,
"loss": 0.1652,
"step": 1860
},
{
"epoch": 6.648888888888889,
"grad_norm": 17.654651641845703,
"learning_rate": 1.858442071965204e-05,
"loss": 0.1959,
"step": 1870
},
{
"epoch": 6.684444444444445,
"grad_norm": 11.6602201461792,
"learning_rate": 1.8386714116251484e-05,
"loss": 0.1927,
"step": 1880
},
{
"epoch": 6.72,
"grad_norm": 13.29917049407959,
"learning_rate": 1.8189007512850932e-05,
"loss": 0.146,
"step": 1890
},
{
"epoch": 6.7555555555555555,
"grad_norm": 20.093284606933594,
"learning_rate": 1.7991300909450377e-05,
"loss": 0.1623,
"step": 1900
},
{
"epoch": 6.791111111111111,
"grad_norm": 8.822929382324219,
"learning_rate": 1.7793594306049825e-05,
"loss": 0.1647,
"step": 1910
},
{
"epoch": 6.826666666666666,
"grad_norm": 5.047310829162598,
"learning_rate": 1.759588770264927e-05,
"loss": 0.1479,
"step": 1920
},
{
"epoch": 6.862222222222222,
"grad_norm": 12.150626182556152,
"learning_rate": 1.7398181099248718e-05,
"loss": 0.1616,
"step": 1930
},
{
"epoch": 6.897777777777778,
"grad_norm": 9.621389389038086,
"learning_rate": 1.7200474495848162e-05,
"loss": 0.1556,
"step": 1940
},
{
"epoch": 6.933333333333334,
"grad_norm": 12.77206039428711,
"learning_rate": 1.7002767892447607e-05,
"loss": 0.1941,
"step": 1950
},
{
"epoch": 6.968888888888889,
"grad_norm": 12.906224250793457,
"learning_rate": 1.6805061289047055e-05,
"loss": 0.1555,
"step": 1960
},
{
"epoch": 6.997333333333334,
"eval_accuracy": 0.94725,
"eval_loss": 0.13042479753494263,
"eval_runtime": 1543.7566,
"eval_samples_per_second": 2.591,
"eval_steps_per_second": 0.081,
"step": 1968
},
{
"epoch": 7.004444444444444,
"grad_norm": 13.00174331665039,
"learning_rate": 1.66073546856465e-05,
"loss": 0.1638,
"step": 1970
},
{
"epoch": 7.04,
"grad_norm": 18.73016929626465,
"learning_rate": 1.6409648082245948e-05,
"loss": 0.1565,
"step": 1980
},
{
"epoch": 7.075555555555556,
"grad_norm": 7.3105010986328125,
"learning_rate": 1.6211941478845393e-05,
"loss": 0.1375,
"step": 1990
},
{
"epoch": 7.111111111111111,
"grad_norm": 9.498517036437988,
"learning_rate": 1.601423487544484e-05,
"loss": 0.1353,
"step": 2000
},
{
"epoch": 7.1466666666666665,
"grad_norm": 19.775840759277344,
"learning_rate": 1.5816528272044286e-05,
"loss": 0.144,
"step": 2010
},
{
"epoch": 7.182222222222222,
"grad_norm": 14.198583602905273,
"learning_rate": 1.5618821668643734e-05,
"loss": 0.1414,
"step": 2020
},
{
"epoch": 7.217777777777778,
"grad_norm": 9.943511962890625,
"learning_rate": 1.5421115065243182e-05,
"loss": 0.143,
"step": 2030
},
{
"epoch": 7.253333333333333,
"grad_norm": 9.717743873596191,
"learning_rate": 1.5223408461842625e-05,
"loss": 0.1644,
"step": 2040
},
{
"epoch": 7.288888888888889,
"grad_norm": 8.998052597045898,
"learning_rate": 1.5025701858442073e-05,
"loss": 0.1434,
"step": 2050
},
{
"epoch": 7.3244444444444445,
"grad_norm": 7.94929313659668,
"learning_rate": 1.4827995255041518e-05,
"loss": 0.1408,
"step": 2060
},
{
"epoch": 7.36,
"grad_norm": 7.949029922485352,
"learning_rate": 1.4630288651640966e-05,
"loss": 0.1426,
"step": 2070
},
{
"epoch": 7.395555555555555,
"grad_norm": 13.912178993225098,
"learning_rate": 1.4432582048240412e-05,
"loss": 0.1423,
"step": 2080
},
{
"epoch": 7.431111111111111,
"grad_norm": 9.720952987670898,
"learning_rate": 1.423487544483986e-05,
"loss": 0.1611,
"step": 2090
},
{
"epoch": 7.466666666666667,
"grad_norm": 15.604865074157715,
"learning_rate": 1.4037168841439305e-05,
"loss": 0.1355,
"step": 2100
},
{
"epoch": 7.502222222222223,
"grad_norm": 9.24775505065918,
"learning_rate": 1.383946223803875e-05,
"loss": 0.1471,
"step": 2110
},
{
"epoch": 7.5377777777777775,
"grad_norm": 10.455300331115723,
"learning_rate": 1.3641755634638198e-05,
"loss": 0.1271,
"step": 2120
},
{
"epoch": 7.573333333333333,
"grad_norm": 15.100184440612793,
"learning_rate": 1.3444049031237643e-05,
"loss": 0.1388,
"step": 2130
},
{
"epoch": 7.608888888888889,
"grad_norm": 10.345260620117188,
"learning_rate": 1.3246342427837091e-05,
"loss": 0.1354,
"step": 2140
},
{
"epoch": 7.644444444444445,
"grad_norm": 12.270657539367676,
"learning_rate": 1.3048635824436536e-05,
"loss": 0.154,
"step": 2150
},
{
"epoch": 7.68,
"grad_norm": 9.241147994995117,
"learning_rate": 1.2850929221035984e-05,
"loss": 0.1259,
"step": 2160
},
{
"epoch": 7.7155555555555555,
"grad_norm": 16.320280075073242,
"learning_rate": 1.265322261763543e-05,
"loss": 0.1351,
"step": 2170
},
{
"epoch": 7.751111111111111,
"grad_norm": 11.753779411315918,
"learning_rate": 1.2455516014234877e-05,
"loss": 0.1476,
"step": 2180
},
{
"epoch": 7.786666666666667,
"grad_norm": 10.116710662841797,
"learning_rate": 1.2257809410834323e-05,
"loss": 0.1461,
"step": 2190
},
{
"epoch": 7.822222222222222,
"grad_norm": 11.41565990447998,
"learning_rate": 1.206010280743377e-05,
"loss": 0.1505,
"step": 2200
},
{
"epoch": 7.857777777777778,
"grad_norm": 12.816720008850098,
"learning_rate": 1.1862396204033216e-05,
"loss": 0.1357,
"step": 2210
},
{
"epoch": 7.8933333333333335,
"grad_norm": 14.3566255569458,
"learning_rate": 1.166468960063266e-05,
"loss": 0.1433,
"step": 2220
},
{
"epoch": 7.928888888888888,
"grad_norm": 13.433180809020996,
"learning_rate": 1.1466982997232107e-05,
"loss": 0.1697,
"step": 2230
},
{
"epoch": 7.964444444444444,
"grad_norm": 10.5477933883667,
"learning_rate": 1.1269276393831553e-05,
"loss": 0.1321,
"step": 2240
},
{
"epoch": 8.0,
"grad_norm": 11.933510780334473,
"learning_rate": 1.1071569790431002e-05,
"loss": 0.1521,
"step": 2250
},
{
"epoch": 8.0,
"eval_accuracy": 0.92925,
"eval_loss": 0.1837126612663269,
"eval_runtime": 1563.6163,
"eval_samples_per_second": 2.558,
"eval_steps_per_second": 0.08,
"step": 2250
},
{
"epoch": 8.035555555555556,
"grad_norm": 22.18363380432129,
"learning_rate": 1.0873863187030448e-05,
"loss": 0.1396,
"step": 2260
},
{
"epoch": 8.071111111111112,
"grad_norm": 13.1504545211792,
"learning_rate": 1.0676156583629894e-05,
"loss": 0.1265,
"step": 2270
},
{
"epoch": 8.106666666666667,
"grad_norm": 21.022546768188477,
"learning_rate": 1.0478449980229341e-05,
"loss": 0.1476,
"step": 2280
},
{
"epoch": 8.142222222222221,
"grad_norm": 15.906450271606445,
"learning_rate": 1.0280743376828787e-05,
"loss": 0.1285,
"step": 2290
},
{
"epoch": 8.177777777777777,
"grad_norm": 10.43397331237793,
"learning_rate": 1.0083036773428232e-05,
"loss": 0.1336,
"step": 2300
},
{
"epoch": 8.213333333333333,
"grad_norm": 7.347660541534424,
"learning_rate": 9.885330170027678e-06,
"loss": 0.1418,
"step": 2310
},
{
"epoch": 8.248888888888889,
"grad_norm": 9.91401481628418,
"learning_rate": 9.687623566627125e-06,
"loss": 0.1212,
"step": 2320
},
{
"epoch": 8.284444444444444,
"grad_norm": 9.150163650512695,
"learning_rate": 9.489916963226571e-06,
"loss": 0.1478,
"step": 2330
},
{
"epoch": 8.32,
"grad_norm": 11.815370559692383,
"learning_rate": 9.29221035982602e-06,
"loss": 0.1258,
"step": 2340
},
{
"epoch": 8.355555555555556,
"grad_norm": 13.915023803710938,
"learning_rate": 9.094503756425466e-06,
"loss": 0.1257,
"step": 2350
},
{
"epoch": 8.391111111111112,
"grad_norm": 8.791934967041016,
"learning_rate": 8.896797153024912e-06,
"loss": 0.1342,
"step": 2360
},
{
"epoch": 8.426666666666666,
"grad_norm": 10.984416961669922,
"learning_rate": 8.699090549624359e-06,
"loss": 0.1292,
"step": 2370
},
{
"epoch": 8.462222222222222,
"grad_norm": 14.471619606018066,
"learning_rate": 8.501383946223804e-06,
"loss": 0.1221,
"step": 2380
},
{
"epoch": 8.497777777777777,
"grad_norm": 8.994637489318848,
"learning_rate": 8.30367734282325e-06,
"loss": 0.1246,
"step": 2390
},
{
"epoch": 8.533333333333333,
"grad_norm": 16.3120059967041,
"learning_rate": 8.105970739422696e-06,
"loss": 0.1345,
"step": 2400
},
{
"epoch": 8.568888888888889,
"grad_norm": 12.578171730041504,
"learning_rate": 7.908264136022143e-06,
"loss": 0.1386,
"step": 2410
},
{
"epoch": 8.604444444444445,
"grad_norm": 10.959859848022461,
"learning_rate": 7.710557532621591e-06,
"loss": 0.1367,
"step": 2420
},
{
"epoch": 8.64,
"grad_norm": 11.834918022155762,
"learning_rate": 7.5128509292210365e-06,
"loss": 0.136,
"step": 2430
},
{
"epoch": 8.675555555555556,
"grad_norm": 14.118315696716309,
"learning_rate": 7.315144325820483e-06,
"loss": 0.1232,
"step": 2440
},
{
"epoch": 8.71111111111111,
"grad_norm": 8.814461708068848,
"learning_rate": 7.11743772241993e-06,
"loss": 0.1052,
"step": 2450
},
{
"epoch": 8.746666666666666,
"grad_norm": 8.637076377868652,
"learning_rate": 6.919731119019375e-06,
"loss": 0.1062,
"step": 2460
},
{
"epoch": 8.782222222222222,
"grad_norm": 9.377944946289062,
"learning_rate": 6.722024515618821e-06,
"loss": 0.1334,
"step": 2470
},
{
"epoch": 8.817777777777778,
"grad_norm": 14.221964836120605,
"learning_rate": 6.524317912218268e-06,
"loss": 0.1387,
"step": 2480
},
{
"epoch": 8.853333333333333,
"grad_norm": 20.073240280151367,
"learning_rate": 6.326611308817715e-06,
"loss": 0.1294,
"step": 2490
},
{
"epoch": 8.88888888888889,
"grad_norm": 9.537182807922363,
"learning_rate": 6.1289047054171615e-06,
"loss": 0.1261,
"step": 2500
},
{
"epoch": 8.924444444444445,
"grad_norm": 12.444225311279297,
"learning_rate": 5.931198102016608e-06,
"loss": 0.129,
"step": 2510
},
{
"epoch": 8.96,
"grad_norm": 10.986297607421875,
"learning_rate": 5.7334914986160535e-06,
"loss": 0.1171,
"step": 2520
},
{
"epoch": 8.995555555555555,
"grad_norm": 5.872843265533447,
"learning_rate": 5.535784895215501e-06,
"loss": 0.1512,
"step": 2530
},
{
"epoch": 8.99911111111111,
"eval_accuracy": 0.9405,
"eval_loss": 0.1708436906337738,
"eval_runtime": 1529.8652,
"eval_samples_per_second": 2.615,
"eval_steps_per_second": 0.082,
"step": 2531
},
{
"epoch": 9.03111111111111,
"grad_norm": 7.123359680175781,
"learning_rate": 5.338078291814947e-06,
"loss": 0.1029,
"step": 2540
},
{
"epoch": 9.066666666666666,
"grad_norm": 14.264687538146973,
"learning_rate": 5.140371688414394e-06,
"loss": 0.1146,
"step": 2550
},
{
"epoch": 9.102222222222222,
"grad_norm": 6.885898113250732,
"learning_rate": 4.942665085013839e-06,
"loss": 0.1054,
"step": 2560
},
{
"epoch": 9.137777777777778,
"grad_norm": 5.8031086921691895,
"learning_rate": 4.744958481613286e-06,
"loss": 0.1048,
"step": 2570
},
{
"epoch": 9.173333333333334,
"grad_norm": 6.764829158782959,
"learning_rate": 4.547251878212733e-06,
"loss": 0.1031,
"step": 2580
},
{
"epoch": 9.20888888888889,
"grad_norm": 3.4530787467956543,
"learning_rate": 4.349545274812179e-06,
"loss": 0.1027,
"step": 2590
},
{
"epoch": 9.244444444444444,
"grad_norm": 19.80527114868164,
"learning_rate": 4.151838671411625e-06,
"loss": 0.1152,
"step": 2600
},
{
"epoch": 9.28,
"grad_norm": 12.928886413574219,
"learning_rate": 3.954132068011071e-06,
"loss": 0.1,
"step": 2610
},
{
"epoch": 9.315555555555555,
"grad_norm": 14.547968864440918,
"learning_rate": 3.7564254646105183e-06,
"loss": 0.1253,
"step": 2620
},
{
"epoch": 9.351111111111111,
"grad_norm": 8.808683395385742,
"learning_rate": 3.558718861209965e-06,
"loss": 0.116,
"step": 2630
},
{
"epoch": 9.386666666666667,
"grad_norm": 18.376087188720703,
"learning_rate": 3.3610122578094107e-06,
"loss": 0.1247,
"step": 2640
},
{
"epoch": 9.422222222222222,
"grad_norm": 9.673834800720215,
"learning_rate": 3.1633056544088575e-06,
"loss": 0.1322,
"step": 2650
},
{
"epoch": 9.457777777777778,
"grad_norm": 10.23854923248291,
"learning_rate": 2.965599051008304e-06,
"loss": 0.1233,
"step": 2660
},
{
"epoch": 9.493333333333334,
"grad_norm": 6.59231424331665,
"learning_rate": 2.7678924476077504e-06,
"loss": 0.1172,
"step": 2670
},
{
"epoch": 9.528888888888888,
"grad_norm": 4.731305122375488,
"learning_rate": 2.570185844207197e-06,
"loss": 0.0819,
"step": 2680
},
{
"epoch": 9.564444444444444,
"grad_norm": 8.215780258178711,
"learning_rate": 2.372479240806643e-06,
"loss": 0.128,
"step": 2690
},
{
"epoch": 9.6,
"grad_norm": 14.254526138305664,
"learning_rate": 2.1747726374060897e-06,
"loss": 0.1286,
"step": 2700
},
{
"epoch": 9.635555555555555,
"grad_norm": 13.742310523986816,
"learning_rate": 1.9770660340055357e-06,
"loss": 0.1205,
"step": 2710
},
{
"epoch": 9.671111111111111,
"grad_norm": 10.408873558044434,
"learning_rate": 1.7793594306049826e-06,
"loss": 0.1158,
"step": 2720
},
{
"epoch": 9.706666666666667,
"grad_norm": 5.809567451477051,
"learning_rate": 1.5816528272044288e-06,
"loss": 0.1195,
"step": 2730
},
{
"epoch": 9.742222222222223,
"grad_norm": 9.508487701416016,
"learning_rate": 1.3839462238038752e-06,
"loss": 0.117,
"step": 2740
},
{
"epoch": 9.777777777777779,
"grad_norm": 9.351639747619629,
"learning_rate": 1.1862396204033214e-06,
"loss": 0.1286,
"step": 2750
},
{
"epoch": 9.813333333333333,
"grad_norm": 11.513580322265625,
"learning_rate": 9.885330170027678e-07,
"loss": 0.0973,
"step": 2760
},
{
"epoch": 9.848888888888888,
"grad_norm": 6.790437698364258,
"learning_rate": 7.908264136022144e-07,
"loss": 0.1026,
"step": 2770
},
{
"epoch": 9.884444444444444,
"grad_norm": 12.467495918273926,
"learning_rate": 5.931198102016607e-07,
"loss": 0.108,
"step": 2780
},
{
"epoch": 9.92,
"grad_norm": 9.36400032043457,
"learning_rate": 3.954132068011072e-07,
"loss": 0.1155,
"step": 2790
},
{
"epoch": 9.955555555555556,
"grad_norm": 6.071395397186279,
"learning_rate": 1.977066034005536e-07,
"loss": 0.1256,
"step": 2800
},
{
"epoch": 9.991111111111111,
"grad_norm": 8.255842208862305,
"learning_rate": 0.0,
"loss": 0.119,
"step": 2810
},
{
"epoch": 9.991111111111111,
"eval_accuracy": 0.954,
"eval_loss": 0.13787274062633514,
"eval_runtime": 1553.5401,
"eval_samples_per_second": 2.575,
"eval_steps_per_second": 0.08,
"step": 2810
},
{
"epoch": 9.991111111111111,
"step": 2810,
"total_flos": 8.940202118432686e+18,
"train_loss": 0.24847593615063568,
"train_runtime": 161511.588,
"train_samples_per_second": 2.229,
"train_steps_per_second": 0.017
}
],
"logging_steps": 10,
"max_steps": 2810,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 8.940202118432686e+18,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}