100rab25's picture
Training in progress, epoch 0
57d9596
raw
history blame
52.7 kB
{
"best_metric": 0.9811772758384668,
"best_model_checkpoint": "swin-tiny-patch4-window7-224-spa_saloon_classification/checkpoint-1849",
"epoch": 9.975669099756692,
"eval_steps": 500,
"global_step": 2050,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 1.2195121951219514e-06,
"loss": 1.8606,
"step": 5
},
{
"epoch": 0.05,
"learning_rate": 2.4390243902439027e-06,
"loss": 1.8294,
"step": 10
},
{
"epoch": 0.07,
"learning_rate": 3.6585365853658537e-06,
"loss": 1.8047,
"step": 15
},
{
"epoch": 0.1,
"learning_rate": 4.8780487804878055e-06,
"loss": 1.7415,
"step": 20
},
{
"epoch": 0.12,
"learning_rate": 6.0975609756097564e-06,
"loss": 1.6899,
"step": 25
},
{
"epoch": 0.15,
"learning_rate": 7.317073170731707e-06,
"loss": 1.6166,
"step": 30
},
{
"epoch": 0.17,
"learning_rate": 8.53658536585366e-06,
"loss": 1.518,
"step": 35
},
{
"epoch": 0.19,
"learning_rate": 9.756097560975611e-06,
"loss": 1.4472,
"step": 40
},
{
"epoch": 0.22,
"learning_rate": 1.0975609756097562e-05,
"loss": 1.2949,
"step": 45
},
{
"epoch": 0.24,
"learning_rate": 1.2195121951219513e-05,
"loss": 1.1811,
"step": 50
},
{
"epoch": 0.27,
"learning_rate": 1.3414634146341466e-05,
"loss": 1.0548,
"step": 55
},
{
"epoch": 0.29,
"learning_rate": 1.4634146341463415e-05,
"loss": 0.9112,
"step": 60
},
{
"epoch": 0.32,
"learning_rate": 1.5853658536585366e-05,
"loss": 0.8244,
"step": 65
},
{
"epoch": 0.34,
"learning_rate": 1.707317073170732e-05,
"loss": 0.7256,
"step": 70
},
{
"epoch": 0.36,
"learning_rate": 1.8292682926829268e-05,
"loss": 0.6848,
"step": 75
},
{
"epoch": 0.39,
"learning_rate": 1.9512195121951222e-05,
"loss": 0.6532,
"step": 80
},
{
"epoch": 0.41,
"learning_rate": 2.073170731707317e-05,
"loss": 0.5777,
"step": 85
},
{
"epoch": 0.44,
"learning_rate": 2.1951219512195124e-05,
"loss": 0.6014,
"step": 90
},
{
"epoch": 0.46,
"learning_rate": 2.3170731707317075e-05,
"loss": 0.5424,
"step": 95
},
{
"epoch": 0.49,
"learning_rate": 2.4390243902439026e-05,
"loss": 0.4876,
"step": 100
},
{
"epoch": 0.51,
"learning_rate": 2.5609756097560977e-05,
"loss": 0.4372,
"step": 105
},
{
"epoch": 0.54,
"learning_rate": 2.682926829268293e-05,
"loss": 0.4551,
"step": 110
},
{
"epoch": 0.56,
"learning_rate": 2.8048780487804882e-05,
"loss": 0.4751,
"step": 115
},
{
"epoch": 0.58,
"learning_rate": 2.926829268292683e-05,
"loss": 0.4652,
"step": 120
},
{
"epoch": 0.61,
"learning_rate": 3.048780487804878e-05,
"loss": 0.4264,
"step": 125
},
{
"epoch": 0.63,
"learning_rate": 3.170731707317073e-05,
"loss": 0.399,
"step": 130
},
{
"epoch": 0.66,
"learning_rate": 3.292682926829269e-05,
"loss": 0.4399,
"step": 135
},
{
"epoch": 0.68,
"learning_rate": 3.414634146341464e-05,
"loss": 0.4074,
"step": 140
},
{
"epoch": 0.71,
"learning_rate": 3.5365853658536584e-05,
"loss": 0.397,
"step": 145
},
{
"epoch": 0.73,
"learning_rate": 3.6585365853658535e-05,
"loss": 0.3578,
"step": 150
},
{
"epoch": 0.75,
"learning_rate": 3.780487804878049e-05,
"loss": 0.3771,
"step": 155
},
{
"epoch": 0.78,
"learning_rate": 3.9024390243902444e-05,
"loss": 0.366,
"step": 160
},
{
"epoch": 0.8,
"learning_rate": 4.0243902439024395e-05,
"loss": 0.3792,
"step": 165
},
{
"epoch": 0.83,
"learning_rate": 4.146341463414634e-05,
"loss": 0.3706,
"step": 170
},
{
"epoch": 0.85,
"learning_rate": 4.26829268292683e-05,
"loss": 0.352,
"step": 175
},
{
"epoch": 0.88,
"learning_rate": 4.390243902439025e-05,
"loss": 0.3481,
"step": 180
},
{
"epoch": 0.9,
"learning_rate": 4.51219512195122e-05,
"loss": 0.2698,
"step": 185
},
{
"epoch": 0.92,
"learning_rate": 4.634146341463415e-05,
"loss": 0.3573,
"step": 190
},
{
"epoch": 0.95,
"learning_rate": 4.75609756097561e-05,
"loss": 0.3479,
"step": 195
},
{
"epoch": 0.97,
"learning_rate": 4.878048780487805e-05,
"loss": 0.3917,
"step": 200
},
{
"epoch": 1.0,
"learning_rate": 5e-05,
"loss": 0.337,
"step": 205
},
{
"epoch": 1.0,
"eval_accuracy": 0.9175222450376455,
"eval_loss": 0.21079373359680176,
"eval_runtime": 21.0784,
"eval_samples_per_second": 138.625,
"eval_steps_per_second": 4.365,
"step": 205
},
{
"epoch": 1.02,
"learning_rate": 4.986449864498645e-05,
"loss": 0.3492,
"step": 210
},
{
"epoch": 1.05,
"learning_rate": 4.97289972899729e-05,
"loss": 0.3251,
"step": 215
},
{
"epoch": 1.07,
"learning_rate": 4.959349593495935e-05,
"loss": 0.2809,
"step": 220
},
{
"epoch": 1.09,
"learning_rate": 4.9457994579945803e-05,
"loss": 0.3412,
"step": 225
},
{
"epoch": 1.12,
"learning_rate": 4.932249322493225e-05,
"loss": 0.3049,
"step": 230
},
{
"epoch": 1.14,
"learning_rate": 4.9186991869918704e-05,
"loss": 0.3123,
"step": 235
},
{
"epoch": 1.17,
"learning_rate": 4.905149051490515e-05,
"loss": 0.2915,
"step": 240
},
{
"epoch": 1.19,
"learning_rate": 4.89159891598916e-05,
"loss": 0.2875,
"step": 245
},
{
"epoch": 1.22,
"learning_rate": 4.878048780487805e-05,
"loss": 0.2721,
"step": 250
},
{
"epoch": 1.24,
"learning_rate": 4.86449864498645e-05,
"loss": 0.2551,
"step": 255
},
{
"epoch": 1.27,
"learning_rate": 4.8509485094850945e-05,
"loss": 0.2956,
"step": 260
},
{
"epoch": 1.29,
"learning_rate": 4.8373983739837406e-05,
"loss": 0.2643,
"step": 265
},
{
"epoch": 1.31,
"learning_rate": 4.823848238482385e-05,
"loss": 0.3148,
"step": 270
},
{
"epoch": 1.34,
"learning_rate": 4.81029810298103e-05,
"loss": 0.2628,
"step": 275
},
{
"epoch": 1.36,
"learning_rate": 4.796747967479675e-05,
"loss": 0.2258,
"step": 280
},
{
"epoch": 1.39,
"learning_rate": 4.78319783197832e-05,
"loss": 0.2483,
"step": 285
},
{
"epoch": 1.41,
"learning_rate": 4.769647696476965e-05,
"loss": 0.2805,
"step": 290
},
{
"epoch": 1.44,
"learning_rate": 4.75609756097561e-05,
"loss": 0.2861,
"step": 295
},
{
"epoch": 1.46,
"learning_rate": 4.7425474254742554e-05,
"loss": 0.2972,
"step": 300
},
{
"epoch": 1.48,
"learning_rate": 4.7289972899729e-05,
"loss": 0.2432,
"step": 305
},
{
"epoch": 1.51,
"learning_rate": 4.715447154471545e-05,
"loss": 0.2517,
"step": 310
},
{
"epoch": 1.53,
"learning_rate": 4.70189701897019e-05,
"loss": 0.2707,
"step": 315
},
{
"epoch": 1.56,
"learning_rate": 4.688346883468835e-05,
"loss": 0.2512,
"step": 320
},
{
"epoch": 1.58,
"learning_rate": 4.6747967479674795e-05,
"loss": 0.2036,
"step": 325
},
{
"epoch": 1.61,
"learning_rate": 4.661246612466125e-05,
"loss": 0.2346,
"step": 330
},
{
"epoch": 1.63,
"learning_rate": 4.6476964769647696e-05,
"loss": 0.2921,
"step": 335
},
{
"epoch": 1.65,
"learning_rate": 4.634146341463415e-05,
"loss": 0.2789,
"step": 340
},
{
"epoch": 1.68,
"learning_rate": 4.62059620596206e-05,
"loss": 0.2456,
"step": 345
},
{
"epoch": 1.7,
"learning_rate": 4.607046070460705e-05,
"loss": 0.2536,
"step": 350
},
{
"epoch": 1.73,
"learning_rate": 4.59349593495935e-05,
"loss": 0.282,
"step": 355
},
{
"epoch": 1.75,
"learning_rate": 4.579945799457995e-05,
"loss": 0.2525,
"step": 360
},
{
"epoch": 1.78,
"learning_rate": 4.56639566395664e-05,
"loss": 0.2284,
"step": 365
},
{
"epoch": 1.8,
"learning_rate": 4.5528455284552844e-05,
"loss": 0.2389,
"step": 370
},
{
"epoch": 1.82,
"learning_rate": 4.53929539295393e-05,
"loss": 0.2425,
"step": 375
},
{
"epoch": 1.85,
"learning_rate": 4.525745257452575e-05,
"loss": 0.2051,
"step": 380
},
{
"epoch": 1.87,
"learning_rate": 4.51219512195122e-05,
"loss": 0.278,
"step": 385
},
{
"epoch": 1.9,
"learning_rate": 4.4986449864498645e-05,
"loss": 0.2004,
"step": 390
},
{
"epoch": 1.92,
"learning_rate": 4.48509485094851e-05,
"loss": 0.2467,
"step": 395
},
{
"epoch": 1.95,
"learning_rate": 4.4715447154471546e-05,
"loss": 0.2411,
"step": 400
},
{
"epoch": 1.97,
"learning_rate": 4.457994579945799e-05,
"loss": 0.218,
"step": 405
},
{
"epoch": 2.0,
"learning_rate": 4.4444444444444447e-05,
"loss": 0.196,
"step": 410
},
{
"epoch": 2.0,
"eval_accuracy": 0.9620123203285421,
"eval_loss": 0.11370620876550674,
"eval_runtime": 21.3607,
"eval_samples_per_second": 136.793,
"eval_steps_per_second": 4.307,
"step": 411
},
{
"epoch": 2.02,
"learning_rate": 4.43089430894309e-05,
"loss": 0.1786,
"step": 415
},
{
"epoch": 2.04,
"learning_rate": 4.417344173441735e-05,
"loss": 0.2308,
"step": 420
},
{
"epoch": 2.07,
"learning_rate": 4.4037940379403794e-05,
"loss": 0.2158,
"step": 425
},
{
"epoch": 2.09,
"learning_rate": 4.390243902439025e-05,
"loss": 0.1875,
"step": 430
},
{
"epoch": 2.12,
"learning_rate": 4.3766937669376695e-05,
"loss": 0.1998,
"step": 435
},
{
"epoch": 2.14,
"learning_rate": 4.363143631436314e-05,
"loss": 0.2001,
"step": 440
},
{
"epoch": 2.17,
"learning_rate": 4.3495934959349595e-05,
"loss": 0.2349,
"step": 445
},
{
"epoch": 2.19,
"learning_rate": 4.336043360433605e-05,
"loss": 0.2191,
"step": 450
},
{
"epoch": 2.21,
"learning_rate": 4.3224932249322496e-05,
"loss": 0.2052,
"step": 455
},
{
"epoch": 2.24,
"learning_rate": 4.308943089430895e-05,
"loss": 0.1963,
"step": 460
},
{
"epoch": 2.26,
"learning_rate": 4.2953929539295396e-05,
"loss": 0.2318,
"step": 465
},
{
"epoch": 2.29,
"learning_rate": 4.281842818428184e-05,
"loss": 0.2105,
"step": 470
},
{
"epoch": 2.31,
"learning_rate": 4.26829268292683e-05,
"loss": 0.2185,
"step": 475
},
{
"epoch": 2.34,
"learning_rate": 4.2547425474254744e-05,
"loss": 0.2426,
"step": 480
},
{
"epoch": 2.36,
"learning_rate": 4.241192411924119e-05,
"loss": 0.2248,
"step": 485
},
{
"epoch": 2.38,
"learning_rate": 4.2276422764227644e-05,
"loss": 0.232,
"step": 490
},
{
"epoch": 2.41,
"learning_rate": 4.21409214092141e-05,
"loss": 0.2263,
"step": 495
},
{
"epoch": 2.43,
"learning_rate": 4.2005420054200545e-05,
"loss": 0.1929,
"step": 500
},
{
"epoch": 2.46,
"learning_rate": 4.186991869918699e-05,
"loss": 0.2151,
"step": 505
},
{
"epoch": 2.48,
"learning_rate": 4.1734417344173445e-05,
"loss": 0.2043,
"step": 510
},
{
"epoch": 2.51,
"learning_rate": 4.159891598915989e-05,
"loss": 0.1585,
"step": 515
},
{
"epoch": 2.53,
"learning_rate": 4.146341463414634e-05,
"loss": 0.2013,
"step": 520
},
{
"epoch": 2.55,
"learning_rate": 4.132791327913279e-05,
"loss": 0.2072,
"step": 525
},
{
"epoch": 2.58,
"learning_rate": 4.1192411924119246e-05,
"loss": 0.1806,
"step": 530
},
{
"epoch": 2.6,
"learning_rate": 4.105691056910569e-05,
"loss": 0.1539,
"step": 535
},
{
"epoch": 2.63,
"learning_rate": 4.092140921409214e-05,
"loss": 0.1582,
"step": 540
},
{
"epoch": 2.65,
"learning_rate": 4.0785907859078594e-05,
"loss": 0.1856,
"step": 545
},
{
"epoch": 2.68,
"learning_rate": 4.065040650406504e-05,
"loss": 0.1966,
"step": 550
},
{
"epoch": 2.7,
"learning_rate": 4.051490514905149e-05,
"loss": 0.205,
"step": 555
},
{
"epoch": 2.73,
"learning_rate": 4.037940379403794e-05,
"loss": 0.2359,
"step": 560
},
{
"epoch": 2.75,
"learning_rate": 4.0243902439024395e-05,
"loss": 0.1834,
"step": 565
},
{
"epoch": 2.77,
"learning_rate": 4.010840108401084e-05,
"loss": 0.2631,
"step": 570
},
{
"epoch": 2.8,
"learning_rate": 3.9972899728997295e-05,
"loss": 0.2,
"step": 575
},
{
"epoch": 2.82,
"learning_rate": 3.983739837398374e-05,
"loss": 0.1802,
"step": 580
},
{
"epoch": 2.85,
"learning_rate": 3.970189701897019e-05,
"loss": 0.2305,
"step": 585
},
{
"epoch": 2.87,
"learning_rate": 3.956639566395664e-05,
"loss": 0.1662,
"step": 590
},
{
"epoch": 2.9,
"learning_rate": 3.943089430894309e-05,
"loss": 0.166,
"step": 595
},
{
"epoch": 2.92,
"learning_rate": 3.9295392953929537e-05,
"loss": 0.167,
"step": 600
},
{
"epoch": 2.94,
"learning_rate": 3.915989159891599e-05,
"loss": 0.2017,
"step": 605
},
{
"epoch": 2.97,
"learning_rate": 3.9024390243902444e-05,
"loss": 0.1826,
"step": 610
},
{
"epoch": 2.99,
"learning_rate": 3.888888888888889e-05,
"loss": 0.1502,
"step": 615
},
{
"epoch": 3.0,
"eval_accuracy": 0.9668035592060232,
"eval_loss": 0.1030467301607132,
"eval_runtime": 22.6678,
"eval_samples_per_second": 128.905,
"eval_steps_per_second": 4.059,
"step": 616
},
{
"epoch": 3.02,
"learning_rate": 3.875338753387534e-05,
"loss": 0.1764,
"step": 620
},
{
"epoch": 3.04,
"learning_rate": 3.861788617886179e-05,
"loss": 0.1602,
"step": 625
},
{
"epoch": 3.07,
"learning_rate": 3.848238482384824e-05,
"loss": 0.139,
"step": 630
},
{
"epoch": 3.09,
"learning_rate": 3.8346883468834685e-05,
"loss": 0.1811,
"step": 635
},
{
"epoch": 3.11,
"learning_rate": 3.8211382113821145e-05,
"loss": 0.1824,
"step": 640
},
{
"epoch": 3.14,
"learning_rate": 3.807588075880759e-05,
"loss": 0.1987,
"step": 645
},
{
"epoch": 3.16,
"learning_rate": 3.794037940379404e-05,
"loss": 0.1861,
"step": 650
},
{
"epoch": 3.19,
"learning_rate": 3.780487804878049e-05,
"loss": 0.2177,
"step": 655
},
{
"epoch": 3.21,
"learning_rate": 3.766937669376694e-05,
"loss": 0.1591,
"step": 660
},
{
"epoch": 3.24,
"learning_rate": 3.753387533875339e-05,
"loss": 0.2049,
"step": 665
},
{
"epoch": 3.26,
"learning_rate": 3.739837398373984e-05,
"loss": 0.1844,
"step": 670
},
{
"epoch": 3.28,
"learning_rate": 3.726287262872629e-05,
"loss": 0.1668,
"step": 675
},
{
"epoch": 3.31,
"learning_rate": 3.712737127371274e-05,
"loss": 0.1768,
"step": 680
},
{
"epoch": 3.33,
"learning_rate": 3.699186991869919e-05,
"loss": 0.1619,
"step": 685
},
{
"epoch": 3.36,
"learning_rate": 3.685636856368564e-05,
"loss": 0.2358,
"step": 690
},
{
"epoch": 3.38,
"learning_rate": 3.672086720867209e-05,
"loss": 0.1658,
"step": 695
},
{
"epoch": 3.41,
"learning_rate": 3.6585365853658535e-05,
"loss": 0.163,
"step": 700
},
{
"epoch": 3.43,
"learning_rate": 3.644986449864499e-05,
"loss": 0.1658,
"step": 705
},
{
"epoch": 3.45,
"learning_rate": 3.6314363143631436e-05,
"loss": 0.2312,
"step": 710
},
{
"epoch": 3.48,
"learning_rate": 3.617886178861789e-05,
"loss": 0.2043,
"step": 715
},
{
"epoch": 3.5,
"learning_rate": 3.6043360433604336e-05,
"loss": 0.1625,
"step": 720
},
{
"epoch": 3.53,
"learning_rate": 3.590785907859079e-05,
"loss": 0.1954,
"step": 725
},
{
"epoch": 3.55,
"learning_rate": 3.577235772357724e-05,
"loss": 0.1613,
"step": 730
},
{
"epoch": 3.58,
"learning_rate": 3.5636856368563684e-05,
"loss": 0.1924,
"step": 735
},
{
"epoch": 3.6,
"learning_rate": 3.550135501355014e-05,
"loss": 0.177,
"step": 740
},
{
"epoch": 3.63,
"learning_rate": 3.5365853658536584e-05,
"loss": 0.1707,
"step": 745
},
{
"epoch": 3.65,
"learning_rate": 3.523035230352303e-05,
"loss": 0.1454,
"step": 750
},
{
"epoch": 3.67,
"learning_rate": 3.509485094850949e-05,
"loss": 0.1731,
"step": 755
},
{
"epoch": 3.7,
"learning_rate": 3.495934959349594e-05,
"loss": 0.1361,
"step": 760
},
{
"epoch": 3.72,
"learning_rate": 3.4823848238482385e-05,
"loss": 0.1592,
"step": 765
},
{
"epoch": 3.75,
"learning_rate": 3.468834688346884e-05,
"loss": 0.1691,
"step": 770
},
{
"epoch": 3.77,
"learning_rate": 3.4552845528455286e-05,
"loss": 0.1321,
"step": 775
},
{
"epoch": 3.8,
"learning_rate": 3.441734417344173e-05,
"loss": 0.133,
"step": 780
},
{
"epoch": 3.82,
"learning_rate": 3.4281842818428186e-05,
"loss": 0.1367,
"step": 785
},
{
"epoch": 3.84,
"learning_rate": 3.414634146341464e-05,
"loss": 0.1517,
"step": 790
},
{
"epoch": 3.87,
"learning_rate": 3.401084010840109e-05,
"loss": 0.1478,
"step": 795
},
{
"epoch": 3.89,
"learning_rate": 3.3875338753387534e-05,
"loss": 0.1408,
"step": 800
},
{
"epoch": 3.92,
"learning_rate": 3.373983739837399e-05,
"loss": 0.2103,
"step": 805
},
{
"epoch": 3.94,
"learning_rate": 3.3604336043360434e-05,
"loss": 0.2157,
"step": 810
},
{
"epoch": 3.97,
"learning_rate": 3.346883468834688e-05,
"loss": 0.1526,
"step": 815
},
{
"epoch": 3.99,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.1476,
"step": 820
},
{
"epoch": 4.0,
"eval_accuracy": 0.9736481861738535,
"eval_loss": 0.08152312785387039,
"eval_runtime": 21.5748,
"eval_samples_per_second": 135.436,
"eval_steps_per_second": 4.264,
"step": 822
},
{
"epoch": 4.01,
"learning_rate": 3.319783197831978e-05,
"loss": 0.1679,
"step": 825
},
{
"epoch": 4.04,
"learning_rate": 3.3062330623306235e-05,
"loss": 0.1668,
"step": 830
},
{
"epoch": 4.06,
"learning_rate": 3.292682926829269e-05,
"loss": 0.1528,
"step": 835
},
{
"epoch": 4.09,
"learning_rate": 3.2791327913279136e-05,
"loss": 0.1984,
"step": 840
},
{
"epoch": 4.11,
"learning_rate": 3.265582655826558e-05,
"loss": 0.1575,
"step": 845
},
{
"epoch": 4.14,
"learning_rate": 3.2520325203252037e-05,
"loss": 0.156,
"step": 850
},
{
"epoch": 4.16,
"learning_rate": 3.2384823848238483e-05,
"loss": 0.1227,
"step": 855
},
{
"epoch": 4.18,
"learning_rate": 3.224932249322493e-05,
"loss": 0.1759,
"step": 860
},
{
"epoch": 4.21,
"learning_rate": 3.2113821138211384e-05,
"loss": 0.1261,
"step": 865
},
{
"epoch": 4.23,
"learning_rate": 3.197831978319784e-05,
"loss": 0.1566,
"step": 870
},
{
"epoch": 4.26,
"learning_rate": 3.1842818428184285e-05,
"loss": 0.1424,
"step": 875
},
{
"epoch": 4.28,
"learning_rate": 3.170731707317073e-05,
"loss": 0.1353,
"step": 880
},
{
"epoch": 4.31,
"learning_rate": 3.1571815718157185e-05,
"loss": 0.1595,
"step": 885
},
{
"epoch": 4.33,
"learning_rate": 3.143631436314363e-05,
"loss": 0.1823,
"step": 890
},
{
"epoch": 4.36,
"learning_rate": 3.130081300813008e-05,
"loss": 0.1428,
"step": 895
},
{
"epoch": 4.38,
"learning_rate": 3.116531165311653e-05,
"loss": 0.1566,
"step": 900
},
{
"epoch": 4.4,
"learning_rate": 3.1029810298102986e-05,
"loss": 0.099,
"step": 905
},
{
"epoch": 4.43,
"learning_rate": 3.089430894308943e-05,
"loss": 0.1311,
"step": 910
},
{
"epoch": 4.45,
"learning_rate": 3.075880758807588e-05,
"loss": 0.1317,
"step": 915
},
{
"epoch": 4.48,
"learning_rate": 3.0623306233062334e-05,
"loss": 0.1647,
"step": 920
},
{
"epoch": 4.5,
"learning_rate": 3.048780487804878e-05,
"loss": 0.1646,
"step": 925
},
{
"epoch": 4.53,
"learning_rate": 3.035230352303523e-05,
"loss": 0.1429,
"step": 930
},
{
"epoch": 4.55,
"learning_rate": 3.021680216802168e-05,
"loss": 0.1511,
"step": 935
},
{
"epoch": 4.57,
"learning_rate": 3.0081300813008135e-05,
"loss": 0.1691,
"step": 940
},
{
"epoch": 4.6,
"learning_rate": 2.9945799457994585e-05,
"loss": 0.1174,
"step": 945
},
{
"epoch": 4.62,
"learning_rate": 2.9810298102981032e-05,
"loss": 0.1743,
"step": 950
},
{
"epoch": 4.65,
"learning_rate": 2.9674796747967482e-05,
"loss": 0.1757,
"step": 955
},
{
"epoch": 4.67,
"learning_rate": 2.9539295392953932e-05,
"loss": 0.1164,
"step": 960
},
{
"epoch": 4.7,
"learning_rate": 2.940379403794038e-05,
"loss": 0.1469,
"step": 965
},
{
"epoch": 4.72,
"learning_rate": 2.926829268292683e-05,
"loss": 0.1539,
"step": 970
},
{
"epoch": 4.74,
"learning_rate": 2.9132791327913276e-05,
"loss": 0.1577,
"step": 975
},
{
"epoch": 4.77,
"learning_rate": 2.8997289972899733e-05,
"loss": 0.141,
"step": 980
},
{
"epoch": 4.79,
"learning_rate": 2.886178861788618e-05,
"loss": 0.1382,
"step": 985
},
{
"epoch": 4.82,
"learning_rate": 2.872628726287263e-05,
"loss": 0.1445,
"step": 990
},
{
"epoch": 4.84,
"learning_rate": 2.859078590785908e-05,
"loss": 0.179,
"step": 995
},
{
"epoch": 4.87,
"learning_rate": 2.8455284552845528e-05,
"loss": 0.1244,
"step": 1000
},
{
"epoch": 4.89,
"learning_rate": 2.8319783197831978e-05,
"loss": 0.172,
"step": 1005
},
{
"epoch": 4.91,
"learning_rate": 2.8184281842818428e-05,
"loss": 0.1341,
"step": 1010
},
{
"epoch": 4.94,
"learning_rate": 2.8048780487804882e-05,
"loss": 0.1456,
"step": 1015
},
{
"epoch": 4.96,
"learning_rate": 2.7913279132791332e-05,
"loss": 0.1839,
"step": 1020
},
{
"epoch": 4.99,
"learning_rate": 2.777777777777778e-05,
"loss": 0.1532,
"step": 1025
},
{
"epoch": 5.0,
"eval_accuracy": 0.9760438056125941,
"eval_loss": 0.08150195330381393,
"eval_runtime": 21.7472,
"eval_samples_per_second": 134.362,
"eval_steps_per_second": 4.23,
"step": 1027
},
{
"epoch": 5.01,
"learning_rate": 2.764227642276423e-05,
"loss": 0.1426,
"step": 1030
},
{
"epoch": 5.04,
"learning_rate": 2.750677506775068e-05,
"loss": 0.1323,
"step": 1035
},
{
"epoch": 5.06,
"learning_rate": 2.7371273712737127e-05,
"loss": 0.101,
"step": 1040
},
{
"epoch": 5.09,
"learning_rate": 2.7235772357723577e-05,
"loss": 0.1545,
"step": 1045
},
{
"epoch": 5.11,
"learning_rate": 2.7100271002710027e-05,
"loss": 0.1368,
"step": 1050
},
{
"epoch": 5.13,
"learning_rate": 2.696476964769648e-05,
"loss": 0.1524,
"step": 1055
},
{
"epoch": 5.16,
"learning_rate": 2.682926829268293e-05,
"loss": 0.1483,
"step": 1060
},
{
"epoch": 5.18,
"learning_rate": 2.6693766937669378e-05,
"loss": 0.1225,
"step": 1065
},
{
"epoch": 5.21,
"learning_rate": 2.6558265582655828e-05,
"loss": 0.1314,
"step": 1070
},
{
"epoch": 5.23,
"learning_rate": 2.642276422764228e-05,
"loss": 0.1565,
"step": 1075
},
{
"epoch": 5.26,
"learning_rate": 2.6287262872628725e-05,
"loss": 0.1479,
"step": 1080
},
{
"epoch": 5.28,
"learning_rate": 2.6151761517615176e-05,
"loss": 0.1391,
"step": 1085
},
{
"epoch": 5.3,
"learning_rate": 2.601626016260163e-05,
"loss": 0.1049,
"step": 1090
},
{
"epoch": 5.33,
"learning_rate": 2.588075880758808e-05,
"loss": 0.156,
"step": 1095
},
{
"epoch": 5.35,
"learning_rate": 2.574525745257453e-05,
"loss": 0.1518,
"step": 1100
},
{
"epoch": 5.38,
"learning_rate": 2.5609756097560977e-05,
"loss": 0.1462,
"step": 1105
},
{
"epoch": 5.4,
"learning_rate": 2.5474254742547427e-05,
"loss": 0.1438,
"step": 1110
},
{
"epoch": 5.43,
"learning_rate": 2.5338753387533877e-05,
"loss": 0.1274,
"step": 1115
},
{
"epoch": 5.45,
"learning_rate": 2.5203252032520324e-05,
"loss": 0.1378,
"step": 1120
},
{
"epoch": 5.47,
"learning_rate": 2.5067750677506774e-05,
"loss": 0.1273,
"step": 1125
},
{
"epoch": 5.5,
"learning_rate": 2.4932249322493225e-05,
"loss": 0.1386,
"step": 1130
},
{
"epoch": 5.52,
"learning_rate": 2.4796747967479675e-05,
"loss": 0.1615,
"step": 1135
},
{
"epoch": 5.55,
"learning_rate": 2.4661246612466125e-05,
"loss": 0.1052,
"step": 1140
},
{
"epoch": 5.57,
"learning_rate": 2.4525745257452575e-05,
"loss": 0.1767,
"step": 1145
},
{
"epoch": 5.6,
"learning_rate": 2.4390243902439026e-05,
"loss": 0.1354,
"step": 1150
},
{
"epoch": 5.62,
"learning_rate": 2.4254742547425473e-05,
"loss": 0.1458,
"step": 1155
},
{
"epoch": 5.64,
"learning_rate": 2.4119241192411926e-05,
"loss": 0.1144,
"step": 1160
},
{
"epoch": 5.67,
"learning_rate": 2.3983739837398377e-05,
"loss": 0.127,
"step": 1165
},
{
"epoch": 5.69,
"learning_rate": 2.3848238482384823e-05,
"loss": 0.1103,
"step": 1170
},
{
"epoch": 5.72,
"learning_rate": 2.3712737127371277e-05,
"loss": 0.1934,
"step": 1175
},
{
"epoch": 5.74,
"learning_rate": 2.3577235772357724e-05,
"loss": 0.1208,
"step": 1180
},
{
"epoch": 5.77,
"learning_rate": 2.3441734417344174e-05,
"loss": 0.1286,
"step": 1185
},
{
"epoch": 5.79,
"learning_rate": 2.3306233062330625e-05,
"loss": 0.1495,
"step": 1190
},
{
"epoch": 5.82,
"learning_rate": 2.3170731707317075e-05,
"loss": 0.1243,
"step": 1195
},
{
"epoch": 5.84,
"learning_rate": 2.3035230352303525e-05,
"loss": 0.1316,
"step": 1200
},
{
"epoch": 5.86,
"learning_rate": 2.2899728997289975e-05,
"loss": 0.1777,
"step": 1205
},
{
"epoch": 5.89,
"learning_rate": 2.2764227642276422e-05,
"loss": 0.1363,
"step": 1210
},
{
"epoch": 5.91,
"learning_rate": 2.2628726287262876e-05,
"loss": 0.1467,
"step": 1215
},
{
"epoch": 5.94,
"learning_rate": 2.2493224932249323e-05,
"loss": 0.1484,
"step": 1220
},
{
"epoch": 5.96,
"learning_rate": 2.2357723577235773e-05,
"loss": 0.1041,
"step": 1225
},
{
"epoch": 5.99,
"learning_rate": 2.2222222222222223e-05,
"loss": 0.1311,
"step": 1230
},
{
"epoch": 6.0,
"eval_accuracy": 0.9804928131416838,
"eval_loss": 0.06673090904951096,
"eval_runtime": 21.2329,
"eval_samples_per_second": 137.616,
"eval_steps_per_second": 4.333,
"step": 1233
},
{
"epoch": 6.01,
"learning_rate": 2.2086720867208674e-05,
"loss": 0.1585,
"step": 1235
},
{
"epoch": 6.03,
"learning_rate": 2.1951219512195124e-05,
"loss": 0.0896,
"step": 1240
},
{
"epoch": 6.06,
"learning_rate": 2.181571815718157e-05,
"loss": 0.1285,
"step": 1245
},
{
"epoch": 6.08,
"learning_rate": 2.1680216802168024e-05,
"loss": 0.1674,
"step": 1250
},
{
"epoch": 6.11,
"learning_rate": 2.1544715447154475e-05,
"loss": 0.129,
"step": 1255
},
{
"epoch": 6.13,
"learning_rate": 2.140921409214092e-05,
"loss": 0.1062,
"step": 1260
},
{
"epoch": 6.16,
"learning_rate": 2.1273712737127372e-05,
"loss": 0.1407,
"step": 1265
},
{
"epoch": 6.18,
"learning_rate": 2.1138211382113822e-05,
"loss": 0.1303,
"step": 1270
},
{
"epoch": 6.2,
"learning_rate": 2.1002710027100272e-05,
"loss": 0.125,
"step": 1275
},
{
"epoch": 6.23,
"learning_rate": 2.0867208672086723e-05,
"loss": 0.1012,
"step": 1280
},
{
"epoch": 6.25,
"learning_rate": 2.073170731707317e-05,
"loss": 0.1349,
"step": 1285
},
{
"epoch": 6.28,
"learning_rate": 2.0596205962059623e-05,
"loss": 0.1091,
"step": 1290
},
{
"epoch": 6.3,
"learning_rate": 2.046070460704607e-05,
"loss": 0.1129,
"step": 1295
},
{
"epoch": 6.33,
"learning_rate": 2.032520325203252e-05,
"loss": 0.1401,
"step": 1300
},
{
"epoch": 6.35,
"learning_rate": 2.018970189701897e-05,
"loss": 0.1221,
"step": 1305
},
{
"epoch": 6.37,
"learning_rate": 2.005420054200542e-05,
"loss": 0.0942,
"step": 1310
},
{
"epoch": 6.4,
"learning_rate": 1.991869918699187e-05,
"loss": 0.1388,
"step": 1315
},
{
"epoch": 6.42,
"learning_rate": 1.978319783197832e-05,
"loss": 0.1218,
"step": 1320
},
{
"epoch": 6.45,
"learning_rate": 1.9647696476964768e-05,
"loss": 0.1153,
"step": 1325
},
{
"epoch": 6.47,
"learning_rate": 1.9512195121951222e-05,
"loss": 0.152,
"step": 1330
},
{
"epoch": 6.5,
"learning_rate": 1.937669376693767e-05,
"loss": 0.1268,
"step": 1335
},
{
"epoch": 6.52,
"learning_rate": 1.924119241192412e-05,
"loss": 0.1328,
"step": 1340
},
{
"epoch": 6.55,
"learning_rate": 1.9105691056910573e-05,
"loss": 0.1374,
"step": 1345
},
{
"epoch": 6.57,
"learning_rate": 1.897018970189702e-05,
"loss": 0.1316,
"step": 1350
},
{
"epoch": 6.59,
"learning_rate": 1.883468834688347e-05,
"loss": 0.1332,
"step": 1355
},
{
"epoch": 6.62,
"learning_rate": 1.869918699186992e-05,
"loss": 0.1308,
"step": 1360
},
{
"epoch": 6.64,
"learning_rate": 1.856368563685637e-05,
"loss": 0.1097,
"step": 1365
},
{
"epoch": 6.67,
"learning_rate": 1.842818428184282e-05,
"loss": 0.1391,
"step": 1370
},
{
"epoch": 6.69,
"learning_rate": 1.8292682926829268e-05,
"loss": 0.1464,
"step": 1375
},
{
"epoch": 6.72,
"learning_rate": 1.8157181571815718e-05,
"loss": 0.1092,
"step": 1380
},
{
"epoch": 6.74,
"learning_rate": 1.8021680216802168e-05,
"loss": 0.1048,
"step": 1385
},
{
"epoch": 6.76,
"learning_rate": 1.788617886178862e-05,
"loss": 0.1089,
"step": 1390
},
{
"epoch": 6.79,
"learning_rate": 1.775067750677507e-05,
"loss": 0.1597,
"step": 1395
},
{
"epoch": 6.81,
"learning_rate": 1.7615176151761516e-05,
"loss": 0.1062,
"step": 1400
},
{
"epoch": 6.84,
"learning_rate": 1.747967479674797e-05,
"loss": 0.1317,
"step": 1405
},
{
"epoch": 6.86,
"learning_rate": 1.734417344173442e-05,
"loss": 0.083,
"step": 1410
},
{
"epoch": 6.89,
"learning_rate": 1.7208672086720866e-05,
"loss": 0.1756,
"step": 1415
},
{
"epoch": 6.91,
"learning_rate": 1.707317073170732e-05,
"loss": 0.1093,
"step": 1420
},
{
"epoch": 6.93,
"learning_rate": 1.6937669376693767e-05,
"loss": 0.1497,
"step": 1425
},
{
"epoch": 6.96,
"learning_rate": 1.6802168021680217e-05,
"loss": 0.1338,
"step": 1430
},
{
"epoch": 6.98,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.1212,
"step": 1435
},
{
"epoch": 7.0,
"eval_accuracy": 0.9804928131416838,
"eval_loss": 0.0675366148352623,
"eval_runtime": 21.3826,
"eval_samples_per_second": 136.653,
"eval_steps_per_second": 4.303,
"step": 1438
},
{
"epoch": 7.01,
"learning_rate": 1.6531165311653118e-05,
"loss": 0.1285,
"step": 1440
},
{
"epoch": 7.03,
"learning_rate": 1.6395663956639568e-05,
"loss": 0.1137,
"step": 1445
},
{
"epoch": 7.06,
"learning_rate": 1.6260162601626018e-05,
"loss": 0.1065,
"step": 1450
},
{
"epoch": 7.08,
"learning_rate": 1.6124661246612465e-05,
"loss": 0.1344,
"step": 1455
},
{
"epoch": 7.1,
"learning_rate": 1.598915989159892e-05,
"loss": 0.1343,
"step": 1460
},
{
"epoch": 7.13,
"learning_rate": 1.5853658536585366e-05,
"loss": 0.1364,
"step": 1465
},
{
"epoch": 7.15,
"learning_rate": 1.5718157181571816e-05,
"loss": 0.0916,
"step": 1470
},
{
"epoch": 7.18,
"learning_rate": 1.5582655826558266e-05,
"loss": 0.1183,
"step": 1475
},
{
"epoch": 7.2,
"learning_rate": 1.5447154471544717e-05,
"loss": 0.0924,
"step": 1480
},
{
"epoch": 7.23,
"learning_rate": 1.5311653116531167e-05,
"loss": 0.0979,
"step": 1485
},
{
"epoch": 7.25,
"learning_rate": 1.5176151761517615e-05,
"loss": 0.1393,
"step": 1490
},
{
"epoch": 7.27,
"learning_rate": 1.5040650406504067e-05,
"loss": 0.1332,
"step": 1495
},
{
"epoch": 7.3,
"learning_rate": 1.4905149051490516e-05,
"loss": 0.1017,
"step": 1500
},
{
"epoch": 7.32,
"learning_rate": 1.4769647696476966e-05,
"loss": 0.1124,
"step": 1505
},
{
"epoch": 7.35,
"learning_rate": 1.4634146341463415e-05,
"loss": 0.133,
"step": 1510
},
{
"epoch": 7.37,
"learning_rate": 1.4498644986449867e-05,
"loss": 0.1389,
"step": 1515
},
{
"epoch": 7.4,
"learning_rate": 1.4363143631436315e-05,
"loss": 0.1296,
"step": 1520
},
{
"epoch": 7.42,
"learning_rate": 1.4227642276422764e-05,
"loss": 0.144,
"step": 1525
},
{
"epoch": 7.45,
"learning_rate": 1.4092140921409214e-05,
"loss": 0.1104,
"step": 1530
},
{
"epoch": 7.47,
"learning_rate": 1.3956639566395666e-05,
"loss": 0.1089,
"step": 1535
},
{
"epoch": 7.49,
"learning_rate": 1.3821138211382115e-05,
"loss": 0.1098,
"step": 1540
},
{
"epoch": 7.52,
"learning_rate": 1.3685636856368563e-05,
"loss": 0.1404,
"step": 1545
},
{
"epoch": 7.54,
"learning_rate": 1.3550135501355014e-05,
"loss": 0.121,
"step": 1550
},
{
"epoch": 7.57,
"learning_rate": 1.3414634146341466e-05,
"loss": 0.1223,
"step": 1555
},
{
"epoch": 7.59,
"learning_rate": 1.3279132791327914e-05,
"loss": 0.1421,
"step": 1560
},
{
"epoch": 7.62,
"learning_rate": 1.3143631436314363e-05,
"loss": 0.1299,
"step": 1565
},
{
"epoch": 7.64,
"learning_rate": 1.3008130081300815e-05,
"loss": 0.1048,
"step": 1570
},
{
"epoch": 7.66,
"learning_rate": 1.2872628726287265e-05,
"loss": 0.0924,
"step": 1575
},
{
"epoch": 7.69,
"learning_rate": 1.2737127371273713e-05,
"loss": 0.1248,
"step": 1580
},
{
"epoch": 7.71,
"learning_rate": 1.2601626016260162e-05,
"loss": 0.1488,
"step": 1585
},
{
"epoch": 7.74,
"learning_rate": 1.2466124661246612e-05,
"loss": 0.1429,
"step": 1590
},
{
"epoch": 7.76,
"learning_rate": 1.2330623306233063e-05,
"loss": 0.1318,
"step": 1595
},
{
"epoch": 7.79,
"learning_rate": 1.2195121951219513e-05,
"loss": 0.1389,
"step": 1600
},
{
"epoch": 7.81,
"learning_rate": 1.2059620596205963e-05,
"loss": 0.0929,
"step": 1605
},
{
"epoch": 7.83,
"learning_rate": 1.1924119241192412e-05,
"loss": 0.0922,
"step": 1610
},
{
"epoch": 7.86,
"learning_rate": 1.1788617886178862e-05,
"loss": 0.0889,
"step": 1615
},
{
"epoch": 7.88,
"learning_rate": 1.1653116531165312e-05,
"loss": 0.1047,
"step": 1620
},
{
"epoch": 7.91,
"learning_rate": 1.1517615176151763e-05,
"loss": 0.1099,
"step": 1625
},
{
"epoch": 7.93,
"learning_rate": 1.1382113821138211e-05,
"loss": 0.1038,
"step": 1630
},
{
"epoch": 7.96,
"learning_rate": 1.1246612466124661e-05,
"loss": 0.0829,
"step": 1635
},
{
"epoch": 7.98,
"learning_rate": 1.1111111111111112e-05,
"loss": 0.1637,
"step": 1640
},
{
"epoch": 8.0,
"eval_accuracy": 0.9798083504449008,
"eval_loss": 0.06967572867870331,
"eval_runtime": 21.6361,
"eval_samples_per_second": 135.052,
"eval_steps_per_second": 4.252,
"step": 1644
},
{
"epoch": 8.0,
"learning_rate": 1.0975609756097562e-05,
"loss": 0.0999,
"step": 1645
},
{
"epoch": 8.03,
"learning_rate": 1.0840108401084012e-05,
"loss": 0.1016,
"step": 1650
},
{
"epoch": 8.05,
"learning_rate": 1.070460704607046e-05,
"loss": 0.1218,
"step": 1655
},
{
"epoch": 8.08,
"learning_rate": 1.0569105691056911e-05,
"loss": 0.1293,
"step": 1660
},
{
"epoch": 8.1,
"learning_rate": 1.0433604336043361e-05,
"loss": 0.1151,
"step": 1665
},
{
"epoch": 8.13,
"learning_rate": 1.0298102981029812e-05,
"loss": 0.1309,
"step": 1670
},
{
"epoch": 8.15,
"learning_rate": 1.016260162601626e-05,
"loss": 0.12,
"step": 1675
},
{
"epoch": 8.18,
"learning_rate": 1.002710027100271e-05,
"loss": 0.1278,
"step": 1680
},
{
"epoch": 8.2,
"learning_rate": 9.89159891598916e-06,
"loss": 0.0949,
"step": 1685
},
{
"epoch": 8.22,
"learning_rate": 9.756097560975611e-06,
"loss": 0.108,
"step": 1690
},
{
"epoch": 8.25,
"learning_rate": 9.62059620596206e-06,
"loss": 0.1144,
"step": 1695
},
{
"epoch": 8.27,
"learning_rate": 9.48509485094851e-06,
"loss": 0.1016,
"step": 1700
},
{
"epoch": 8.3,
"learning_rate": 9.34959349593496e-06,
"loss": 0.0884,
"step": 1705
},
{
"epoch": 8.32,
"learning_rate": 9.21409214092141e-06,
"loss": 0.093,
"step": 1710
},
{
"epoch": 8.35,
"learning_rate": 9.078590785907859e-06,
"loss": 0.0766,
"step": 1715
},
{
"epoch": 8.37,
"learning_rate": 8.94308943089431e-06,
"loss": 0.1495,
"step": 1720
},
{
"epoch": 8.39,
"learning_rate": 8.807588075880758e-06,
"loss": 0.1037,
"step": 1725
},
{
"epoch": 8.42,
"learning_rate": 8.67208672086721e-06,
"loss": 0.1294,
"step": 1730
},
{
"epoch": 8.44,
"learning_rate": 8.53658536585366e-06,
"loss": 0.0902,
"step": 1735
},
{
"epoch": 8.47,
"learning_rate": 8.401084010840109e-06,
"loss": 0.0931,
"step": 1740
},
{
"epoch": 8.49,
"learning_rate": 8.265582655826559e-06,
"loss": 0.108,
"step": 1745
},
{
"epoch": 8.52,
"learning_rate": 8.130081300813009e-06,
"loss": 0.0974,
"step": 1750
},
{
"epoch": 8.54,
"learning_rate": 7.99457994579946e-06,
"loss": 0.092,
"step": 1755
},
{
"epoch": 8.56,
"learning_rate": 7.859078590785908e-06,
"loss": 0.095,
"step": 1760
},
{
"epoch": 8.59,
"learning_rate": 7.723577235772358e-06,
"loss": 0.1177,
"step": 1765
},
{
"epoch": 8.61,
"learning_rate": 7.588075880758808e-06,
"loss": 0.1242,
"step": 1770
},
{
"epoch": 8.64,
"learning_rate": 7.452574525745258e-06,
"loss": 0.1228,
"step": 1775
},
{
"epoch": 8.66,
"learning_rate": 7.317073170731707e-06,
"loss": 0.1003,
"step": 1780
},
{
"epoch": 8.69,
"learning_rate": 7.181571815718158e-06,
"loss": 0.1152,
"step": 1785
},
{
"epoch": 8.71,
"learning_rate": 7.046070460704607e-06,
"loss": 0.0998,
"step": 1790
},
{
"epoch": 8.73,
"learning_rate": 6.910569105691057e-06,
"loss": 0.0974,
"step": 1795
},
{
"epoch": 8.76,
"learning_rate": 6.775067750677507e-06,
"loss": 0.0862,
"step": 1800
},
{
"epoch": 8.78,
"learning_rate": 6.639566395663957e-06,
"loss": 0.134,
"step": 1805
},
{
"epoch": 8.81,
"learning_rate": 6.504065040650407e-06,
"loss": 0.1038,
"step": 1810
},
{
"epoch": 8.83,
"learning_rate": 6.368563685636857e-06,
"loss": 0.1416,
"step": 1815
},
{
"epoch": 8.86,
"learning_rate": 6.233062330623306e-06,
"loss": 0.1246,
"step": 1820
},
{
"epoch": 8.88,
"learning_rate": 6.0975609756097564e-06,
"loss": 0.0954,
"step": 1825
},
{
"epoch": 8.91,
"learning_rate": 5.962059620596206e-06,
"loss": 0.1269,
"step": 1830
},
{
"epoch": 8.93,
"learning_rate": 5.826558265582656e-06,
"loss": 0.0913,
"step": 1835
},
{
"epoch": 8.95,
"learning_rate": 5.6910569105691056e-06,
"loss": 0.1073,
"step": 1840
},
{
"epoch": 8.98,
"learning_rate": 5.555555555555556e-06,
"loss": 0.116,
"step": 1845
},
{
"epoch": 9.0,
"eval_accuracy": 0.9811772758384668,
"eval_loss": 0.06383541971445084,
"eval_runtime": 21.8412,
"eval_samples_per_second": 133.784,
"eval_steps_per_second": 4.212,
"step": 1849
},
{
"epoch": 9.0,
"learning_rate": 5.420054200542006e-06,
"loss": 0.0959,
"step": 1850
},
{
"epoch": 9.03,
"learning_rate": 5.2845528455284555e-06,
"loss": 0.1091,
"step": 1855
},
{
"epoch": 9.05,
"learning_rate": 5.149051490514906e-06,
"loss": 0.0918,
"step": 1860
},
{
"epoch": 9.08,
"learning_rate": 5.013550135501355e-06,
"loss": 0.0973,
"step": 1865
},
{
"epoch": 9.1,
"learning_rate": 4.8780487804878055e-06,
"loss": 0.0981,
"step": 1870
},
{
"epoch": 9.12,
"learning_rate": 4.742547425474255e-06,
"loss": 0.0797,
"step": 1875
},
{
"epoch": 9.15,
"learning_rate": 4.607046070460705e-06,
"loss": 0.1161,
"step": 1880
},
{
"epoch": 9.17,
"learning_rate": 4.471544715447155e-06,
"loss": 0.1062,
"step": 1885
},
{
"epoch": 9.2,
"learning_rate": 4.336043360433605e-06,
"loss": 0.0973,
"step": 1890
},
{
"epoch": 9.22,
"learning_rate": 4.200542005420054e-06,
"loss": 0.0964,
"step": 1895
},
{
"epoch": 9.25,
"learning_rate": 4.0650406504065046e-06,
"loss": 0.0953,
"step": 1900
},
{
"epoch": 9.27,
"learning_rate": 3.929539295392954e-06,
"loss": 0.0841,
"step": 1905
},
{
"epoch": 9.29,
"learning_rate": 3.794037940379404e-06,
"loss": 0.1088,
"step": 1910
},
{
"epoch": 9.32,
"learning_rate": 3.6585365853658537e-06,
"loss": 0.1275,
"step": 1915
},
{
"epoch": 9.34,
"learning_rate": 3.5230352303523035e-06,
"loss": 0.1055,
"step": 1920
},
{
"epoch": 9.37,
"learning_rate": 3.3875338753387534e-06,
"loss": 0.1103,
"step": 1925
},
{
"epoch": 9.39,
"learning_rate": 3.2520325203252037e-06,
"loss": 0.0943,
"step": 1930
},
{
"epoch": 9.42,
"learning_rate": 3.116531165311653e-06,
"loss": 0.1117,
"step": 1935
},
{
"epoch": 9.44,
"learning_rate": 2.981029810298103e-06,
"loss": 0.0888,
"step": 1940
},
{
"epoch": 9.46,
"learning_rate": 2.8455284552845528e-06,
"loss": 0.1169,
"step": 1945
},
{
"epoch": 9.49,
"learning_rate": 2.710027100271003e-06,
"loss": 0.0857,
"step": 1950
},
{
"epoch": 9.51,
"learning_rate": 2.574525745257453e-06,
"loss": 0.0776,
"step": 1955
},
{
"epoch": 9.54,
"learning_rate": 2.4390243902439027e-06,
"loss": 0.0843,
"step": 1960
},
{
"epoch": 9.56,
"learning_rate": 2.3035230352303526e-06,
"loss": 0.0758,
"step": 1965
},
{
"epoch": 9.59,
"learning_rate": 2.1680216802168024e-06,
"loss": 0.1109,
"step": 1970
},
{
"epoch": 9.61,
"learning_rate": 2.0325203252032523e-06,
"loss": 0.1277,
"step": 1975
},
{
"epoch": 9.64,
"learning_rate": 1.897018970189702e-06,
"loss": 0.1218,
"step": 1980
},
{
"epoch": 9.66,
"learning_rate": 1.7615176151761518e-06,
"loss": 0.1389,
"step": 1985
},
{
"epoch": 9.68,
"learning_rate": 1.6260162601626018e-06,
"loss": 0.1061,
"step": 1990
},
{
"epoch": 9.71,
"learning_rate": 1.4905149051490515e-06,
"loss": 0.1006,
"step": 1995
},
{
"epoch": 9.73,
"learning_rate": 1.3550135501355015e-06,
"loss": 0.116,
"step": 2000
},
{
"epoch": 9.76,
"learning_rate": 1.2195121951219514e-06,
"loss": 0.1143,
"step": 2005
},
{
"epoch": 9.78,
"learning_rate": 1.0840108401084012e-06,
"loss": 0.1214,
"step": 2010
},
{
"epoch": 9.81,
"learning_rate": 9.48509485094851e-07,
"loss": 0.1353,
"step": 2015
},
{
"epoch": 9.83,
"learning_rate": 8.130081300813009e-07,
"loss": 0.1078,
"step": 2020
},
{
"epoch": 9.85,
"learning_rate": 6.775067750677508e-07,
"loss": 0.0809,
"step": 2025
},
{
"epoch": 9.88,
"learning_rate": 5.420054200542006e-07,
"loss": 0.1068,
"step": 2030
},
{
"epoch": 9.9,
"learning_rate": 4.0650406504065046e-07,
"loss": 0.0909,
"step": 2035
},
{
"epoch": 9.93,
"learning_rate": 2.710027100271003e-07,
"loss": 0.0828,
"step": 2040
},
{
"epoch": 9.95,
"learning_rate": 1.3550135501355015e-07,
"loss": 0.1054,
"step": 2045
},
{
"epoch": 9.98,
"learning_rate": 0.0,
"loss": 0.085,
"step": 2050
},
{
"epoch": 9.98,
"eval_accuracy": 0.9798083504449008,
"eval_loss": 0.06385670602321625,
"eval_runtime": 21.9428,
"eval_samples_per_second": 133.164,
"eval_steps_per_second": 4.193,
"step": 2050
},
{
"epoch": 9.98,
"step": 2050,
"total_flos": 6.521150663842333e+18,
"train_loss": 0.21471095208714647,
"train_runtime": 4563.3157,
"train_samples_per_second": 57.625,
"train_steps_per_second": 0.449
}
],
"logging_steps": 5,
"max_steps": 2050,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 6.521150663842333e+18,
"trial_name": null,
"trial_params": null
}