mansee's picture
End of training
e05af56
raw
history blame
No virus
126 kB
{
"best_metric": 0.9661252256004442,
"best_model_checkpoint": "swin-tiny-patch4-window7-224-img_orientation/checkpoint-4558",
"epoch": 9.990128331688055,
"eval_steps": 500,
"global_step": 5060,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.940711462450593e-07,
"loss": 1.4271,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 9.881422924901187e-07,
"loss": 1.4728,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 1.4822134387351778e-06,
"loss": 1.4485,
"step": 15
},
{
"epoch": 0.04,
"learning_rate": 1.9762845849802374e-06,
"loss": 1.4446,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 2.4703557312252965e-06,
"loss": 1.4544,
"step": 25
},
{
"epoch": 0.06,
"learning_rate": 2.9644268774703556e-06,
"loss": 1.4466,
"step": 30
},
{
"epoch": 0.07,
"learning_rate": 3.458498023715415e-06,
"loss": 1.3844,
"step": 35
},
{
"epoch": 0.08,
"learning_rate": 3.952569169960475e-06,
"loss": 1.4013,
"step": 40
},
{
"epoch": 0.09,
"learning_rate": 4.4466403162055334e-06,
"loss": 1.3652,
"step": 45
},
{
"epoch": 0.1,
"learning_rate": 4.940711462450593e-06,
"loss": 1.352,
"step": 50
},
{
"epoch": 0.11,
"learning_rate": 5.4347826086956525e-06,
"loss": 1.3491,
"step": 55
},
{
"epoch": 0.12,
"learning_rate": 5.928853754940711e-06,
"loss": 1.2971,
"step": 60
},
{
"epoch": 0.13,
"learning_rate": 6.422924901185772e-06,
"loss": 1.3132,
"step": 65
},
{
"epoch": 0.14,
"learning_rate": 6.91699604743083e-06,
"loss": 1.28,
"step": 70
},
{
"epoch": 0.15,
"learning_rate": 7.41106719367589e-06,
"loss": 1.2403,
"step": 75
},
{
"epoch": 0.16,
"learning_rate": 7.90513833992095e-06,
"loss": 1.2324,
"step": 80
},
{
"epoch": 0.17,
"learning_rate": 8.399209486166009e-06,
"loss": 1.1972,
"step": 85
},
{
"epoch": 0.18,
"learning_rate": 8.893280632411067e-06,
"loss": 1.158,
"step": 90
},
{
"epoch": 0.19,
"learning_rate": 9.387351778656126e-06,
"loss": 1.1602,
"step": 95
},
{
"epoch": 0.2,
"learning_rate": 9.881422924901186e-06,
"loss": 1.1085,
"step": 100
},
{
"epoch": 0.21,
"learning_rate": 1.0375494071146246e-05,
"loss": 1.074,
"step": 105
},
{
"epoch": 0.22,
"learning_rate": 1.0869565217391305e-05,
"loss": 1.0475,
"step": 110
},
{
"epoch": 0.23,
"learning_rate": 1.1363636363636365e-05,
"loss": 1.0326,
"step": 115
},
{
"epoch": 0.24,
"learning_rate": 1.1857707509881423e-05,
"loss": 1.0471,
"step": 120
},
{
"epoch": 0.25,
"learning_rate": 1.2351778656126482e-05,
"loss": 0.9761,
"step": 125
},
{
"epoch": 0.26,
"learning_rate": 1.2845849802371543e-05,
"loss": 0.9621,
"step": 130
},
{
"epoch": 0.27,
"learning_rate": 1.3339920948616603e-05,
"loss": 0.9279,
"step": 135
},
{
"epoch": 0.28,
"learning_rate": 1.383399209486166e-05,
"loss": 0.8971,
"step": 140
},
{
"epoch": 0.29,
"learning_rate": 1.432806324110672e-05,
"loss": 0.9041,
"step": 145
},
{
"epoch": 0.3,
"learning_rate": 1.482213438735178e-05,
"loss": 0.8725,
"step": 150
},
{
"epoch": 0.31,
"learning_rate": 1.531620553359684e-05,
"loss": 0.8433,
"step": 155
},
{
"epoch": 0.32,
"learning_rate": 1.58102766798419e-05,
"loss": 0.8415,
"step": 160
},
{
"epoch": 0.33,
"learning_rate": 1.630434782608696e-05,
"loss": 0.8407,
"step": 165
},
{
"epoch": 0.34,
"learning_rate": 1.6798418972332018e-05,
"loss": 0.8394,
"step": 170
},
{
"epoch": 0.35,
"learning_rate": 1.7292490118577078e-05,
"loss": 0.825,
"step": 175
},
{
"epoch": 0.36,
"learning_rate": 1.7786561264822134e-05,
"loss": 0.7952,
"step": 180
},
{
"epoch": 0.37,
"learning_rate": 1.8280632411067193e-05,
"loss": 0.7608,
"step": 185
},
{
"epoch": 0.38,
"learning_rate": 1.8774703557312253e-05,
"loss": 0.7986,
"step": 190
},
{
"epoch": 0.38,
"learning_rate": 1.9268774703557312e-05,
"loss": 0.7804,
"step": 195
},
{
"epoch": 0.39,
"learning_rate": 1.9762845849802372e-05,
"loss": 0.7821,
"step": 200
},
{
"epoch": 0.4,
"learning_rate": 2.025691699604743e-05,
"loss": 0.7888,
"step": 205
},
{
"epoch": 0.41,
"learning_rate": 2.075098814229249e-05,
"loss": 0.7183,
"step": 210
},
{
"epoch": 0.42,
"learning_rate": 2.124505928853755e-05,
"loss": 0.7486,
"step": 215
},
{
"epoch": 0.43,
"learning_rate": 2.173913043478261e-05,
"loss": 0.7264,
"step": 220
},
{
"epoch": 0.44,
"learning_rate": 2.223320158102767e-05,
"loss": 0.7409,
"step": 225
},
{
"epoch": 0.45,
"learning_rate": 2.272727272727273e-05,
"loss": 0.7215,
"step": 230
},
{
"epoch": 0.46,
"learning_rate": 2.3221343873517785e-05,
"loss": 0.7346,
"step": 235
},
{
"epoch": 0.47,
"learning_rate": 2.3715415019762845e-05,
"loss": 0.7276,
"step": 240
},
{
"epoch": 0.48,
"learning_rate": 2.4209486166007905e-05,
"loss": 0.7492,
"step": 245
},
{
"epoch": 0.49,
"learning_rate": 2.4703557312252964e-05,
"loss": 0.6962,
"step": 250
},
{
"epoch": 0.5,
"learning_rate": 2.5197628458498024e-05,
"loss": 0.6649,
"step": 255
},
{
"epoch": 0.51,
"learning_rate": 2.5691699604743087e-05,
"loss": 0.6883,
"step": 260
},
{
"epoch": 0.52,
"learning_rate": 2.6185770750988143e-05,
"loss": 0.6681,
"step": 265
},
{
"epoch": 0.53,
"learning_rate": 2.6679841897233206e-05,
"loss": 0.7106,
"step": 270
},
{
"epoch": 0.54,
"learning_rate": 2.7173913043478262e-05,
"loss": 0.6501,
"step": 275
},
{
"epoch": 0.55,
"learning_rate": 2.766798418972332e-05,
"loss": 0.6985,
"step": 280
},
{
"epoch": 0.56,
"learning_rate": 2.8162055335968378e-05,
"loss": 0.6143,
"step": 285
},
{
"epoch": 0.57,
"learning_rate": 2.865612648221344e-05,
"loss": 0.6328,
"step": 290
},
{
"epoch": 0.58,
"learning_rate": 2.9150197628458497e-05,
"loss": 0.6562,
"step": 295
},
{
"epoch": 0.59,
"learning_rate": 2.964426877470356e-05,
"loss": 0.6741,
"step": 300
},
{
"epoch": 0.6,
"learning_rate": 3.0138339920948616e-05,
"loss": 0.673,
"step": 305
},
{
"epoch": 0.61,
"learning_rate": 3.063241106719368e-05,
"loss": 0.6348,
"step": 310
},
{
"epoch": 0.62,
"learning_rate": 3.1126482213438735e-05,
"loss": 0.5974,
"step": 315
},
{
"epoch": 0.63,
"learning_rate": 3.16205533596838e-05,
"loss": 0.6521,
"step": 320
},
{
"epoch": 0.64,
"learning_rate": 3.2114624505928854e-05,
"loss": 0.6293,
"step": 325
},
{
"epoch": 0.65,
"learning_rate": 3.260869565217392e-05,
"loss": 0.6233,
"step": 330
},
{
"epoch": 0.66,
"learning_rate": 3.310276679841897e-05,
"loss": 0.6,
"step": 335
},
{
"epoch": 0.67,
"learning_rate": 3.3596837944664036e-05,
"loss": 0.5833,
"step": 340
},
{
"epoch": 0.68,
"learning_rate": 3.409090909090909e-05,
"loss": 0.621,
"step": 345
},
{
"epoch": 0.69,
"learning_rate": 3.4584980237154155e-05,
"loss": 0.673,
"step": 350
},
{
"epoch": 0.7,
"learning_rate": 3.507905138339921e-05,
"loss": 0.6416,
"step": 355
},
{
"epoch": 0.71,
"learning_rate": 3.557312252964427e-05,
"loss": 0.6474,
"step": 360
},
{
"epoch": 0.72,
"learning_rate": 3.606719367588933e-05,
"loss": 0.605,
"step": 365
},
{
"epoch": 0.73,
"learning_rate": 3.656126482213439e-05,
"loss": 0.6383,
"step": 370
},
{
"epoch": 0.74,
"learning_rate": 3.705533596837945e-05,
"loss": 0.5592,
"step": 375
},
{
"epoch": 0.75,
"learning_rate": 3.7549407114624506e-05,
"loss": 0.5992,
"step": 380
},
{
"epoch": 0.76,
"learning_rate": 3.804347826086957e-05,
"loss": 0.6087,
"step": 385
},
{
"epoch": 0.77,
"learning_rate": 3.8537549407114625e-05,
"loss": 0.5849,
"step": 390
},
{
"epoch": 0.78,
"learning_rate": 3.903162055335969e-05,
"loss": 0.5662,
"step": 395
},
{
"epoch": 0.79,
"learning_rate": 3.9525691699604744e-05,
"loss": 0.6036,
"step": 400
},
{
"epoch": 0.8,
"learning_rate": 4.001976284584981e-05,
"loss": 0.6162,
"step": 405
},
{
"epoch": 0.81,
"learning_rate": 4.051383399209486e-05,
"loss": 0.5624,
"step": 410
},
{
"epoch": 0.82,
"learning_rate": 4.1007905138339926e-05,
"loss": 0.5839,
"step": 415
},
{
"epoch": 0.83,
"learning_rate": 4.150197628458498e-05,
"loss": 0.5767,
"step": 420
},
{
"epoch": 0.84,
"learning_rate": 4.1996047430830045e-05,
"loss": 0.6021,
"step": 425
},
{
"epoch": 0.85,
"learning_rate": 4.24901185770751e-05,
"loss": 0.5837,
"step": 430
},
{
"epoch": 0.86,
"learning_rate": 4.2984189723320164e-05,
"loss": 0.563,
"step": 435
},
{
"epoch": 0.87,
"learning_rate": 4.347826086956522e-05,
"loss": 0.5428,
"step": 440
},
{
"epoch": 0.88,
"learning_rate": 4.397233201581028e-05,
"loss": 0.6214,
"step": 445
},
{
"epoch": 0.89,
"learning_rate": 4.446640316205534e-05,
"loss": 0.6165,
"step": 450
},
{
"epoch": 0.9,
"learning_rate": 4.4960474308300396e-05,
"loss": 0.614,
"step": 455
},
{
"epoch": 0.91,
"learning_rate": 4.545454545454546e-05,
"loss": 0.5263,
"step": 460
},
{
"epoch": 0.92,
"learning_rate": 4.5948616600790515e-05,
"loss": 0.5776,
"step": 465
},
{
"epoch": 0.93,
"learning_rate": 4.644268774703557e-05,
"loss": 0.5647,
"step": 470
},
{
"epoch": 0.94,
"learning_rate": 4.6936758893280634e-05,
"loss": 0.5481,
"step": 475
},
{
"epoch": 0.95,
"learning_rate": 4.743083003952569e-05,
"loss": 0.5715,
"step": 480
},
{
"epoch": 0.96,
"learning_rate": 4.792490118577075e-05,
"loss": 0.5634,
"step": 485
},
{
"epoch": 0.97,
"learning_rate": 4.841897233201581e-05,
"loss": 0.5397,
"step": 490
},
{
"epoch": 0.98,
"learning_rate": 4.891304347826087e-05,
"loss": 0.5563,
"step": 495
},
{
"epoch": 0.99,
"learning_rate": 4.940711462450593e-05,
"loss": 0.5612,
"step": 500
},
{
"epoch": 1.0,
"learning_rate": 4.990118577075099e-05,
"loss": 0.5043,
"step": 505
},
{
"epoch": 1.0,
"eval_accuracy": 0.8425655976676385,
"eval_loss": 0.3764127790927887,
"eval_runtime": 55.1529,
"eval_samples_per_second": 130.6,
"eval_steps_per_second": 4.098,
"step": 506
},
{
"epoch": 1.01,
"learning_rate": 4.995608256477822e-05,
"loss": 0.5622,
"step": 510
},
{
"epoch": 1.02,
"learning_rate": 4.990118577075099e-05,
"loss": 0.4983,
"step": 515
},
{
"epoch": 1.03,
"learning_rate": 4.984628897672376e-05,
"loss": 0.5185,
"step": 520
},
{
"epoch": 1.04,
"learning_rate": 4.9791392182696533e-05,
"loss": 0.5266,
"step": 525
},
{
"epoch": 1.05,
"learning_rate": 4.97364953886693e-05,
"loss": 0.4936,
"step": 530
},
{
"epoch": 1.06,
"learning_rate": 4.9681598594642076e-05,
"loss": 0.5081,
"step": 535
},
{
"epoch": 1.07,
"learning_rate": 4.9626701800614844e-05,
"loss": 0.5257,
"step": 540
},
{
"epoch": 1.08,
"learning_rate": 4.957180500658762e-05,
"loss": 0.4901,
"step": 545
},
{
"epoch": 1.09,
"learning_rate": 4.9516908212560386e-05,
"loss": 0.4648,
"step": 550
},
{
"epoch": 1.1,
"learning_rate": 4.946201141853316e-05,
"loss": 0.446,
"step": 555
},
{
"epoch": 1.11,
"learning_rate": 4.940711462450593e-05,
"loss": 0.4747,
"step": 560
},
{
"epoch": 1.12,
"learning_rate": 4.93522178304787e-05,
"loss": 0.4507,
"step": 565
},
{
"epoch": 1.13,
"learning_rate": 4.929732103645147e-05,
"loss": 0.5195,
"step": 570
},
{
"epoch": 1.14,
"learning_rate": 4.9242424242424245e-05,
"loss": 0.4642,
"step": 575
},
{
"epoch": 1.15,
"learning_rate": 4.918752744839701e-05,
"loss": 0.5075,
"step": 580
},
{
"epoch": 1.15,
"learning_rate": 4.913263065436979e-05,
"loss": 0.4903,
"step": 585
},
{
"epoch": 1.16,
"learning_rate": 4.9077733860342555e-05,
"loss": 0.4523,
"step": 590
},
{
"epoch": 1.17,
"learning_rate": 4.902283706631533e-05,
"loss": 0.4752,
"step": 595
},
{
"epoch": 1.18,
"learning_rate": 4.89679402722881e-05,
"loss": 0.4744,
"step": 600
},
{
"epoch": 1.19,
"learning_rate": 4.891304347826087e-05,
"loss": 0.4685,
"step": 605
},
{
"epoch": 1.2,
"learning_rate": 4.885814668423364e-05,
"loss": 0.4264,
"step": 610
},
{
"epoch": 1.21,
"learning_rate": 4.8803249890206414e-05,
"loss": 0.4308,
"step": 615
},
{
"epoch": 1.22,
"learning_rate": 4.874835309617918e-05,
"loss": 0.4463,
"step": 620
},
{
"epoch": 1.23,
"learning_rate": 4.869345630215196e-05,
"loss": 0.4457,
"step": 625
},
{
"epoch": 1.24,
"learning_rate": 4.8638559508124724e-05,
"loss": 0.4439,
"step": 630
},
{
"epoch": 1.25,
"learning_rate": 4.85836627140975e-05,
"loss": 0.4143,
"step": 635
},
{
"epoch": 1.26,
"learning_rate": 4.852876592007027e-05,
"loss": 0.4427,
"step": 640
},
{
"epoch": 1.27,
"learning_rate": 4.847386912604304e-05,
"loss": 0.4234,
"step": 645
},
{
"epoch": 1.28,
"learning_rate": 4.841897233201581e-05,
"loss": 0.4547,
"step": 650
},
{
"epoch": 1.29,
"learning_rate": 4.8364075537988584e-05,
"loss": 0.4632,
"step": 655
},
{
"epoch": 1.3,
"learning_rate": 4.830917874396135e-05,
"loss": 0.493,
"step": 660
},
{
"epoch": 1.31,
"learning_rate": 4.8254281949934126e-05,
"loss": 0.3747,
"step": 665
},
{
"epoch": 1.32,
"learning_rate": 4.8199385155906894e-05,
"loss": 0.415,
"step": 670
},
{
"epoch": 1.33,
"learning_rate": 4.814448836187967e-05,
"loss": 0.4875,
"step": 675
},
{
"epoch": 1.34,
"learning_rate": 4.8089591567852436e-05,
"loss": 0.4151,
"step": 680
},
{
"epoch": 1.35,
"learning_rate": 4.803469477382521e-05,
"loss": 0.4619,
"step": 685
},
{
"epoch": 1.36,
"learning_rate": 4.797979797979798e-05,
"loss": 0.478,
"step": 690
},
{
"epoch": 1.37,
"learning_rate": 4.792490118577075e-05,
"loss": 0.4896,
"step": 695
},
{
"epoch": 1.38,
"learning_rate": 4.787000439174352e-05,
"loss": 0.4223,
"step": 700
},
{
"epoch": 1.39,
"learning_rate": 4.7815107597716295e-05,
"loss": 0.4238,
"step": 705
},
{
"epoch": 1.4,
"learning_rate": 4.776021080368906e-05,
"loss": 0.4715,
"step": 710
},
{
"epoch": 1.41,
"learning_rate": 4.770531400966184e-05,
"loss": 0.4563,
"step": 715
},
{
"epoch": 1.42,
"learning_rate": 4.7650417215634605e-05,
"loss": 0.3945,
"step": 720
},
{
"epoch": 1.43,
"learning_rate": 4.759552042160738e-05,
"loss": 0.4104,
"step": 725
},
{
"epoch": 1.44,
"learning_rate": 4.754062362758015e-05,
"loss": 0.4016,
"step": 730
},
{
"epoch": 1.45,
"learning_rate": 4.748572683355292e-05,
"loss": 0.4068,
"step": 735
},
{
"epoch": 1.46,
"learning_rate": 4.743083003952569e-05,
"loss": 0.4448,
"step": 740
},
{
"epoch": 1.47,
"learning_rate": 4.7375933245498465e-05,
"loss": 0.4053,
"step": 745
},
{
"epoch": 1.48,
"learning_rate": 4.732103645147123e-05,
"loss": 0.4126,
"step": 750
},
{
"epoch": 1.49,
"learning_rate": 4.726613965744401e-05,
"loss": 0.4311,
"step": 755
},
{
"epoch": 1.5,
"learning_rate": 4.7211242863416775e-05,
"loss": 0.3973,
"step": 760
},
{
"epoch": 1.51,
"learning_rate": 4.715634606938955e-05,
"loss": 0.4088,
"step": 765
},
{
"epoch": 1.52,
"learning_rate": 4.710144927536232e-05,
"loss": 0.417,
"step": 770
},
{
"epoch": 1.53,
"learning_rate": 4.704655248133509e-05,
"loss": 0.4202,
"step": 775
},
{
"epoch": 1.54,
"learning_rate": 4.699165568730786e-05,
"loss": 0.4816,
"step": 780
},
{
"epoch": 1.55,
"learning_rate": 4.6936758893280634e-05,
"loss": 0.3376,
"step": 785
},
{
"epoch": 1.56,
"learning_rate": 4.68818620992534e-05,
"loss": 0.3922,
"step": 790
},
{
"epoch": 1.57,
"learning_rate": 4.6826965305226176e-05,
"loss": 0.3594,
"step": 795
},
{
"epoch": 1.58,
"learning_rate": 4.6772068511198944e-05,
"loss": 0.426,
"step": 800
},
{
"epoch": 1.59,
"learning_rate": 4.671717171717172e-05,
"loss": 0.4086,
"step": 805
},
{
"epoch": 1.6,
"learning_rate": 4.6662274923144486e-05,
"loss": 0.3917,
"step": 810
},
{
"epoch": 1.61,
"learning_rate": 4.660737812911726e-05,
"loss": 0.4075,
"step": 815
},
{
"epoch": 1.62,
"learning_rate": 4.655248133509003e-05,
"loss": 0.424,
"step": 820
},
{
"epoch": 1.63,
"learning_rate": 4.64975845410628e-05,
"loss": 0.3704,
"step": 825
},
{
"epoch": 1.64,
"learning_rate": 4.644268774703557e-05,
"loss": 0.328,
"step": 830
},
{
"epoch": 1.65,
"learning_rate": 4.6387790953008345e-05,
"loss": 0.4172,
"step": 835
},
{
"epoch": 1.66,
"learning_rate": 4.633289415898111e-05,
"loss": 0.4171,
"step": 840
},
{
"epoch": 1.67,
"learning_rate": 4.627799736495389e-05,
"loss": 0.4141,
"step": 845
},
{
"epoch": 1.68,
"learning_rate": 4.6223100570926656e-05,
"loss": 0.358,
"step": 850
},
{
"epoch": 1.69,
"learning_rate": 4.616820377689943e-05,
"loss": 0.4976,
"step": 855
},
{
"epoch": 1.7,
"learning_rate": 4.61133069828722e-05,
"loss": 0.4737,
"step": 860
},
{
"epoch": 1.71,
"learning_rate": 4.605841018884497e-05,
"loss": 0.4455,
"step": 865
},
{
"epoch": 1.72,
"learning_rate": 4.600351339481774e-05,
"loss": 0.3808,
"step": 870
},
{
"epoch": 1.73,
"learning_rate": 4.5948616600790515e-05,
"loss": 0.3901,
"step": 875
},
{
"epoch": 1.74,
"learning_rate": 4.589371980676328e-05,
"loss": 0.4087,
"step": 880
},
{
"epoch": 1.75,
"learning_rate": 4.583882301273606e-05,
"loss": 0.3863,
"step": 885
},
{
"epoch": 1.76,
"learning_rate": 4.5783926218708825e-05,
"loss": 0.3825,
"step": 890
},
{
"epoch": 1.77,
"learning_rate": 4.57290294246816e-05,
"loss": 0.3795,
"step": 895
},
{
"epoch": 1.78,
"learning_rate": 4.567413263065437e-05,
"loss": 0.3517,
"step": 900
},
{
"epoch": 1.79,
"learning_rate": 4.561923583662714e-05,
"loss": 0.3911,
"step": 905
},
{
"epoch": 1.8,
"learning_rate": 4.556433904259991e-05,
"loss": 0.4049,
"step": 910
},
{
"epoch": 1.81,
"learning_rate": 4.5509442248572684e-05,
"loss": 0.4536,
"step": 915
},
{
"epoch": 1.82,
"learning_rate": 4.545454545454546e-05,
"loss": 0.3358,
"step": 920
},
{
"epoch": 1.83,
"learning_rate": 4.5399648660518226e-05,
"loss": 0.3745,
"step": 925
},
{
"epoch": 1.84,
"learning_rate": 4.5344751866491e-05,
"loss": 0.3679,
"step": 930
},
{
"epoch": 1.85,
"learning_rate": 4.528985507246377e-05,
"loss": 0.3687,
"step": 935
},
{
"epoch": 1.86,
"learning_rate": 4.523495827843654e-05,
"loss": 0.4058,
"step": 940
},
{
"epoch": 1.87,
"learning_rate": 4.518006148440931e-05,
"loss": 0.3416,
"step": 945
},
{
"epoch": 1.88,
"learning_rate": 4.5125164690382086e-05,
"loss": 0.3625,
"step": 950
},
{
"epoch": 1.89,
"learning_rate": 4.507026789635485e-05,
"loss": 0.3841,
"step": 955
},
{
"epoch": 1.9,
"learning_rate": 4.501537110232763e-05,
"loss": 0.3686,
"step": 960
},
{
"epoch": 1.91,
"learning_rate": 4.4960474308300396e-05,
"loss": 0.4008,
"step": 965
},
{
"epoch": 1.92,
"learning_rate": 4.490557751427317e-05,
"loss": 0.3666,
"step": 970
},
{
"epoch": 1.92,
"learning_rate": 4.485068072024594e-05,
"loss": 0.3949,
"step": 975
},
{
"epoch": 1.93,
"learning_rate": 4.479578392621871e-05,
"loss": 0.4004,
"step": 980
},
{
"epoch": 1.94,
"learning_rate": 4.474088713219148e-05,
"loss": 0.3778,
"step": 985
},
{
"epoch": 1.95,
"learning_rate": 4.4685990338164255e-05,
"loss": 0.3422,
"step": 990
},
{
"epoch": 1.96,
"learning_rate": 4.463109354413702e-05,
"loss": 0.358,
"step": 995
},
{
"epoch": 1.97,
"learning_rate": 4.45761967501098e-05,
"loss": 0.3793,
"step": 1000
},
{
"epoch": 1.98,
"learning_rate": 4.452129995608257e-05,
"loss": 0.3498,
"step": 1005
},
{
"epoch": 1.99,
"learning_rate": 4.446640316205534e-05,
"loss": 0.3557,
"step": 1010
},
{
"epoch": 2.0,
"eval_accuracy": 0.9244759128141052,
"eval_loss": 0.2067592442035675,
"eval_runtime": 51.3148,
"eval_samples_per_second": 140.369,
"eval_steps_per_second": 4.404,
"step": 1013
},
{
"epoch": 2.0,
"learning_rate": 4.4411506368028114e-05,
"loss": 0.3604,
"step": 1015
},
{
"epoch": 2.01,
"learning_rate": 4.435660957400088e-05,
"loss": 0.3552,
"step": 1020
},
{
"epoch": 2.02,
"learning_rate": 4.4301712779973656e-05,
"loss": 0.3639,
"step": 1025
},
{
"epoch": 2.03,
"learning_rate": 4.4246815985946424e-05,
"loss": 0.3874,
"step": 1030
},
{
"epoch": 2.04,
"learning_rate": 4.41919191919192e-05,
"loss": 0.2964,
"step": 1035
},
{
"epoch": 2.05,
"learning_rate": 4.4137022397891966e-05,
"loss": 0.3453,
"step": 1040
},
{
"epoch": 2.06,
"learning_rate": 4.408212560386474e-05,
"loss": 0.3409,
"step": 1045
},
{
"epoch": 2.07,
"learning_rate": 4.402722880983751e-05,
"loss": 0.3809,
"step": 1050
},
{
"epoch": 2.08,
"learning_rate": 4.397233201581028e-05,
"loss": 0.3293,
"step": 1055
},
{
"epoch": 2.09,
"learning_rate": 4.391743522178305e-05,
"loss": 0.3849,
"step": 1060
},
{
"epoch": 2.1,
"learning_rate": 4.3862538427755826e-05,
"loss": 0.3578,
"step": 1065
},
{
"epoch": 2.11,
"learning_rate": 4.3807641633728593e-05,
"loss": 0.3279,
"step": 1070
},
{
"epoch": 2.12,
"learning_rate": 4.375274483970137e-05,
"loss": 0.3067,
"step": 1075
},
{
"epoch": 2.13,
"learning_rate": 4.3697848045674136e-05,
"loss": 0.3505,
"step": 1080
},
{
"epoch": 2.14,
"learning_rate": 4.364295125164691e-05,
"loss": 0.3546,
"step": 1085
},
{
"epoch": 2.15,
"learning_rate": 4.358805445761968e-05,
"loss": 0.2668,
"step": 1090
},
{
"epoch": 2.16,
"learning_rate": 4.353315766359245e-05,
"loss": 0.3755,
"step": 1095
},
{
"epoch": 2.17,
"learning_rate": 4.347826086956522e-05,
"loss": 0.3385,
"step": 1100
},
{
"epoch": 2.18,
"learning_rate": 4.3423364075537995e-05,
"loss": 0.2852,
"step": 1105
},
{
"epoch": 2.19,
"learning_rate": 4.336846728151076e-05,
"loss": 0.3846,
"step": 1110
},
{
"epoch": 2.2,
"learning_rate": 4.331357048748354e-05,
"loss": 0.3196,
"step": 1115
},
{
"epoch": 2.21,
"learning_rate": 4.3258673693456305e-05,
"loss": 0.3515,
"step": 1120
},
{
"epoch": 2.22,
"learning_rate": 4.320377689942908e-05,
"loss": 0.3262,
"step": 1125
},
{
"epoch": 2.23,
"learning_rate": 4.314888010540185e-05,
"loss": 0.3932,
"step": 1130
},
{
"epoch": 2.24,
"learning_rate": 4.309398331137462e-05,
"loss": 0.34,
"step": 1135
},
{
"epoch": 2.25,
"learning_rate": 4.303908651734739e-05,
"loss": 0.3434,
"step": 1140
},
{
"epoch": 2.26,
"learning_rate": 4.2984189723320164e-05,
"loss": 0.3564,
"step": 1145
},
{
"epoch": 2.27,
"learning_rate": 4.292929292929293e-05,
"loss": 0.3208,
"step": 1150
},
{
"epoch": 2.28,
"learning_rate": 4.2874396135265707e-05,
"loss": 0.3166,
"step": 1155
},
{
"epoch": 2.29,
"learning_rate": 4.2819499341238474e-05,
"loss": 0.3681,
"step": 1160
},
{
"epoch": 2.3,
"learning_rate": 4.276460254721125e-05,
"loss": 0.364,
"step": 1165
},
{
"epoch": 2.31,
"learning_rate": 4.2709705753184017e-05,
"loss": 0.357,
"step": 1170
},
{
"epoch": 2.32,
"learning_rate": 4.265480895915679e-05,
"loss": 0.3222,
"step": 1175
},
{
"epoch": 2.33,
"learning_rate": 4.259991216512956e-05,
"loss": 0.3315,
"step": 1180
},
{
"epoch": 2.34,
"learning_rate": 4.2545015371102333e-05,
"loss": 0.3176,
"step": 1185
},
{
"epoch": 2.35,
"learning_rate": 4.24901185770751e-05,
"loss": 0.2913,
"step": 1190
},
{
"epoch": 2.36,
"learning_rate": 4.2435221783047876e-05,
"loss": 0.306,
"step": 1195
},
{
"epoch": 2.37,
"learning_rate": 4.2380324989020644e-05,
"loss": 0.3648,
"step": 1200
},
{
"epoch": 2.38,
"learning_rate": 4.232542819499342e-05,
"loss": 0.316,
"step": 1205
},
{
"epoch": 2.39,
"learning_rate": 4.2270531400966186e-05,
"loss": 0.319,
"step": 1210
},
{
"epoch": 2.4,
"learning_rate": 4.221563460693896e-05,
"loss": 0.3,
"step": 1215
},
{
"epoch": 2.41,
"learning_rate": 4.216073781291173e-05,
"loss": 0.2939,
"step": 1220
},
{
"epoch": 2.42,
"learning_rate": 4.21058410188845e-05,
"loss": 0.352,
"step": 1225
},
{
"epoch": 2.43,
"learning_rate": 4.205094422485727e-05,
"loss": 0.3613,
"step": 1230
},
{
"epoch": 2.44,
"learning_rate": 4.1996047430830045e-05,
"loss": 0.3254,
"step": 1235
},
{
"epoch": 2.45,
"learning_rate": 4.194115063680281e-05,
"loss": 0.3473,
"step": 1240
},
{
"epoch": 2.46,
"learning_rate": 4.188625384277559e-05,
"loss": 0.362,
"step": 1245
},
{
"epoch": 2.47,
"learning_rate": 4.1831357048748355e-05,
"loss": 0.3234,
"step": 1250
},
{
"epoch": 2.48,
"learning_rate": 4.177646025472113e-05,
"loss": 0.3153,
"step": 1255
},
{
"epoch": 2.49,
"learning_rate": 4.17215634606939e-05,
"loss": 0.273,
"step": 1260
},
{
"epoch": 2.5,
"learning_rate": 4.166666666666667e-05,
"loss": 0.3564,
"step": 1265
},
{
"epoch": 2.51,
"learning_rate": 4.161176987263944e-05,
"loss": 0.3012,
"step": 1270
},
{
"epoch": 2.52,
"learning_rate": 4.1556873078612214e-05,
"loss": 0.3128,
"step": 1275
},
{
"epoch": 2.53,
"learning_rate": 4.150197628458498e-05,
"loss": 0.2873,
"step": 1280
},
{
"epoch": 2.54,
"learning_rate": 4.144707949055776e-05,
"loss": 0.2928,
"step": 1285
},
{
"epoch": 2.55,
"learning_rate": 4.1392182696530524e-05,
"loss": 0.2622,
"step": 1290
},
{
"epoch": 2.56,
"learning_rate": 4.13372859025033e-05,
"loss": 0.3412,
"step": 1295
},
{
"epoch": 2.57,
"learning_rate": 4.128238910847607e-05,
"loss": 0.3046,
"step": 1300
},
{
"epoch": 2.58,
"learning_rate": 4.122749231444884e-05,
"loss": 0.2975,
"step": 1305
},
{
"epoch": 2.59,
"learning_rate": 4.117259552042161e-05,
"loss": 0.3947,
"step": 1310
},
{
"epoch": 2.6,
"learning_rate": 4.1117698726394384e-05,
"loss": 0.2926,
"step": 1315
},
{
"epoch": 2.61,
"learning_rate": 4.106280193236715e-05,
"loss": 0.3231,
"step": 1320
},
{
"epoch": 2.62,
"learning_rate": 4.1007905138339926e-05,
"loss": 0.3772,
"step": 1325
},
{
"epoch": 2.63,
"learning_rate": 4.0953008344312694e-05,
"loss": 0.3615,
"step": 1330
},
{
"epoch": 2.64,
"learning_rate": 4.089811155028547e-05,
"loss": 0.328,
"step": 1335
},
{
"epoch": 2.65,
"learning_rate": 4.0843214756258236e-05,
"loss": 0.3023,
"step": 1340
},
{
"epoch": 2.66,
"learning_rate": 4.078831796223101e-05,
"loss": 0.3026,
"step": 1345
},
{
"epoch": 2.67,
"learning_rate": 4.073342116820378e-05,
"loss": 0.2928,
"step": 1350
},
{
"epoch": 2.68,
"learning_rate": 4.067852437417655e-05,
"loss": 0.2841,
"step": 1355
},
{
"epoch": 2.69,
"learning_rate": 4.062362758014932e-05,
"loss": 0.3415,
"step": 1360
},
{
"epoch": 2.69,
"learning_rate": 4.0568730786122095e-05,
"loss": 0.3042,
"step": 1365
},
{
"epoch": 2.7,
"learning_rate": 4.051383399209486e-05,
"loss": 0.3291,
"step": 1370
},
{
"epoch": 2.71,
"learning_rate": 4.045893719806764e-05,
"loss": 0.3488,
"step": 1375
},
{
"epoch": 2.72,
"learning_rate": 4.0404040404040405e-05,
"loss": 0.2918,
"step": 1380
},
{
"epoch": 2.73,
"learning_rate": 4.034914361001318e-05,
"loss": 0.2679,
"step": 1385
},
{
"epoch": 2.74,
"learning_rate": 4.029424681598595e-05,
"loss": 0.3045,
"step": 1390
},
{
"epoch": 2.75,
"learning_rate": 4.023935002195872e-05,
"loss": 0.3199,
"step": 1395
},
{
"epoch": 2.76,
"learning_rate": 4.018445322793149e-05,
"loss": 0.3409,
"step": 1400
},
{
"epoch": 2.77,
"learning_rate": 4.0129556433904265e-05,
"loss": 0.2806,
"step": 1405
},
{
"epoch": 2.78,
"learning_rate": 4.007465963987703e-05,
"loss": 0.2914,
"step": 1410
},
{
"epoch": 2.79,
"learning_rate": 4.001976284584981e-05,
"loss": 0.3025,
"step": 1415
},
{
"epoch": 2.8,
"learning_rate": 3.9964866051822575e-05,
"loss": 0.3326,
"step": 1420
},
{
"epoch": 2.81,
"learning_rate": 3.990996925779535e-05,
"loss": 0.3617,
"step": 1425
},
{
"epoch": 2.82,
"learning_rate": 3.985507246376812e-05,
"loss": 0.2963,
"step": 1430
},
{
"epoch": 2.83,
"learning_rate": 3.980017566974089e-05,
"loss": 0.3481,
"step": 1435
},
{
"epoch": 2.84,
"learning_rate": 3.974527887571366e-05,
"loss": 0.341,
"step": 1440
},
{
"epoch": 2.85,
"learning_rate": 3.9690382081686434e-05,
"loss": 0.3044,
"step": 1445
},
{
"epoch": 2.86,
"learning_rate": 3.96354852876592e-05,
"loss": 0.3403,
"step": 1450
},
{
"epoch": 2.87,
"learning_rate": 3.9580588493631976e-05,
"loss": 0.3192,
"step": 1455
},
{
"epoch": 2.88,
"learning_rate": 3.9525691699604744e-05,
"loss": 0.2861,
"step": 1460
},
{
"epoch": 2.89,
"learning_rate": 3.947079490557752e-05,
"loss": 0.336,
"step": 1465
},
{
"epoch": 2.9,
"learning_rate": 3.9415898111550286e-05,
"loss": 0.3312,
"step": 1470
},
{
"epoch": 2.91,
"learning_rate": 3.936100131752306e-05,
"loss": 0.3228,
"step": 1475
},
{
"epoch": 2.92,
"learning_rate": 3.930610452349583e-05,
"loss": 0.2692,
"step": 1480
},
{
"epoch": 2.93,
"learning_rate": 3.92512077294686e-05,
"loss": 0.3171,
"step": 1485
},
{
"epoch": 2.94,
"learning_rate": 3.919631093544137e-05,
"loss": 0.2864,
"step": 1490
},
{
"epoch": 2.95,
"learning_rate": 3.9141414141414145e-05,
"loss": 0.3201,
"step": 1495
},
{
"epoch": 2.96,
"learning_rate": 3.908651734738691e-05,
"loss": 0.3013,
"step": 1500
},
{
"epoch": 2.97,
"learning_rate": 3.903162055335969e-05,
"loss": 0.3035,
"step": 1505
},
{
"epoch": 2.98,
"learning_rate": 3.8976723759332456e-05,
"loss": 0.2841,
"step": 1510
},
{
"epoch": 2.99,
"learning_rate": 3.892182696530523e-05,
"loss": 0.315,
"step": 1515
},
{
"epoch": 3.0,
"eval_accuracy": 0.9441899208663057,
"eval_loss": 0.1580982208251953,
"eval_runtime": 55.0236,
"eval_samples_per_second": 130.907,
"eval_steps_per_second": 4.107,
"step": 1519
},
{
"epoch": 3.0,
"learning_rate": 3.8866930171278e-05,
"loss": 0.3133,
"step": 1520
},
{
"epoch": 3.01,
"learning_rate": 3.881203337725077e-05,
"loss": 0.2697,
"step": 1525
},
{
"epoch": 3.02,
"learning_rate": 3.875713658322354e-05,
"loss": 0.296,
"step": 1530
},
{
"epoch": 3.03,
"learning_rate": 3.8702239789196315e-05,
"loss": 0.2538,
"step": 1535
},
{
"epoch": 3.04,
"learning_rate": 3.864734299516908e-05,
"loss": 0.2988,
"step": 1540
},
{
"epoch": 3.05,
"learning_rate": 3.859244620114186e-05,
"loss": 0.2975,
"step": 1545
},
{
"epoch": 3.06,
"learning_rate": 3.8537549407114625e-05,
"loss": 0.2862,
"step": 1550
},
{
"epoch": 3.07,
"learning_rate": 3.84826526130874e-05,
"loss": 0.3158,
"step": 1555
},
{
"epoch": 3.08,
"learning_rate": 3.842775581906017e-05,
"loss": 0.263,
"step": 1560
},
{
"epoch": 3.09,
"learning_rate": 3.837285902503294e-05,
"loss": 0.3284,
"step": 1565
},
{
"epoch": 3.1,
"learning_rate": 3.831796223100571e-05,
"loss": 0.2677,
"step": 1570
},
{
"epoch": 3.11,
"learning_rate": 3.8263065436978484e-05,
"loss": 0.2934,
"step": 1575
},
{
"epoch": 3.12,
"learning_rate": 3.820816864295125e-05,
"loss": 0.2269,
"step": 1580
},
{
"epoch": 3.13,
"learning_rate": 3.8153271848924026e-05,
"loss": 0.3281,
"step": 1585
},
{
"epoch": 3.14,
"learning_rate": 3.8098375054896794e-05,
"loss": 0.2411,
"step": 1590
},
{
"epoch": 3.15,
"learning_rate": 3.804347826086957e-05,
"loss": 0.2978,
"step": 1595
},
{
"epoch": 3.16,
"learning_rate": 3.7988581466842336e-05,
"loss": 0.2954,
"step": 1600
},
{
"epoch": 3.17,
"learning_rate": 3.793368467281511e-05,
"loss": 0.2712,
"step": 1605
},
{
"epoch": 3.18,
"learning_rate": 3.787878787878788e-05,
"loss": 0.2974,
"step": 1610
},
{
"epoch": 3.19,
"learning_rate": 3.782389108476065e-05,
"loss": 0.3113,
"step": 1615
},
{
"epoch": 3.2,
"learning_rate": 3.776899429073342e-05,
"loss": 0.2591,
"step": 1620
},
{
"epoch": 3.21,
"learning_rate": 3.7714097496706196e-05,
"loss": 0.2647,
"step": 1625
},
{
"epoch": 3.22,
"learning_rate": 3.7659200702678963e-05,
"loss": 0.2794,
"step": 1630
},
{
"epoch": 3.23,
"learning_rate": 3.760430390865174e-05,
"loss": 0.3031,
"step": 1635
},
{
"epoch": 3.24,
"learning_rate": 3.7549407114624506e-05,
"loss": 0.2611,
"step": 1640
},
{
"epoch": 3.25,
"learning_rate": 3.749451032059728e-05,
"loss": 0.3101,
"step": 1645
},
{
"epoch": 3.26,
"learning_rate": 3.743961352657005e-05,
"loss": 0.2773,
"step": 1650
},
{
"epoch": 3.27,
"learning_rate": 3.738471673254282e-05,
"loss": 0.3262,
"step": 1655
},
{
"epoch": 3.28,
"learning_rate": 3.732981993851559e-05,
"loss": 0.2893,
"step": 1660
},
{
"epoch": 3.29,
"learning_rate": 3.7274923144488365e-05,
"loss": 0.2995,
"step": 1665
},
{
"epoch": 3.3,
"learning_rate": 3.722002635046113e-05,
"loss": 0.3008,
"step": 1670
},
{
"epoch": 3.31,
"learning_rate": 3.716512955643391e-05,
"loss": 0.2954,
"step": 1675
},
{
"epoch": 3.32,
"learning_rate": 3.7110232762406675e-05,
"loss": 0.3018,
"step": 1680
},
{
"epoch": 3.33,
"learning_rate": 3.705533596837945e-05,
"loss": 0.2914,
"step": 1685
},
{
"epoch": 3.34,
"learning_rate": 3.700043917435222e-05,
"loss": 0.3288,
"step": 1690
},
{
"epoch": 3.35,
"learning_rate": 3.694554238032499e-05,
"loss": 0.2908,
"step": 1695
},
{
"epoch": 3.36,
"learning_rate": 3.689064558629776e-05,
"loss": 0.2563,
"step": 1700
},
{
"epoch": 3.37,
"learning_rate": 3.6835748792270534e-05,
"loss": 0.2733,
"step": 1705
},
{
"epoch": 3.38,
"learning_rate": 3.67808519982433e-05,
"loss": 0.2711,
"step": 1710
},
{
"epoch": 3.39,
"learning_rate": 3.6725955204216077e-05,
"loss": 0.3239,
"step": 1715
},
{
"epoch": 3.4,
"learning_rate": 3.6671058410188844e-05,
"loss": 0.289,
"step": 1720
},
{
"epoch": 3.41,
"learning_rate": 3.661616161616162e-05,
"loss": 0.2647,
"step": 1725
},
{
"epoch": 3.42,
"learning_rate": 3.656126482213439e-05,
"loss": 0.3167,
"step": 1730
},
{
"epoch": 3.43,
"learning_rate": 3.650636802810716e-05,
"loss": 0.2878,
"step": 1735
},
{
"epoch": 3.44,
"learning_rate": 3.645147123407993e-05,
"loss": 0.36,
"step": 1740
},
{
"epoch": 3.45,
"learning_rate": 3.6396574440052703e-05,
"loss": 0.2293,
"step": 1745
},
{
"epoch": 3.46,
"learning_rate": 3.634167764602547e-05,
"loss": 0.2681,
"step": 1750
},
{
"epoch": 3.46,
"learning_rate": 3.6286780851998246e-05,
"loss": 0.3122,
"step": 1755
},
{
"epoch": 3.47,
"learning_rate": 3.6231884057971014e-05,
"loss": 0.2786,
"step": 1760
},
{
"epoch": 3.48,
"learning_rate": 3.617698726394379e-05,
"loss": 0.2393,
"step": 1765
},
{
"epoch": 3.49,
"learning_rate": 3.6122090469916556e-05,
"loss": 0.2756,
"step": 1770
},
{
"epoch": 3.5,
"learning_rate": 3.606719367588933e-05,
"loss": 0.2966,
"step": 1775
},
{
"epoch": 3.51,
"learning_rate": 3.60122968818621e-05,
"loss": 0.2693,
"step": 1780
},
{
"epoch": 3.52,
"learning_rate": 3.595740008783487e-05,
"loss": 0.246,
"step": 1785
},
{
"epoch": 3.53,
"learning_rate": 3.590250329380764e-05,
"loss": 0.254,
"step": 1790
},
{
"epoch": 3.54,
"learning_rate": 3.5847606499780415e-05,
"loss": 0.2764,
"step": 1795
},
{
"epoch": 3.55,
"learning_rate": 3.579270970575318e-05,
"loss": 0.2776,
"step": 1800
},
{
"epoch": 3.56,
"learning_rate": 3.573781291172596e-05,
"loss": 0.2368,
"step": 1805
},
{
"epoch": 3.57,
"learning_rate": 3.5682916117698725e-05,
"loss": 0.3022,
"step": 1810
},
{
"epoch": 3.58,
"learning_rate": 3.56280193236715e-05,
"loss": 0.2784,
"step": 1815
},
{
"epoch": 3.59,
"learning_rate": 3.557312252964427e-05,
"loss": 0.3102,
"step": 1820
},
{
"epoch": 3.6,
"learning_rate": 3.551822573561704e-05,
"loss": 0.2816,
"step": 1825
},
{
"epoch": 3.61,
"learning_rate": 3.546332894158981e-05,
"loss": 0.3343,
"step": 1830
},
{
"epoch": 3.62,
"learning_rate": 3.5408432147562584e-05,
"loss": 0.2906,
"step": 1835
},
{
"epoch": 3.63,
"learning_rate": 3.535353535353535e-05,
"loss": 0.2679,
"step": 1840
},
{
"epoch": 3.64,
"learning_rate": 3.529863855950813e-05,
"loss": 0.252,
"step": 1845
},
{
"epoch": 3.65,
"learning_rate": 3.5243741765480894e-05,
"loss": 0.2851,
"step": 1850
},
{
"epoch": 3.66,
"learning_rate": 3.518884497145367e-05,
"loss": 0.331,
"step": 1855
},
{
"epoch": 3.67,
"learning_rate": 3.513394817742644e-05,
"loss": 0.3088,
"step": 1860
},
{
"epoch": 3.68,
"learning_rate": 3.507905138339921e-05,
"loss": 0.3091,
"step": 1865
},
{
"epoch": 3.69,
"learning_rate": 3.502415458937198e-05,
"loss": 0.296,
"step": 1870
},
{
"epoch": 3.7,
"learning_rate": 3.4969257795344754e-05,
"loss": 0.3127,
"step": 1875
},
{
"epoch": 3.71,
"learning_rate": 3.491436100131753e-05,
"loss": 0.2878,
"step": 1880
},
{
"epoch": 3.72,
"learning_rate": 3.4859464207290296e-05,
"loss": 0.2499,
"step": 1885
},
{
"epoch": 3.73,
"learning_rate": 3.480456741326307e-05,
"loss": 0.2787,
"step": 1890
},
{
"epoch": 3.74,
"learning_rate": 3.474967061923584e-05,
"loss": 0.2589,
"step": 1895
},
{
"epoch": 3.75,
"learning_rate": 3.469477382520861e-05,
"loss": 0.2741,
"step": 1900
},
{
"epoch": 3.76,
"learning_rate": 3.463987703118138e-05,
"loss": 0.2834,
"step": 1905
},
{
"epoch": 3.77,
"learning_rate": 3.4584980237154155e-05,
"loss": 0.254,
"step": 1910
},
{
"epoch": 3.78,
"learning_rate": 3.453008344312692e-05,
"loss": 0.2743,
"step": 1915
},
{
"epoch": 3.79,
"learning_rate": 3.44751866490997e-05,
"loss": 0.2957,
"step": 1920
},
{
"epoch": 3.8,
"learning_rate": 3.4420289855072465e-05,
"loss": 0.2449,
"step": 1925
},
{
"epoch": 3.81,
"learning_rate": 3.436539306104524e-05,
"loss": 0.2753,
"step": 1930
},
{
"epoch": 3.82,
"learning_rate": 3.431049626701801e-05,
"loss": 0.325,
"step": 1935
},
{
"epoch": 3.83,
"learning_rate": 3.425559947299078e-05,
"loss": 0.3038,
"step": 1940
},
{
"epoch": 3.84,
"learning_rate": 3.420070267896355e-05,
"loss": 0.2642,
"step": 1945
},
{
"epoch": 3.85,
"learning_rate": 3.4145805884936324e-05,
"loss": 0.2756,
"step": 1950
},
{
"epoch": 3.86,
"learning_rate": 3.409090909090909e-05,
"loss": 0.2907,
"step": 1955
},
{
"epoch": 3.87,
"learning_rate": 3.403601229688187e-05,
"loss": 0.2647,
"step": 1960
},
{
"epoch": 3.88,
"learning_rate": 3.3981115502854635e-05,
"loss": 0.3021,
"step": 1965
},
{
"epoch": 3.89,
"learning_rate": 3.392621870882741e-05,
"loss": 0.289,
"step": 1970
},
{
"epoch": 3.9,
"learning_rate": 3.387132191480018e-05,
"loss": 0.2339,
"step": 1975
},
{
"epoch": 3.91,
"learning_rate": 3.381642512077295e-05,
"loss": 0.2493,
"step": 1980
},
{
"epoch": 3.92,
"learning_rate": 3.376152832674572e-05,
"loss": 0.2605,
"step": 1985
},
{
"epoch": 3.93,
"learning_rate": 3.3706631532718494e-05,
"loss": 0.2813,
"step": 1990
},
{
"epoch": 3.94,
"learning_rate": 3.365173473869126e-05,
"loss": 0.2456,
"step": 1995
},
{
"epoch": 3.95,
"learning_rate": 3.3596837944664036e-05,
"loss": 0.2886,
"step": 2000
},
{
"epoch": 3.96,
"learning_rate": 3.3541941150636804e-05,
"loss": 0.2504,
"step": 2005
},
{
"epoch": 3.97,
"learning_rate": 3.348704435660958e-05,
"loss": 0.2457,
"step": 2010
},
{
"epoch": 3.98,
"learning_rate": 3.3432147562582346e-05,
"loss": 0.2425,
"step": 2015
},
{
"epoch": 3.99,
"learning_rate": 3.337725076855512e-05,
"loss": 0.2663,
"step": 2020
},
{
"epoch": 4.0,
"learning_rate": 3.332235397452789e-05,
"loss": 0.2674,
"step": 2025
},
{
"epoch": 4.0,
"eval_accuracy": 0.9490490073580452,
"eval_loss": 0.14682187139987946,
"eval_runtime": 54.1375,
"eval_samples_per_second": 133.05,
"eval_steps_per_second": 4.175,
"step": 2026
},
{
"epoch": 4.01,
"learning_rate": 3.326745718050066e-05,
"loss": 0.1938,
"step": 2030
},
{
"epoch": 4.02,
"learning_rate": 3.321256038647343e-05,
"loss": 0.1967,
"step": 2035
},
{
"epoch": 4.03,
"learning_rate": 3.3157663592446205e-05,
"loss": 0.2657,
"step": 2040
},
{
"epoch": 4.04,
"learning_rate": 3.310276679841897e-05,
"loss": 0.2729,
"step": 2045
},
{
"epoch": 4.05,
"learning_rate": 3.304787000439175e-05,
"loss": 0.2918,
"step": 2050
},
{
"epoch": 4.06,
"learning_rate": 3.2992973210364515e-05,
"loss": 0.2435,
"step": 2055
},
{
"epoch": 4.07,
"learning_rate": 3.293807641633729e-05,
"loss": 0.2502,
"step": 2060
},
{
"epoch": 4.08,
"learning_rate": 3.288317962231006e-05,
"loss": 0.2898,
"step": 2065
},
{
"epoch": 4.09,
"learning_rate": 3.282828282828283e-05,
"loss": 0.2745,
"step": 2070
},
{
"epoch": 4.1,
"learning_rate": 3.27733860342556e-05,
"loss": 0.2614,
"step": 2075
},
{
"epoch": 4.11,
"learning_rate": 3.2718489240228375e-05,
"loss": 0.2625,
"step": 2080
},
{
"epoch": 4.12,
"learning_rate": 3.266359244620114e-05,
"loss": 0.2188,
"step": 2085
},
{
"epoch": 4.13,
"learning_rate": 3.260869565217392e-05,
"loss": 0.2431,
"step": 2090
},
{
"epoch": 4.14,
"learning_rate": 3.2553798858146685e-05,
"loss": 0.2829,
"step": 2095
},
{
"epoch": 4.15,
"learning_rate": 3.249890206411946e-05,
"loss": 0.2268,
"step": 2100
},
{
"epoch": 4.16,
"learning_rate": 3.244400527009223e-05,
"loss": 0.2594,
"step": 2105
},
{
"epoch": 4.17,
"learning_rate": 3.2389108476065e-05,
"loss": 0.2283,
"step": 2110
},
{
"epoch": 4.18,
"learning_rate": 3.233421168203777e-05,
"loss": 0.2399,
"step": 2115
},
{
"epoch": 4.19,
"learning_rate": 3.2279314888010544e-05,
"loss": 0.2553,
"step": 2120
},
{
"epoch": 4.2,
"learning_rate": 3.222441809398331e-05,
"loss": 0.282,
"step": 2125
},
{
"epoch": 4.21,
"learning_rate": 3.2169521299956086e-05,
"loss": 0.2523,
"step": 2130
},
{
"epoch": 4.22,
"learning_rate": 3.2114624505928854e-05,
"loss": 0.2307,
"step": 2135
},
{
"epoch": 4.23,
"learning_rate": 3.205972771190163e-05,
"loss": 0.2287,
"step": 2140
},
{
"epoch": 4.23,
"learning_rate": 3.2004830917874396e-05,
"loss": 0.2458,
"step": 2145
},
{
"epoch": 4.24,
"learning_rate": 3.194993412384717e-05,
"loss": 0.2113,
"step": 2150
},
{
"epoch": 4.25,
"learning_rate": 3.189503732981994e-05,
"loss": 0.2573,
"step": 2155
},
{
"epoch": 4.26,
"learning_rate": 3.184014053579271e-05,
"loss": 0.2591,
"step": 2160
},
{
"epoch": 4.27,
"learning_rate": 3.178524374176548e-05,
"loss": 0.2234,
"step": 2165
},
{
"epoch": 4.28,
"learning_rate": 3.1730346947738256e-05,
"loss": 0.2663,
"step": 2170
},
{
"epoch": 4.29,
"learning_rate": 3.167545015371102e-05,
"loss": 0.2881,
"step": 2175
},
{
"epoch": 4.3,
"learning_rate": 3.16205533596838e-05,
"loss": 0.2178,
"step": 2180
},
{
"epoch": 4.31,
"learning_rate": 3.1565656565656566e-05,
"loss": 0.2891,
"step": 2185
},
{
"epoch": 4.32,
"learning_rate": 3.151075977162934e-05,
"loss": 0.2453,
"step": 2190
},
{
"epoch": 4.33,
"learning_rate": 3.145586297760211e-05,
"loss": 0.2665,
"step": 2195
},
{
"epoch": 4.34,
"learning_rate": 3.140096618357488e-05,
"loss": 0.2022,
"step": 2200
},
{
"epoch": 4.35,
"learning_rate": 3.134606938954765e-05,
"loss": 0.2906,
"step": 2205
},
{
"epoch": 4.36,
"learning_rate": 3.1291172595520425e-05,
"loss": 0.2221,
"step": 2210
},
{
"epoch": 4.37,
"learning_rate": 3.123627580149319e-05,
"loss": 0.2012,
"step": 2215
},
{
"epoch": 4.38,
"learning_rate": 3.118137900746597e-05,
"loss": 0.2561,
"step": 2220
},
{
"epoch": 4.39,
"learning_rate": 3.1126482213438735e-05,
"loss": 0.2661,
"step": 2225
},
{
"epoch": 4.4,
"learning_rate": 3.107158541941151e-05,
"loss": 0.225,
"step": 2230
},
{
"epoch": 4.41,
"learning_rate": 3.101668862538428e-05,
"loss": 0.1995,
"step": 2235
},
{
"epoch": 4.42,
"learning_rate": 3.096179183135705e-05,
"loss": 0.2971,
"step": 2240
},
{
"epoch": 4.43,
"learning_rate": 3.090689503732982e-05,
"loss": 0.2892,
"step": 2245
},
{
"epoch": 4.44,
"learning_rate": 3.0851998243302594e-05,
"loss": 0.2248,
"step": 2250
},
{
"epoch": 4.45,
"learning_rate": 3.079710144927536e-05,
"loss": 0.2338,
"step": 2255
},
{
"epoch": 4.46,
"learning_rate": 3.0742204655248136e-05,
"loss": 0.2079,
"step": 2260
},
{
"epoch": 4.47,
"learning_rate": 3.0687307861220904e-05,
"loss": 0.2255,
"step": 2265
},
{
"epoch": 4.48,
"learning_rate": 3.063241106719368e-05,
"loss": 0.2429,
"step": 2270
},
{
"epoch": 4.49,
"learning_rate": 3.0577514273166447e-05,
"loss": 0.2908,
"step": 2275
},
{
"epoch": 4.5,
"learning_rate": 3.052261747913922e-05,
"loss": 0.2378,
"step": 2280
},
{
"epoch": 4.51,
"learning_rate": 3.046772068511199e-05,
"loss": 0.2077,
"step": 2285
},
{
"epoch": 4.52,
"learning_rate": 3.0412823891084763e-05,
"loss": 0.2577,
"step": 2290
},
{
"epoch": 4.53,
"learning_rate": 3.035792709705753e-05,
"loss": 0.2328,
"step": 2295
},
{
"epoch": 4.54,
"learning_rate": 3.0303030303030306e-05,
"loss": 0.2641,
"step": 2300
},
{
"epoch": 4.55,
"learning_rate": 3.0248133509003073e-05,
"loss": 0.2391,
"step": 2305
},
{
"epoch": 4.56,
"learning_rate": 3.0193236714975848e-05,
"loss": 0.2412,
"step": 2310
},
{
"epoch": 4.57,
"learning_rate": 3.0138339920948616e-05,
"loss": 0.2414,
"step": 2315
},
{
"epoch": 4.58,
"learning_rate": 3.008344312692139e-05,
"loss": 0.229,
"step": 2320
},
{
"epoch": 4.59,
"learning_rate": 3.0028546332894158e-05,
"loss": 0.301,
"step": 2325
},
{
"epoch": 4.6,
"learning_rate": 2.9973649538866933e-05,
"loss": 0.2405,
"step": 2330
},
{
"epoch": 4.61,
"learning_rate": 2.99187527448397e-05,
"loss": 0.2183,
"step": 2335
},
{
"epoch": 4.62,
"learning_rate": 2.9863855950812475e-05,
"loss": 0.2528,
"step": 2340
},
{
"epoch": 4.63,
"learning_rate": 2.9808959156785243e-05,
"loss": 0.2866,
"step": 2345
},
{
"epoch": 4.64,
"learning_rate": 2.9754062362758017e-05,
"loss": 0.2639,
"step": 2350
},
{
"epoch": 4.65,
"learning_rate": 2.9699165568730785e-05,
"loss": 0.28,
"step": 2355
},
{
"epoch": 4.66,
"learning_rate": 2.964426877470356e-05,
"loss": 0.2441,
"step": 2360
},
{
"epoch": 4.67,
"learning_rate": 2.9589371980676327e-05,
"loss": 0.3054,
"step": 2365
},
{
"epoch": 4.68,
"learning_rate": 2.9534475186649102e-05,
"loss": 0.2511,
"step": 2370
},
{
"epoch": 4.69,
"learning_rate": 2.947957839262187e-05,
"loss": 0.2416,
"step": 2375
},
{
"epoch": 4.7,
"learning_rate": 2.9424681598594644e-05,
"loss": 0.2269,
"step": 2380
},
{
"epoch": 4.71,
"learning_rate": 2.9369784804567412e-05,
"loss": 0.2288,
"step": 2385
},
{
"epoch": 4.72,
"learning_rate": 2.9314888010540187e-05,
"loss": 0.2765,
"step": 2390
},
{
"epoch": 4.73,
"learning_rate": 2.9259991216512954e-05,
"loss": 0.2638,
"step": 2395
},
{
"epoch": 4.74,
"learning_rate": 2.920509442248573e-05,
"loss": 0.2372,
"step": 2400
},
{
"epoch": 4.75,
"learning_rate": 2.9150197628458497e-05,
"loss": 0.2928,
"step": 2405
},
{
"epoch": 4.76,
"learning_rate": 2.909530083443127e-05,
"loss": 0.3002,
"step": 2410
},
{
"epoch": 4.77,
"learning_rate": 2.904040404040404e-05,
"loss": 0.1989,
"step": 2415
},
{
"epoch": 4.78,
"learning_rate": 2.8985507246376814e-05,
"loss": 0.2392,
"step": 2420
},
{
"epoch": 4.79,
"learning_rate": 2.893061045234958e-05,
"loss": 0.2337,
"step": 2425
},
{
"epoch": 4.8,
"learning_rate": 2.8875713658322356e-05,
"loss": 0.2297,
"step": 2430
},
{
"epoch": 4.81,
"learning_rate": 2.8820816864295124e-05,
"loss": 0.2654,
"step": 2435
},
{
"epoch": 4.82,
"learning_rate": 2.8765920070267898e-05,
"loss": 0.2251,
"step": 2440
},
{
"epoch": 4.83,
"learning_rate": 2.8711023276240666e-05,
"loss": 0.1948,
"step": 2445
},
{
"epoch": 4.84,
"learning_rate": 2.865612648221344e-05,
"loss": 0.2139,
"step": 2450
},
{
"epoch": 4.85,
"learning_rate": 2.860122968818621e-05,
"loss": 0.2555,
"step": 2455
},
{
"epoch": 4.86,
"learning_rate": 2.8546332894158983e-05,
"loss": 0.279,
"step": 2460
},
{
"epoch": 4.87,
"learning_rate": 2.849143610013175e-05,
"loss": 0.2344,
"step": 2465
},
{
"epoch": 4.88,
"learning_rate": 2.8436539306104525e-05,
"loss": 0.236,
"step": 2470
},
{
"epoch": 4.89,
"learning_rate": 2.8381642512077293e-05,
"loss": 0.2628,
"step": 2475
},
{
"epoch": 4.9,
"learning_rate": 2.8326745718050068e-05,
"loss": 0.2676,
"step": 2480
},
{
"epoch": 4.91,
"learning_rate": 2.8271848924022835e-05,
"loss": 0.2553,
"step": 2485
},
{
"epoch": 4.92,
"learning_rate": 2.821695212999561e-05,
"loss": 0.2108,
"step": 2490
},
{
"epoch": 4.93,
"learning_rate": 2.8162055335968378e-05,
"loss": 0.214,
"step": 2495
},
{
"epoch": 4.94,
"learning_rate": 2.8107158541941152e-05,
"loss": 0.2783,
"step": 2500
},
{
"epoch": 4.95,
"learning_rate": 2.805226174791392e-05,
"loss": 0.235,
"step": 2505
},
{
"epoch": 4.96,
"learning_rate": 2.7997364953886694e-05,
"loss": 0.2275,
"step": 2510
},
{
"epoch": 4.97,
"learning_rate": 2.7942468159859466e-05,
"loss": 0.2462,
"step": 2515
},
{
"epoch": 4.98,
"learning_rate": 2.7887571365832237e-05,
"loss": 0.2126,
"step": 2520
},
{
"epoch": 4.99,
"learning_rate": 2.7832674571805008e-05,
"loss": 0.2792,
"step": 2525
},
{
"epoch": 5.0,
"learning_rate": 2.777777777777778e-05,
"loss": 0.2615,
"step": 2530
},
{
"epoch": 5.0,
"eval_accuracy": 0.9561293905317229,
"eval_loss": 0.12448281794786453,
"eval_runtime": 51.2669,
"eval_samples_per_second": 140.5,
"eval_steps_per_second": 4.408,
"step": 2532
},
{
"epoch": 5.0,
"learning_rate": 2.772288098375055e-05,
"loss": 0.2336,
"step": 2535
},
{
"epoch": 5.01,
"learning_rate": 2.766798418972332e-05,
"loss": 0.2125,
"step": 2540
},
{
"epoch": 5.02,
"learning_rate": 2.7613087395696093e-05,
"loss": 0.2391,
"step": 2545
},
{
"epoch": 5.03,
"learning_rate": 2.7558190601668864e-05,
"loss": 0.2131,
"step": 2550
},
{
"epoch": 5.04,
"learning_rate": 2.7503293807641635e-05,
"loss": 0.2108,
"step": 2555
},
{
"epoch": 5.05,
"learning_rate": 2.7448397013614406e-05,
"loss": 0.2425,
"step": 2560
},
{
"epoch": 5.06,
"learning_rate": 2.7393500219587177e-05,
"loss": 0.1914,
"step": 2565
},
{
"epoch": 5.07,
"learning_rate": 2.733860342555995e-05,
"loss": 0.2023,
"step": 2570
},
{
"epoch": 5.08,
"learning_rate": 2.728370663153272e-05,
"loss": 0.224,
"step": 2575
},
{
"epoch": 5.09,
"learning_rate": 2.722880983750549e-05,
"loss": 0.1963,
"step": 2580
},
{
"epoch": 5.1,
"learning_rate": 2.7173913043478262e-05,
"loss": 0.2277,
"step": 2585
},
{
"epoch": 5.11,
"learning_rate": 2.7119016249451033e-05,
"loss": 0.1917,
"step": 2590
},
{
"epoch": 5.12,
"learning_rate": 2.7064119455423804e-05,
"loss": 0.1786,
"step": 2595
},
{
"epoch": 5.13,
"learning_rate": 2.700922266139658e-05,
"loss": 0.2102,
"step": 2600
},
{
"epoch": 5.14,
"learning_rate": 2.6954325867369347e-05,
"loss": 0.2062,
"step": 2605
},
{
"epoch": 5.15,
"learning_rate": 2.689942907334212e-05,
"loss": 0.216,
"step": 2610
},
{
"epoch": 5.16,
"learning_rate": 2.684453227931489e-05,
"loss": 0.2043,
"step": 2615
},
{
"epoch": 5.17,
"learning_rate": 2.6789635485287663e-05,
"loss": 0.1962,
"step": 2620
},
{
"epoch": 5.18,
"learning_rate": 2.673473869126043e-05,
"loss": 0.2229,
"step": 2625
},
{
"epoch": 5.19,
"learning_rate": 2.6679841897233206e-05,
"loss": 0.2573,
"step": 2630
},
{
"epoch": 5.2,
"learning_rate": 2.6624945103205973e-05,
"loss": 0.2302,
"step": 2635
},
{
"epoch": 5.21,
"learning_rate": 2.6570048309178748e-05,
"loss": 0.2261,
"step": 2640
},
{
"epoch": 5.22,
"learning_rate": 2.6515151515151516e-05,
"loss": 0.209,
"step": 2645
},
{
"epoch": 5.23,
"learning_rate": 2.646025472112429e-05,
"loss": 0.3026,
"step": 2650
},
{
"epoch": 5.24,
"learning_rate": 2.6405357927097058e-05,
"loss": 0.197,
"step": 2655
},
{
"epoch": 5.25,
"learning_rate": 2.6350461133069833e-05,
"loss": 0.1836,
"step": 2660
},
{
"epoch": 5.26,
"learning_rate": 2.62955643390426e-05,
"loss": 0.2196,
"step": 2665
},
{
"epoch": 5.27,
"learning_rate": 2.6240667545015375e-05,
"loss": 0.193,
"step": 2670
},
{
"epoch": 5.28,
"learning_rate": 2.6185770750988143e-05,
"loss": 0.2354,
"step": 2675
},
{
"epoch": 5.29,
"learning_rate": 2.6130873956960917e-05,
"loss": 0.2473,
"step": 2680
},
{
"epoch": 5.3,
"learning_rate": 2.6075977162933685e-05,
"loss": 0.2392,
"step": 2685
},
{
"epoch": 5.31,
"learning_rate": 2.602108036890646e-05,
"loss": 0.2063,
"step": 2690
},
{
"epoch": 5.32,
"learning_rate": 2.5966183574879227e-05,
"loss": 0.2476,
"step": 2695
},
{
"epoch": 5.33,
"learning_rate": 2.5911286780852002e-05,
"loss": 0.2662,
"step": 2700
},
{
"epoch": 5.34,
"learning_rate": 2.585638998682477e-05,
"loss": 0.2364,
"step": 2705
},
{
"epoch": 5.35,
"learning_rate": 2.5801493192797544e-05,
"loss": 0.2075,
"step": 2710
},
{
"epoch": 5.36,
"learning_rate": 2.5746596398770312e-05,
"loss": 0.2885,
"step": 2715
},
{
"epoch": 5.37,
"learning_rate": 2.5691699604743087e-05,
"loss": 0.2157,
"step": 2720
},
{
"epoch": 5.38,
"learning_rate": 2.5636802810715854e-05,
"loss": 0.2527,
"step": 2725
},
{
"epoch": 5.39,
"learning_rate": 2.558190601668863e-05,
"loss": 0.196,
"step": 2730
},
{
"epoch": 5.4,
"learning_rate": 2.5527009222661397e-05,
"loss": 0.2352,
"step": 2735
},
{
"epoch": 5.41,
"learning_rate": 2.547211242863417e-05,
"loss": 0.2429,
"step": 2740
},
{
"epoch": 5.42,
"learning_rate": 2.541721563460694e-05,
"loss": 0.2271,
"step": 2745
},
{
"epoch": 5.43,
"learning_rate": 2.5362318840579714e-05,
"loss": 0.1973,
"step": 2750
},
{
"epoch": 5.44,
"learning_rate": 2.530742204655248e-05,
"loss": 0.2325,
"step": 2755
},
{
"epoch": 5.45,
"learning_rate": 2.5252525252525256e-05,
"loss": 0.2038,
"step": 2760
},
{
"epoch": 5.46,
"learning_rate": 2.5197628458498024e-05,
"loss": 0.2133,
"step": 2765
},
{
"epoch": 5.47,
"learning_rate": 2.5142731664470798e-05,
"loss": 0.2148,
"step": 2770
},
{
"epoch": 5.48,
"learning_rate": 2.5087834870443566e-05,
"loss": 0.2115,
"step": 2775
},
{
"epoch": 5.49,
"learning_rate": 2.503293807641634e-05,
"loss": 0.2091,
"step": 2780
},
{
"epoch": 5.5,
"learning_rate": 2.497804128238911e-05,
"loss": 0.2258,
"step": 2785
},
{
"epoch": 5.51,
"learning_rate": 2.492314448836188e-05,
"loss": 0.2205,
"step": 2790
},
{
"epoch": 5.52,
"learning_rate": 2.486824769433465e-05,
"loss": 0.219,
"step": 2795
},
{
"epoch": 5.53,
"learning_rate": 2.4813350900307422e-05,
"loss": 0.2085,
"step": 2800
},
{
"epoch": 5.54,
"learning_rate": 2.4758454106280193e-05,
"loss": 0.254,
"step": 2805
},
{
"epoch": 5.55,
"learning_rate": 2.4703557312252964e-05,
"loss": 0.2292,
"step": 2810
},
{
"epoch": 5.56,
"learning_rate": 2.4648660518225735e-05,
"loss": 0.2969,
"step": 2815
},
{
"epoch": 5.57,
"learning_rate": 2.4593763724198506e-05,
"loss": 0.2486,
"step": 2820
},
{
"epoch": 5.58,
"learning_rate": 2.4538866930171278e-05,
"loss": 0.2543,
"step": 2825
},
{
"epoch": 5.59,
"learning_rate": 2.448397013614405e-05,
"loss": 0.2197,
"step": 2830
},
{
"epoch": 5.6,
"learning_rate": 2.442907334211682e-05,
"loss": 0.2528,
"step": 2835
},
{
"epoch": 5.61,
"learning_rate": 2.437417654808959e-05,
"loss": 0.2163,
"step": 2840
},
{
"epoch": 5.62,
"learning_rate": 2.4319279754062362e-05,
"loss": 0.2257,
"step": 2845
},
{
"epoch": 5.63,
"learning_rate": 2.4264382960035133e-05,
"loss": 0.255,
"step": 2850
},
{
"epoch": 5.64,
"learning_rate": 2.4209486166007905e-05,
"loss": 0.2043,
"step": 2855
},
{
"epoch": 5.65,
"learning_rate": 2.4154589371980676e-05,
"loss": 0.1934,
"step": 2860
},
{
"epoch": 5.66,
"learning_rate": 2.4099692577953447e-05,
"loss": 0.2678,
"step": 2865
},
{
"epoch": 5.67,
"learning_rate": 2.4044795783926218e-05,
"loss": 0.2449,
"step": 2870
},
{
"epoch": 5.68,
"learning_rate": 2.398989898989899e-05,
"loss": 0.2674,
"step": 2875
},
{
"epoch": 5.69,
"learning_rate": 2.393500219587176e-05,
"loss": 0.263,
"step": 2880
},
{
"epoch": 5.7,
"learning_rate": 2.388010540184453e-05,
"loss": 0.207,
"step": 2885
},
{
"epoch": 5.71,
"learning_rate": 2.3825208607817303e-05,
"loss": 0.236,
"step": 2890
},
{
"epoch": 5.72,
"learning_rate": 2.3770311813790074e-05,
"loss": 0.193,
"step": 2895
},
{
"epoch": 5.73,
"learning_rate": 2.3715415019762845e-05,
"loss": 0.1961,
"step": 2900
},
{
"epoch": 5.74,
"learning_rate": 2.3660518225735616e-05,
"loss": 0.2226,
"step": 2905
},
{
"epoch": 5.75,
"learning_rate": 2.3605621431708387e-05,
"loss": 0.2035,
"step": 2910
},
{
"epoch": 5.76,
"learning_rate": 2.355072463768116e-05,
"loss": 0.2166,
"step": 2915
},
{
"epoch": 5.77,
"learning_rate": 2.349582784365393e-05,
"loss": 0.2369,
"step": 2920
},
{
"epoch": 5.77,
"learning_rate": 2.34409310496267e-05,
"loss": 0.2606,
"step": 2925
},
{
"epoch": 5.78,
"learning_rate": 2.3386034255599472e-05,
"loss": 0.2501,
"step": 2930
},
{
"epoch": 5.79,
"learning_rate": 2.3331137461572243e-05,
"loss": 0.2418,
"step": 2935
},
{
"epoch": 5.8,
"learning_rate": 2.3276240667545014e-05,
"loss": 0.2142,
"step": 2940
},
{
"epoch": 5.81,
"learning_rate": 2.3221343873517785e-05,
"loss": 0.2415,
"step": 2945
},
{
"epoch": 5.82,
"learning_rate": 2.3166447079490557e-05,
"loss": 0.2044,
"step": 2950
},
{
"epoch": 5.83,
"learning_rate": 2.3111550285463328e-05,
"loss": 0.2522,
"step": 2955
},
{
"epoch": 5.84,
"learning_rate": 2.30566534914361e-05,
"loss": 0.2299,
"step": 2960
},
{
"epoch": 5.85,
"learning_rate": 2.300175669740887e-05,
"loss": 0.2184,
"step": 2965
},
{
"epoch": 5.86,
"learning_rate": 2.294685990338164e-05,
"loss": 0.2392,
"step": 2970
},
{
"epoch": 5.87,
"learning_rate": 2.2891963109354412e-05,
"loss": 0.284,
"step": 2975
},
{
"epoch": 5.88,
"learning_rate": 2.2837066315327184e-05,
"loss": 0.2388,
"step": 2980
},
{
"epoch": 5.89,
"learning_rate": 2.2782169521299955e-05,
"loss": 0.2054,
"step": 2985
},
{
"epoch": 5.9,
"learning_rate": 2.272727272727273e-05,
"loss": 0.2397,
"step": 2990
},
{
"epoch": 5.91,
"learning_rate": 2.26723759332455e-05,
"loss": 0.2174,
"step": 2995
},
{
"epoch": 5.92,
"learning_rate": 2.261747913921827e-05,
"loss": 0.2038,
"step": 3000
},
{
"epoch": 5.93,
"learning_rate": 2.2562582345191043e-05,
"loss": 0.2037,
"step": 3005
},
{
"epoch": 5.94,
"learning_rate": 2.2507685551163814e-05,
"loss": 0.2307,
"step": 3010
},
{
"epoch": 5.95,
"learning_rate": 2.2452788757136585e-05,
"loss": 0.1792,
"step": 3015
},
{
"epoch": 5.96,
"learning_rate": 2.2397891963109356e-05,
"loss": 0.2024,
"step": 3020
},
{
"epoch": 5.97,
"learning_rate": 2.2342995169082127e-05,
"loss": 0.2057,
"step": 3025
},
{
"epoch": 5.98,
"learning_rate": 2.22880983750549e-05,
"loss": 0.2315,
"step": 3030
},
{
"epoch": 5.99,
"learning_rate": 2.223320158102767e-05,
"loss": 0.2115,
"step": 3035
},
{
"epoch": 6.0,
"eval_accuracy": 0.9559905594891017,
"eval_loss": 0.12357248365879059,
"eval_runtime": 51.7389,
"eval_samples_per_second": 139.218,
"eval_steps_per_second": 4.368,
"step": 3039
},
{
"epoch": 6.0,
"learning_rate": 2.217830478700044e-05,
"loss": 0.2039,
"step": 3040
},
{
"epoch": 6.01,
"learning_rate": 2.2123407992973212e-05,
"loss": 0.1936,
"step": 3045
},
{
"epoch": 6.02,
"learning_rate": 2.2068511198945983e-05,
"loss": 0.2619,
"step": 3050
},
{
"epoch": 6.03,
"learning_rate": 2.2013614404918754e-05,
"loss": 0.2437,
"step": 3055
},
{
"epoch": 6.04,
"learning_rate": 2.1958717610891526e-05,
"loss": 0.2116,
"step": 3060
},
{
"epoch": 6.05,
"learning_rate": 2.1903820816864297e-05,
"loss": 0.2223,
"step": 3065
},
{
"epoch": 6.06,
"learning_rate": 2.1848924022837068e-05,
"loss": 0.1803,
"step": 3070
},
{
"epoch": 6.07,
"learning_rate": 2.179402722880984e-05,
"loss": 0.22,
"step": 3075
},
{
"epoch": 6.08,
"learning_rate": 2.173913043478261e-05,
"loss": 0.1908,
"step": 3080
},
{
"epoch": 6.09,
"learning_rate": 2.168423364075538e-05,
"loss": 0.2056,
"step": 3085
},
{
"epoch": 6.1,
"learning_rate": 2.1629336846728153e-05,
"loss": 0.2383,
"step": 3090
},
{
"epoch": 6.11,
"learning_rate": 2.1574440052700924e-05,
"loss": 0.2097,
"step": 3095
},
{
"epoch": 6.12,
"learning_rate": 2.1519543258673695e-05,
"loss": 0.2114,
"step": 3100
},
{
"epoch": 6.13,
"learning_rate": 2.1464646464646466e-05,
"loss": 0.2131,
"step": 3105
},
{
"epoch": 6.14,
"learning_rate": 2.1409749670619237e-05,
"loss": 0.2345,
"step": 3110
},
{
"epoch": 6.15,
"learning_rate": 2.1354852876592008e-05,
"loss": 0.2012,
"step": 3115
},
{
"epoch": 6.16,
"learning_rate": 2.129995608256478e-05,
"loss": 0.2152,
"step": 3120
},
{
"epoch": 6.17,
"learning_rate": 2.124505928853755e-05,
"loss": 0.2218,
"step": 3125
},
{
"epoch": 6.18,
"learning_rate": 2.1190162494510322e-05,
"loss": 0.2006,
"step": 3130
},
{
"epoch": 6.19,
"learning_rate": 2.1135265700483093e-05,
"loss": 0.2049,
"step": 3135
},
{
"epoch": 6.2,
"learning_rate": 2.1080368906455864e-05,
"loss": 0.1926,
"step": 3140
},
{
"epoch": 6.21,
"learning_rate": 2.1025472112428635e-05,
"loss": 0.1766,
"step": 3145
},
{
"epoch": 6.22,
"learning_rate": 2.0970575318401406e-05,
"loss": 0.2113,
"step": 3150
},
{
"epoch": 6.23,
"learning_rate": 2.0915678524374178e-05,
"loss": 0.2244,
"step": 3155
},
{
"epoch": 6.24,
"learning_rate": 2.086078173034695e-05,
"loss": 0.2165,
"step": 3160
},
{
"epoch": 6.25,
"learning_rate": 2.080588493631972e-05,
"loss": 0.1999,
"step": 3165
},
{
"epoch": 6.26,
"learning_rate": 2.075098814229249e-05,
"loss": 0.2218,
"step": 3170
},
{
"epoch": 6.27,
"learning_rate": 2.0696091348265262e-05,
"loss": 0.1994,
"step": 3175
},
{
"epoch": 6.28,
"learning_rate": 2.0641194554238033e-05,
"loss": 0.1961,
"step": 3180
},
{
"epoch": 6.29,
"learning_rate": 2.0586297760210805e-05,
"loss": 0.2465,
"step": 3185
},
{
"epoch": 6.3,
"learning_rate": 2.0531400966183576e-05,
"loss": 0.2212,
"step": 3190
},
{
"epoch": 6.31,
"learning_rate": 2.0476504172156347e-05,
"loss": 0.2409,
"step": 3195
},
{
"epoch": 6.32,
"learning_rate": 2.0421607378129118e-05,
"loss": 0.1848,
"step": 3200
},
{
"epoch": 6.33,
"learning_rate": 2.036671058410189e-05,
"loss": 0.2033,
"step": 3205
},
{
"epoch": 6.34,
"learning_rate": 2.031181379007466e-05,
"loss": 0.1974,
"step": 3210
},
{
"epoch": 6.35,
"learning_rate": 2.025691699604743e-05,
"loss": 0.2438,
"step": 3215
},
{
"epoch": 6.36,
"learning_rate": 2.0202020202020203e-05,
"loss": 0.2161,
"step": 3220
},
{
"epoch": 6.37,
"learning_rate": 2.0147123407992974e-05,
"loss": 0.2211,
"step": 3225
},
{
"epoch": 6.38,
"learning_rate": 2.0092226613965745e-05,
"loss": 0.2201,
"step": 3230
},
{
"epoch": 6.39,
"learning_rate": 2.0037329819938516e-05,
"loss": 0.1997,
"step": 3235
},
{
"epoch": 6.4,
"learning_rate": 1.9982433025911287e-05,
"loss": 0.2191,
"step": 3240
},
{
"epoch": 6.41,
"learning_rate": 1.992753623188406e-05,
"loss": 0.2317,
"step": 3245
},
{
"epoch": 6.42,
"learning_rate": 1.987263943785683e-05,
"loss": 0.1966,
"step": 3250
},
{
"epoch": 6.43,
"learning_rate": 1.98177426438296e-05,
"loss": 0.2154,
"step": 3255
},
{
"epoch": 6.44,
"learning_rate": 1.9762845849802372e-05,
"loss": 0.1904,
"step": 3260
},
{
"epoch": 6.45,
"learning_rate": 1.9707949055775143e-05,
"loss": 0.2209,
"step": 3265
},
{
"epoch": 6.46,
"learning_rate": 1.9653052261747914e-05,
"loss": 0.2386,
"step": 3270
},
{
"epoch": 6.47,
"learning_rate": 1.9598155467720685e-05,
"loss": 0.1871,
"step": 3275
},
{
"epoch": 6.48,
"learning_rate": 1.9543258673693457e-05,
"loss": 0.2084,
"step": 3280
},
{
"epoch": 6.49,
"learning_rate": 1.9488361879666228e-05,
"loss": 0.2129,
"step": 3285
},
{
"epoch": 6.5,
"learning_rate": 1.9433465085639e-05,
"loss": 0.1722,
"step": 3290
},
{
"epoch": 6.51,
"learning_rate": 1.937856829161177e-05,
"loss": 0.2339,
"step": 3295
},
{
"epoch": 6.52,
"learning_rate": 1.932367149758454e-05,
"loss": 0.2338,
"step": 3300
},
{
"epoch": 6.53,
"learning_rate": 1.9268774703557312e-05,
"loss": 0.2279,
"step": 3305
},
{
"epoch": 6.54,
"learning_rate": 1.9213877909530084e-05,
"loss": 0.2279,
"step": 3310
},
{
"epoch": 6.54,
"learning_rate": 1.9158981115502855e-05,
"loss": 0.2582,
"step": 3315
},
{
"epoch": 6.55,
"learning_rate": 1.9104084321475626e-05,
"loss": 0.2221,
"step": 3320
},
{
"epoch": 6.56,
"learning_rate": 1.9049187527448397e-05,
"loss": 0.2344,
"step": 3325
},
{
"epoch": 6.57,
"learning_rate": 1.8994290733421168e-05,
"loss": 0.1447,
"step": 3330
},
{
"epoch": 6.58,
"learning_rate": 1.893939393939394e-05,
"loss": 0.1777,
"step": 3335
},
{
"epoch": 6.59,
"learning_rate": 1.888449714536671e-05,
"loss": 0.2065,
"step": 3340
},
{
"epoch": 6.6,
"learning_rate": 1.8829600351339482e-05,
"loss": 0.1902,
"step": 3345
},
{
"epoch": 6.61,
"learning_rate": 1.8774703557312253e-05,
"loss": 0.2282,
"step": 3350
},
{
"epoch": 6.62,
"learning_rate": 1.8719806763285024e-05,
"loss": 0.1694,
"step": 3355
},
{
"epoch": 6.63,
"learning_rate": 1.8664909969257795e-05,
"loss": 0.1897,
"step": 3360
},
{
"epoch": 6.64,
"learning_rate": 1.8610013175230566e-05,
"loss": 0.1661,
"step": 3365
},
{
"epoch": 6.65,
"learning_rate": 1.8555116381203338e-05,
"loss": 0.2396,
"step": 3370
},
{
"epoch": 6.66,
"learning_rate": 1.850021958717611e-05,
"loss": 0.1993,
"step": 3375
},
{
"epoch": 6.67,
"learning_rate": 1.844532279314888e-05,
"loss": 0.206,
"step": 3380
},
{
"epoch": 6.68,
"learning_rate": 1.839042599912165e-05,
"loss": 0.2015,
"step": 3385
},
{
"epoch": 6.69,
"learning_rate": 1.8335529205094422e-05,
"loss": 0.2085,
"step": 3390
},
{
"epoch": 6.7,
"learning_rate": 1.8280632411067193e-05,
"loss": 0.1839,
"step": 3395
},
{
"epoch": 6.71,
"learning_rate": 1.8225735617039964e-05,
"loss": 0.2086,
"step": 3400
},
{
"epoch": 6.72,
"learning_rate": 1.8170838823012736e-05,
"loss": 0.222,
"step": 3405
},
{
"epoch": 6.73,
"learning_rate": 1.8115942028985507e-05,
"loss": 0.1971,
"step": 3410
},
{
"epoch": 6.74,
"learning_rate": 1.8061045234958278e-05,
"loss": 0.2444,
"step": 3415
},
{
"epoch": 6.75,
"learning_rate": 1.800614844093105e-05,
"loss": 0.2434,
"step": 3420
},
{
"epoch": 6.76,
"learning_rate": 1.795125164690382e-05,
"loss": 0.2485,
"step": 3425
},
{
"epoch": 6.77,
"learning_rate": 1.789635485287659e-05,
"loss": 0.2072,
"step": 3430
},
{
"epoch": 6.78,
"learning_rate": 1.7841458058849363e-05,
"loss": 0.2063,
"step": 3435
},
{
"epoch": 6.79,
"learning_rate": 1.7786561264822134e-05,
"loss": 0.2136,
"step": 3440
},
{
"epoch": 6.8,
"learning_rate": 1.7731664470794905e-05,
"loss": 0.1954,
"step": 3445
},
{
"epoch": 6.81,
"learning_rate": 1.7676767676767676e-05,
"loss": 0.203,
"step": 3450
},
{
"epoch": 6.82,
"learning_rate": 1.7621870882740447e-05,
"loss": 0.1845,
"step": 3455
},
{
"epoch": 6.83,
"learning_rate": 1.756697408871322e-05,
"loss": 0.163,
"step": 3460
},
{
"epoch": 6.84,
"learning_rate": 1.751207729468599e-05,
"loss": 0.189,
"step": 3465
},
{
"epoch": 6.85,
"learning_rate": 1.7457180500658764e-05,
"loss": 0.2157,
"step": 3470
},
{
"epoch": 6.86,
"learning_rate": 1.7402283706631535e-05,
"loss": 0.1858,
"step": 3475
},
{
"epoch": 6.87,
"learning_rate": 1.7347386912604306e-05,
"loss": 0.1893,
"step": 3480
},
{
"epoch": 6.88,
"learning_rate": 1.7292490118577078e-05,
"loss": 0.1798,
"step": 3485
},
{
"epoch": 6.89,
"learning_rate": 1.723759332454985e-05,
"loss": 0.2043,
"step": 3490
},
{
"epoch": 6.9,
"learning_rate": 1.718269653052262e-05,
"loss": 0.2484,
"step": 3495
},
{
"epoch": 6.91,
"learning_rate": 1.712779973649539e-05,
"loss": 0.2098,
"step": 3500
},
{
"epoch": 6.92,
"learning_rate": 1.7072902942468162e-05,
"loss": 0.1843,
"step": 3505
},
{
"epoch": 6.93,
"learning_rate": 1.7018006148440933e-05,
"loss": 0.213,
"step": 3510
},
{
"epoch": 6.94,
"learning_rate": 1.6963109354413705e-05,
"loss": 0.1658,
"step": 3515
},
{
"epoch": 6.95,
"learning_rate": 1.6908212560386476e-05,
"loss": 0.1834,
"step": 3520
},
{
"epoch": 6.96,
"learning_rate": 1.6853315766359247e-05,
"loss": 0.2144,
"step": 3525
},
{
"epoch": 6.97,
"learning_rate": 1.6798418972332018e-05,
"loss": 0.2105,
"step": 3530
},
{
"epoch": 6.98,
"learning_rate": 1.674352217830479e-05,
"loss": 0.1878,
"step": 3535
},
{
"epoch": 6.99,
"learning_rate": 1.668862538427756e-05,
"loss": 0.171,
"step": 3540
},
{
"epoch": 7.0,
"learning_rate": 1.663372859025033e-05,
"loss": 0.2121,
"step": 3545
},
{
"epoch": 7.0,
"eval_accuracy": 0.9623767874496737,
"eval_loss": 0.1144011914730072,
"eval_runtime": 51.6438,
"eval_samples_per_second": 139.475,
"eval_steps_per_second": 4.376,
"step": 3545
},
{
"epoch": 7.01,
"learning_rate": 1.6578831796223103e-05,
"loss": 0.1758,
"step": 3550
},
{
"epoch": 7.02,
"learning_rate": 1.6523935002195874e-05,
"loss": 0.1976,
"step": 3555
},
{
"epoch": 7.03,
"learning_rate": 1.6469038208168645e-05,
"loss": 0.2239,
"step": 3560
},
{
"epoch": 7.04,
"learning_rate": 1.6414141414141416e-05,
"loss": 0.2128,
"step": 3565
},
{
"epoch": 7.05,
"learning_rate": 1.6359244620114187e-05,
"loss": 0.1668,
"step": 3570
},
{
"epoch": 7.06,
"learning_rate": 1.630434782608696e-05,
"loss": 0.2042,
"step": 3575
},
{
"epoch": 7.07,
"learning_rate": 1.624945103205973e-05,
"loss": 0.163,
"step": 3580
},
{
"epoch": 7.08,
"learning_rate": 1.61945542380325e-05,
"loss": 0.1947,
"step": 3585
},
{
"epoch": 7.09,
"learning_rate": 1.6139657444005272e-05,
"loss": 0.2136,
"step": 3590
},
{
"epoch": 7.1,
"learning_rate": 1.6084760649978043e-05,
"loss": 0.1931,
"step": 3595
},
{
"epoch": 7.11,
"learning_rate": 1.6029863855950814e-05,
"loss": 0.1992,
"step": 3600
},
{
"epoch": 7.12,
"learning_rate": 1.5974967061923585e-05,
"loss": 0.1926,
"step": 3605
},
{
"epoch": 7.13,
"learning_rate": 1.5920070267896357e-05,
"loss": 0.1883,
"step": 3610
},
{
"epoch": 7.14,
"learning_rate": 1.5865173473869128e-05,
"loss": 0.1905,
"step": 3615
},
{
"epoch": 7.15,
"learning_rate": 1.58102766798419e-05,
"loss": 0.1806,
"step": 3620
},
{
"epoch": 7.16,
"learning_rate": 1.575537988581467e-05,
"loss": 0.1793,
"step": 3625
},
{
"epoch": 7.17,
"learning_rate": 1.570048309178744e-05,
"loss": 0.1827,
"step": 3630
},
{
"epoch": 7.18,
"learning_rate": 1.5645586297760212e-05,
"loss": 0.226,
"step": 3635
},
{
"epoch": 7.19,
"learning_rate": 1.5590689503732984e-05,
"loss": 0.2125,
"step": 3640
},
{
"epoch": 7.2,
"learning_rate": 1.5535792709705755e-05,
"loss": 0.1769,
"step": 3645
},
{
"epoch": 7.21,
"learning_rate": 1.5480895915678526e-05,
"loss": 0.2294,
"step": 3650
},
{
"epoch": 7.22,
"learning_rate": 1.5425999121651297e-05,
"loss": 0.1822,
"step": 3655
},
{
"epoch": 7.23,
"learning_rate": 1.5371102327624068e-05,
"loss": 0.1867,
"step": 3660
},
{
"epoch": 7.24,
"learning_rate": 1.531620553359684e-05,
"loss": 0.1598,
"step": 3665
},
{
"epoch": 7.25,
"learning_rate": 1.526130873956961e-05,
"loss": 0.1858,
"step": 3670
},
{
"epoch": 7.26,
"learning_rate": 1.5206411945542382e-05,
"loss": 0.2025,
"step": 3675
},
{
"epoch": 7.27,
"learning_rate": 1.5151515151515153e-05,
"loss": 0.1924,
"step": 3680
},
{
"epoch": 7.28,
"learning_rate": 1.5096618357487924e-05,
"loss": 0.2071,
"step": 3685
},
{
"epoch": 7.29,
"learning_rate": 1.5041721563460695e-05,
"loss": 0.1926,
"step": 3690
},
{
"epoch": 7.3,
"learning_rate": 1.4986824769433466e-05,
"loss": 0.1621,
"step": 3695
},
{
"epoch": 7.31,
"learning_rate": 1.4931927975406238e-05,
"loss": 0.1783,
"step": 3700
},
{
"epoch": 7.31,
"learning_rate": 1.4877031181379009e-05,
"loss": 0.1935,
"step": 3705
},
{
"epoch": 7.32,
"learning_rate": 1.482213438735178e-05,
"loss": 0.197,
"step": 3710
},
{
"epoch": 7.33,
"learning_rate": 1.4767237593324551e-05,
"loss": 0.2328,
"step": 3715
},
{
"epoch": 7.34,
"learning_rate": 1.4712340799297322e-05,
"loss": 0.1772,
"step": 3720
},
{
"epoch": 7.35,
"learning_rate": 1.4657444005270093e-05,
"loss": 0.197,
"step": 3725
},
{
"epoch": 7.36,
"learning_rate": 1.4602547211242864e-05,
"loss": 0.1737,
"step": 3730
},
{
"epoch": 7.37,
"learning_rate": 1.4547650417215636e-05,
"loss": 0.1661,
"step": 3735
},
{
"epoch": 7.38,
"learning_rate": 1.4492753623188407e-05,
"loss": 0.1644,
"step": 3740
},
{
"epoch": 7.39,
"learning_rate": 1.4437856829161178e-05,
"loss": 0.1756,
"step": 3745
},
{
"epoch": 7.4,
"learning_rate": 1.4382960035133949e-05,
"loss": 0.1609,
"step": 3750
},
{
"epoch": 7.41,
"learning_rate": 1.432806324110672e-05,
"loss": 0.1839,
"step": 3755
},
{
"epoch": 7.42,
"learning_rate": 1.4273166447079491e-05,
"loss": 0.2365,
"step": 3760
},
{
"epoch": 7.43,
"learning_rate": 1.4218269653052263e-05,
"loss": 0.1859,
"step": 3765
},
{
"epoch": 7.44,
"learning_rate": 1.4163372859025034e-05,
"loss": 0.1761,
"step": 3770
},
{
"epoch": 7.45,
"learning_rate": 1.4108476064997805e-05,
"loss": 0.1886,
"step": 3775
},
{
"epoch": 7.46,
"learning_rate": 1.4053579270970576e-05,
"loss": 0.175,
"step": 3780
},
{
"epoch": 7.47,
"learning_rate": 1.3998682476943347e-05,
"loss": 0.2263,
"step": 3785
},
{
"epoch": 7.48,
"learning_rate": 1.3943785682916118e-05,
"loss": 0.1959,
"step": 3790
},
{
"epoch": 7.49,
"learning_rate": 1.388888888888889e-05,
"loss": 0.2155,
"step": 3795
},
{
"epoch": 7.5,
"learning_rate": 1.383399209486166e-05,
"loss": 0.1916,
"step": 3800
},
{
"epoch": 7.51,
"learning_rate": 1.3779095300834432e-05,
"loss": 0.2154,
"step": 3805
},
{
"epoch": 7.52,
"learning_rate": 1.3724198506807203e-05,
"loss": 0.1921,
"step": 3810
},
{
"epoch": 7.53,
"learning_rate": 1.3669301712779974e-05,
"loss": 0.1969,
"step": 3815
},
{
"epoch": 7.54,
"learning_rate": 1.3614404918752745e-05,
"loss": 0.1884,
"step": 3820
},
{
"epoch": 7.55,
"learning_rate": 1.3559508124725517e-05,
"loss": 0.184,
"step": 3825
},
{
"epoch": 7.56,
"learning_rate": 1.350461133069829e-05,
"loss": 0.2173,
"step": 3830
},
{
"epoch": 7.57,
"learning_rate": 1.344971453667106e-05,
"loss": 0.1653,
"step": 3835
},
{
"epoch": 7.58,
"learning_rate": 1.3394817742643832e-05,
"loss": 0.1994,
"step": 3840
},
{
"epoch": 7.59,
"learning_rate": 1.3339920948616603e-05,
"loss": 0.1895,
"step": 3845
},
{
"epoch": 7.6,
"learning_rate": 1.3285024154589374e-05,
"loss": 0.1764,
"step": 3850
},
{
"epoch": 7.61,
"learning_rate": 1.3230127360562145e-05,
"loss": 0.1722,
"step": 3855
},
{
"epoch": 7.62,
"learning_rate": 1.3175230566534916e-05,
"loss": 0.2353,
"step": 3860
},
{
"epoch": 7.63,
"learning_rate": 1.3120333772507687e-05,
"loss": 0.1534,
"step": 3865
},
{
"epoch": 7.64,
"learning_rate": 1.3065436978480459e-05,
"loss": 0.1782,
"step": 3870
},
{
"epoch": 7.65,
"learning_rate": 1.301054018445323e-05,
"loss": 0.2011,
"step": 3875
},
{
"epoch": 7.66,
"learning_rate": 1.2955643390426001e-05,
"loss": 0.2198,
"step": 3880
},
{
"epoch": 7.67,
"learning_rate": 1.2900746596398772e-05,
"loss": 0.2048,
"step": 3885
},
{
"epoch": 7.68,
"learning_rate": 1.2845849802371543e-05,
"loss": 0.1791,
"step": 3890
},
{
"epoch": 7.69,
"learning_rate": 1.2790953008344314e-05,
"loss": 0.2045,
"step": 3895
},
{
"epoch": 7.7,
"learning_rate": 1.2736056214317086e-05,
"loss": 0.213,
"step": 3900
},
{
"epoch": 7.71,
"learning_rate": 1.2681159420289857e-05,
"loss": 0.1909,
"step": 3905
},
{
"epoch": 7.72,
"learning_rate": 1.2626262626262628e-05,
"loss": 0.1724,
"step": 3910
},
{
"epoch": 7.73,
"learning_rate": 1.2571365832235399e-05,
"loss": 0.1804,
"step": 3915
},
{
"epoch": 7.74,
"learning_rate": 1.251646903820817e-05,
"loss": 0.2074,
"step": 3920
},
{
"epoch": 7.75,
"learning_rate": 1.246157224418094e-05,
"loss": 0.2097,
"step": 3925
},
{
"epoch": 7.76,
"learning_rate": 1.2406675450153711e-05,
"loss": 0.1674,
"step": 3930
},
{
"epoch": 7.77,
"learning_rate": 1.2351778656126482e-05,
"loss": 0.1728,
"step": 3935
},
{
"epoch": 7.78,
"learning_rate": 1.2296881862099253e-05,
"loss": 0.1714,
"step": 3940
},
{
"epoch": 7.79,
"learning_rate": 1.2241985068072024e-05,
"loss": 0.1531,
"step": 3945
},
{
"epoch": 7.8,
"learning_rate": 1.2187088274044796e-05,
"loss": 0.1726,
"step": 3950
},
{
"epoch": 7.81,
"learning_rate": 1.2132191480017567e-05,
"loss": 0.1871,
"step": 3955
},
{
"epoch": 7.82,
"learning_rate": 1.2077294685990338e-05,
"loss": 0.1941,
"step": 3960
},
{
"epoch": 7.83,
"learning_rate": 1.2022397891963109e-05,
"loss": 0.1907,
"step": 3965
},
{
"epoch": 7.84,
"learning_rate": 1.196750109793588e-05,
"loss": 0.2232,
"step": 3970
},
{
"epoch": 7.85,
"learning_rate": 1.1912604303908651e-05,
"loss": 0.1671,
"step": 3975
},
{
"epoch": 7.86,
"learning_rate": 1.1857707509881423e-05,
"loss": 0.1904,
"step": 3980
},
{
"epoch": 7.87,
"learning_rate": 1.1802810715854194e-05,
"loss": 0.18,
"step": 3985
},
{
"epoch": 7.88,
"learning_rate": 1.1747913921826965e-05,
"loss": 0.157,
"step": 3990
},
{
"epoch": 7.89,
"learning_rate": 1.1693017127799736e-05,
"loss": 0.2119,
"step": 3995
},
{
"epoch": 7.9,
"learning_rate": 1.1638120333772507e-05,
"loss": 0.2005,
"step": 4000
},
{
"epoch": 7.91,
"learning_rate": 1.1583223539745278e-05,
"loss": 0.1833,
"step": 4005
},
{
"epoch": 7.92,
"learning_rate": 1.152832674571805e-05,
"loss": 0.2156,
"step": 4010
},
{
"epoch": 7.93,
"learning_rate": 1.147342995169082e-05,
"loss": 0.1768,
"step": 4015
},
{
"epoch": 7.94,
"learning_rate": 1.1418533157663592e-05,
"loss": 0.1668,
"step": 4020
},
{
"epoch": 7.95,
"learning_rate": 1.1363636363636365e-05,
"loss": 0.1708,
"step": 4025
},
{
"epoch": 7.96,
"learning_rate": 1.1308739569609136e-05,
"loss": 0.1699,
"step": 4030
},
{
"epoch": 7.97,
"learning_rate": 1.1253842775581907e-05,
"loss": 0.1839,
"step": 4035
},
{
"epoch": 7.98,
"learning_rate": 1.1198945981554678e-05,
"loss": 0.1849,
"step": 4040
},
{
"epoch": 7.99,
"learning_rate": 1.114404918752745e-05,
"loss": 0.1974,
"step": 4045
},
{
"epoch": 8.0,
"learning_rate": 1.108915239350022e-05,
"loss": 0.2053,
"step": 4050
},
{
"epoch": 8.0,
"eval_accuracy": 0.9614049701513259,
"eval_loss": 0.11431404203176498,
"eval_runtime": 51.069,
"eval_samples_per_second": 141.045,
"eval_steps_per_second": 4.425,
"step": 4052
},
{
"epoch": 8.01,
"learning_rate": 1.1034255599472992e-05,
"loss": 0.1923,
"step": 4055
},
{
"epoch": 8.02,
"learning_rate": 1.0979358805445763e-05,
"loss": 0.1585,
"step": 4060
},
{
"epoch": 8.03,
"learning_rate": 1.0924462011418534e-05,
"loss": 0.1563,
"step": 4065
},
{
"epoch": 8.04,
"learning_rate": 1.0869565217391305e-05,
"loss": 0.189,
"step": 4070
},
{
"epoch": 8.05,
"learning_rate": 1.0814668423364076e-05,
"loss": 0.219,
"step": 4075
},
{
"epoch": 8.06,
"learning_rate": 1.0759771629336847e-05,
"loss": 0.2097,
"step": 4080
},
{
"epoch": 8.07,
"learning_rate": 1.0704874835309619e-05,
"loss": 0.1607,
"step": 4085
},
{
"epoch": 8.08,
"learning_rate": 1.064997804128239e-05,
"loss": 0.1497,
"step": 4090
},
{
"epoch": 8.08,
"learning_rate": 1.0595081247255161e-05,
"loss": 0.1723,
"step": 4095
},
{
"epoch": 8.09,
"learning_rate": 1.0540184453227932e-05,
"loss": 0.2022,
"step": 4100
},
{
"epoch": 8.1,
"learning_rate": 1.0485287659200703e-05,
"loss": 0.1984,
"step": 4105
},
{
"epoch": 8.11,
"learning_rate": 1.0430390865173474e-05,
"loss": 0.1892,
"step": 4110
},
{
"epoch": 8.12,
"learning_rate": 1.0375494071146246e-05,
"loss": 0.1777,
"step": 4115
},
{
"epoch": 8.13,
"learning_rate": 1.0320597277119017e-05,
"loss": 0.1985,
"step": 4120
},
{
"epoch": 8.14,
"learning_rate": 1.0265700483091788e-05,
"loss": 0.1856,
"step": 4125
},
{
"epoch": 8.15,
"learning_rate": 1.0210803689064559e-05,
"loss": 0.1375,
"step": 4130
},
{
"epoch": 8.16,
"learning_rate": 1.015590689503733e-05,
"loss": 0.1704,
"step": 4135
},
{
"epoch": 8.17,
"learning_rate": 1.0101010101010101e-05,
"loss": 0.1713,
"step": 4140
},
{
"epoch": 8.18,
"learning_rate": 1.0046113306982873e-05,
"loss": 0.1811,
"step": 4145
},
{
"epoch": 8.19,
"learning_rate": 9.991216512955644e-06,
"loss": 0.1597,
"step": 4150
},
{
"epoch": 8.2,
"learning_rate": 9.936319718928415e-06,
"loss": 0.162,
"step": 4155
},
{
"epoch": 8.21,
"learning_rate": 9.881422924901186e-06,
"loss": 0.176,
"step": 4160
},
{
"epoch": 8.22,
"learning_rate": 9.826526130873957e-06,
"loss": 0.1772,
"step": 4165
},
{
"epoch": 8.23,
"learning_rate": 9.771629336846728e-06,
"loss": 0.21,
"step": 4170
},
{
"epoch": 8.24,
"learning_rate": 9.7167325428195e-06,
"loss": 0.1877,
"step": 4175
},
{
"epoch": 8.25,
"learning_rate": 9.66183574879227e-06,
"loss": 0.1819,
"step": 4180
},
{
"epoch": 8.26,
"learning_rate": 9.606938954765042e-06,
"loss": 0.1813,
"step": 4185
},
{
"epoch": 8.27,
"learning_rate": 9.552042160737813e-06,
"loss": 0.1692,
"step": 4190
},
{
"epoch": 8.28,
"learning_rate": 9.497145366710584e-06,
"loss": 0.1203,
"step": 4195
},
{
"epoch": 8.29,
"learning_rate": 9.442248572683355e-06,
"loss": 0.1589,
"step": 4200
},
{
"epoch": 8.3,
"learning_rate": 9.387351778656126e-06,
"loss": 0.2057,
"step": 4205
},
{
"epoch": 8.31,
"learning_rate": 9.332454984628898e-06,
"loss": 0.1631,
"step": 4210
},
{
"epoch": 8.32,
"learning_rate": 9.277558190601669e-06,
"loss": 0.1513,
"step": 4215
},
{
"epoch": 8.33,
"learning_rate": 9.22266139657444e-06,
"loss": 0.166,
"step": 4220
},
{
"epoch": 8.34,
"learning_rate": 9.167764602547211e-06,
"loss": 0.1654,
"step": 4225
},
{
"epoch": 8.35,
"learning_rate": 9.112867808519982e-06,
"loss": 0.2081,
"step": 4230
},
{
"epoch": 8.36,
"learning_rate": 9.057971014492753e-06,
"loss": 0.1855,
"step": 4235
},
{
"epoch": 8.37,
"learning_rate": 9.003074220465525e-06,
"loss": 0.1508,
"step": 4240
},
{
"epoch": 8.38,
"learning_rate": 8.948177426438296e-06,
"loss": 0.1636,
"step": 4245
},
{
"epoch": 8.39,
"learning_rate": 8.893280632411067e-06,
"loss": 0.1857,
"step": 4250
},
{
"epoch": 8.4,
"learning_rate": 8.838383838383838e-06,
"loss": 0.1706,
"step": 4255
},
{
"epoch": 8.41,
"learning_rate": 8.78348704435661e-06,
"loss": 0.1654,
"step": 4260
},
{
"epoch": 8.42,
"learning_rate": 8.728590250329382e-06,
"loss": 0.1585,
"step": 4265
},
{
"epoch": 8.43,
"learning_rate": 8.673693456302153e-06,
"loss": 0.1734,
"step": 4270
},
{
"epoch": 8.44,
"learning_rate": 8.618796662274924e-06,
"loss": 0.1785,
"step": 4275
},
{
"epoch": 8.45,
"learning_rate": 8.563899868247696e-06,
"loss": 0.192,
"step": 4280
},
{
"epoch": 8.46,
"learning_rate": 8.509003074220467e-06,
"loss": 0.1908,
"step": 4285
},
{
"epoch": 8.47,
"learning_rate": 8.454106280193238e-06,
"loss": 0.1438,
"step": 4290
},
{
"epoch": 8.48,
"learning_rate": 8.399209486166009e-06,
"loss": 0.1642,
"step": 4295
},
{
"epoch": 8.49,
"learning_rate": 8.34431269213878e-06,
"loss": 0.1757,
"step": 4300
},
{
"epoch": 8.5,
"learning_rate": 8.289415898111551e-06,
"loss": 0.1518,
"step": 4305
},
{
"epoch": 8.51,
"learning_rate": 8.234519104084322e-06,
"loss": 0.1811,
"step": 4310
},
{
"epoch": 8.52,
"learning_rate": 8.179622310057094e-06,
"loss": 0.201,
"step": 4315
},
{
"epoch": 8.53,
"learning_rate": 8.124725516029865e-06,
"loss": 0.182,
"step": 4320
},
{
"epoch": 8.54,
"learning_rate": 8.069828722002636e-06,
"loss": 0.1848,
"step": 4325
},
{
"epoch": 8.55,
"learning_rate": 8.014931927975407e-06,
"loss": 0.1549,
"step": 4330
},
{
"epoch": 8.56,
"learning_rate": 7.960035133948178e-06,
"loss": 0.1816,
"step": 4335
},
{
"epoch": 8.57,
"learning_rate": 7.90513833992095e-06,
"loss": 0.1813,
"step": 4340
},
{
"epoch": 8.58,
"learning_rate": 7.85024154589372e-06,
"loss": 0.2008,
"step": 4345
},
{
"epoch": 8.59,
"learning_rate": 7.795344751866492e-06,
"loss": 0.1562,
"step": 4350
},
{
"epoch": 8.6,
"learning_rate": 7.740447957839263e-06,
"loss": 0.1778,
"step": 4355
},
{
"epoch": 8.61,
"learning_rate": 7.685551163812034e-06,
"loss": 0.2054,
"step": 4360
},
{
"epoch": 8.62,
"learning_rate": 7.630654369784805e-06,
"loss": 0.1477,
"step": 4365
},
{
"epoch": 8.63,
"learning_rate": 7.5757575757575764e-06,
"loss": 0.165,
"step": 4370
},
{
"epoch": 8.64,
"learning_rate": 7.520860781730348e-06,
"loss": 0.1847,
"step": 4375
},
{
"epoch": 8.65,
"learning_rate": 7.465963987703119e-06,
"loss": 0.1839,
"step": 4380
},
{
"epoch": 8.66,
"learning_rate": 7.41106719367589e-06,
"loss": 0.1719,
"step": 4385
},
{
"epoch": 8.67,
"learning_rate": 7.356170399648661e-06,
"loss": 0.1688,
"step": 4390
},
{
"epoch": 8.68,
"learning_rate": 7.301273605621432e-06,
"loss": 0.1799,
"step": 4395
},
{
"epoch": 8.69,
"learning_rate": 7.246376811594203e-06,
"loss": 0.164,
"step": 4400
},
{
"epoch": 8.7,
"learning_rate": 7.1914800175669746e-06,
"loss": 0.2199,
"step": 4405
},
{
"epoch": 8.71,
"learning_rate": 7.136583223539746e-06,
"loss": 0.2112,
"step": 4410
},
{
"epoch": 8.72,
"learning_rate": 7.081686429512517e-06,
"loss": 0.1747,
"step": 4415
},
{
"epoch": 8.73,
"learning_rate": 7.026789635485288e-06,
"loss": 0.1584,
"step": 4420
},
{
"epoch": 8.74,
"learning_rate": 6.971892841458059e-06,
"loss": 0.2012,
"step": 4425
},
{
"epoch": 8.75,
"learning_rate": 6.91699604743083e-06,
"loss": 0.1748,
"step": 4430
},
{
"epoch": 8.76,
"learning_rate": 6.8620992534036015e-06,
"loss": 0.1748,
"step": 4435
},
{
"epoch": 8.77,
"learning_rate": 6.807202459376373e-06,
"loss": 0.1671,
"step": 4440
},
{
"epoch": 8.78,
"learning_rate": 6.752305665349145e-06,
"loss": 0.1937,
"step": 4445
},
{
"epoch": 8.79,
"learning_rate": 6.697408871321916e-06,
"loss": 0.1355,
"step": 4450
},
{
"epoch": 8.8,
"learning_rate": 6.642512077294687e-06,
"loss": 0.1671,
"step": 4455
},
{
"epoch": 8.81,
"learning_rate": 6.587615283267458e-06,
"loss": 0.1475,
"step": 4460
},
{
"epoch": 8.82,
"learning_rate": 6.532718489240229e-06,
"loss": 0.1452,
"step": 4465
},
{
"epoch": 8.83,
"learning_rate": 6.4778216952130005e-06,
"loss": 0.1702,
"step": 4470
},
{
"epoch": 8.84,
"learning_rate": 6.422924901185772e-06,
"loss": 0.1963,
"step": 4475
},
{
"epoch": 8.85,
"learning_rate": 6.368028107158543e-06,
"loss": 0.1625,
"step": 4480
},
{
"epoch": 8.85,
"learning_rate": 6.313131313131314e-06,
"loss": 0.1307,
"step": 4485
},
{
"epoch": 8.86,
"learning_rate": 6.258234519104085e-06,
"loss": 0.1634,
"step": 4490
},
{
"epoch": 8.87,
"learning_rate": 6.2033377250768554e-06,
"loss": 0.2081,
"step": 4495
},
{
"epoch": 8.88,
"learning_rate": 6.148440931049627e-06,
"loss": 0.1818,
"step": 4500
},
{
"epoch": 8.89,
"learning_rate": 6.093544137022398e-06,
"loss": 0.1427,
"step": 4505
},
{
"epoch": 8.9,
"learning_rate": 6.038647342995169e-06,
"loss": 0.2032,
"step": 4510
},
{
"epoch": 8.91,
"learning_rate": 5.98375054896794e-06,
"loss": 0.2115,
"step": 4515
},
{
"epoch": 8.92,
"learning_rate": 5.928853754940711e-06,
"loss": 0.1963,
"step": 4520
},
{
"epoch": 8.93,
"learning_rate": 5.873956960913482e-06,
"loss": 0.1727,
"step": 4525
},
{
"epoch": 8.94,
"learning_rate": 5.8190601668862536e-06,
"loss": 0.1795,
"step": 4530
},
{
"epoch": 8.95,
"learning_rate": 5.764163372859025e-06,
"loss": 0.1891,
"step": 4535
},
{
"epoch": 8.96,
"learning_rate": 5.709266578831796e-06,
"loss": 0.1593,
"step": 4540
},
{
"epoch": 8.97,
"learning_rate": 5.654369784804568e-06,
"loss": 0.134,
"step": 4545
},
{
"epoch": 8.98,
"learning_rate": 5.599472990777339e-06,
"loss": 0.2108,
"step": 4550
},
{
"epoch": 8.99,
"learning_rate": 5.54457619675011e-06,
"loss": 0.1576,
"step": 4555
},
{
"epoch": 9.0,
"eval_accuracy": 0.9661252256004442,
"eval_loss": 0.10865508764982224,
"eval_runtime": 51.0506,
"eval_samples_per_second": 141.095,
"eval_steps_per_second": 4.427,
"step": 4558
},
{
"epoch": 9.0,
"learning_rate": 5.489679402722881e-06,
"loss": 0.1562,
"step": 4560
},
{
"epoch": 9.01,
"learning_rate": 5.4347826086956525e-06,
"loss": 0.1787,
"step": 4565
},
{
"epoch": 9.02,
"learning_rate": 5.379885814668424e-06,
"loss": 0.1655,
"step": 4570
},
{
"epoch": 9.03,
"learning_rate": 5.324989020641195e-06,
"loss": 0.205,
"step": 4575
},
{
"epoch": 9.04,
"learning_rate": 5.270092226613966e-06,
"loss": 0.1784,
"step": 4580
},
{
"epoch": 9.05,
"learning_rate": 5.215195432586737e-06,
"loss": 0.1485,
"step": 4585
},
{
"epoch": 9.06,
"learning_rate": 5.160298638559508e-06,
"loss": 0.1755,
"step": 4590
},
{
"epoch": 9.07,
"learning_rate": 5.1054018445322795e-06,
"loss": 0.1725,
"step": 4595
},
{
"epoch": 9.08,
"learning_rate": 5.050505050505051e-06,
"loss": 0.1643,
"step": 4600
},
{
"epoch": 9.09,
"learning_rate": 4.995608256477822e-06,
"loss": 0.1475,
"step": 4605
},
{
"epoch": 9.1,
"learning_rate": 4.940711462450593e-06,
"loss": 0.1811,
"step": 4610
},
{
"epoch": 9.11,
"learning_rate": 4.885814668423364e-06,
"loss": 0.1957,
"step": 4615
},
{
"epoch": 9.12,
"learning_rate": 4.830917874396135e-06,
"loss": 0.1341,
"step": 4620
},
{
"epoch": 9.13,
"learning_rate": 4.7760210803689065e-06,
"loss": 0.1866,
"step": 4625
},
{
"epoch": 9.14,
"learning_rate": 4.721124286341678e-06,
"loss": 0.1947,
"step": 4630
},
{
"epoch": 9.15,
"learning_rate": 4.666227492314449e-06,
"loss": 0.1974,
"step": 4635
},
{
"epoch": 9.16,
"learning_rate": 4.61133069828722e-06,
"loss": 0.1522,
"step": 4640
},
{
"epoch": 9.17,
"learning_rate": 4.556433904259991e-06,
"loss": 0.1691,
"step": 4645
},
{
"epoch": 9.18,
"learning_rate": 4.501537110232762e-06,
"loss": 0.1974,
"step": 4650
},
{
"epoch": 9.19,
"learning_rate": 4.4466403162055334e-06,
"loss": 0.1449,
"step": 4655
},
{
"epoch": 9.2,
"learning_rate": 4.391743522178305e-06,
"loss": 0.1666,
"step": 4660
},
{
"epoch": 9.21,
"learning_rate": 4.336846728151077e-06,
"loss": 0.1505,
"step": 4665
},
{
"epoch": 9.22,
"learning_rate": 4.281949934123848e-06,
"loss": 0.1745,
"step": 4670
},
{
"epoch": 9.23,
"learning_rate": 4.227053140096619e-06,
"loss": 0.1542,
"step": 4675
},
{
"epoch": 9.24,
"learning_rate": 4.17215634606939e-06,
"loss": 0.1625,
"step": 4680
},
{
"epoch": 9.25,
"learning_rate": 4.117259552042161e-06,
"loss": 0.1761,
"step": 4685
},
{
"epoch": 9.26,
"learning_rate": 4.062362758014932e-06,
"loss": 0.1114,
"step": 4690
},
{
"epoch": 9.27,
"learning_rate": 4.0074659639877036e-06,
"loss": 0.2169,
"step": 4695
},
{
"epoch": 9.28,
"learning_rate": 3.952569169960475e-06,
"loss": 0.1946,
"step": 4700
},
{
"epoch": 9.29,
"learning_rate": 3.897672375933246e-06,
"loss": 0.1281,
"step": 4705
},
{
"epoch": 9.3,
"learning_rate": 3.842775581906017e-06,
"loss": 0.2078,
"step": 4710
},
{
"epoch": 9.31,
"learning_rate": 3.7878787878787882e-06,
"loss": 0.2115,
"step": 4715
},
{
"epoch": 9.32,
"learning_rate": 3.7329819938515594e-06,
"loss": 0.203,
"step": 4720
},
{
"epoch": 9.33,
"learning_rate": 3.6780851998243305e-06,
"loss": 0.1916,
"step": 4725
},
{
"epoch": 9.34,
"learning_rate": 3.6231884057971017e-06,
"loss": 0.1747,
"step": 4730
},
{
"epoch": 9.35,
"learning_rate": 3.568291611769873e-06,
"loss": 0.1627,
"step": 4735
},
{
"epoch": 9.36,
"learning_rate": 3.513394817742644e-06,
"loss": 0.1454,
"step": 4740
},
{
"epoch": 9.37,
"learning_rate": 3.458498023715415e-06,
"loss": 0.1719,
"step": 4745
},
{
"epoch": 9.38,
"learning_rate": 3.4036012296881863e-06,
"loss": 0.1866,
"step": 4750
},
{
"epoch": 9.39,
"learning_rate": 3.348704435660958e-06,
"loss": 0.2064,
"step": 4755
},
{
"epoch": 9.4,
"learning_rate": 3.293807641633729e-06,
"loss": 0.1783,
"step": 4760
},
{
"epoch": 9.41,
"learning_rate": 3.2389108476065002e-06,
"loss": 0.1662,
"step": 4765
},
{
"epoch": 9.42,
"learning_rate": 3.1840140535792714e-06,
"loss": 0.1372,
"step": 4770
},
{
"epoch": 9.43,
"learning_rate": 3.1291172595520426e-06,
"loss": 0.1827,
"step": 4775
},
{
"epoch": 9.44,
"learning_rate": 3.0742204655248133e-06,
"loss": 0.1585,
"step": 4780
},
{
"epoch": 9.45,
"learning_rate": 3.0193236714975845e-06,
"loss": 0.1872,
"step": 4785
},
{
"epoch": 9.46,
"learning_rate": 2.9644268774703556e-06,
"loss": 0.1632,
"step": 4790
},
{
"epoch": 9.47,
"learning_rate": 2.9095300834431268e-06,
"loss": 0.1642,
"step": 4795
},
{
"epoch": 9.48,
"learning_rate": 2.854633289415898e-06,
"loss": 0.1719,
"step": 4800
},
{
"epoch": 9.49,
"learning_rate": 2.7997364953886695e-06,
"loss": 0.1645,
"step": 4805
},
{
"epoch": 9.5,
"learning_rate": 2.7448397013614407e-06,
"loss": 0.1916,
"step": 4810
},
{
"epoch": 9.51,
"learning_rate": 2.689942907334212e-06,
"loss": 0.2097,
"step": 4815
},
{
"epoch": 9.52,
"learning_rate": 2.635046113306983e-06,
"loss": 0.1856,
"step": 4820
},
{
"epoch": 9.53,
"learning_rate": 2.580149319279754e-06,
"loss": 0.1657,
"step": 4825
},
{
"epoch": 9.54,
"learning_rate": 2.5252525252525253e-06,
"loss": 0.1552,
"step": 4830
},
{
"epoch": 9.55,
"learning_rate": 2.4703557312252965e-06,
"loss": 0.1634,
"step": 4835
},
{
"epoch": 9.56,
"learning_rate": 2.4154589371980677e-06,
"loss": 0.1705,
"step": 4840
},
{
"epoch": 9.57,
"learning_rate": 2.360562143170839e-06,
"loss": 0.1925,
"step": 4845
},
{
"epoch": 9.58,
"learning_rate": 2.30566534914361e-06,
"loss": 0.1783,
"step": 4850
},
{
"epoch": 9.59,
"learning_rate": 2.250768555116381e-06,
"loss": 0.1522,
"step": 4855
},
{
"epoch": 9.6,
"learning_rate": 2.1958717610891523e-06,
"loss": 0.1761,
"step": 4860
},
{
"epoch": 9.61,
"learning_rate": 2.140974967061924e-06,
"loss": 0.1899,
"step": 4865
},
{
"epoch": 9.62,
"learning_rate": 2.086078173034695e-06,
"loss": 0.185,
"step": 4870
},
{
"epoch": 9.62,
"learning_rate": 2.031181379007466e-06,
"loss": 0.1678,
"step": 4875
},
{
"epoch": 9.63,
"learning_rate": 1.9762845849802374e-06,
"loss": 0.1245,
"step": 4880
},
{
"epoch": 9.64,
"learning_rate": 1.9213877909530085e-06,
"loss": 0.1869,
"step": 4885
},
{
"epoch": 9.65,
"learning_rate": 1.8664909969257797e-06,
"loss": 0.1514,
"step": 4890
},
{
"epoch": 9.66,
"learning_rate": 1.8115942028985508e-06,
"loss": 0.1891,
"step": 4895
},
{
"epoch": 9.67,
"learning_rate": 1.756697408871322e-06,
"loss": 0.1682,
"step": 4900
},
{
"epoch": 9.68,
"learning_rate": 1.7018006148440932e-06,
"loss": 0.1885,
"step": 4905
},
{
"epoch": 9.69,
"learning_rate": 1.6469038208168645e-06,
"loss": 0.1438,
"step": 4910
},
{
"epoch": 9.7,
"learning_rate": 1.5920070267896357e-06,
"loss": 0.1409,
"step": 4915
},
{
"epoch": 9.71,
"learning_rate": 1.5371102327624067e-06,
"loss": 0.167,
"step": 4920
},
{
"epoch": 9.72,
"learning_rate": 1.4822134387351778e-06,
"loss": 0.1669,
"step": 4925
},
{
"epoch": 9.73,
"learning_rate": 1.427316644707949e-06,
"loss": 0.1522,
"step": 4930
},
{
"epoch": 9.74,
"learning_rate": 1.3724198506807203e-06,
"loss": 0.1747,
"step": 4935
},
{
"epoch": 9.75,
"learning_rate": 1.3175230566534915e-06,
"loss": 0.1767,
"step": 4940
},
{
"epoch": 9.76,
"learning_rate": 1.2626262626262627e-06,
"loss": 0.1865,
"step": 4945
},
{
"epoch": 9.77,
"learning_rate": 1.2077294685990338e-06,
"loss": 0.1615,
"step": 4950
},
{
"epoch": 9.78,
"learning_rate": 1.152832674571805e-06,
"loss": 0.1499,
"step": 4955
},
{
"epoch": 9.79,
"learning_rate": 1.0979358805445761e-06,
"loss": 0.1756,
"step": 4960
},
{
"epoch": 9.8,
"learning_rate": 1.0430390865173475e-06,
"loss": 0.1407,
"step": 4965
},
{
"epoch": 9.81,
"learning_rate": 9.881422924901187e-07,
"loss": 0.1566,
"step": 4970
},
{
"epoch": 9.82,
"learning_rate": 9.332454984628898e-07,
"loss": 0.1357,
"step": 4975
},
{
"epoch": 9.83,
"learning_rate": 8.78348704435661e-07,
"loss": 0.1629,
"step": 4980
},
{
"epoch": 9.84,
"learning_rate": 8.234519104084323e-07,
"loss": 0.2166,
"step": 4985
},
{
"epoch": 9.85,
"learning_rate": 7.685551163812033e-07,
"loss": 0.1424,
"step": 4990
},
{
"epoch": 9.86,
"learning_rate": 7.136583223539745e-07,
"loss": 0.1453,
"step": 4995
},
{
"epoch": 9.87,
"learning_rate": 6.587615283267458e-07,
"loss": 0.1663,
"step": 5000
},
{
"epoch": 9.88,
"learning_rate": 6.038647342995169e-07,
"loss": 0.1608,
"step": 5005
},
{
"epoch": 9.89,
"learning_rate": 5.489679402722881e-07,
"loss": 0.1588,
"step": 5010
},
{
"epoch": 9.9,
"learning_rate": 4.940711462450593e-07,
"loss": 0.1558,
"step": 5015
},
{
"epoch": 9.91,
"learning_rate": 4.391743522178305e-07,
"loss": 0.1555,
"step": 5020
},
{
"epoch": 9.92,
"learning_rate": 3.8427755819060166e-07,
"loss": 0.1697,
"step": 5025
},
{
"epoch": 9.93,
"learning_rate": 3.293807641633729e-07,
"loss": 0.1898,
"step": 5030
},
{
"epoch": 9.94,
"learning_rate": 2.7448397013614404e-07,
"loss": 0.1328,
"step": 5035
},
{
"epoch": 9.95,
"learning_rate": 2.1958717610891525e-07,
"loss": 0.1841,
"step": 5040
},
{
"epoch": 9.96,
"learning_rate": 1.6469038208168644e-07,
"loss": 0.19,
"step": 5045
},
{
"epoch": 9.97,
"learning_rate": 1.0979358805445763e-07,
"loss": 0.1437,
"step": 5050
},
{
"epoch": 9.98,
"learning_rate": 5.489679402722881e-08,
"loss": 0.1835,
"step": 5055
},
{
"epoch": 9.99,
"learning_rate": 0.0,
"loss": 0.2054,
"step": 5060
},
{
"epoch": 9.99,
"eval_accuracy": 0.9657087324725808,
"eval_loss": 0.10856541246175766,
"eval_runtime": 51.4651,
"eval_samples_per_second": 139.959,
"eval_steps_per_second": 4.391,
"step": 5060
},
{
"epoch": 9.99,
"step": 5060,
"total_flos": 1.6098284322345738e+19,
"train_loss": 0.3068045905574037,
"train_runtime": 10592.7037,
"train_samples_per_second": 61.199,
"train_steps_per_second": 0.478
}
],
"logging_steps": 5,
"max_steps": 5060,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 1.6098284322345738e+19,
"trial_name": null,
"trial_params": null
}