verbosity / trainer_state.json
poojakabber1997's picture
Upload 12 files
9493941
raw
history blame contribute delete
No virus
122 kB
{
"best_metric": 0.386042058467865,
"best_model_checkpoint": "/content/drive/MyDrive/DL/SubModels/verbosity/checkpoint-9850",
"epoch": 10.0,
"global_step": 9850,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.994923857868021e-05,
"loss": 0.5532,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 4.9898477157360406e-05,
"loss": 0.4378,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 4.984771573604061e-05,
"loss": 0.4103,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 4.9796954314720816e-05,
"loss": 0.4301,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 4.9746192893401014e-05,
"loss": 0.3845,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 4.969543147208122e-05,
"loss": 0.4607,
"step": 60
},
{
"epoch": 0.07,
"learning_rate": 4.9644670050761425e-05,
"loss": 0.3689,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 4.959390862944163e-05,
"loss": 0.3972,
"step": 80
},
{
"epoch": 0.09,
"learning_rate": 4.9543147208121835e-05,
"loss": 0.3851,
"step": 90
},
{
"epoch": 0.1,
"learning_rate": 4.949238578680203e-05,
"loss": 0.3504,
"step": 100
},
{
"epoch": 0.11,
"learning_rate": 4.944162436548224e-05,
"loss": 0.3989,
"step": 110
},
{
"epoch": 0.12,
"learning_rate": 4.9390862944162443e-05,
"loss": 0.4199,
"step": 120
},
{
"epoch": 0.13,
"learning_rate": 4.934010152284264e-05,
"loss": 0.3906,
"step": 130
},
{
"epoch": 0.14,
"learning_rate": 4.928934010152285e-05,
"loss": 0.4219,
"step": 140
},
{
"epoch": 0.15,
"learning_rate": 4.9238578680203045e-05,
"loss": 0.4,
"step": 150
},
{
"epoch": 0.16,
"learning_rate": 4.918781725888325e-05,
"loss": 0.4463,
"step": 160
},
{
"epoch": 0.17,
"learning_rate": 4.9137055837563455e-05,
"loss": 0.4171,
"step": 170
},
{
"epoch": 0.18,
"learning_rate": 4.9086294416243654e-05,
"loss": 0.3629,
"step": 180
},
{
"epoch": 0.19,
"learning_rate": 4.903553299492386e-05,
"loss": 0.4211,
"step": 190
},
{
"epoch": 0.2,
"learning_rate": 4.8984771573604064e-05,
"loss": 0.4126,
"step": 200
},
{
"epoch": 0.21,
"learning_rate": 4.893401015228426e-05,
"loss": 0.3225,
"step": 210
},
{
"epoch": 0.22,
"learning_rate": 4.888324873096447e-05,
"loss": 0.4605,
"step": 220
},
{
"epoch": 0.23,
"learning_rate": 4.883248730964467e-05,
"loss": 0.4175,
"step": 230
},
{
"epoch": 0.24,
"learning_rate": 4.878172588832488e-05,
"loss": 0.3844,
"step": 240
},
{
"epoch": 0.25,
"learning_rate": 4.873096446700508e-05,
"loss": 0.4615,
"step": 250
},
{
"epoch": 0.26,
"learning_rate": 4.868020304568528e-05,
"loss": 0.3762,
"step": 260
},
{
"epoch": 0.27,
"learning_rate": 4.8629441624365486e-05,
"loss": 0.4174,
"step": 270
},
{
"epoch": 0.28,
"learning_rate": 4.857868020304569e-05,
"loss": 0.4097,
"step": 280
},
{
"epoch": 0.29,
"learning_rate": 4.852791878172589e-05,
"loss": 0.4264,
"step": 290
},
{
"epoch": 0.3,
"learning_rate": 4.8477157360406095e-05,
"loss": 0.4398,
"step": 300
},
{
"epoch": 0.31,
"learning_rate": 4.842639593908629e-05,
"loss": 0.3588,
"step": 310
},
{
"epoch": 0.32,
"learning_rate": 4.83756345177665e-05,
"loss": 0.4412,
"step": 320
},
{
"epoch": 0.34,
"learning_rate": 4.8324873096446703e-05,
"loss": 0.3612,
"step": 330
},
{
"epoch": 0.35,
"learning_rate": 4.82741116751269e-05,
"loss": 0.3681,
"step": 340
},
{
"epoch": 0.36,
"learning_rate": 4.822335025380711e-05,
"loss": 0.4063,
"step": 350
},
{
"epoch": 0.37,
"learning_rate": 4.817258883248731e-05,
"loss": 0.3721,
"step": 360
},
{
"epoch": 0.38,
"learning_rate": 4.812182741116752e-05,
"loss": 0.4079,
"step": 370
},
{
"epoch": 0.39,
"learning_rate": 4.807106598984772e-05,
"loss": 0.3885,
"step": 380
},
{
"epoch": 0.4,
"learning_rate": 4.802030456852792e-05,
"loss": 0.3781,
"step": 390
},
{
"epoch": 0.41,
"learning_rate": 4.7969543147208126e-05,
"loss": 0.3571,
"step": 400
},
{
"epoch": 0.42,
"learning_rate": 4.791878172588833e-05,
"loss": 0.4309,
"step": 410
},
{
"epoch": 0.43,
"learning_rate": 4.786802030456853e-05,
"loss": 0.45,
"step": 420
},
{
"epoch": 0.44,
"learning_rate": 4.7817258883248734e-05,
"loss": 0.4403,
"step": 430
},
{
"epoch": 0.45,
"learning_rate": 4.776649746192894e-05,
"loss": 0.3797,
"step": 440
},
{
"epoch": 0.46,
"learning_rate": 4.771573604060914e-05,
"loss": 0.4103,
"step": 450
},
{
"epoch": 0.47,
"learning_rate": 4.766497461928934e-05,
"loss": 0.4047,
"step": 460
},
{
"epoch": 0.48,
"learning_rate": 4.761421319796954e-05,
"loss": 0.4097,
"step": 470
},
{
"epoch": 0.49,
"learning_rate": 4.7563451776649746e-05,
"loss": 0.4324,
"step": 480
},
{
"epoch": 0.5,
"learning_rate": 4.751269035532995e-05,
"loss": 0.4119,
"step": 490
},
{
"epoch": 0.51,
"learning_rate": 4.746192893401015e-05,
"loss": 0.4601,
"step": 500
},
{
"epoch": 0.52,
"learning_rate": 4.7411167512690355e-05,
"loss": 0.3864,
"step": 510
},
{
"epoch": 0.53,
"learning_rate": 4.736040609137056e-05,
"loss": 0.3908,
"step": 520
},
{
"epoch": 0.54,
"learning_rate": 4.7309644670050765e-05,
"loss": 0.5185,
"step": 530
},
{
"epoch": 0.55,
"learning_rate": 4.725888324873097e-05,
"loss": 0.4126,
"step": 540
},
{
"epoch": 0.56,
"learning_rate": 4.7208121827411175e-05,
"loss": 0.4078,
"step": 550
},
{
"epoch": 0.57,
"learning_rate": 4.7157360406091374e-05,
"loss": 0.3872,
"step": 560
},
{
"epoch": 0.58,
"learning_rate": 4.710659898477158e-05,
"loss": 0.4159,
"step": 570
},
{
"epoch": 0.59,
"learning_rate": 4.705583756345178e-05,
"loss": 0.3731,
"step": 580
},
{
"epoch": 0.6,
"learning_rate": 4.700507614213198e-05,
"loss": 0.392,
"step": 590
},
{
"epoch": 0.61,
"learning_rate": 4.695431472081219e-05,
"loss": 0.3607,
"step": 600
},
{
"epoch": 0.62,
"learning_rate": 4.6903553299492386e-05,
"loss": 0.4177,
"step": 610
},
{
"epoch": 0.63,
"learning_rate": 4.685279187817259e-05,
"loss": 0.3928,
"step": 620
},
{
"epoch": 0.64,
"learning_rate": 4.6802030456852796e-05,
"loss": 0.4178,
"step": 630
},
{
"epoch": 0.65,
"learning_rate": 4.6751269035532994e-05,
"loss": 0.3755,
"step": 640
},
{
"epoch": 0.66,
"learning_rate": 4.67005076142132e-05,
"loss": 0.4239,
"step": 650
},
{
"epoch": 0.67,
"learning_rate": 4.66497461928934e-05,
"loss": 0.3965,
"step": 660
},
{
"epoch": 0.68,
"learning_rate": 4.65989847715736e-05,
"loss": 0.4498,
"step": 670
},
{
"epoch": 0.69,
"learning_rate": 4.654822335025381e-05,
"loss": 0.3656,
"step": 680
},
{
"epoch": 0.7,
"learning_rate": 4.649746192893401e-05,
"loss": 0.4384,
"step": 690
},
{
"epoch": 0.71,
"learning_rate": 4.644670050761422e-05,
"loss": 0.3932,
"step": 700
},
{
"epoch": 0.72,
"learning_rate": 4.639593908629442e-05,
"loss": 0.4041,
"step": 710
},
{
"epoch": 0.73,
"learning_rate": 4.634517766497462e-05,
"loss": 0.4188,
"step": 720
},
{
"epoch": 0.74,
"learning_rate": 4.629441624365483e-05,
"loss": 0.419,
"step": 730
},
{
"epoch": 0.75,
"learning_rate": 4.6243654822335025e-05,
"loss": 0.4641,
"step": 740
},
{
"epoch": 0.76,
"learning_rate": 4.619289340101523e-05,
"loss": 0.4375,
"step": 750
},
{
"epoch": 0.77,
"learning_rate": 4.6142131979695435e-05,
"loss": 0.3922,
"step": 760
},
{
"epoch": 0.78,
"learning_rate": 4.6091370558375634e-05,
"loss": 0.3871,
"step": 770
},
{
"epoch": 0.79,
"learning_rate": 4.604060913705584e-05,
"loss": 0.3642,
"step": 780
},
{
"epoch": 0.8,
"learning_rate": 4.5989847715736044e-05,
"loss": 0.3959,
"step": 790
},
{
"epoch": 0.81,
"learning_rate": 4.593908629441624e-05,
"loss": 0.4425,
"step": 800
},
{
"epoch": 0.82,
"learning_rate": 4.588832487309645e-05,
"loss": 0.3632,
"step": 810
},
{
"epoch": 0.83,
"learning_rate": 4.583756345177665e-05,
"loss": 0.3658,
"step": 820
},
{
"epoch": 0.84,
"learning_rate": 4.578680203045686e-05,
"loss": 0.4967,
"step": 830
},
{
"epoch": 0.85,
"learning_rate": 4.573604060913706e-05,
"loss": 0.4057,
"step": 840
},
{
"epoch": 0.86,
"learning_rate": 4.568527918781726e-05,
"loss": 0.4152,
"step": 850
},
{
"epoch": 0.87,
"learning_rate": 4.5634517766497466e-05,
"loss": 0.4198,
"step": 860
},
{
"epoch": 0.88,
"learning_rate": 4.558375634517767e-05,
"loss": 0.3987,
"step": 870
},
{
"epoch": 0.89,
"learning_rate": 4.553299492385787e-05,
"loss": 0.3964,
"step": 880
},
{
"epoch": 0.9,
"learning_rate": 4.5482233502538075e-05,
"loss": 0.3831,
"step": 890
},
{
"epoch": 0.91,
"learning_rate": 4.543147208121827e-05,
"loss": 0.4085,
"step": 900
},
{
"epoch": 0.92,
"learning_rate": 4.538071065989848e-05,
"loss": 0.3806,
"step": 910
},
{
"epoch": 0.93,
"learning_rate": 4.532994923857868e-05,
"loss": 0.3584,
"step": 920
},
{
"epoch": 0.94,
"learning_rate": 4.527918781725888e-05,
"loss": 0.3434,
"step": 930
},
{
"epoch": 0.95,
"learning_rate": 4.5228426395939087e-05,
"loss": 0.3882,
"step": 940
},
{
"epoch": 0.96,
"learning_rate": 4.517766497461929e-05,
"loss": 0.3979,
"step": 950
},
{
"epoch": 0.97,
"learning_rate": 4.512690355329949e-05,
"loss": 0.4363,
"step": 960
},
{
"epoch": 0.98,
"learning_rate": 4.5076142131979695e-05,
"loss": 0.3899,
"step": 970
},
{
"epoch": 0.99,
"learning_rate": 4.50253807106599e-05,
"loss": 0.4147,
"step": 980
},
{
"epoch": 1.0,
"eval_accuracy": 0.8571428571428571,
"eval_loss": 0.39593541622161865,
"eval_runtime": 19.8117,
"eval_samples_per_second": 176.664,
"eval_steps_per_second": 22.108,
"step": 985
},
{
"epoch": 1.01,
"learning_rate": 4.4974619289340105e-05,
"loss": 0.3605,
"step": 990
},
{
"epoch": 1.02,
"learning_rate": 4.492385786802031e-05,
"loss": 0.3734,
"step": 1000
},
{
"epoch": 1.03,
"learning_rate": 4.487309644670051e-05,
"loss": 0.3405,
"step": 1010
},
{
"epoch": 1.04,
"learning_rate": 4.4822335025380714e-05,
"loss": 0.4121,
"step": 1020
},
{
"epoch": 1.05,
"learning_rate": 4.477157360406092e-05,
"loss": 0.4162,
"step": 1030
},
{
"epoch": 1.06,
"learning_rate": 4.472081218274112e-05,
"loss": 0.4345,
"step": 1040
},
{
"epoch": 1.07,
"learning_rate": 4.467005076142132e-05,
"loss": 0.4002,
"step": 1050
},
{
"epoch": 1.08,
"learning_rate": 4.461928934010153e-05,
"loss": 0.4233,
"step": 1060
},
{
"epoch": 1.09,
"learning_rate": 4.4568527918781726e-05,
"loss": 0.3661,
"step": 1070
},
{
"epoch": 1.1,
"learning_rate": 4.451776649746193e-05,
"loss": 0.3287,
"step": 1080
},
{
"epoch": 1.11,
"learning_rate": 4.446700507614213e-05,
"loss": 0.4031,
"step": 1090
},
{
"epoch": 1.12,
"learning_rate": 4.4416243654822335e-05,
"loss": 0.3646,
"step": 1100
},
{
"epoch": 1.13,
"learning_rate": 4.436548223350254e-05,
"loss": 0.3925,
"step": 1110
},
{
"epoch": 1.14,
"learning_rate": 4.4314720812182745e-05,
"loss": 0.4058,
"step": 1120
},
{
"epoch": 1.15,
"learning_rate": 4.426395939086295e-05,
"loss": 0.3849,
"step": 1130
},
{
"epoch": 1.16,
"learning_rate": 4.4213197969543155e-05,
"loss": 0.3863,
"step": 1140
},
{
"epoch": 1.17,
"learning_rate": 4.416243654822335e-05,
"loss": 0.4214,
"step": 1150
},
{
"epoch": 1.18,
"learning_rate": 4.411167512690356e-05,
"loss": 0.4409,
"step": 1160
},
{
"epoch": 1.19,
"learning_rate": 4.406091370558376e-05,
"loss": 0.3959,
"step": 1170
},
{
"epoch": 1.2,
"learning_rate": 4.401015228426396e-05,
"loss": 0.3991,
"step": 1180
},
{
"epoch": 1.21,
"learning_rate": 4.395939086294417e-05,
"loss": 0.4443,
"step": 1190
},
{
"epoch": 1.22,
"learning_rate": 4.3908629441624365e-05,
"loss": 0.4043,
"step": 1200
},
{
"epoch": 1.23,
"learning_rate": 4.385786802030457e-05,
"loss": 0.4478,
"step": 1210
},
{
"epoch": 1.24,
"learning_rate": 4.3807106598984776e-05,
"loss": 0.3738,
"step": 1220
},
{
"epoch": 1.25,
"learning_rate": 4.3756345177664974e-05,
"loss": 0.4101,
"step": 1230
},
{
"epoch": 1.26,
"learning_rate": 4.370558375634518e-05,
"loss": 0.3963,
"step": 1240
},
{
"epoch": 1.27,
"learning_rate": 4.365482233502538e-05,
"loss": 0.4278,
"step": 1250
},
{
"epoch": 1.28,
"learning_rate": 4.360406091370558e-05,
"loss": 0.4026,
"step": 1260
},
{
"epoch": 1.29,
"learning_rate": 4.355329949238579e-05,
"loss": 0.4346,
"step": 1270
},
{
"epoch": 1.3,
"learning_rate": 4.350253807106599e-05,
"loss": 0.4034,
"step": 1280
},
{
"epoch": 1.31,
"learning_rate": 4.34517766497462e-05,
"loss": 0.3901,
"step": 1290
},
{
"epoch": 1.32,
"learning_rate": 4.34010152284264e-05,
"loss": 0.3955,
"step": 1300
},
{
"epoch": 1.33,
"learning_rate": 4.33502538071066e-05,
"loss": 0.5117,
"step": 1310
},
{
"epoch": 1.34,
"learning_rate": 4.3299492385786806e-05,
"loss": 0.3806,
"step": 1320
},
{
"epoch": 1.35,
"learning_rate": 4.3248730964467005e-05,
"loss": 0.4294,
"step": 1330
},
{
"epoch": 1.36,
"learning_rate": 4.319796954314721e-05,
"loss": 0.4372,
"step": 1340
},
{
"epoch": 1.37,
"learning_rate": 4.3147208121827415e-05,
"loss": 0.4537,
"step": 1350
},
{
"epoch": 1.38,
"learning_rate": 4.309644670050761e-05,
"loss": 0.3783,
"step": 1360
},
{
"epoch": 1.39,
"learning_rate": 4.304568527918782e-05,
"loss": 0.3754,
"step": 1370
},
{
"epoch": 1.4,
"learning_rate": 4.2994923857868024e-05,
"loss": 0.4043,
"step": 1380
},
{
"epoch": 1.41,
"learning_rate": 4.294416243654822e-05,
"loss": 0.4235,
"step": 1390
},
{
"epoch": 1.42,
"learning_rate": 4.289340101522843e-05,
"loss": 0.3935,
"step": 1400
},
{
"epoch": 1.43,
"learning_rate": 4.284263959390863e-05,
"loss": 0.3714,
"step": 1410
},
{
"epoch": 1.44,
"learning_rate": 4.279187817258884e-05,
"loss": 0.4033,
"step": 1420
},
{
"epoch": 1.45,
"learning_rate": 4.274111675126904e-05,
"loss": 0.2394,
"step": 1430
},
{
"epoch": 1.46,
"learning_rate": 4.269035532994924e-05,
"loss": 0.3611,
"step": 1440
},
{
"epoch": 1.47,
"learning_rate": 4.2639593908629446e-05,
"loss": 0.3919,
"step": 1450
},
{
"epoch": 1.48,
"learning_rate": 4.258883248730965e-05,
"loss": 0.4383,
"step": 1460
},
{
"epoch": 1.49,
"learning_rate": 4.253807106598985e-05,
"loss": 0.3556,
"step": 1470
},
{
"epoch": 1.5,
"learning_rate": 4.2487309644670054e-05,
"loss": 0.3842,
"step": 1480
},
{
"epoch": 1.51,
"learning_rate": 4.243654822335025e-05,
"loss": 0.3229,
"step": 1490
},
{
"epoch": 1.52,
"learning_rate": 4.238578680203046e-05,
"loss": 0.4302,
"step": 1500
},
{
"epoch": 1.53,
"learning_rate": 4.233502538071066e-05,
"loss": 0.471,
"step": 1510
},
{
"epoch": 1.54,
"learning_rate": 4.228426395939086e-05,
"loss": 0.3157,
"step": 1520
},
{
"epoch": 1.55,
"learning_rate": 4.2233502538071066e-05,
"loss": 0.3509,
"step": 1530
},
{
"epoch": 1.56,
"learning_rate": 4.218274111675127e-05,
"loss": 0.3847,
"step": 1540
},
{
"epoch": 1.57,
"learning_rate": 4.213197969543147e-05,
"loss": 0.3995,
"step": 1550
},
{
"epoch": 1.58,
"learning_rate": 4.2081218274111675e-05,
"loss": 0.3945,
"step": 1560
},
{
"epoch": 1.59,
"learning_rate": 4.203045685279188e-05,
"loss": 0.4244,
"step": 1570
},
{
"epoch": 1.6,
"learning_rate": 4.1979695431472085e-05,
"loss": 0.3442,
"step": 1580
},
{
"epoch": 1.61,
"learning_rate": 4.192893401015229e-05,
"loss": 0.313,
"step": 1590
},
{
"epoch": 1.62,
"learning_rate": 4.187817258883249e-05,
"loss": 0.4063,
"step": 1600
},
{
"epoch": 1.63,
"learning_rate": 4.1827411167512694e-05,
"loss": 0.3997,
"step": 1610
},
{
"epoch": 1.64,
"learning_rate": 4.17766497461929e-05,
"loss": 0.3741,
"step": 1620
},
{
"epoch": 1.65,
"learning_rate": 4.17258883248731e-05,
"loss": 0.3801,
"step": 1630
},
{
"epoch": 1.66,
"learning_rate": 4.16751269035533e-05,
"loss": 0.3723,
"step": 1640
},
{
"epoch": 1.68,
"learning_rate": 4.162436548223351e-05,
"loss": 0.428,
"step": 1650
},
{
"epoch": 1.69,
"learning_rate": 4.1573604060913706e-05,
"loss": 0.2968,
"step": 1660
},
{
"epoch": 1.7,
"learning_rate": 4.152284263959391e-05,
"loss": 0.4483,
"step": 1670
},
{
"epoch": 1.71,
"learning_rate": 4.147208121827411e-05,
"loss": 0.4255,
"step": 1680
},
{
"epoch": 1.72,
"learning_rate": 4.1421319796954314e-05,
"loss": 0.3807,
"step": 1690
},
{
"epoch": 1.73,
"learning_rate": 4.137055837563452e-05,
"loss": 0.3724,
"step": 1700
},
{
"epoch": 1.74,
"learning_rate": 4.1319796954314725e-05,
"loss": 0.3777,
"step": 1710
},
{
"epoch": 1.75,
"learning_rate": 4.126903553299493e-05,
"loss": 0.4134,
"step": 1720
},
{
"epoch": 1.76,
"learning_rate": 4.1218274111675135e-05,
"loss": 0.4392,
"step": 1730
},
{
"epoch": 1.77,
"learning_rate": 4.116751269035533e-05,
"loss": 0.3869,
"step": 1740
},
{
"epoch": 1.78,
"learning_rate": 4.111675126903554e-05,
"loss": 0.381,
"step": 1750
},
{
"epoch": 1.79,
"learning_rate": 4.1065989847715737e-05,
"loss": 0.3818,
"step": 1760
},
{
"epoch": 1.8,
"learning_rate": 4.101522842639594e-05,
"loss": 0.3747,
"step": 1770
},
{
"epoch": 1.81,
"learning_rate": 4.096446700507615e-05,
"loss": 0.4192,
"step": 1780
},
{
"epoch": 1.82,
"learning_rate": 4.0913705583756345e-05,
"loss": 0.4194,
"step": 1790
},
{
"epoch": 1.83,
"learning_rate": 4.086294416243655e-05,
"loss": 0.349,
"step": 1800
},
{
"epoch": 1.84,
"learning_rate": 4.0812182741116755e-05,
"loss": 0.4368,
"step": 1810
},
{
"epoch": 1.85,
"learning_rate": 4.0761421319796954e-05,
"loss": 0.3589,
"step": 1820
},
{
"epoch": 1.86,
"learning_rate": 4.071065989847716e-05,
"loss": 0.4052,
"step": 1830
},
{
"epoch": 1.87,
"learning_rate": 4.065989847715736e-05,
"loss": 0.3886,
"step": 1840
},
{
"epoch": 1.88,
"learning_rate": 4.060913705583756e-05,
"loss": 0.3991,
"step": 1850
},
{
"epoch": 1.89,
"learning_rate": 4.055837563451777e-05,
"loss": 0.3755,
"step": 1860
},
{
"epoch": 1.9,
"learning_rate": 4.050761421319797e-05,
"loss": 0.3942,
"step": 1870
},
{
"epoch": 1.91,
"learning_rate": 4.045685279187818e-05,
"loss": 0.3745,
"step": 1880
},
{
"epoch": 1.92,
"learning_rate": 4.040609137055838e-05,
"loss": 0.392,
"step": 1890
},
{
"epoch": 1.93,
"learning_rate": 4.035532994923858e-05,
"loss": 0.3932,
"step": 1900
},
{
"epoch": 1.94,
"learning_rate": 4.0304568527918786e-05,
"loss": 0.4318,
"step": 1910
},
{
"epoch": 1.95,
"learning_rate": 4.0253807106598984e-05,
"loss": 0.3953,
"step": 1920
},
{
"epoch": 1.96,
"learning_rate": 4.020304568527919e-05,
"loss": 0.4037,
"step": 1930
},
{
"epoch": 1.97,
"learning_rate": 4.0152284263959395e-05,
"loss": 0.4069,
"step": 1940
},
{
"epoch": 1.98,
"learning_rate": 4.010152284263959e-05,
"loss": 0.4056,
"step": 1950
},
{
"epoch": 1.99,
"learning_rate": 4.00507614213198e-05,
"loss": 0.3887,
"step": 1960
},
{
"epoch": 2.0,
"learning_rate": 4e-05,
"loss": 0.3803,
"step": 1970
},
{
"epoch": 2.0,
"eval_accuracy": 0.858,
"eval_loss": 0.39155587553977966,
"eval_runtime": 19.7782,
"eval_samples_per_second": 176.962,
"eval_steps_per_second": 22.146,
"step": 1970
},
{
"epoch": 2.01,
"learning_rate": 3.99492385786802e-05,
"loss": 0.3731,
"step": 1980
},
{
"epoch": 2.02,
"learning_rate": 3.989847715736041e-05,
"loss": 0.3964,
"step": 1990
},
{
"epoch": 2.03,
"learning_rate": 3.9847715736040605e-05,
"loss": 0.4343,
"step": 2000
},
{
"epoch": 2.04,
"learning_rate": 3.979695431472081e-05,
"loss": 0.4026,
"step": 2010
},
{
"epoch": 2.05,
"learning_rate": 3.9746192893401015e-05,
"loss": 0.4465,
"step": 2020
},
{
"epoch": 2.06,
"learning_rate": 3.969543147208122e-05,
"loss": 0.405,
"step": 2030
},
{
"epoch": 2.07,
"learning_rate": 3.9644670050761426e-05,
"loss": 0.3498,
"step": 2040
},
{
"epoch": 2.08,
"learning_rate": 3.959390862944163e-05,
"loss": 0.4224,
"step": 2050
},
{
"epoch": 2.09,
"learning_rate": 3.954314720812183e-05,
"loss": 0.3303,
"step": 2060
},
{
"epoch": 2.1,
"learning_rate": 3.9492385786802034e-05,
"loss": 0.3733,
"step": 2070
},
{
"epoch": 2.11,
"learning_rate": 3.944162436548224e-05,
"loss": 0.4184,
"step": 2080
},
{
"epoch": 2.12,
"learning_rate": 3.939086294416244e-05,
"loss": 0.46,
"step": 2090
},
{
"epoch": 2.13,
"learning_rate": 3.934010152284264e-05,
"loss": 0.3706,
"step": 2100
},
{
"epoch": 2.14,
"learning_rate": 3.928934010152284e-05,
"loss": 0.4202,
"step": 2110
},
{
"epoch": 2.15,
"learning_rate": 3.9238578680203046e-05,
"loss": 0.313,
"step": 2120
},
{
"epoch": 2.16,
"learning_rate": 3.918781725888325e-05,
"loss": 0.4384,
"step": 2130
},
{
"epoch": 2.17,
"learning_rate": 3.913705583756345e-05,
"loss": 0.3985,
"step": 2140
},
{
"epoch": 2.18,
"learning_rate": 3.9086294416243655e-05,
"loss": 0.3551,
"step": 2150
},
{
"epoch": 2.19,
"learning_rate": 3.903553299492386e-05,
"loss": 0.3821,
"step": 2160
},
{
"epoch": 2.2,
"learning_rate": 3.8984771573604065e-05,
"loss": 0.39,
"step": 2170
},
{
"epoch": 2.21,
"learning_rate": 3.893401015228427e-05,
"loss": 0.3478,
"step": 2180
},
{
"epoch": 2.22,
"learning_rate": 3.888324873096447e-05,
"loss": 0.4064,
"step": 2190
},
{
"epoch": 2.23,
"learning_rate": 3.8832487309644673e-05,
"loss": 0.4513,
"step": 2200
},
{
"epoch": 2.24,
"learning_rate": 3.878172588832488e-05,
"loss": 0.4007,
"step": 2210
},
{
"epoch": 2.25,
"learning_rate": 3.873096446700508e-05,
"loss": 0.4374,
"step": 2220
},
{
"epoch": 2.26,
"learning_rate": 3.868020304568528e-05,
"loss": 0.3945,
"step": 2230
},
{
"epoch": 2.27,
"learning_rate": 3.862944162436549e-05,
"loss": 0.3578,
"step": 2240
},
{
"epoch": 2.28,
"learning_rate": 3.8578680203045685e-05,
"loss": 0.3728,
"step": 2250
},
{
"epoch": 2.29,
"learning_rate": 3.852791878172589e-05,
"loss": 0.4369,
"step": 2260
},
{
"epoch": 2.3,
"learning_rate": 3.847715736040609e-05,
"loss": 0.4054,
"step": 2270
},
{
"epoch": 2.31,
"learning_rate": 3.8426395939086294e-05,
"loss": 0.3366,
"step": 2280
},
{
"epoch": 2.32,
"learning_rate": 3.83756345177665e-05,
"loss": 0.408,
"step": 2290
},
{
"epoch": 2.34,
"learning_rate": 3.83248730964467e-05,
"loss": 0.4143,
"step": 2300
},
{
"epoch": 2.35,
"learning_rate": 3.82741116751269e-05,
"loss": 0.4403,
"step": 2310
},
{
"epoch": 2.36,
"learning_rate": 3.822335025380711e-05,
"loss": 0.4167,
"step": 2320
},
{
"epoch": 2.37,
"learning_rate": 3.817258883248731e-05,
"loss": 0.3318,
"step": 2330
},
{
"epoch": 2.38,
"learning_rate": 3.812182741116752e-05,
"loss": 0.4405,
"step": 2340
},
{
"epoch": 2.39,
"learning_rate": 3.8071065989847716e-05,
"loss": 0.3928,
"step": 2350
},
{
"epoch": 2.4,
"learning_rate": 3.802030456852792e-05,
"loss": 0.392,
"step": 2360
},
{
"epoch": 2.41,
"learning_rate": 3.7969543147208127e-05,
"loss": 0.3302,
"step": 2370
},
{
"epoch": 2.42,
"learning_rate": 3.7918781725888325e-05,
"loss": 0.36,
"step": 2380
},
{
"epoch": 2.43,
"learning_rate": 3.786802030456853e-05,
"loss": 0.3502,
"step": 2390
},
{
"epoch": 2.44,
"learning_rate": 3.7817258883248735e-05,
"loss": 0.3965,
"step": 2400
},
{
"epoch": 2.45,
"learning_rate": 3.7766497461928933e-05,
"loss": 0.4067,
"step": 2410
},
{
"epoch": 2.46,
"learning_rate": 3.771573604060914e-05,
"loss": 0.3278,
"step": 2420
},
{
"epoch": 2.47,
"learning_rate": 3.766497461928934e-05,
"loss": 0.3779,
"step": 2430
},
{
"epoch": 2.48,
"learning_rate": 3.761421319796954e-05,
"loss": 0.3429,
"step": 2440
},
{
"epoch": 2.49,
"learning_rate": 3.756345177664975e-05,
"loss": 0.3557,
"step": 2450
},
{
"epoch": 2.5,
"learning_rate": 3.751269035532995e-05,
"loss": 0.3995,
"step": 2460
},
{
"epoch": 2.51,
"learning_rate": 3.746192893401016e-05,
"loss": 0.3029,
"step": 2470
},
{
"epoch": 2.52,
"learning_rate": 3.741116751269036e-05,
"loss": 0.3468,
"step": 2480
},
{
"epoch": 2.53,
"learning_rate": 3.736040609137056e-05,
"loss": 0.4119,
"step": 2490
},
{
"epoch": 2.54,
"learning_rate": 3.7309644670050766e-05,
"loss": 0.3773,
"step": 2500
},
{
"epoch": 2.55,
"learning_rate": 3.7258883248730964e-05,
"loss": 0.3299,
"step": 2510
},
{
"epoch": 2.56,
"learning_rate": 3.720812182741117e-05,
"loss": 0.4274,
"step": 2520
},
{
"epoch": 2.57,
"learning_rate": 3.7157360406091374e-05,
"loss": 0.4321,
"step": 2530
},
{
"epoch": 2.58,
"learning_rate": 3.710659898477157e-05,
"loss": 0.3843,
"step": 2540
},
{
"epoch": 2.59,
"learning_rate": 3.705583756345178e-05,
"loss": 0.4113,
"step": 2550
},
{
"epoch": 2.6,
"learning_rate": 3.700507614213198e-05,
"loss": 0.3664,
"step": 2560
},
{
"epoch": 2.61,
"learning_rate": 3.695431472081218e-05,
"loss": 0.3492,
"step": 2570
},
{
"epoch": 2.62,
"learning_rate": 3.6903553299492386e-05,
"loss": 0.3136,
"step": 2580
},
{
"epoch": 2.63,
"learning_rate": 3.6852791878172585e-05,
"loss": 0.4451,
"step": 2590
},
{
"epoch": 2.64,
"learning_rate": 3.680203045685279e-05,
"loss": 0.3288,
"step": 2600
},
{
"epoch": 2.65,
"learning_rate": 3.6751269035532995e-05,
"loss": 0.4154,
"step": 2610
},
{
"epoch": 2.66,
"learning_rate": 3.67005076142132e-05,
"loss": 0.3186,
"step": 2620
},
{
"epoch": 2.67,
"learning_rate": 3.6649746192893405e-05,
"loss": 0.4266,
"step": 2630
},
{
"epoch": 2.68,
"learning_rate": 3.659898477157361e-05,
"loss": 0.3476,
"step": 2640
},
{
"epoch": 2.69,
"learning_rate": 3.654822335025381e-05,
"loss": 0.453,
"step": 2650
},
{
"epoch": 2.7,
"learning_rate": 3.6497461928934014e-05,
"loss": 0.4393,
"step": 2660
},
{
"epoch": 2.71,
"learning_rate": 3.644670050761422e-05,
"loss": 0.4109,
"step": 2670
},
{
"epoch": 2.72,
"learning_rate": 3.639593908629442e-05,
"loss": 0.3821,
"step": 2680
},
{
"epoch": 2.73,
"learning_rate": 3.634517766497462e-05,
"loss": 0.4341,
"step": 2690
},
{
"epoch": 2.74,
"learning_rate": 3.629441624365482e-05,
"loss": 0.4191,
"step": 2700
},
{
"epoch": 2.75,
"learning_rate": 3.6243654822335026e-05,
"loss": 0.3332,
"step": 2710
},
{
"epoch": 2.76,
"learning_rate": 3.619289340101523e-05,
"loss": 0.3688,
"step": 2720
},
{
"epoch": 2.77,
"learning_rate": 3.614213197969543e-05,
"loss": 0.4091,
"step": 2730
},
{
"epoch": 2.78,
"learning_rate": 3.6091370558375634e-05,
"loss": 0.4299,
"step": 2740
},
{
"epoch": 2.79,
"learning_rate": 3.604060913705584e-05,
"loss": 0.401,
"step": 2750
},
{
"epoch": 2.8,
"learning_rate": 3.5989847715736045e-05,
"loss": 0.3687,
"step": 2760
},
{
"epoch": 2.81,
"learning_rate": 3.593908629441625e-05,
"loss": 0.4258,
"step": 2770
},
{
"epoch": 2.82,
"learning_rate": 3.588832487309645e-05,
"loss": 0.4089,
"step": 2780
},
{
"epoch": 2.83,
"learning_rate": 3.583756345177665e-05,
"loss": 0.3714,
"step": 2790
},
{
"epoch": 2.84,
"learning_rate": 3.578680203045686e-05,
"loss": 0.3988,
"step": 2800
},
{
"epoch": 2.85,
"learning_rate": 3.573604060913706e-05,
"loss": 0.3893,
"step": 2810
},
{
"epoch": 2.86,
"learning_rate": 3.568527918781726e-05,
"loss": 0.3374,
"step": 2820
},
{
"epoch": 2.87,
"learning_rate": 3.563451776649747e-05,
"loss": 0.3663,
"step": 2830
},
{
"epoch": 2.88,
"learning_rate": 3.5583756345177665e-05,
"loss": 0.4273,
"step": 2840
},
{
"epoch": 2.89,
"learning_rate": 3.553299492385787e-05,
"loss": 0.3795,
"step": 2850
},
{
"epoch": 2.9,
"learning_rate": 3.548223350253807e-05,
"loss": 0.3177,
"step": 2860
},
{
"epoch": 2.91,
"learning_rate": 3.5431472081218274e-05,
"loss": 0.4003,
"step": 2870
},
{
"epoch": 2.92,
"learning_rate": 3.538071065989848e-05,
"loss": 0.3894,
"step": 2880
},
{
"epoch": 2.93,
"learning_rate": 3.532994923857868e-05,
"loss": 0.3616,
"step": 2890
},
{
"epoch": 2.94,
"learning_rate": 3.527918781725888e-05,
"loss": 0.4411,
"step": 2900
},
{
"epoch": 2.95,
"learning_rate": 3.522842639593909e-05,
"loss": 0.3545,
"step": 2910
},
{
"epoch": 2.96,
"learning_rate": 3.517766497461929e-05,
"loss": 0.4279,
"step": 2920
},
{
"epoch": 2.97,
"learning_rate": 3.51269035532995e-05,
"loss": 0.445,
"step": 2930
},
{
"epoch": 2.98,
"learning_rate": 3.5076142131979696e-05,
"loss": 0.4134,
"step": 2940
},
{
"epoch": 2.99,
"learning_rate": 3.50253807106599e-05,
"loss": 0.4002,
"step": 2950
},
{
"epoch": 3.0,
"eval_accuracy": 0.8568571428571429,
"eval_loss": 0.3892107903957367,
"eval_runtime": 19.8681,
"eval_samples_per_second": 176.162,
"eval_steps_per_second": 22.045,
"step": 2955
},
{
"epoch": 3.01,
"learning_rate": 3.4974619289340106e-05,
"loss": 0.367,
"step": 2960
},
{
"epoch": 3.02,
"learning_rate": 3.4923857868020305e-05,
"loss": 0.3745,
"step": 2970
},
{
"epoch": 3.03,
"learning_rate": 3.487309644670051e-05,
"loss": 0.4265,
"step": 2980
},
{
"epoch": 3.04,
"learning_rate": 3.4822335025380715e-05,
"loss": 0.4277,
"step": 2990
},
{
"epoch": 3.05,
"learning_rate": 3.477157360406091e-05,
"loss": 0.3423,
"step": 3000
},
{
"epoch": 3.06,
"learning_rate": 3.472081218274112e-05,
"loss": 0.4104,
"step": 3010
},
{
"epoch": 3.07,
"learning_rate": 3.467005076142132e-05,
"loss": 0.3992,
"step": 3020
},
{
"epoch": 3.08,
"learning_rate": 3.461928934010152e-05,
"loss": 0.4172,
"step": 3030
},
{
"epoch": 3.09,
"learning_rate": 3.456852791878173e-05,
"loss": 0.3759,
"step": 3040
},
{
"epoch": 3.1,
"learning_rate": 3.451776649746193e-05,
"loss": 0.4048,
"step": 3050
},
{
"epoch": 3.11,
"learning_rate": 3.446700507614214e-05,
"loss": 0.4231,
"step": 3060
},
{
"epoch": 3.12,
"learning_rate": 3.441624365482234e-05,
"loss": 0.4089,
"step": 3070
},
{
"epoch": 3.13,
"learning_rate": 3.436548223350254e-05,
"loss": 0.345,
"step": 3080
},
{
"epoch": 3.14,
"learning_rate": 3.4314720812182746e-05,
"loss": 0.4196,
"step": 3090
},
{
"epoch": 3.15,
"learning_rate": 3.4263959390862944e-05,
"loss": 0.414,
"step": 3100
},
{
"epoch": 3.16,
"learning_rate": 3.421319796954315e-05,
"loss": 0.318,
"step": 3110
},
{
"epoch": 3.17,
"learning_rate": 3.4162436548223354e-05,
"loss": 0.4169,
"step": 3120
},
{
"epoch": 3.18,
"learning_rate": 3.411167512690355e-05,
"loss": 0.4215,
"step": 3130
},
{
"epoch": 3.19,
"learning_rate": 3.406091370558376e-05,
"loss": 0.4421,
"step": 3140
},
{
"epoch": 3.2,
"learning_rate": 3.401015228426396e-05,
"loss": 0.3581,
"step": 3150
},
{
"epoch": 3.21,
"learning_rate": 3.395939086294416e-05,
"loss": 0.3941,
"step": 3160
},
{
"epoch": 3.22,
"learning_rate": 3.3908629441624366e-05,
"loss": 0.4445,
"step": 3170
},
{
"epoch": 3.23,
"learning_rate": 3.385786802030457e-05,
"loss": 0.3477,
"step": 3180
},
{
"epoch": 3.24,
"learning_rate": 3.380710659898477e-05,
"loss": 0.4128,
"step": 3190
},
{
"epoch": 3.25,
"learning_rate": 3.3756345177664975e-05,
"loss": 0.3819,
"step": 3200
},
{
"epoch": 3.26,
"learning_rate": 3.370558375634518e-05,
"loss": 0.3581,
"step": 3210
},
{
"epoch": 3.27,
"learning_rate": 3.3654822335025385e-05,
"loss": 0.4257,
"step": 3220
},
{
"epoch": 3.28,
"learning_rate": 3.360406091370559e-05,
"loss": 0.3836,
"step": 3230
},
{
"epoch": 3.29,
"learning_rate": 3.355329949238579e-05,
"loss": 0.3176,
"step": 3240
},
{
"epoch": 3.3,
"learning_rate": 3.3502538071065994e-05,
"loss": 0.3963,
"step": 3250
},
{
"epoch": 3.31,
"learning_rate": 3.34517766497462e-05,
"loss": 0.469,
"step": 3260
},
{
"epoch": 3.32,
"learning_rate": 3.34010152284264e-05,
"loss": 0.4402,
"step": 3270
},
{
"epoch": 3.33,
"learning_rate": 3.33502538071066e-05,
"loss": 0.361,
"step": 3280
},
{
"epoch": 3.34,
"learning_rate": 3.32994923857868e-05,
"loss": 0.3902,
"step": 3290
},
{
"epoch": 3.35,
"learning_rate": 3.3248730964467006e-05,
"loss": 0.3878,
"step": 3300
},
{
"epoch": 3.36,
"learning_rate": 3.319796954314721e-05,
"loss": 0.3695,
"step": 3310
},
{
"epoch": 3.37,
"learning_rate": 3.314720812182741e-05,
"loss": 0.3654,
"step": 3320
},
{
"epoch": 3.38,
"learning_rate": 3.3096446700507614e-05,
"loss": 0.3482,
"step": 3330
},
{
"epoch": 3.39,
"learning_rate": 3.304568527918782e-05,
"loss": 0.3789,
"step": 3340
},
{
"epoch": 3.4,
"learning_rate": 3.299492385786802e-05,
"loss": 0.3331,
"step": 3350
},
{
"epoch": 3.41,
"learning_rate": 3.294416243654822e-05,
"loss": 0.4221,
"step": 3360
},
{
"epoch": 3.42,
"learning_rate": 3.289340101522843e-05,
"loss": 0.3463,
"step": 3370
},
{
"epoch": 3.43,
"learning_rate": 3.284263959390863e-05,
"loss": 0.3812,
"step": 3380
},
{
"epoch": 3.44,
"learning_rate": 3.279187817258884e-05,
"loss": 0.4034,
"step": 3390
},
{
"epoch": 3.45,
"learning_rate": 3.2741116751269036e-05,
"loss": 0.3488,
"step": 3400
},
{
"epoch": 3.46,
"learning_rate": 3.269035532994924e-05,
"loss": 0.4176,
"step": 3410
},
{
"epoch": 3.47,
"learning_rate": 3.263959390862945e-05,
"loss": 0.4551,
"step": 3420
},
{
"epoch": 3.48,
"learning_rate": 3.2588832487309645e-05,
"loss": 0.3318,
"step": 3430
},
{
"epoch": 3.49,
"learning_rate": 3.253807106598985e-05,
"loss": 0.4266,
"step": 3440
},
{
"epoch": 3.5,
"learning_rate": 3.248730964467005e-05,
"loss": 0.3024,
"step": 3450
},
{
"epoch": 3.51,
"learning_rate": 3.2436548223350254e-05,
"loss": 0.417,
"step": 3460
},
{
"epoch": 3.52,
"learning_rate": 3.238578680203046e-05,
"loss": 0.3731,
"step": 3470
},
{
"epoch": 3.53,
"learning_rate": 3.233502538071066e-05,
"loss": 0.3935,
"step": 3480
},
{
"epoch": 3.54,
"learning_rate": 3.228426395939086e-05,
"loss": 0.4481,
"step": 3490
},
{
"epoch": 3.55,
"learning_rate": 3.223350253807107e-05,
"loss": 0.3675,
"step": 3500
},
{
"epoch": 3.56,
"learning_rate": 3.218274111675127e-05,
"loss": 0.4011,
"step": 3510
},
{
"epoch": 3.57,
"learning_rate": 3.213197969543148e-05,
"loss": 0.4287,
"step": 3520
},
{
"epoch": 3.58,
"learning_rate": 3.2081218274111676e-05,
"loss": 0.3682,
"step": 3530
},
{
"epoch": 3.59,
"learning_rate": 3.203045685279188e-05,
"loss": 0.3619,
"step": 3540
},
{
"epoch": 3.6,
"learning_rate": 3.1979695431472086e-05,
"loss": 0.4637,
"step": 3550
},
{
"epoch": 3.61,
"learning_rate": 3.1928934010152284e-05,
"loss": 0.3748,
"step": 3560
},
{
"epoch": 3.62,
"learning_rate": 3.187817258883249e-05,
"loss": 0.4392,
"step": 3570
},
{
"epoch": 3.63,
"learning_rate": 3.1827411167512695e-05,
"loss": 0.3777,
"step": 3580
},
{
"epoch": 3.64,
"learning_rate": 3.177664974619289e-05,
"loss": 0.3575,
"step": 3590
},
{
"epoch": 3.65,
"learning_rate": 3.17258883248731e-05,
"loss": 0.3066,
"step": 3600
},
{
"epoch": 3.66,
"learning_rate": 3.1675126903553296e-05,
"loss": 0.4467,
"step": 3610
},
{
"epoch": 3.68,
"learning_rate": 3.16243654822335e-05,
"loss": 0.3688,
"step": 3620
},
{
"epoch": 3.69,
"learning_rate": 3.1573604060913707e-05,
"loss": 0.3773,
"step": 3630
},
{
"epoch": 3.7,
"learning_rate": 3.1522842639593905e-05,
"loss": 0.3131,
"step": 3640
},
{
"epoch": 3.71,
"learning_rate": 3.147208121827411e-05,
"loss": 0.4146,
"step": 3650
},
{
"epoch": 3.72,
"learning_rate": 3.1421319796954315e-05,
"loss": 0.4786,
"step": 3660
},
{
"epoch": 3.73,
"learning_rate": 3.137055837563452e-05,
"loss": 0.3547,
"step": 3670
},
{
"epoch": 3.74,
"learning_rate": 3.1319796954314725e-05,
"loss": 0.3503,
"step": 3680
},
{
"epoch": 3.75,
"learning_rate": 3.126903553299493e-05,
"loss": 0.4115,
"step": 3690
},
{
"epoch": 3.76,
"learning_rate": 3.121827411167513e-05,
"loss": 0.3992,
"step": 3700
},
{
"epoch": 3.77,
"learning_rate": 3.1167512690355334e-05,
"loss": 0.2793,
"step": 3710
},
{
"epoch": 3.78,
"learning_rate": 3.111675126903553e-05,
"loss": 0.4142,
"step": 3720
},
{
"epoch": 3.79,
"learning_rate": 3.106598984771574e-05,
"loss": 0.3488,
"step": 3730
},
{
"epoch": 3.8,
"learning_rate": 3.101522842639594e-05,
"loss": 0.342,
"step": 3740
},
{
"epoch": 3.81,
"learning_rate": 3.096446700507614e-05,
"loss": 0.3806,
"step": 3750
},
{
"epoch": 3.82,
"learning_rate": 3.0913705583756346e-05,
"loss": 0.292,
"step": 3760
},
{
"epoch": 3.83,
"learning_rate": 3.086294416243655e-05,
"loss": 0.4243,
"step": 3770
},
{
"epoch": 3.84,
"learning_rate": 3.081218274111675e-05,
"loss": 0.2939,
"step": 3780
},
{
"epoch": 3.85,
"learning_rate": 3.0761421319796955e-05,
"loss": 0.4192,
"step": 3790
},
{
"epoch": 3.86,
"learning_rate": 3.071065989847716e-05,
"loss": 0.498,
"step": 3800
},
{
"epoch": 3.87,
"learning_rate": 3.0659898477157365e-05,
"loss": 0.3754,
"step": 3810
},
{
"epoch": 3.88,
"learning_rate": 3.060913705583757e-05,
"loss": 0.3842,
"step": 3820
},
{
"epoch": 3.89,
"learning_rate": 3.055837563451777e-05,
"loss": 0.3752,
"step": 3830
},
{
"epoch": 3.9,
"learning_rate": 3.050761421319797e-05,
"loss": 0.438,
"step": 3840
},
{
"epoch": 3.91,
"learning_rate": 3.0456852791878175e-05,
"loss": 0.3612,
"step": 3850
},
{
"epoch": 3.92,
"learning_rate": 3.0406091370558377e-05,
"loss": 0.3791,
"step": 3860
},
{
"epoch": 3.93,
"learning_rate": 3.0355329949238582e-05,
"loss": 0.3606,
"step": 3870
},
{
"epoch": 3.94,
"learning_rate": 3.030456852791878e-05,
"loss": 0.3613,
"step": 3880
},
{
"epoch": 3.95,
"learning_rate": 3.0253807106598985e-05,
"loss": 0.3295,
"step": 3890
},
{
"epoch": 3.96,
"learning_rate": 3.020304568527919e-05,
"loss": 0.331,
"step": 3900
},
{
"epoch": 3.97,
"learning_rate": 3.0152284263959392e-05,
"loss": 0.3931,
"step": 3910
},
{
"epoch": 3.98,
"learning_rate": 3.0101522842639597e-05,
"loss": 0.3725,
"step": 3920
},
{
"epoch": 3.99,
"learning_rate": 3.0050761421319802e-05,
"loss": 0.3683,
"step": 3930
},
{
"epoch": 4.0,
"learning_rate": 3e-05,
"loss": 0.4519,
"step": 3940
},
{
"epoch": 4.0,
"eval_accuracy": 0.8531428571428571,
"eval_loss": 0.39148667454719543,
"eval_runtime": 19.8507,
"eval_samples_per_second": 176.316,
"eval_steps_per_second": 22.065,
"step": 3940
},
{
"epoch": 4.01,
"learning_rate": 2.9949238578680206e-05,
"loss": 0.373,
"step": 3950
},
{
"epoch": 4.02,
"learning_rate": 2.9898477157360404e-05,
"loss": 0.3963,
"step": 3960
},
{
"epoch": 4.03,
"learning_rate": 2.984771573604061e-05,
"loss": 0.3793,
"step": 3970
},
{
"epoch": 4.04,
"learning_rate": 2.9796954314720814e-05,
"loss": 0.4453,
"step": 3980
},
{
"epoch": 4.05,
"learning_rate": 2.9746192893401016e-05,
"loss": 0.3986,
"step": 3990
},
{
"epoch": 4.06,
"learning_rate": 2.969543147208122e-05,
"loss": 0.2925,
"step": 4000
},
{
"epoch": 4.07,
"learning_rate": 2.9644670050761426e-05,
"loss": 0.3813,
"step": 4010
},
{
"epoch": 4.08,
"learning_rate": 2.9593908629441625e-05,
"loss": 0.4348,
"step": 4020
},
{
"epoch": 4.09,
"learning_rate": 2.954314720812183e-05,
"loss": 0.4067,
"step": 4030
},
{
"epoch": 4.1,
"learning_rate": 2.9492385786802028e-05,
"loss": 0.3097,
"step": 4040
},
{
"epoch": 4.11,
"learning_rate": 2.9441624365482233e-05,
"loss": 0.4141,
"step": 4050
},
{
"epoch": 4.12,
"learning_rate": 2.939086294416244e-05,
"loss": 0.3614,
"step": 4060
},
{
"epoch": 4.13,
"learning_rate": 2.934010152284264e-05,
"loss": 0.3358,
"step": 4070
},
{
"epoch": 4.14,
"learning_rate": 2.9289340101522845e-05,
"loss": 0.3355,
"step": 4080
},
{
"epoch": 4.15,
"learning_rate": 2.923857868020305e-05,
"loss": 0.4534,
"step": 4090
},
{
"epoch": 4.16,
"learning_rate": 2.918781725888325e-05,
"loss": 0.4016,
"step": 4100
},
{
"epoch": 4.17,
"learning_rate": 2.9137055837563454e-05,
"loss": 0.3837,
"step": 4110
},
{
"epoch": 4.18,
"learning_rate": 2.9086294416243652e-05,
"loss": 0.4147,
"step": 4120
},
{
"epoch": 4.19,
"learning_rate": 2.9035532994923857e-05,
"loss": 0.3748,
"step": 4130
},
{
"epoch": 4.2,
"learning_rate": 2.8984771573604062e-05,
"loss": 0.3307,
"step": 4140
},
{
"epoch": 4.21,
"learning_rate": 2.8934010152284264e-05,
"loss": 0.3875,
"step": 4150
},
{
"epoch": 4.22,
"learning_rate": 2.888324873096447e-05,
"loss": 0.4073,
"step": 4160
},
{
"epoch": 4.23,
"learning_rate": 2.8832487309644674e-05,
"loss": 0.3765,
"step": 4170
},
{
"epoch": 4.24,
"learning_rate": 2.8781725888324873e-05,
"loss": 0.4269,
"step": 4180
},
{
"epoch": 4.25,
"learning_rate": 2.8730964467005078e-05,
"loss": 0.348,
"step": 4190
},
{
"epoch": 4.26,
"learning_rate": 2.8680203045685283e-05,
"loss": 0.4445,
"step": 4200
},
{
"epoch": 4.27,
"learning_rate": 2.862944162436548e-05,
"loss": 0.3896,
"step": 4210
},
{
"epoch": 4.28,
"learning_rate": 2.8578680203045686e-05,
"loss": 0.4005,
"step": 4220
},
{
"epoch": 4.29,
"learning_rate": 2.8527918781725888e-05,
"loss": 0.3395,
"step": 4230
},
{
"epoch": 4.3,
"learning_rate": 2.8477157360406093e-05,
"loss": 0.3701,
"step": 4240
},
{
"epoch": 4.31,
"learning_rate": 2.84263959390863e-05,
"loss": 0.4229,
"step": 4250
},
{
"epoch": 4.32,
"learning_rate": 2.8375634517766497e-05,
"loss": 0.3533,
"step": 4260
},
{
"epoch": 4.34,
"learning_rate": 2.8324873096446702e-05,
"loss": 0.4154,
"step": 4270
},
{
"epoch": 4.35,
"learning_rate": 2.8274111675126907e-05,
"loss": 0.3604,
"step": 4280
},
{
"epoch": 4.36,
"learning_rate": 2.822335025380711e-05,
"loss": 0.3565,
"step": 4290
},
{
"epoch": 4.37,
"learning_rate": 2.8172588832487314e-05,
"loss": 0.4146,
"step": 4300
},
{
"epoch": 4.38,
"learning_rate": 2.8121827411167512e-05,
"loss": 0.4074,
"step": 4310
},
{
"epoch": 4.39,
"learning_rate": 2.8071065989847717e-05,
"loss": 0.3668,
"step": 4320
},
{
"epoch": 4.4,
"learning_rate": 2.8020304568527922e-05,
"loss": 0.3406,
"step": 4330
},
{
"epoch": 4.41,
"learning_rate": 2.796954314720812e-05,
"loss": 0.4381,
"step": 4340
},
{
"epoch": 4.42,
"learning_rate": 2.7918781725888326e-05,
"loss": 0.3967,
"step": 4350
},
{
"epoch": 4.43,
"learning_rate": 2.786802030456853e-05,
"loss": 0.3976,
"step": 4360
},
{
"epoch": 4.44,
"learning_rate": 2.7817258883248733e-05,
"loss": 0.3477,
"step": 4370
},
{
"epoch": 4.45,
"learning_rate": 2.7766497461928938e-05,
"loss": 0.4629,
"step": 4380
},
{
"epoch": 4.46,
"learning_rate": 2.7715736040609136e-05,
"loss": 0.4813,
"step": 4390
},
{
"epoch": 4.47,
"learning_rate": 2.766497461928934e-05,
"loss": 0.3481,
"step": 4400
},
{
"epoch": 4.48,
"learning_rate": 2.7614213197969546e-05,
"loss": 0.4149,
"step": 4410
},
{
"epoch": 4.49,
"learning_rate": 2.7563451776649745e-05,
"loss": 0.3538,
"step": 4420
},
{
"epoch": 4.5,
"learning_rate": 2.751269035532995e-05,
"loss": 0.3486,
"step": 4430
},
{
"epoch": 4.51,
"learning_rate": 2.7461928934010155e-05,
"loss": 0.4116,
"step": 4440
},
{
"epoch": 4.52,
"learning_rate": 2.7411167512690357e-05,
"loss": 0.3864,
"step": 4450
},
{
"epoch": 4.53,
"learning_rate": 2.736040609137056e-05,
"loss": 0.3974,
"step": 4460
},
{
"epoch": 4.54,
"learning_rate": 2.730964467005076e-05,
"loss": 0.4256,
"step": 4470
},
{
"epoch": 4.55,
"learning_rate": 2.7258883248730965e-05,
"loss": 0.3802,
"step": 4480
},
{
"epoch": 4.56,
"learning_rate": 2.720812182741117e-05,
"loss": 0.4206,
"step": 4490
},
{
"epoch": 4.57,
"learning_rate": 2.715736040609137e-05,
"loss": 0.3524,
"step": 4500
},
{
"epoch": 4.58,
"learning_rate": 2.7106598984771574e-05,
"loss": 0.3377,
"step": 4510
},
{
"epoch": 4.59,
"learning_rate": 2.705583756345178e-05,
"loss": 0.4705,
"step": 4520
},
{
"epoch": 4.6,
"learning_rate": 2.700507614213198e-05,
"loss": 0.3578,
"step": 4530
},
{
"epoch": 4.61,
"learning_rate": 2.6954314720812186e-05,
"loss": 0.383,
"step": 4540
},
{
"epoch": 4.62,
"learning_rate": 2.6903553299492384e-05,
"loss": 0.4292,
"step": 4550
},
{
"epoch": 4.63,
"learning_rate": 2.685279187817259e-05,
"loss": 0.335,
"step": 4560
},
{
"epoch": 4.64,
"learning_rate": 2.6802030456852794e-05,
"loss": 0.4163,
"step": 4570
},
{
"epoch": 4.65,
"learning_rate": 2.6751269035532996e-05,
"loss": 0.4059,
"step": 4580
},
{
"epoch": 4.66,
"learning_rate": 2.67005076142132e-05,
"loss": 0.3261,
"step": 4590
},
{
"epoch": 4.67,
"learning_rate": 2.6649746192893406e-05,
"loss": 0.3938,
"step": 4600
},
{
"epoch": 4.68,
"learning_rate": 2.6598984771573604e-05,
"loss": 0.344,
"step": 4610
},
{
"epoch": 4.69,
"learning_rate": 2.654822335025381e-05,
"loss": 0.4534,
"step": 4620
},
{
"epoch": 4.7,
"learning_rate": 2.6497461928934008e-05,
"loss": 0.4403,
"step": 4630
},
{
"epoch": 4.71,
"learning_rate": 2.6446700507614213e-05,
"loss": 0.3344,
"step": 4640
},
{
"epoch": 4.72,
"learning_rate": 2.6395939086294418e-05,
"loss": 0.379,
"step": 4650
},
{
"epoch": 4.73,
"learning_rate": 2.634517766497462e-05,
"loss": 0.3483,
"step": 4660
},
{
"epoch": 4.74,
"learning_rate": 2.6294416243654825e-05,
"loss": 0.336,
"step": 4670
},
{
"epoch": 4.75,
"learning_rate": 2.624365482233503e-05,
"loss": 0.357,
"step": 4680
},
{
"epoch": 4.76,
"learning_rate": 2.619289340101523e-05,
"loss": 0.3867,
"step": 4690
},
{
"epoch": 4.77,
"learning_rate": 2.6142131979695434e-05,
"loss": 0.3044,
"step": 4700
},
{
"epoch": 4.78,
"learning_rate": 2.609137055837564e-05,
"loss": 0.3668,
"step": 4710
},
{
"epoch": 4.79,
"learning_rate": 2.6040609137055837e-05,
"loss": 0.3332,
"step": 4720
},
{
"epoch": 4.8,
"learning_rate": 2.5989847715736042e-05,
"loss": 0.3798,
"step": 4730
},
{
"epoch": 4.81,
"learning_rate": 2.5939086294416244e-05,
"loss": 0.345,
"step": 4740
},
{
"epoch": 4.82,
"learning_rate": 2.588832487309645e-05,
"loss": 0.3389,
"step": 4750
},
{
"epoch": 4.83,
"learning_rate": 2.5837563451776654e-05,
"loss": 0.3659,
"step": 4760
},
{
"epoch": 4.84,
"learning_rate": 2.5786802030456852e-05,
"loss": 0.4076,
"step": 4770
},
{
"epoch": 4.85,
"learning_rate": 2.5736040609137058e-05,
"loss": 0.4096,
"step": 4780
},
{
"epoch": 4.86,
"learning_rate": 2.5685279187817263e-05,
"loss": 0.3349,
"step": 4790
},
{
"epoch": 4.87,
"learning_rate": 2.563451776649746e-05,
"loss": 0.3115,
"step": 4800
},
{
"epoch": 4.88,
"learning_rate": 2.5583756345177666e-05,
"loss": 0.3828,
"step": 4810
},
{
"epoch": 4.89,
"learning_rate": 2.5532994923857868e-05,
"loss": 0.3503,
"step": 4820
},
{
"epoch": 4.9,
"learning_rate": 2.5482233502538073e-05,
"loss": 0.4065,
"step": 4830
},
{
"epoch": 4.91,
"learning_rate": 2.5431472081218278e-05,
"loss": 0.4275,
"step": 4840
},
{
"epoch": 4.92,
"learning_rate": 2.5380710659898476e-05,
"loss": 0.3854,
"step": 4850
},
{
"epoch": 4.93,
"learning_rate": 2.532994923857868e-05,
"loss": 0.3756,
"step": 4860
},
{
"epoch": 4.94,
"learning_rate": 2.5279187817258887e-05,
"loss": 0.4309,
"step": 4870
},
{
"epoch": 4.95,
"learning_rate": 2.5228426395939085e-05,
"loss": 0.3899,
"step": 4880
},
{
"epoch": 4.96,
"learning_rate": 2.517766497461929e-05,
"loss": 0.4105,
"step": 4890
},
{
"epoch": 4.97,
"learning_rate": 2.5126903553299492e-05,
"loss": 0.4001,
"step": 4900
},
{
"epoch": 4.98,
"learning_rate": 2.5076142131979697e-05,
"loss": 0.3559,
"step": 4910
},
{
"epoch": 4.99,
"learning_rate": 2.5025380710659902e-05,
"loss": 0.3506,
"step": 4920
},
{
"epoch": 5.0,
"eval_accuracy": 0.8571428571428571,
"eval_loss": 0.3885991871356964,
"eval_runtime": 19.8882,
"eval_samples_per_second": 175.984,
"eval_steps_per_second": 22.023,
"step": 4925
},
{
"epoch": 5.01,
"learning_rate": 2.4974619289340104e-05,
"loss": 0.3446,
"step": 4930
},
{
"epoch": 5.02,
"learning_rate": 2.4923857868020305e-05,
"loss": 0.4058,
"step": 4940
},
{
"epoch": 5.03,
"learning_rate": 2.4873096446700507e-05,
"loss": 0.382,
"step": 4950
},
{
"epoch": 5.04,
"learning_rate": 2.4822335025380712e-05,
"loss": 0.3582,
"step": 4960
},
{
"epoch": 5.05,
"learning_rate": 2.4771573604060917e-05,
"loss": 0.3851,
"step": 4970
},
{
"epoch": 5.06,
"learning_rate": 2.472081218274112e-05,
"loss": 0.4078,
"step": 4980
},
{
"epoch": 5.07,
"learning_rate": 2.467005076142132e-05,
"loss": 0.388,
"step": 4990
},
{
"epoch": 5.08,
"learning_rate": 2.4619289340101523e-05,
"loss": 0.3382,
"step": 5000
},
{
"epoch": 5.09,
"learning_rate": 2.4568527918781728e-05,
"loss": 0.4007,
"step": 5010
},
{
"epoch": 5.1,
"learning_rate": 2.451776649746193e-05,
"loss": 0.3791,
"step": 5020
},
{
"epoch": 5.11,
"learning_rate": 2.446700507614213e-05,
"loss": 0.3567,
"step": 5030
},
{
"epoch": 5.12,
"learning_rate": 2.4416243654822336e-05,
"loss": 0.2921,
"step": 5040
},
{
"epoch": 5.13,
"learning_rate": 2.436548223350254e-05,
"loss": 0.3606,
"step": 5050
},
{
"epoch": 5.14,
"learning_rate": 2.4314720812182743e-05,
"loss": 0.3695,
"step": 5060
},
{
"epoch": 5.15,
"learning_rate": 2.4263959390862945e-05,
"loss": 0.3112,
"step": 5070
},
{
"epoch": 5.16,
"learning_rate": 2.4213197969543147e-05,
"loss": 0.356,
"step": 5080
},
{
"epoch": 5.17,
"learning_rate": 2.4162436548223352e-05,
"loss": 0.3975,
"step": 5090
},
{
"epoch": 5.18,
"learning_rate": 2.4111675126903553e-05,
"loss": 0.3599,
"step": 5100
},
{
"epoch": 5.19,
"learning_rate": 2.406091370558376e-05,
"loss": 0.4426,
"step": 5110
},
{
"epoch": 5.2,
"learning_rate": 2.401015228426396e-05,
"loss": 0.4331,
"step": 5120
},
{
"epoch": 5.21,
"learning_rate": 2.3959390862944165e-05,
"loss": 0.4215,
"step": 5130
},
{
"epoch": 5.22,
"learning_rate": 2.3908629441624367e-05,
"loss": 0.3844,
"step": 5140
},
{
"epoch": 5.23,
"learning_rate": 2.385786802030457e-05,
"loss": 0.3595,
"step": 5150
},
{
"epoch": 5.24,
"learning_rate": 2.380710659898477e-05,
"loss": 0.3766,
"step": 5160
},
{
"epoch": 5.25,
"learning_rate": 2.3756345177664976e-05,
"loss": 0.4273,
"step": 5170
},
{
"epoch": 5.26,
"learning_rate": 2.3705583756345177e-05,
"loss": 0.4262,
"step": 5180
},
{
"epoch": 5.27,
"learning_rate": 2.3654822335025383e-05,
"loss": 0.3806,
"step": 5190
},
{
"epoch": 5.28,
"learning_rate": 2.3604060913705588e-05,
"loss": 0.3403,
"step": 5200
},
{
"epoch": 5.29,
"learning_rate": 2.355329949238579e-05,
"loss": 0.3768,
"step": 5210
},
{
"epoch": 5.3,
"learning_rate": 2.350253807106599e-05,
"loss": 0.3363,
"step": 5220
},
{
"epoch": 5.31,
"learning_rate": 2.3451776649746193e-05,
"loss": 0.3793,
"step": 5230
},
{
"epoch": 5.32,
"learning_rate": 2.3401015228426398e-05,
"loss": 0.3677,
"step": 5240
},
{
"epoch": 5.33,
"learning_rate": 2.33502538071066e-05,
"loss": 0.3613,
"step": 5250
},
{
"epoch": 5.34,
"learning_rate": 2.32994923857868e-05,
"loss": 0.4361,
"step": 5260
},
{
"epoch": 5.35,
"learning_rate": 2.3248730964467006e-05,
"loss": 0.3408,
"step": 5270
},
{
"epoch": 5.36,
"learning_rate": 2.319796954314721e-05,
"loss": 0.3219,
"step": 5280
},
{
"epoch": 5.37,
"learning_rate": 2.3147208121827413e-05,
"loss": 0.3074,
"step": 5290
},
{
"epoch": 5.38,
"learning_rate": 2.3096446700507615e-05,
"loss": 0.3713,
"step": 5300
},
{
"epoch": 5.39,
"learning_rate": 2.3045685279187817e-05,
"loss": 0.3718,
"step": 5310
},
{
"epoch": 5.4,
"learning_rate": 2.2994923857868022e-05,
"loss": 0.3814,
"step": 5320
},
{
"epoch": 5.41,
"learning_rate": 2.2944162436548224e-05,
"loss": 0.4148,
"step": 5330
},
{
"epoch": 5.42,
"learning_rate": 2.289340101522843e-05,
"loss": 0.3701,
"step": 5340
},
{
"epoch": 5.43,
"learning_rate": 2.284263959390863e-05,
"loss": 0.347,
"step": 5350
},
{
"epoch": 5.44,
"learning_rate": 2.2791878172588836e-05,
"loss": 0.3604,
"step": 5360
},
{
"epoch": 5.45,
"learning_rate": 2.2741116751269037e-05,
"loss": 0.405,
"step": 5370
},
{
"epoch": 5.46,
"learning_rate": 2.269035532994924e-05,
"loss": 0.3937,
"step": 5380
},
{
"epoch": 5.47,
"learning_rate": 2.263959390862944e-05,
"loss": 0.3532,
"step": 5390
},
{
"epoch": 5.48,
"learning_rate": 2.2588832487309646e-05,
"loss": 0.3425,
"step": 5400
},
{
"epoch": 5.49,
"learning_rate": 2.2538071065989848e-05,
"loss": 0.4022,
"step": 5410
},
{
"epoch": 5.5,
"learning_rate": 2.2487309644670053e-05,
"loss": 0.3922,
"step": 5420
},
{
"epoch": 5.51,
"learning_rate": 2.2436548223350254e-05,
"loss": 0.4058,
"step": 5430
},
{
"epoch": 5.52,
"learning_rate": 2.238578680203046e-05,
"loss": 0.4179,
"step": 5440
},
{
"epoch": 5.53,
"learning_rate": 2.233502538071066e-05,
"loss": 0.4044,
"step": 5450
},
{
"epoch": 5.54,
"learning_rate": 2.2284263959390863e-05,
"loss": 0.3934,
"step": 5460
},
{
"epoch": 5.55,
"learning_rate": 2.2233502538071065e-05,
"loss": 0.3527,
"step": 5470
},
{
"epoch": 5.56,
"learning_rate": 2.218274111675127e-05,
"loss": 0.4063,
"step": 5480
},
{
"epoch": 5.57,
"learning_rate": 2.2131979695431475e-05,
"loss": 0.3655,
"step": 5490
},
{
"epoch": 5.58,
"learning_rate": 2.2081218274111677e-05,
"loss": 0.4152,
"step": 5500
},
{
"epoch": 5.59,
"learning_rate": 2.203045685279188e-05,
"loss": 0.3893,
"step": 5510
},
{
"epoch": 5.6,
"learning_rate": 2.1979695431472084e-05,
"loss": 0.3459,
"step": 5520
},
{
"epoch": 5.61,
"learning_rate": 2.1928934010152285e-05,
"loss": 0.3419,
"step": 5530
},
{
"epoch": 5.62,
"learning_rate": 2.1878172588832487e-05,
"loss": 0.3907,
"step": 5540
},
{
"epoch": 5.63,
"learning_rate": 2.182741116751269e-05,
"loss": 0.4164,
"step": 5550
},
{
"epoch": 5.64,
"learning_rate": 2.1776649746192894e-05,
"loss": 0.3795,
"step": 5560
},
{
"epoch": 5.65,
"learning_rate": 2.17258883248731e-05,
"loss": 0.3622,
"step": 5570
},
{
"epoch": 5.66,
"learning_rate": 2.16751269035533e-05,
"loss": 0.4174,
"step": 5580
},
{
"epoch": 5.68,
"learning_rate": 2.1624365482233502e-05,
"loss": 0.3589,
"step": 5590
},
{
"epoch": 5.69,
"learning_rate": 2.1573604060913707e-05,
"loss": 0.3721,
"step": 5600
},
{
"epoch": 5.7,
"learning_rate": 2.152284263959391e-05,
"loss": 0.3829,
"step": 5610
},
{
"epoch": 5.71,
"learning_rate": 2.147208121827411e-05,
"loss": 0.4149,
"step": 5620
},
{
"epoch": 5.72,
"learning_rate": 2.1421319796954316e-05,
"loss": 0.4396,
"step": 5630
},
{
"epoch": 5.73,
"learning_rate": 2.137055837563452e-05,
"loss": 0.3922,
"step": 5640
},
{
"epoch": 5.74,
"learning_rate": 2.1319796954314723e-05,
"loss": 0.3873,
"step": 5650
},
{
"epoch": 5.75,
"learning_rate": 2.1269035532994925e-05,
"loss": 0.405,
"step": 5660
},
{
"epoch": 5.76,
"learning_rate": 2.1218274111675126e-05,
"loss": 0.3701,
"step": 5670
},
{
"epoch": 5.77,
"learning_rate": 2.116751269035533e-05,
"loss": 0.3207,
"step": 5680
},
{
"epoch": 5.78,
"learning_rate": 2.1116751269035533e-05,
"loss": 0.3931,
"step": 5690
},
{
"epoch": 5.79,
"learning_rate": 2.1065989847715735e-05,
"loss": 0.4098,
"step": 5700
},
{
"epoch": 5.8,
"learning_rate": 2.101522842639594e-05,
"loss": 0.4069,
"step": 5710
},
{
"epoch": 5.81,
"learning_rate": 2.0964467005076145e-05,
"loss": 0.3233,
"step": 5720
},
{
"epoch": 5.82,
"learning_rate": 2.0913705583756347e-05,
"loss": 0.3945,
"step": 5730
},
{
"epoch": 5.83,
"learning_rate": 2.086294416243655e-05,
"loss": 0.3842,
"step": 5740
},
{
"epoch": 5.84,
"learning_rate": 2.0812182741116754e-05,
"loss": 0.4139,
"step": 5750
},
{
"epoch": 5.85,
"learning_rate": 2.0761421319796955e-05,
"loss": 0.39,
"step": 5760
},
{
"epoch": 5.86,
"learning_rate": 2.0710659898477157e-05,
"loss": 0.4047,
"step": 5770
},
{
"epoch": 5.87,
"learning_rate": 2.0659898477157362e-05,
"loss": 0.3982,
"step": 5780
},
{
"epoch": 5.88,
"learning_rate": 2.0609137055837567e-05,
"loss": 0.4173,
"step": 5790
},
{
"epoch": 5.89,
"learning_rate": 2.055837563451777e-05,
"loss": 0.3544,
"step": 5800
},
{
"epoch": 5.9,
"learning_rate": 2.050761421319797e-05,
"loss": 0.3759,
"step": 5810
},
{
"epoch": 5.91,
"learning_rate": 2.0456852791878173e-05,
"loss": 0.3782,
"step": 5820
},
{
"epoch": 5.92,
"learning_rate": 2.0406091370558378e-05,
"loss": 0.3903,
"step": 5830
},
{
"epoch": 5.93,
"learning_rate": 2.035532994923858e-05,
"loss": 0.3417,
"step": 5840
},
{
"epoch": 5.94,
"learning_rate": 2.030456852791878e-05,
"loss": 0.3638,
"step": 5850
},
{
"epoch": 5.95,
"learning_rate": 2.0253807106598986e-05,
"loss": 0.396,
"step": 5860
},
{
"epoch": 5.96,
"learning_rate": 2.020304568527919e-05,
"loss": 0.3742,
"step": 5870
},
{
"epoch": 5.97,
"learning_rate": 2.0152284263959393e-05,
"loss": 0.3842,
"step": 5880
},
{
"epoch": 5.98,
"learning_rate": 2.0101522842639595e-05,
"loss": 0.3892,
"step": 5890
},
{
"epoch": 5.99,
"learning_rate": 2.0050761421319797e-05,
"loss": 0.3951,
"step": 5900
},
{
"epoch": 6.0,
"learning_rate": 2e-05,
"loss": 0.3599,
"step": 5910
},
{
"epoch": 6.0,
"eval_accuracy": 0.8562857142857143,
"eval_loss": 0.3865005671977997,
"eval_runtime": 19.7922,
"eval_samples_per_second": 176.838,
"eval_steps_per_second": 22.13,
"step": 5910
},
{
"epoch": 6.01,
"learning_rate": 1.9949238578680203e-05,
"loss": 0.3538,
"step": 5920
},
{
"epoch": 6.02,
"learning_rate": 1.9898477157360405e-05,
"loss": 0.3692,
"step": 5930
},
{
"epoch": 6.03,
"learning_rate": 1.984771573604061e-05,
"loss": 0.3842,
"step": 5940
},
{
"epoch": 6.04,
"learning_rate": 1.9796954314720815e-05,
"loss": 0.3844,
"step": 5950
},
{
"epoch": 6.05,
"learning_rate": 1.9746192893401017e-05,
"loss": 0.3265,
"step": 5960
},
{
"epoch": 6.06,
"learning_rate": 1.969543147208122e-05,
"loss": 0.4204,
"step": 5970
},
{
"epoch": 6.07,
"learning_rate": 1.964467005076142e-05,
"loss": 0.4072,
"step": 5980
},
{
"epoch": 6.08,
"learning_rate": 1.9593908629441626e-05,
"loss": 0.4564,
"step": 5990
},
{
"epoch": 6.09,
"learning_rate": 1.9543147208121827e-05,
"loss": 0.3835,
"step": 6000
},
{
"epoch": 6.1,
"learning_rate": 1.9492385786802032e-05,
"loss": 0.4157,
"step": 6010
},
{
"epoch": 6.11,
"learning_rate": 1.9441624365482234e-05,
"loss": 0.3792,
"step": 6020
},
{
"epoch": 6.12,
"learning_rate": 1.939086294416244e-05,
"loss": 0.4049,
"step": 6030
},
{
"epoch": 6.13,
"learning_rate": 1.934010152284264e-05,
"loss": 0.3558,
"step": 6040
},
{
"epoch": 6.14,
"learning_rate": 1.9289340101522843e-05,
"loss": 0.3814,
"step": 6050
},
{
"epoch": 6.15,
"learning_rate": 1.9238578680203044e-05,
"loss": 0.3463,
"step": 6060
},
{
"epoch": 6.16,
"learning_rate": 1.918781725888325e-05,
"loss": 0.3479,
"step": 6070
},
{
"epoch": 6.17,
"learning_rate": 1.913705583756345e-05,
"loss": 0.3263,
"step": 6080
},
{
"epoch": 6.18,
"learning_rate": 1.9086294416243656e-05,
"loss": 0.4178,
"step": 6090
},
{
"epoch": 6.19,
"learning_rate": 1.9035532994923858e-05,
"loss": 0.4024,
"step": 6100
},
{
"epoch": 6.2,
"learning_rate": 1.8984771573604063e-05,
"loss": 0.4496,
"step": 6110
},
{
"epoch": 6.21,
"learning_rate": 1.8934010152284265e-05,
"loss": 0.442,
"step": 6120
},
{
"epoch": 6.22,
"learning_rate": 1.8883248730964467e-05,
"loss": 0.383,
"step": 6130
},
{
"epoch": 6.23,
"learning_rate": 1.883248730964467e-05,
"loss": 0.3836,
"step": 6140
},
{
"epoch": 6.24,
"learning_rate": 1.8781725888324874e-05,
"loss": 0.3411,
"step": 6150
},
{
"epoch": 6.25,
"learning_rate": 1.873096446700508e-05,
"loss": 0.3916,
"step": 6160
},
{
"epoch": 6.26,
"learning_rate": 1.868020304568528e-05,
"loss": 0.35,
"step": 6170
},
{
"epoch": 6.27,
"learning_rate": 1.8629441624365482e-05,
"loss": 0.36,
"step": 6180
},
{
"epoch": 6.28,
"learning_rate": 1.8578680203045687e-05,
"loss": 0.4536,
"step": 6190
},
{
"epoch": 6.29,
"learning_rate": 1.852791878172589e-05,
"loss": 0.3201,
"step": 6200
},
{
"epoch": 6.3,
"learning_rate": 1.847715736040609e-05,
"loss": 0.4068,
"step": 6210
},
{
"epoch": 6.31,
"learning_rate": 1.8426395939086292e-05,
"loss": 0.3351,
"step": 6220
},
{
"epoch": 6.32,
"learning_rate": 1.8375634517766498e-05,
"loss": 0.3872,
"step": 6230
},
{
"epoch": 6.34,
"learning_rate": 1.8324873096446703e-05,
"loss": 0.3594,
"step": 6240
},
{
"epoch": 6.35,
"learning_rate": 1.8274111675126904e-05,
"loss": 0.4154,
"step": 6250
},
{
"epoch": 6.36,
"learning_rate": 1.822335025380711e-05,
"loss": 0.3946,
"step": 6260
},
{
"epoch": 6.37,
"learning_rate": 1.817258883248731e-05,
"loss": 0.3896,
"step": 6270
},
{
"epoch": 6.38,
"learning_rate": 1.8121827411167513e-05,
"loss": 0.382,
"step": 6280
},
{
"epoch": 6.39,
"learning_rate": 1.8071065989847715e-05,
"loss": 0.411,
"step": 6290
},
{
"epoch": 6.4,
"learning_rate": 1.802030456852792e-05,
"loss": 0.3748,
"step": 6300
},
{
"epoch": 6.41,
"learning_rate": 1.7969543147208125e-05,
"loss": 0.381,
"step": 6310
},
{
"epoch": 6.42,
"learning_rate": 1.7918781725888327e-05,
"loss": 0.3253,
"step": 6320
},
{
"epoch": 6.43,
"learning_rate": 1.786802030456853e-05,
"loss": 0.3783,
"step": 6330
},
{
"epoch": 6.44,
"learning_rate": 1.7817258883248733e-05,
"loss": 0.4101,
"step": 6340
},
{
"epoch": 6.45,
"learning_rate": 1.7766497461928935e-05,
"loss": 0.3653,
"step": 6350
},
{
"epoch": 6.46,
"learning_rate": 1.7715736040609137e-05,
"loss": 0.3586,
"step": 6360
},
{
"epoch": 6.47,
"learning_rate": 1.766497461928934e-05,
"loss": 0.3771,
"step": 6370
},
{
"epoch": 6.48,
"learning_rate": 1.7614213197969544e-05,
"loss": 0.345,
"step": 6380
},
{
"epoch": 6.49,
"learning_rate": 1.756345177664975e-05,
"loss": 0.3442,
"step": 6390
},
{
"epoch": 6.5,
"learning_rate": 1.751269035532995e-05,
"loss": 0.3473,
"step": 6400
},
{
"epoch": 6.51,
"learning_rate": 1.7461928934010152e-05,
"loss": 0.409,
"step": 6410
},
{
"epoch": 6.52,
"learning_rate": 1.7411167512690357e-05,
"loss": 0.3839,
"step": 6420
},
{
"epoch": 6.53,
"learning_rate": 1.736040609137056e-05,
"loss": 0.3232,
"step": 6430
},
{
"epoch": 6.54,
"learning_rate": 1.730964467005076e-05,
"loss": 0.3825,
"step": 6440
},
{
"epoch": 6.55,
"learning_rate": 1.7258883248730966e-05,
"loss": 0.3524,
"step": 6450
},
{
"epoch": 6.56,
"learning_rate": 1.720812182741117e-05,
"loss": 0.3783,
"step": 6460
},
{
"epoch": 6.57,
"learning_rate": 1.7157360406091373e-05,
"loss": 0.3666,
"step": 6470
},
{
"epoch": 6.58,
"learning_rate": 1.7106598984771575e-05,
"loss": 0.4148,
"step": 6480
},
{
"epoch": 6.59,
"learning_rate": 1.7055837563451776e-05,
"loss": 0.4269,
"step": 6490
},
{
"epoch": 6.6,
"learning_rate": 1.700507614213198e-05,
"loss": 0.3923,
"step": 6500
},
{
"epoch": 6.61,
"learning_rate": 1.6954314720812183e-05,
"loss": 0.3439,
"step": 6510
},
{
"epoch": 6.62,
"learning_rate": 1.6903553299492385e-05,
"loss": 0.3851,
"step": 6520
},
{
"epoch": 6.63,
"learning_rate": 1.685279187817259e-05,
"loss": 0.3426,
"step": 6530
},
{
"epoch": 6.64,
"learning_rate": 1.6802030456852795e-05,
"loss": 0.3954,
"step": 6540
},
{
"epoch": 6.65,
"learning_rate": 1.6751269035532997e-05,
"loss": 0.3818,
"step": 6550
},
{
"epoch": 6.66,
"learning_rate": 1.67005076142132e-05,
"loss": 0.436,
"step": 6560
},
{
"epoch": 6.67,
"learning_rate": 1.66497461928934e-05,
"loss": 0.3368,
"step": 6570
},
{
"epoch": 6.68,
"learning_rate": 1.6598984771573605e-05,
"loss": 0.4061,
"step": 6580
},
{
"epoch": 6.69,
"learning_rate": 1.6548223350253807e-05,
"loss": 0.3457,
"step": 6590
},
{
"epoch": 6.7,
"learning_rate": 1.649746192893401e-05,
"loss": 0.3837,
"step": 6600
},
{
"epoch": 6.71,
"learning_rate": 1.6446700507614214e-05,
"loss": 0.3655,
"step": 6610
},
{
"epoch": 6.72,
"learning_rate": 1.639593908629442e-05,
"loss": 0.3761,
"step": 6620
},
{
"epoch": 6.73,
"learning_rate": 1.634517766497462e-05,
"loss": 0.3745,
"step": 6630
},
{
"epoch": 6.74,
"learning_rate": 1.6294416243654822e-05,
"loss": 0.447,
"step": 6640
},
{
"epoch": 6.75,
"learning_rate": 1.6243654822335024e-05,
"loss": 0.4076,
"step": 6650
},
{
"epoch": 6.76,
"learning_rate": 1.619289340101523e-05,
"loss": 0.3989,
"step": 6660
},
{
"epoch": 6.77,
"learning_rate": 1.614213197969543e-05,
"loss": 0.3921,
"step": 6670
},
{
"epoch": 6.78,
"learning_rate": 1.6091370558375636e-05,
"loss": 0.3933,
"step": 6680
},
{
"epoch": 6.79,
"learning_rate": 1.6040609137055838e-05,
"loss": 0.3643,
"step": 6690
},
{
"epoch": 6.8,
"learning_rate": 1.5989847715736043e-05,
"loss": 0.3666,
"step": 6700
},
{
"epoch": 6.81,
"learning_rate": 1.5939086294416245e-05,
"loss": 0.388,
"step": 6710
},
{
"epoch": 6.82,
"learning_rate": 1.5888324873096446e-05,
"loss": 0.3176,
"step": 6720
},
{
"epoch": 6.83,
"learning_rate": 1.5837563451776648e-05,
"loss": 0.4355,
"step": 6730
},
{
"epoch": 6.84,
"learning_rate": 1.5786802030456853e-05,
"loss": 0.3897,
"step": 6740
},
{
"epoch": 6.85,
"learning_rate": 1.5736040609137055e-05,
"loss": 0.3711,
"step": 6750
},
{
"epoch": 6.86,
"learning_rate": 1.568527918781726e-05,
"loss": 0.3908,
"step": 6760
},
{
"epoch": 6.87,
"learning_rate": 1.5634517766497465e-05,
"loss": 0.4077,
"step": 6770
},
{
"epoch": 6.88,
"learning_rate": 1.5583756345177667e-05,
"loss": 0.3356,
"step": 6780
},
{
"epoch": 6.89,
"learning_rate": 1.553299492385787e-05,
"loss": 0.373,
"step": 6790
},
{
"epoch": 6.9,
"learning_rate": 1.548223350253807e-05,
"loss": 0.4087,
"step": 6800
},
{
"epoch": 6.91,
"learning_rate": 1.5431472081218276e-05,
"loss": 0.3155,
"step": 6810
},
{
"epoch": 6.92,
"learning_rate": 1.5380710659898477e-05,
"loss": 0.3394,
"step": 6820
},
{
"epoch": 6.93,
"learning_rate": 1.5329949238578682e-05,
"loss": 0.3548,
"step": 6830
},
{
"epoch": 6.94,
"learning_rate": 1.5279187817258884e-05,
"loss": 0.3772,
"step": 6840
},
{
"epoch": 6.95,
"learning_rate": 1.5228426395939088e-05,
"loss": 0.3938,
"step": 6850
},
{
"epoch": 6.96,
"learning_rate": 1.5177664974619291e-05,
"loss": 0.3342,
"step": 6860
},
{
"epoch": 6.97,
"learning_rate": 1.5126903553299493e-05,
"loss": 0.4157,
"step": 6870
},
{
"epoch": 6.98,
"learning_rate": 1.5076142131979696e-05,
"loss": 0.333,
"step": 6880
},
{
"epoch": 6.99,
"learning_rate": 1.5025380710659901e-05,
"loss": 0.3496,
"step": 6890
},
{
"epoch": 7.0,
"eval_accuracy": 0.8568571428571429,
"eval_loss": 0.38769659399986267,
"eval_runtime": 19.8049,
"eval_samples_per_second": 176.724,
"eval_steps_per_second": 22.116,
"step": 6895
},
{
"epoch": 7.01,
"learning_rate": 1.4974619289340103e-05,
"loss": 0.3786,
"step": 6900
},
{
"epoch": 7.02,
"learning_rate": 1.4923857868020305e-05,
"loss": 0.419,
"step": 6910
},
{
"epoch": 7.03,
"learning_rate": 1.4873096446700508e-05,
"loss": 0.4602,
"step": 6920
},
{
"epoch": 7.04,
"learning_rate": 1.4822335025380713e-05,
"loss": 0.3858,
"step": 6930
},
{
"epoch": 7.05,
"learning_rate": 1.4771573604060915e-05,
"loss": 0.3427,
"step": 6940
},
{
"epoch": 7.06,
"learning_rate": 1.4720812182741117e-05,
"loss": 0.3676,
"step": 6950
},
{
"epoch": 7.07,
"learning_rate": 1.467005076142132e-05,
"loss": 0.3281,
"step": 6960
},
{
"epoch": 7.08,
"learning_rate": 1.4619289340101525e-05,
"loss": 0.3975,
"step": 6970
},
{
"epoch": 7.09,
"learning_rate": 1.4568527918781727e-05,
"loss": 0.4531,
"step": 6980
},
{
"epoch": 7.1,
"learning_rate": 1.4517766497461929e-05,
"loss": 0.4018,
"step": 6990
},
{
"epoch": 7.11,
"learning_rate": 1.4467005076142132e-05,
"loss": 0.4084,
"step": 7000
},
{
"epoch": 7.12,
"learning_rate": 1.4416243654822337e-05,
"loss": 0.3383,
"step": 7010
},
{
"epoch": 7.13,
"learning_rate": 1.4365482233502539e-05,
"loss": 0.4297,
"step": 7020
},
{
"epoch": 7.14,
"learning_rate": 1.431472081218274e-05,
"loss": 0.3684,
"step": 7030
},
{
"epoch": 7.15,
"learning_rate": 1.4263959390862944e-05,
"loss": 0.3568,
"step": 7040
},
{
"epoch": 7.16,
"learning_rate": 1.421319796954315e-05,
"loss": 0.4487,
"step": 7050
},
{
"epoch": 7.17,
"learning_rate": 1.4162436548223351e-05,
"loss": 0.3284,
"step": 7060
},
{
"epoch": 7.18,
"learning_rate": 1.4111675126903554e-05,
"loss": 0.3299,
"step": 7070
},
{
"epoch": 7.19,
"learning_rate": 1.4060913705583756e-05,
"loss": 0.3468,
"step": 7080
},
{
"epoch": 7.2,
"learning_rate": 1.4010152284263961e-05,
"loss": 0.3865,
"step": 7090
},
{
"epoch": 7.21,
"learning_rate": 1.3959390862944163e-05,
"loss": 0.3839,
"step": 7100
},
{
"epoch": 7.22,
"learning_rate": 1.3908629441624366e-05,
"loss": 0.3617,
"step": 7110
},
{
"epoch": 7.23,
"learning_rate": 1.3857868020304568e-05,
"loss": 0.3888,
"step": 7120
},
{
"epoch": 7.24,
"learning_rate": 1.3807106598984773e-05,
"loss": 0.3577,
"step": 7130
},
{
"epoch": 7.25,
"learning_rate": 1.3756345177664975e-05,
"loss": 0.4505,
"step": 7140
},
{
"epoch": 7.26,
"learning_rate": 1.3705583756345178e-05,
"loss": 0.413,
"step": 7150
},
{
"epoch": 7.27,
"learning_rate": 1.365482233502538e-05,
"loss": 0.3694,
"step": 7160
},
{
"epoch": 7.28,
"learning_rate": 1.3604060913705585e-05,
"loss": 0.4337,
"step": 7170
},
{
"epoch": 7.29,
"learning_rate": 1.3553299492385787e-05,
"loss": 0.4234,
"step": 7180
},
{
"epoch": 7.3,
"learning_rate": 1.350253807106599e-05,
"loss": 0.334,
"step": 7190
},
{
"epoch": 7.31,
"learning_rate": 1.3451776649746192e-05,
"loss": 0.3134,
"step": 7200
},
{
"epoch": 7.32,
"learning_rate": 1.3401015228426397e-05,
"loss": 0.4215,
"step": 7210
},
{
"epoch": 7.33,
"learning_rate": 1.33502538071066e-05,
"loss": 0.3893,
"step": 7220
},
{
"epoch": 7.34,
"learning_rate": 1.3299492385786802e-05,
"loss": 0.3833,
"step": 7230
},
{
"epoch": 7.35,
"learning_rate": 1.3248730964467004e-05,
"loss": 0.4122,
"step": 7240
},
{
"epoch": 7.36,
"learning_rate": 1.3197969543147209e-05,
"loss": 0.3011,
"step": 7250
},
{
"epoch": 7.37,
"learning_rate": 1.3147208121827413e-05,
"loss": 0.3562,
"step": 7260
},
{
"epoch": 7.38,
"learning_rate": 1.3096446700507614e-05,
"loss": 0.3642,
"step": 7270
},
{
"epoch": 7.39,
"learning_rate": 1.304568527918782e-05,
"loss": 0.3409,
"step": 7280
},
{
"epoch": 7.4,
"learning_rate": 1.2994923857868021e-05,
"loss": 0.3534,
"step": 7290
},
{
"epoch": 7.41,
"learning_rate": 1.2944162436548224e-05,
"loss": 0.3548,
"step": 7300
},
{
"epoch": 7.42,
"learning_rate": 1.2893401015228426e-05,
"loss": 0.3549,
"step": 7310
},
{
"epoch": 7.43,
"learning_rate": 1.2842639593908631e-05,
"loss": 0.371,
"step": 7320
},
{
"epoch": 7.44,
"learning_rate": 1.2791878172588833e-05,
"loss": 0.3675,
"step": 7330
},
{
"epoch": 7.45,
"learning_rate": 1.2741116751269036e-05,
"loss": 0.3702,
"step": 7340
},
{
"epoch": 7.46,
"learning_rate": 1.2690355329949238e-05,
"loss": 0.3949,
"step": 7350
},
{
"epoch": 7.47,
"learning_rate": 1.2639593908629443e-05,
"loss": 0.4053,
"step": 7360
},
{
"epoch": 7.48,
"learning_rate": 1.2588832487309645e-05,
"loss": 0.3999,
"step": 7370
},
{
"epoch": 7.49,
"learning_rate": 1.2538071065989848e-05,
"loss": 0.4261,
"step": 7380
},
{
"epoch": 7.5,
"learning_rate": 1.2487309644670052e-05,
"loss": 0.3865,
"step": 7390
},
{
"epoch": 7.51,
"learning_rate": 1.2436548223350254e-05,
"loss": 0.3076,
"step": 7400
},
{
"epoch": 7.52,
"learning_rate": 1.2385786802030459e-05,
"loss": 0.3722,
"step": 7410
},
{
"epoch": 7.53,
"learning_rate": 1.233502538071066e-05,
"loss": 0.3718,
"step": 7420
},
{
"epoch": 7.54,
"learning_rate": 1.2284263959390864e-05,
"loss": 0.3712,
"step": 7430
},
{
"epoch": 7.55,
"learning_rate": 1.2233502538071066e-05,
"loss": 0.3739,
"step": 7440
},
{
"epoch": 7.56,
"learning_rate": 1.218274111675127e-05,
"loss": 0.3785,
"step": 7450
},
{
"epoch": 7.57,
"learning_rate": 1.2131979695431472e-05,
"loss": 0.4023,
"step": 7460
},
{
"epoch": 7.58,
"learning_rate": 1.2081218274111676e-05,
"loss": 0.3679,
"step": 7470
},
{
"epoch": 7.59,
"learning_rate": 1.203045685279188e-05,
"loss": 0.3654,
"step": 7480
},
{
"epoch": 7.6,
"learning_rate": 1.1979695431472083e-05,
"loss": 0.3795,
"step": 7490
},
{
"epoch": 7.61,
"learning_rate": 1.1928934010152284e-05,
"loss": 0.388,
"step": 7500
},
{
"epoch": 7.62,
"learning_rate": 1.1878172588832488e-05,
"loss": 0.4037,
"step": 7510
},
{
"epoch": 7.63,
"learning_rate": 1.1827411167512691e-05,
"loss": 0.4065,
"step": 7520
},
{
"epoch": 7.64,
"learning_rate": 1.1776649746192895e-05,
"loss": 0.4386,
"step": 7530
},
{
"epoch": 7.65,
"learning_rate": 1.1725888324873096e-05,
"loss": 0.3756,
"step": 7540
},
{
"epoch": 7.66,
"learning_rate": 1.16751269035533e-05,
"loss": 0.3961,
"step": 7550
},
{
"epoch": 7.68,
"learning_rate": 1.1624365482233503e-05,
"loss": 0.3452,
"step": 7560
},
{
"epoch": 7.69,
"learning_rate": 1.1573604060913707e-05,
"loss": 0.3705,
"step": 7570
},
{
"epoch": 7.7,
"learning_rate": 1.1522842639593908e-05,
"loss": 0.4477,
"step": 7580
},
{
"epoch": 7.71,
"learning_rate": 1.1472081218274112e-05,
"loss": 0.3151,
"step": 7590
},
{
"epoch": 7.72,
"learning_rate": 1.1421319796954315e-05,
"loss": 0.3672,
"step": 7600
},
{
"epoch": 7.73,
"learning_rate": 1.1370558375634519e-05,
"loss": 0.3785,
"step": 7610
},
{
"epoch": 7.74,
"learning_rate": 1.131979695431472e-05,
"loss": 0.4126,
"step": 7620
},
{
"epoch": 7.75,
"learning_rate": 1.1269035532994924e-05,
"loss": 0.3809,
"step": 7630
},
{
"epoch": 7.76,
"learning_rate": 1.1218274111675127e-05,
"loss": 0.3474,
"step": 7640
},
{
"epoch": 7.77,
"learning_rate": 1.116751269035533e-05,
"loss": 0.3703,
"step": 7650
},
{
"epoch": 7.78,
"learning_rate": 1.1116751269035532e-05,
"loss": 0.3723,
"step": 7660
},
{
"epoch": 7.79,
"learning_rate": 1.1065989847715737e-05,
"loss": 0.3367,
"step": 7670
},
{
"epoch": 7.8,
"learning_rate": 1.101522842639594e-05,
"loss": 0.3852,
"step": 7680
},
{
"epoch": 7.81,
"learning_rate": 1.0964467005076143e-05,
"loss": 0.3682,
"step": 7690
},
{
"epoch": 7.82,
"learning_rate": 1.0913705583756344e-05,
"loss": 0.3827,
"step": 7700
},
{
"epoch": 7.83,
"learning_rate": 1.086294416243655e-05,
"loss": 0.3728,
"step": 7710
},
{
"epoch": 7.84,
"learning_rate": 1.0812182741116751e-05,
"loss": 0.4147,
"step": 7720
},
{
"epoch": 7.85,
"learning_rate": 1.0761421319796955e-05,
"loss": 0.4071,
"step": 7730
},
{
"epoch": 7.86,
"learning_rate": 1.0710659898477158e-05,
"loss": 0.4398,
"step": 7740
},
{
"epoch": 7.87,
"learning_rate": 1.0659898477157361e-05,
"loss": 0.3647,
"step": 7750
},
{
"epoch": 7.88,
"learning_rate": 1.0609137055837563e-05,
"loss": 0.3465,
"step": 7760
},
{
"epoch": 7.89,
"learning_rate": 1.0558375634517767e-05,
"loss": 0.3823,
"step": 7770
},
{
"epoch": 7.9,
"learning_rate": 1.050761421319797e-05,
"loss": 0.3775,
"step": 7780
},
{
"epoch": 7.91,
"learning_rate": 1.0456852791878173e-05,
"loss": 0.35,
"step": 7790
},
{
"epoch": 7.92,
"learning_rate": 1.0406091370558377e-05,
"loss": 0.4043,
"step": 7800
},
{
"epoch": 7.93,
"learning_rate": 1.0355329949238579e-05,
"loss": 0.3295,
"step": 7810
},
{
"epoch": 7.94,
"learning_rate": 1.0304568527918784e-05,
"loss": 0.325,
"step": 7820
},
{
"epoch": 7.95,
"learning_rate": 1.0253807106598985e-05,
"loss": 0.3443,
"step": 7830
},
{
"epoch": 7.96,
"learning_rate": 1.0203045685279189e-05,
"loss": 0.3893,
"step": 7840
},
{
"epoch": 7.97,
"learning_rate": 1.015228426395939e-05,
"loss": 0.3447,
"step": 7850
},
{
"epoch": 7.98,
"learning_rate": 1.0101522842639596e-05,
"loss": 0.3641,
"step": 7860
},
{
"epoch": 7.99,
"learning_rate": 1.0050761421319797e-05,
"loss": 0.3708,
"step": 7870
},
{
"epoch": 8.0,
"learning_rate": 1e-05,
"loss": 0.3843,
"step": 7880
},
{
"epoch": 8.0,
"eval_accuracy": 0.856,
"eval_loss": 0.3862883448600769,
"eval_runtime": 19.8008,
"eval_samples_per_second": 176.76,
"eval_steps_per_second": 22.12,
"step": 7880
},
{
"epoch": 8.01,
"learning_rate": 9.949238578680203e-06,
"loss": 0.4072,
"step": 7890
},
{
"epoch": 8.02,
"learning_rate": 9.898477157360408e-06,
"loss": 0.3572,
"step": 7900
},
{
"epoch": 8.03,
"learning_rate": 9.84771573604061e-06,
"loss": 0.4366,
"step": 7910
},
{
"epoch": 8.04,
"learning_rate": 9.796954314720813e-06,
"loss": 0.3389,
"step": 7920
},
{
"epoch": 8.05,
"learning_rate": 9.746192893401016e-06,
"loss": 0.3548,
"step": 7930
},
{
"epoch": 8.06,
"learning_rate": 9.69543147208122e-06,
"loss": 0.3839,
"step": 7940
},
{
"epoch": 8.07,
"learning_rate": 9.644670050761421e-06,
"loss": 0.3448,
"step": 7950
},
{
"epoch": 8.08,
"learning_rate": 9.593908629441625e-06,
"loss": 0.3689,
"step": 7960
},
{
"epoch": 8.09,
"learning_rate": 9.543147208121828e-06,
"loss": 0.3998,
"step": 7970
},
{
"epoch": 8.1,
"learning_rate": 9.492385786802032e-06,
"loss": 0.4348,
"step": 7980
},
{
"epoch": 8.11,
"learning_rate": 9.441624365482233e-06,
"loss": 0.355,
"step": 7990
},
{
"epoch": 8.12,
"learning_rate": 9.390862944162437e-06,
"loss": 0.3786,
"step": 8000
},
{
"epoch": 8.13,
"learning_rate": 9.34010152284264e-06,
"loss": 0.3997,
"step": 8010
},
{
"epoch": 8.14,
"learning_rate": 9.289340101522844e-06,
"loss": 0.3836,
"step": 8020
},
{
"epoch": 8.15,
"learning_rate": 9.238578680203045e-06,
"loss": 0.362,
"step": 8030
},
{
"epoch": 8.16,
"learning_rate": 9.187817258883249e-06,
"loss": 0.3865,
"step": 8040
},
{
"epoch": 8.17,
"learning_rate": 9.137055837563452e-06,
"loss": 0.3759,
"step": 8050
},
{
"epoch": 8.18,
"learning_rate": 9.086294416243656e-06,
"loss": 0.4245,
"step": 8060
},
{
"epoch": 8.19,
"learning_rate": 9.035532994923857e-06,
"loss": 0.4016,
"step": 8070
},
{
"epoch": 8.2,
"learning_rate": 8.984771573604062e-06,
"loss": 0.3923,
"step": 8080
},
{
"epoch": 8.21,
"learning_rate": 8.934010152284264e-06,
"loss": 0.3883,
"step": 8090
},
{
"epoch": 8.22,
"learning_rate": 8.883248730964468e-06,
"loss": 0.3787,
"step": 8100
},
{
"epoch": 8.23,
"learning_rate": 8.83248730964467e-06,
"loss": 0.384,
"step": 8110
},
{
"epoch": 8.24,
"learning_rate": 8.781725888324874e-06,
"loss": 0.3519,
"step": 8120
},
{
"epoch": 8.25,
"learning_rate": 8.730964467005076e-06,
"loss": 0.4376,
"step": 8130
},
{
"epoch": 8.26,
"learning_rate": 8.68020304568528e-06,
"loss": 0.3796,
"step": 8140
},
{
"epoch": 8.27,
"learning_rate": 8.629441624365483e-06,
"loss": 0.355,
"step": 8150
},
{
"epoch": 8.28,
"learning_rate": 8.578680203045686e-06,
"loss": 0.3477,
"step": 8160
},
{
"epoch": 8.29,
"learning_rate": 8.527918781725888e-06,
"loss": 0.3579,
"step": 8170
},
{
"epoch": 8.3,
"learning_rate": 8.477157360406092e-06,
"loss": 0.3265,
"step": 8180
},
{
"epoch": 8.31,
"learning_rate": 8.426395939086295e-06,
"loss": 0.3444,
"step": 8190
},
{
"epoch": 8.32,
"learning_rate": 8.375634517766498e-06,
"loss": 0.3519,
"step": 8200
},
{
"epoch": 8.34,
"learning_rate": 8.3248730964467e-06,
"loss": 0.3379,
"step": 8210
},
{
"epoch": 8.35,
"learning_rate": 8.274111675126904e-06,
"loss": 0.3741,
"step": 8220
},
{
"epoch": 8.36,
"learning_rate": 8.223350253807107e-06,
"loss": 0.3451,
"step": 8230
},
{
"epoch": 8.37,
"learning_rate": 8.17258883248731e-06,
"loss": 0.408,
"step": 8240
},
{
"epoch": 8.38,
"learning_rate": 8.121827411167512e-06,
"loss": 0.4492,
"step": 8250
},
{
"epoch": 8.39,
"learning_rate": 8.071065989847716e-06,
"loss": 0.3403,
"step": 8260
},
{
"epoch": 8.4,
"learning_rate": 8.020304568527919e-06,
"loss": 0.3697,
"step": 8270
},
{
"epoch": 8.41,
"learning_rate": 7.969543147208122e-06,
"loss": 0.3149,
"step": 8280
},
{
"epoch": 8.42,
"learning_rate": 7.918781725888324e-06,
"loss": 0.3825,
"step": 8290
},
{
"epoch": 8.43,
"learning_rate": 7.868020304568528e-06,
"loss": 0.3197,
"step": 8300
},
{
"epoch": 8.44,
"learning_rate": 7.817258883248733e-06,
"loss": 0.3891,
"step": 8310
},
{
"epoch": 8.45,
"learning_rate": 7.766497461928934e-06,
"loss": 0.3408,
"step": 8320
},
{
"epoch": 8.46,
"learning_rate": 7.715736040609138e-06,
"loss": 0.349,
"step": 8330
},
{
"epoch": 8.47,
"learning_rate": 7.664974619289341e-06,
"loss": 0.3381,
"step": 8340
},
{
"epoch": 8.48,
"learning_rate": 7.614213197969544e-06,
"loss": 0.3685,
"step": 8350
},
{
"epoch": 8.49,
"learning_rate": 7.563451776649746e-06,
"loss": 0.397,
"step": 8360
},
{
"epoch": 8.5,
"learning_rate": 7.512690355329951e-06,
"loss": 0.4219,
"step": 8370
},
{
"epoch": 8.51,
"learning_rate": 7.461928934010152e-06,
"loss": 0.3278,
"step": 8380
},
{
"epoch": 8.52,
"learning_rate": 7.411167512690357e-06,
"loss": 0.327,
"step": 8390
},
{
"epoch": 8.53,
"learning_rate": 7.360406091370558e-06,
"loss": 0.331,
"step": 8400
},
{
"epoch": 8.54,
"learning_rate": 7.309644670050763e-06,
"loss": 0.4005,
"step": 8410
},
{
"epoch": 8.55,
"learning_rate": 7.258883248730964e-06,
"loss": 0.4331,
"step": 8420
},
{
"epoch": 8.56,
"learning_rate": 7.208121827411169e-06,
"loss": 0.3391,
"step": 8430
},
{
"epoch": 8.57,
"learning_rate": 7.15736040609137e-06,
"loss": 0.4072,
"step": 8440
},
{
"epoch": 8.58,
"learning_rate": 7.106598984771575e-06,
"loss": 0.3726,
"step": 8450
},
{
"epoch": 8.59,
"learning_rate": 7.055837563451777e-06,
"loss": 0.4324,
"step": 8460
},
{
"epoch": 8.6,
"learning_rate": 7.0050761421319806e-06,
"loss": 0.4151,
"step": 8470
},
{
"epoch": 8.61,
"learning_rate": 6.954314720812183e-06,
"loss": 0.3809,
"step": 8480
},
{
"epoch": 8.62,
"learning_rate": 6.9035532994923866e-06,
"loss": 0.4054,
"step": 8490
},
{
"epoch": 8.63,
"learning_rate": 6.852791878172589e-06,
"loss": 0.3865,
"step": 8500
},
{
"epoch": 8.64,
"learning_rate": 6.8020304568527926e-06,
"loss": 0.3678,
"step": 8510
},
{
"epoch": 8.65,
"learning_rate": 6.751269035532995e-06,
"loss": 0.3814,
"step": 8520
},
{
"epoch": 8.66,
"learning_rate": 6.7005076142131985e-06,
"loss": 0.3767,
"step": 8530
},
{
"epoch": 8.67,
"learning_rate": 6.649746192893401e-06,
"loss": 0.378,
"step": 8540
},
{
"epoch": 8.68,
"learning_rate": 6.5989847715736045e-06,
"loss": 0.3617,
"step": 8550
},
{
"epoch": 8.69,
"learning_rate": 6.548223350253807e-06,
"loss": 0.3578,
"step": 8560
},
{
"epoch": 8.7,
"learning_rate": 6.4974619289340105e-06,
"loss": 0.3382,
"step": 8570
},
{
"epoch": 8.71,
"learning_rate": 6.446700507614213e-06,
"loss": 0.444,
"step": 8580
},
{
"epoch": 8.72,
"learning_rate": 6.3959390862944165e-06,
"loss": 0.3734,
"step": 8590
},
{
"epoch": 8.73,
"learning_rate": 6.345177664974619e-06,
"loss": 0.4135,
"step": 8600
},
{
"epoch": 8.74,
"learning_rate": 6.2944162436548225e-06,
"loss": 0.3715,
"step": 8610
},
{
"epoch": 8.75,
"learning_rate": 6.243654822335026e-06,
"loss": 0.3966,
"step": 8620
},
{
"epoch": 8.76,
"learning_rate": 6.192893401015229e-06,
"loss": 0.368,
"step": 8630
},
{
"epoch": 8.77,
"learning_rate": 6.142131979695432e-06,
"loss": 0.3784,
"step": 8640
},
{
"epoch": 8.78,
"learning_rate": 6.091370558375635e-06,
"loss": 0.403,
"step": 8650
},
{
"epoch": 8.79,
"learning_rate": 6.040609137055838e-06,
"loss": 0.377,
"step": 8660
},
{
"epoch": 8.8,
"learning_rate": 5.989847715736041e-06,
"loss": 0.41,
"step": 8670
},
{
"epoch": 8.81,
"learning_rate": 5.939086294416244e-06,
"loss": 0.3931,
"step": 8680
},
{
"epoch": 8.82,
"learning_rate": 5.888324873096447e-06,
"loss": 0.3659,
"step": 8690
},
{
"epoch": 8.83,
"learning_rate": 5.83756345177665e-06,
"loss": 0.3085,
"step": 8700
},
{
"epoch": 8.84,
"learning_rate": 5.786802030456853e-06,
"loss": 0.3969,
"step": 8710
},
{
"epoch": 8.85,
"learning_rate": 5.736040609137056e-06,
"loss": 0.4041,
"step": 8720
},
{
"epoch": 8.86,
"learning_rate": 5.685279187817259e-06,
"loss": 0.4323,
"step": 8730
},
{
"epoch": 8.87,
"learning_rate": 5.634517766497462e-06,
"loss": 0.37,
"step": 8740
},
{
"epoch": 8.88,
"learning_rate": 5.583756345177665e-06,
"loss": 0.3864,
"step": 8750
},
{
"epoch": 8.89,
"learning_rate": 5.532994923857869e-06,
"loss": 0.355,
"step": 8760
},
{
"epoch": 8.9,
"learning_rate": 5.482233502538071e-06,
"loss": 0.4104,
"step": 8770
},
{
"epoch": 8.91,
"learning_rate": 5.431472081218275e-06,
"loss": 0.4028,
"step": 8780
},
{
"epoch": 8.92,
"learning_rate": 5.380710659898477e-06,
"loss": 0.388,
"step": 8790
},
{
"epoch": 8.93,
"learning_rate": 5.329949238578681e-06,
"loss": 0.3545,
"step": 8800
},
{
"epoch": 8.94,
"learning_rate": 5.279187817258883e-06,
"loss": 0.3448,
"step": 8810
},
{
"epoch": 8.95,
"learning_rate": 5.228426395939087e-06,
"loss": 0.3331,
"step": 8820
},
{
"epoch": 8.96,
"learning_rate": 5.177664974619289e-06,
"loss": 0.4178,
"step": 8830
},
{
"epoch": 8.97,
"learning_rate": 5.126903553299493e-06,
"loss": 0.3534,
"step": 8840
},
{
"epoch": 8.98,
"learning_rate": 5.076142131979695e-06,
"loss": 0.3956,
"step": 8850
},
{
"epoch": 8.99,
"learning_rate": 5.025380710659899e-06,
"loss": 0.3923,
"step": 8860
},
{
"epoch": 9.0,
"eval_accuracy": 0.8574285714285714,
"eval_loss": 0.3861573338508606,
"eval_runtime": 19.7492,
"eval_samples_per_second": 177.223,
"eval_steps_per_second": 22.178,
"step": 8865
},
{
"epoch": 9.01,
"learning_rate": 4.974619289340101e-06,
"loss": 0.3303,
"step": 8870
},
{
"epoch": 9.02,
"learning_rate": 4.923857868020305e-06,
"loss": 0.3999,
"step": 8880
},
{
"epoch": 9.03,
"learning_rate": 4.873096446700508e-06,
"loss": 0.3881,
"step": 8890
},
{
"epoch": 9.04,
"learning_rate": 4.822335025380711e-06,
"loss": 0.3501,
"step": 8900
},
{
"epoch": 9.05,
"learning_rate": 4.771573604060914e-06,
"loss": 0.4286,
"step": 8910
},
{
"epoch": 9.06,
"learning_rate": 4.720812182741117e-06,
"loss": 0.3885,
"step": 8920
},
{
"epoch": 9.07,
"learning_rate": 4.67005076142132e-06,
"loss": 0.3726,
"step": 8930
},
{
"epoch": 9.08,
"learning_rate": 4.619289340101523e-06,
"loss": 0.3412,
"step": 8940
},
{
"epoch": 9.09,
"learning_rate": 4.568527918781726e-06,
"loss": 0.404,
"step": 8950
},
{
"epoch": 9.1,
"learning_rate": 4.517766497461929e-06,
"loss": 0.3262,
"step": 8960
},
{
"epoch": 9.11,
"learning_rate": 4.467005076142132e-06,
"loss": 0.3921,
"step": 8970
},
{
"epoch": 9.12,
"learning_rate": 4.416243654822335e-06,
"loss": 0.2955,
"step": 8980
},
{
"epoch": 9.13,
"learning_rate": 4.365482233502538e-06,
"loss": 0.3931,
"step": 8990
},
{
"epoch": 9.14,
"learning_rate": 4.3147208121827415e-06,
"loss": 0.3772,
"step": 9000
},
{
"epoch": 9.15,
"learning_rate": 4.263959390862944e-06,
"loss": 0.4227,
"step": 9010
},
{
"epoch": 9.16,
"learning_rate": 4.2131979695431475e-06,
"loss": 0.392,
"step": 9020
},
{
"epoch": 9.17,
"learning_rate": 4.16243654822335e-06,
"loss": 0.3915,
"step": 9030
},
{
"epoch": 9.18,
"learning_rate": 4.1116751269035535e-06,
"loss": 0.3616,
"step": 9040
},
{
"epoch": 9.19,
"learning_rate": 4.060913705583756e-06,
"loss": 0.3551,
"step": 9050
},
{
"epoch": 9.2,
"learning_rate": 4.0101522842639595e-06,
"loss": 0.4249,
"step": 9060
},
{
"epoch": 9.21,
"learning_rate": 3.959390862944162e-06,
"loss": 0.4044,
"step": 9070
},
{
"epoch": 9.22,
"learning_rate": 3.908629441624366e-06,
"loss": 0.4028,
"step": 9080
},
{
"epoch": 9.23,
"learning_rate": 3.857868020304569e-06,
"loss": 0.3671,
"step": 9090
},
{
"epoch": 9.24,
"learning_rate": 3.807106598984772e-06,
"loss": 0.3787,
"step": 9100
},
{
"epoch": 9.25,
"learning_rate": 3.7563451776649753e-06,
"loss": 0.3415,
"step": 9110
},
{
"epoch": 9.26,
"learning_rate": 3.7055837563451783e-06,
"loss": 0.413,
"step": 9120
},
{
"epoch": 9.27,
"learning_rate": 3.6548223350253813e-06,
"loss": 0.3902,
"step": 9130
},
{
"epoch": 9.28,
"learning_rate": 3.6040609137055843e-06,
"loss": 0.3658,
"step": 9140
},
{
"epoch": 9.29,
"learning_rate": 3.5532994923857873e-06,
"loss": 0.353,
"step": 9150
},
{
"epoch": 9.3,
"learning_rate": 3.5025380710659903e-06,
"loss": 0.4033,
"step": 9160
},
{
"epoch": 9.31,
"learning_rate": 3.4517766497461933e-06,
"loss": 0.3492,
"step": 9170
},
{
"epoch": 9.32,
"learning_rate": 3.4010152284263963e-06,
"loss": 0.3469,
"step": 9180
},
{
"epoch": 9.33,
"learning_rate": 3.3502538071065993e-06,
"loss": 0.3735,
"step": 9190
},
{
"epoch": 9.34,
"learning_rate": 3.2994923857868023e-06,
"loss": 0.4166,
"step": 9200
},
{
"epoch": 9.35,
"learning_rate": 3.2487309644670053e-06,
"loss": 0.3491,
"step": 9210
},
{
"epoch": 9.36,
"learning_rate": 3.1979695431472083e-06,
"loss": 0.4068,
"step": 9220
},
{
"epoch": 9.37,
"learning_rate": 3.1472081218274113e-06,
"loss": 0.3818,
"step": 9230
},
{
"epoch": 9.38,
"learning_rate": 3.0964467005076147e-06,
"loss": 0.3416,
"step": 9240
},
{
"epoch": 9.39,
"learning_rate": 3.0456852791878177e-06,
"loss": 0.3663,
"step": 9250
},
{
"epoch": 9.4,
"learning_rate": 2.9949238578680207e-06,
"loss": 0.3441,
"step": 9260
},
{
"epoch": 9.41,
"learning_rate": 2.9441624365482237e-06,
"loss": 0.3255,
"step": 9270
},
{
"epoch": 9.42,
"learning_rate": 2.8934010152284267e-06,
"loss": 0.4247,
"step": 9280
},
{
"epoch": 9.43,
"learning_rate": 2.8426395939086297e-06,
"loss": 0.3584,
"step": 9290
},
{
"epoch": 9.44,
"learning_rate": 2.7918781725888327e-06,
"loss": 0.3966,
"step": 9300
},
{
"epoch": 9.45,
"learning_rate": 2.7411167512690357e-06,
"loss": 0.3965,
"step": 9310
},
{
"epoch": 9.46,
"learning_rate": 2.6903553299492387e-06,
"loss": 0.4403,
"step": 9320
},
{
"epoch": 9.47,
"learning_rate": 2.6395939086294416e-06,
"loss": 0.422,
"step": 9330
},
{
"epoch": 9.48,
"learning_rate": 2.5888324873096446e-06,
"loss": 0.3455,
"step": 9340
},
{
"epoch": 9.49,
"learning_rate": 2.5380710659898476e-06,
"loss": 0.4231,
"step": 9350
},
{
"epoch": 9.5,
"learning_rate": 2.4873096446700506e-06,
"loss": 0.365,
"step": 9360
},
{
"epoch": 9.51,
"learning_rate": 2.436548223350254e-06,
"loss": 0.3742,
"step": 9370
},
{
"epoch": 9.52,
"learning_rate": 2.385786802030457e-06,
"loss": 0.3381,
"step": 9380
},
{
"epoch": 9.53,
"learning_rate": 2.33502538071066e-06,
"loss": 0.3927,
"step": 9390
},
{
"epoch": 9.54,
"learning_rate": 2.284263959390863e-06,
"loss": 0.3304,
"step": 9400
},
{
"epoch": 9.55,
"learning_rate": 2.233502538071066e-06,
"loss": 0.374,
"step": 9410
},
{
"epoch": 9.56,
"learning_rate": 2.182741116751269e-06,
"loss": 0.3525,
"step": 9420
},
{
"epoch": 9.57,
"learning_rate": 2.131979695431472e-06,
"loss": 0.436,
"step": 9430
},
{
"epoch": 9.58,
"learning_rate": 2.081218274111675e-06,
"loss": 0.3924,
"step": 9440
},
{
"epoch": 9.59,
"learning_rate": 2.030456852791878e-06,
"loss": 0.4045,
"step": 9450
},
{
"epoch": 9.6,
"learning_rate": 1.979695431472081e-06,
"loss": 0.4145,
"step": 9460
},
{
"epoch": 9.61,
"learning_rate": 1.9289340101522844e-06,
"loss": 0.3316,
"step": 9470
},
{
"epoch": 9.62,
"learning_rate": 1.8781725888324877e-06,
"loss": 0.3521,
"step": 9480
},
{
"epoch": 9.63,
"learning_rate": 1.8274111675126906e-06,
"loss": 0.3796,
"step": 9490
},
{
"epoch": 9.64,
"learning_rate": 1.7766497461928936e-06,
"loss": 0.3927,
"step": 9500
},
{
"epoch": 9.65,
"learning_rate": 1.7258883248730966e-06,
"loss": 0.3598,
"step": 9510
},
{
"epoch": 9.66,
"learning_rate": 1.6751269035532996e-06,
"loss": 0.3668,
"step": 9520
},
{
"epoch": 9.68,
"learning_rate": 1.6243654822335026e-06,
"loss": 0.424,
"step": 9530
},
{
"epoch": 9.69,
"learning_rate": 1.5736040609137056e-06,
"loss": 0.3362,
"step": 9540
},
{
"epoch": 9.7,
"learning_rate": 1.5228426395939088e-06,
"loss": 0.3922,
"step": 9550
},
{
"epoch": 9.71,
"learning_rate": 1.4720812182741118e-06,
"loss": 0.394,
"step": 9560
},
{
"epoch": 9.72,
"learning_rate": 1.4213197969543148e-06,
"loss": 0.3718,
"step": 9570
},
{
"epoch": 9.73,
"learning_rate": 1.3705583756345178e-06,
"loss": 0.3932,
"step": 9580
},
{
"epoch": 9.74,
"learning_rate": 1.3197969543147208e-06,
"loss": 0.3343,
"step": 9590
},
{
"epoch": 9.75,
"learning_rate": 1.2690355329949238e-06,
"loss": 0.4285,
"step": 9600
},
{
"epoch": 9.76,
"learning_rate": 1.218274111675127e-06,
"loss": 0.3403,
"step": 9610
},
{
"epoch": 9.77,
"learning_rate": 1.16751269035533e-06,
"loss": 0.3399,
"step": 9620
},
{
"epoch": 9.78,
"learning_rate": 1.116751269035533e-06,
"loss": 0.3668,
"step": 9630
},
{
"epoch": 9.79,
"learning_rate": 1.065989847715736e-06,
"loss": 0.3751,
"step": 9640
},
{
"epoch": 9.8,
"learning_rate": 1.015228426395939e-06,
"loss": 0.3423,
"step": 9650
},
{
"epoch": 9.81,
"learning_rate": 9.644670050761422e-07,
"loss": 0.329,
"step": 9660
},
{
"epoch": 9.82,
"learning_rate": 9.137055837563453e-07,
"loss": 0.4278,
"step": 9670
},
{
"epoch": 9.83,
"learning_rate": 8.629441624365483e-07,
"loss": 0.3725,
"step": 9680
},
{
"epoch": 9.84,
"learning_rate": 8.121827411167513e-07,
"loss": 0.3725,
"step": 9690
},
{
"epoch": 9.85,
"learning_rate": 7.614213197969544e-07,
"loss": 0.4105,
"step": 9700
},
{
"epoch": 9.86,
"learning_rate": 7.106598984771574e-07,
"loss": 0.3478,
"step": 9710
},
{
"epoch": 9.87,
"learning_rate": 6.598984771573604e-07,
"loss": 0.3152,
"step": 9720
},
{
"epoch": 9.88,
"learning_rate": 6.091370558375635e-07,
"loss": 0.2872,
"step": 9730
},
{
"epoch": 9.89,
"learning_rate": 5.583756345177665e-07,
"loss": 0.4,
"step": 9740
},
{
"epoch": 9.9,
"learning_rate": 5.076142131979695e-07,
"loss": 0.348,
"step": 9750
},
{
"epoch": 9.91,
"learning_rate": 4.5685279187817266e-07,
"loss": 0.3532,
"step": 9760
},
{
"epoch": 9.92,
"learning_rate": 4.0609137055837566e-07,
"loss": 0.4404,
"step": 9770
},
{
"epoch": 9.93,
"learning_rate": 3.553299492385787e-07,
"loss": 0.4072,
"step": 9780
},
{
"epoch": 9.94,
"learning_rate": 3.0456852791878176e-07,
"loss": 0.3772,
"step": 9790
},
{
"epoch": 9.95,
"learning_rate": 2.5380710659898475e-07,
"loss": 0.3952,
"step": 9800
},
{
"epoch": 9.96,
"learning_rate": 2.0304568527918783e-07,
"loss": 0.3343,
"step": 9810
},
{
"epoch": 9.97,
"learning_rate": 1.5228426395939088e-07,
"loss": 0.3766,
"step": 9820
},
{
"epoch": 9.98,
"learning_rate": 1.0152284263959391e-07,
"loss": 0.4123,
"step": 9830
},
{
"epoch": 9.99,
"learning_rate": 5.076142131979696e-08,
"loss": 0.3489,
"step": 9840
},
{
"epoch": 10.0,
"learning_rate": 0.0,
"loss": 0.3425,
"step": 9850
},
{
"epoch": 10.0,
"eval_accuracy": 0.8568571428571429,
"eval_loss": 0.386042058467865,
"eval_runtime": 19.7991,
"eval_samples_per_second": 176.776,
"eval_steps_per_second": 22.122,
"step": 9850
}
],
"max_steps": 9850,
"num_train_epochs": 10,
"total_flos": 4.233589549056e+16,
"trial_name": null,
"trial_params": null
}