rqadri's picture
Add files using upload-large-folder tool
11c496b verified
Raw History Blame Contribute Delete
180 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9990182954038376,
"eval_steps": 500,
"global_step": 11194,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.000892458723784025,
"grad_norm": 3.045154571533203,
"learning_rate": 1.1061797752808989e-06,
"loss": 1.3662,
"step": 10
},
{
"epoch": 0.00178491744756805,
"grad_norm": 2.2175650596618652,
"learning_rate": 2.2241573033707866e-06,
"loss": 1.4403,
"step": 20
},
{
"epoch": 0.002677376171352075,
"grad_norm": 1.860337734222412,
"learning_rate": 3.342134831460675e-06,
"loss": 1.1652,
"step": 30
},
{
"epoch": 0.0035698348951361,
"grad_norm": 0.9244102239608765,
"learning_rate": 4.4601123595505624e-06,
"loss": 0.9807,
"step": 40
},
{
"epoch": 0.004462293618920125,
"grad_norm": 0.6792669296264648,
"learning_rate": 5.5780898876404495e-06,
"loss": 0.8353,
"step": 50
},
{
"epoch": 0.00535475234270415,
"grad_norm": 0.47331929206848145,
"learning_rate": 6.6960674157303374e-06,
"loss": 0.8033,
"step": 60
},
{
"epoch": 0.006247211066488175,
"grad_norm": 0.44425472617149353,
"learning_rate": 7.814044943820226e-06,
"loss": 0.7722,
"step": 70
},
{
"epoch": 0.0071396697902722,
"grad_norm": 0.48765331506729126,
"learning_rate": 8.932022471910112e-06,
"loss": 0.7988,
"step": 80
},
{
"epoch": 0.008032128514056224,
"grad_norm": 0.5558447241783142,
"learning_rate": 1.005e-05,
"loss": 0.7813,
"step": 90
},
{
"epoch": 0.00892458723784025,
"grad_norm": 0.4752425253391266,
"learning_rate": 1.1167977528089888e-05,
"loss": 0.7892,
"step": 100
},
{
"epoch": 0.009817045961624275,
"grad_norm": 0.4644387364387512,
"learning_rate": 1.2285955056179776e-05,
"loss": 0.7592,
"step": 110
},
{
"epoch": 0.0107095046854083,
"grad_norm": 0.5231781601905823,
"learning_rate": 1.3403932584269664e-05,
"loss": 0.7798,
"step": 120
},
{
"epoch": 0.011601963409192326,
"grad_norm": 0.5505983233451843,
"learning_rate": 1.4521910112359552e-05,
"loss": 0.778,
"step": 130
},
{
"epoch": 0.01249442213297635,
"grad_norm": 0.805553138256073,
"learning_rate": 1.563988764044944e-05,
"loss": 0.7573,
"step": 140
},
{
"epoch": 0.013386880856760375,
"grad_norm": 0.4206564724445343,
"learning_rate": 1.6757865168539328e-05,
"loss": 0.7692,
"step": 150
},
{
"epoch": 0.0142793395805444,
"grad_norm": 0.49315696954727173,
"learning_rate": 1.7875842696629214e-05,
"loss": 0.7773,
"step": 160
},
{
"epoch": 0.015171798304328426,
"grad_norm": 0.5224491953849792,
"learning_rate": 1.89938202247191e-05,
"loss": 0.7728,
"step": 170
},
{
"epoch": 0.01606425702811245,
"grad_norm": 0.43197882175445557,
"learning_rate": 2e-05,
"loss": 0.7919,
"step": 180
},
{
"epoch": 0.016956715751896476,
"grad_norm": 0.49200326204299927,
"learning_rate": 2e-05,
"loss": 0.7639,
"step": 190
},
{
"epoch": 0.0178491744756805,
"grad_norm": 0.44408541917800903,
"learning_rate": 2e-05,
"loss": 0.7361,
"step": 200
},
{
"epoch": 0.018741633199464525,
"grad_norm": 0.5795125961303711,
"learning_rate": 2e-05,
"loss": 0.8062,
"step": 210
},
{
"epoch": 0.01963409192324855,
"grad_norm": 0.4349335730075836,
"learning_rate": 2e-05,
"loss": 0.7885,
"step": 220
},
{
"epoch": 0.020526550647032574,
"grad_norm": 0.4409690201282501,
"learning_rate": 2e-05,
"loss": 0.7942,
"step": 230
},
{
"epoch": 0.0214190093708166,
"grad_norm": 0.43803665041923523,
"learning_rate": 2e-05,
"loss": 0.7597,
"step": 240
},
{
"epoch": 0.022311468094600623,
"grad_norm": 0.43824803829193115,
"learning_rate": 2e-05,
"loss": 0.7669,
"step": 250
},
{
"epoch": 0.02320392681838465,
"grad_norm": 0.43911799788475037,
"learning_rate": 2e-05,
"loss": 0.7453,
"step": 260
},
{
"epoch": 0.024096385542168676,
"grad_norm": 0.39943230152130127,
"learning_rate": 2e-05,
"loss": 0.7293,
"step": 270
},
{
"epoch": 0.0249888442659527,
"grad_norm": 0.44129323959350586,
"learning_rate": 2e-05,
"loss": 0.8173,
"step": 280
},
{
"epoch": 0.025881302989736725,
"grad_norm": 0.40437787771224976,
"learning_rate": 2e-05,
"loss": 0.7626,
"step": 290
},
{
"epoch": 0.02677376171352075,
"grad_norm": 0.46044057607650757,
"learning_rate": 2e-05,
"loss": 0.7705,
"step": 300
},
{
"epoch": 0.027666220437304774,
"grad_norm": 0.5197446346282959,
"learning_rate": 2e-05,
"loss": 0.7439,
"step": 310
},
{
"epoch": 0.0285586791610888,
"grad_norm": 0.4308314323425293,
"learning_rate": 2e-05,
"loss": 0.8261,
"step": 320
},
{
"epoch": 0.029451137884872823,
"grad_norm": 0.43585020303726196,
"learning_rate": 2e-05,
"loss": 0.7583,
"step": 330
},
{
"epoch": 0.03034359660865685,
"grad_norm": 0.43804678320884705,
"learning_rate": 2e-05,
"loss": 0.7712,
"step": 340
},
{
"epoch": 0.031236055332440876,
"grad_norm": 0.4321230351924896,
"learning_rate": 2e-05,
"loss": 0.7558,
"step": 350
},
{
"epoch": 0.0321285140562249,
"grad_norm": 0.426249623298645,
"learning_rate": 2e-05,
"loss": 0.7652,
"step": 360
},
{
"epoch": 0.03302097278000892,
"grad_norm": 0.4081008732318878,
"learning_rate": 2e-05,
"loss": 0.7536,
"step": 370
},
{
"epoch": 0.03391343150379295,
"grad_norm": 0.6208111047744751,
"learning_rate": 2e-05,
"loss": 0.7511,
"step": 380
},
{
"epoch": 0.03480589022757698,
"grad_norm": 0.45165306329727173,
"learning_rate": 2e-05,
"loss": 0.7612,
"step": 390
},
{
"epoch": 0.035698348951361,
"grad_norm": 0.8442327380180359,
"learning_rate": 2e-05,
"loss": 0.7757,
"step": 400
},
{
"epoch": 0.036590807675145026,
"grad_norm": 0.43777230381965637,
"learning_rate": 2e-05,
"loss": 0.7554,
"step": 410
},
{
"epoch": 0.03748326639892905,
"grad_norm": 0.4242396950721741,
"learning_rate": 2e-05,
"loss": 0.7437,
"step": 420
},
{
"epoch": 0.038375725122713075,
"grad_norm": 0.44561508297920227,
"learning_rate": 2e-05,
"loss": 0.7579,
"step": 430
},
{
"epoch": 0.0392681838464971,
"grad_norm": 0.4057537615299225,
"learning_rate": 2e-05,
"loss": 0.7672,
"step": 440
},
{
"epoch": 0.040160642570281124,
"grad_norm": 0.4248247444629669,
"learning_rate": 2e-05,
"loss": 0.7517,
"step": 450
},
{
"epoch": 0.04105310129406515,
"grad_norm": 0.38674187660217285,
"learning_rate": 2e-05,
"loss": 0.7649,
"step": 460
},
{
"epoch": 0.04194556001784917,
"grad_norm": 0.4590655267238617,
"learning_rate": 2e-05,
"loss": 0.7138,
"step": 470
},
{
"epoch": 0.0428380187416332,
"grad_norm": 0.38914060592651367,
"learning_rate": 2e-05,
"loss": 0.7533,
"step": 480
},
{
"epoch": 0.04373047746541722,
"grad_norm": 0.4345904588699341,
"learning_rate": 2e-05,
"loss": 0.7323,
"step": 490
},
{
"epoch": 0.04462293618920125,
"grad_norm": 0.372398316860199,
"learning_rate": 2e-05,
"loss": 0.722,
"step": 500
},
{
"epoch": 0.04551539491298527,
"grad_norm": 0.39427366852760315,
"learning_rate": 2e-05,
"loss": 0.7649,
"step": 510
},
{
"epoch": 0.0464078536367693,
"grad_norm": 0.45776817202568054,
"learning_rate": 2e-05,
"loss": 0.761,
"step": 520
},
{
"epoch": 0.04730031236055333,
"grad_norm": 0.4311637282371521,
"learning_rate": 2e-05,
"loss": 0.7761,
"step": 530
},
{
"epoch": 0.04819277108433735,
"grad_norm": 0.3782254457473755,
"learning_rate": 2e-05,
"loss": 0.734,
"step": 540
},
{
"epoch": 0.049085229808121376,
"grad_norm": 0.4318030774593353,
"learning_rate": 2e-05,
"loss": 0.7658,
"step": 550
},
{
"epoch": 0.0499776885319054,
"grad_norm": 0.4350939691066742,
"learning_rate": 2e-05,
"loss": 0.7765,
"step": 560
},
{
"epoch": 0.050870147255689425,
"grad_norm": 0.4095909595489502,
"learning_rate": 2e-05,
"loss": 0.76,
"step": 570
},
{
"epoch": 0.05176260597947345,
"grad_norm": 0.3846561908721924,
"learning_rate": 2e-05,
"loss": 0.7516,
"step": 580
},
{
"epoch": 0.052655064703257475,
"grad_norm": 0.4147850573062897,
"learning_rate": 2e-05,
"loss": 0.7674,
"step": 590
},
{
"epoch": 0.0535475234270415,
"grad_norm": 0.41225138306617737,
"learning_rate": 2e-05,
"loss": 0.7489,
"step": 600
},
{
"epoch": 0.054439982150825524,
"grad_norm": 0.4051811099052429,
"learning_rate": 2e-05,
"loss": 0.7396,
"step": 610
},
{
"epoch": 0.05533244087460955,
"grad_norm": 0.3863374590873718,
"learning_rate": 2e-05,
"loss": 0.7477,
"step": 620
},
{
"epoch": 0.05622489959839357,
"grad_norm": 0.3682566285133362,
"learning_rate": 2e-05,
"loss": 0.7675,
"step": 630
},
{
"epoch": 0.0571173583221776,
"grad_norm": 0.38680627942085266,
"learning_rate": 2e-05,
"loss": 0.7149,
"step": 640
},
{
"epoch": 0.05800981704596162,
"grad_norm": 0.4512251317501068,
"learning_rate": 2e-05,
"loss": 0.7598,
"step": 650
},
{
"epoch": 0.058902275769745646,
"grad_norm": 0.45277082920074463,
"learning_rate": 2e-05,
"loss": 0.7227,
"step": 660
},
{
"epoch": 0.05979473449352968,
"grad_norm": 0.4341653287410736,
"learning_rate": 2e-05,
"loss": 0.7798,
"step": 670
},
{
"epoch": 0.0606871932173137,
"grad_norm": 0.4053642749786377,
"learning_rate": 2e-05,
"loss": 0.7448,
"step": 680
},
{
"epoch": 0.06157965194109773,
"grad_norm": 0.4231747090816498,
"learning_rate": 2e-05,
"loss": 0.7582,
"step": 690
},
{
"epoch": 0.06247211066488175,
"grad_norm": 0.3956149220466614,
"learning_rate": 2e-05,
"loss": 0.7584,
"step": 700
},
{
"epoch": 0.06336456938866578,
"grad_norm": 0.4424019157886505,
"learning_rate": 2e-05,
"loss": 0.731,
"step": 710
},
{
"epoch": 0.0642570281124498,
"grad_norm": 0.44977128505706787,
"learning_rate": 2e-05,
"loss": 0.7346,
"step": 720
},
{
"epoch": 0.06514948683623382,
"grad_norm": 0.4080374240875244,
"learning_rate": 2e-05,
"loss": 0.7478,
"step": 730
},
{
"epoch": 0.06604194556001784,
"grad_norm": 0.40351366996765137,
"learning_rate": 2e-05,
"loss": 0.7308,
"step": 740
},
{
"epoch": 0.06693440428380187,
"grad_norm": 0.3880046606063843,
"learning_rate": 2e-05,
"loss": 0.7466,
"step": 750
},
{
"epoch": 0.0678268630075859,
"grad_norm": 0.3946651518344879,
"learning_rate": 2e-05,
"loss": 0.7579,
"step": 760
},
{
"epoch": 0.06871932173136992,
"grad_norm": 0.3880173861980438,
"learning_rate": 2e-05,
"loss": 0.7346,
"step": 770
},
{
"epoch": 0.06961178045515395,
"grad_norm": 0.38916459679603577,
"learning_rate": 2e-05,
"loss": 0.7219,
"step": 780
},
{
"epoch": 0.07050423917893797,
"grad_norm": 0.3937828838825226,
"learning_rate": 2e-05,
"loss": 0.76,
"step": 790
},
{
"epoch": 0.071396697902722,
"grad_norm": 0.43031296133995056,
"learning_rate": 2e-05,
"loss": 0.758,
"step": 800
},
{
"epoch": 0.07228915662650602,
"grad_norm": 0.4201333224773407,
"learning_rate": 2e-05,
"loss": 0.7449,
"step": 810
},
{
"epoch": 0.07318161535029005,
"grad_norm": 0.3999972343444824,
"learning_rate": 2e-05,
"loss": 0.7487,
"step": 820
},
{
"epoch": 0.07407407407407407,
"grad_norm": 0.39585524797439575,
"learning_rate": 2e-05,
"loss": 0.7076,
"step": 830
},
{
"epoch": 0.0749665327978581,
"grad_norm": 0.3961842656135559,
"learning_rate": 2e-05,
"loss": 0.7031,
"step": 840
},
{
"epoch": 0.07585899152164212,
"grad_norm": 0.3905622363090515,
"learning_rate": 2e-05,
"loss": 0.7484,
"step": 850
},
{
"epoch": 0.07675145024542615,
"grad_norm": 0.40534672141075134,
"learning_rate": 2e-05,
"loss": 0.739,
"step": 860
},
{
"epoch": 0.07764390896921017,
"grad_norm": 0.38796329498291016,
"learning_rate": 2e-05,
"loss": 0.7236,
"step": 870
},
{
"epoch": 0.0785363676929942,
"grad_norm": 0.5421860218048096,
"learning_rate": 2e-05,
"loss": 0.7263,
"step": 880
},
{
"epoch": 0.07942882641677822,
"grad_norm": 0.4691896140575409,
"learning_rate": 2e-05,
"loss": 0.7289,
"step": 890
},
{
"epoch": 0.08032128514056225,
"grad_norm": 0.4255770742893219,
"learning_rate": 2e-05,
"loss": 0.7399,
"step": 900
},
{
"epoch": 0.08121374386434628,
"grad_norm": 0.3914809823036194,
"learning_rate": 2e-05,
"loss": 0.7908,
"step": 910
},
{
"epoch": 0.0821062025881303,
"grad_norm": 0.3992801010608673,
"learning_rate": 2e-05,
"loss": 0.7144,
"step": 920
},
{
"epoch": 0.08299866131191433,
"grad_norm": 0.3806823194026947,
"learning_rate": 2e-05,
"loss": 0.7471,
"step": 930
},
{
"epoch": 0.08389112003569835,
"grad_norm": 0.546196460723877,
"learning_rate": 2e-05,
"loss": 0.6958,
"step": 940
},
{
"epoch": 0.08478357875948238,
"grad_norm": 0.5522550344467163,
"learning_rate": 2e-05,
"loss": 0.7481,
"step": 950
},
{
"epoch": 0.0856760374832664,
"grad_norm": 0.421906977891922,
"learning_rate": 2e-05,
"loss": 0.7771,
"step": 960
},
{
"epoch": 0.08656849620705043,
"grad_norm": 0.381605327129364,
"learning_rate": 2e-05,
"loss": 0.7512,
"step": 970
},
{
"epoch": 0.08746095493083444,
"grad_norm": 0.5547103881835938,
"learning_rate": 2e-05,
"loss": 0.7529,
"step": 980
},
{
"epoch": 0.08835341365461848,
"grad_norm": 0.41171810030937195,
"learning_rate": 2e-05,
"loss": 0.7224,
"step": 990
},
{
"epoch": 0.0892458723784025,
"grad_norm": 0.3596498370170593,
"learning_rate": 2e-05,
"loss": 0.7414,
"step": 1000
},
{
"epoch": 0.09013833110218653,
"grad_norm": 0.46202516555786133,
"learning_rate": 2e-05,
"loss": 0.7322,
"step": 1010
},
{
"epoch": 0.09103078982597054,
"grad_norm": 0.39855870604515076,
"learning_rate": 2e-05,
"loss": 0.7243,
"step": 1020
},
{
"epoch": 0.09192324854975457,
"grad_norm": 0.38900578022003174,
"learning_rate": 2e-05,
"loss": 0.7178,
"step": 1030
},
{
"epoch": 0.0928157072735386,
"grad_norm": 0.4451678395271301,
"learning_rate": 2e-05,
"loss": 0.7473,
"step": 1040
},
{
"epoch": 0.09370816599732262,
"grad_norm": 0.3663797676563263,
"learning_rate": 2e-05,
"loss": 0.7148,
"step": 1050
},
{
"epoch": 0.09460062472110665,
"grad_norm": 0.3737003803253174,
"learning_rate": 2e-05,
"loss": 0.7308,
"step": 1060
},
{
"epoch": 0.09549308344489067,
"grad_norm": 0.5132238864898682,
"learning_rate": 2e-05,
"loss": 0.7483,
"step": 1070
},
{
"epoch": 0.0963855421686747,
"grad_norm": 0.39757436513900757,
"learning_rate": 2e-05,
"loss": 0.7055,
"step": 1080
},
{
"epoch": 0.09727800089245872,
"grad_norm": 0.3889594078063965,
"learning_rate": 2e-05,
"loss": 0.7647,
"step": 1090
},
{
"epoch": 0.09817045961624275,
"grad_norm": 0.40366658568382263,
"learning_rate": 2e-05,
"loss": 0.7453,
"step": 1100
},
{
"epoch": 0.09906291834002677,
"grad_norm": 0.37995877861976624,
"learning_rate": 2e-05,
"loss": 0.7417,
"step": 1110
},
{
"epoch": 0.0999553770638108,
"grad_norm": 0.3837803304195404,
"learning_rate": 2e-05,
"loss": 0.728,
"step": 1120
},
{
"epoch": 0.10084783578759482,
"grad_norm": 0.37044045329093933,
"learning_rate": 2e-05,
"loss": 0.7216,
"step": 1130
},
{
"epoch": 0.10174029451137885,
"grad_norm": 0.3822389245033264,
"learning_rate": 2e-05,
"loss": 0.7075,
"step": 1140
},
{
"epoch": 0.10263275323516287,
"grad_norm": 0.3520481288433075,
"learning_rate": 2e-05,
"loss": 0.7131,
"step": 1150
},
{
"epoch": 0.1035252119589469,
"grad_norm": 0.38390985131263733,
"learning_rate": 2e-05,
"loss": 0.7559,
"step": 1160
},
{
"epoch": 0.10441767068273092,
"grad_norm": 0.3780132830142975,
"learning_rate": 2e-05,
"loss": 0.7224,
"step": 1170
},
{
"epoch": 0.10531012940651495,
"grad_norm": 0.4197860062122345,
"learning_rate": 2e-05,
"loss": 0.7275,
"step": 1180
},
{
"epoch": 0.10620258813029898,
"grad_norm": 0.3551185131072998,
"learning_rate": 2e-05,
"loss": 0.7118,
"step": 1190
},
{
"epoch": 0.107095046854083,
"grad_norm": 0.36302730441093445,
"learning_rate": 2e-05,
"loss": 0.7032,
"step": 1200
},
{
"epoch": 0.10798750557786703,
"grad_norm": 0.4428386688232422,
"learning_rate": 2e-05,
"loss": 0.7687,
"step": 1210
},
{
"epoch": 0.10887996430165105,
"grad_norm": 0.3998299539089203,
"learning_rate": 2e-05,
"loss": 0.7204,
"step": 1220
},
{
"epoch": 0.10977242302543508,
"grad_norm": 0.3677099347114563,
"learning_rate": 2e-05,
"loss": 0.7057,
"step": 1230
},
{
"epoch": 0.1106648817492191,
"grad_norm": 0.4453865885734558,
"learning_rate": 2e-05,
"loss": 0.7309,
"step": 1240
},
{
"epoch": 0.11155734047300313,
"grad_norm": 0.35671019554138184,
"learning_rate": 2e-05,
"loss": 0.6845,
"step": 1250
},
{
"epoch": 0.11244979919678715,
"grad_norm": 0.38202935457229614,
"learning_rate": 2e-05,
"loss": 0.72,
"step": 1260
},
{
"epoch": 0.11334225792057118,
"grad_norm": 0.38386300206184387,
"learning_rate": 2e-05,
"loss": 0.7228,
"step": 1270
},
{
"epoch": 0.1142347166443552,
"grad_norm": 0.41439297795295715,
"learning_rate": 2e-05,
"loss": 0.7334,
"step": 1280
},
{
"epoch": 0.11512717536813923,
"grad_norm": 0.39205095171928406,
"learning_rate": 2e-05,
"loss": 0.7325,
"step": 1290
},
{
"epoch": 0.11601963409192324,
"grad_norm": 0.4260752201080322,
"learning_rate": 2e-05,
"loss": 0.7129,
"step": 1300
},
{
"epoch": 0.11691209281570727,
"grad_norm": 0.35168108344078064,
"learning_rate": 2e-05,
"loss": 0.7003,
"step": 1310
},
{
"epoch": 0.11780455153949129,
"grad_norm": 0.354591965675354,
"learning_rate": 2e-05,
"loss": 0.7081,
"step": 1320
},
{
"epoch": 0.11869701026327532,
"grad_norm": 0.3994496762752533,
"learning_rate": 2e-05,
"loss": 0.7348,
"step": 1330
},
{
"epoch": 0.11958946898705936,
"grad_norm": 0.3687463402748108,
"learning_rate": 2e-05,
"loss": 0.7138,
"step": 1340
},
{
"epoch": 0.12048192771084337,
"grad_norm": 0.3527894914150238,
"learning_rate": 2e-05,
"loss": 0.7331,
"step": 1350
},
{
"epoch": 0.1213743864346274,
"grad_norm": 0.39547526836395264,
"learning_rate": 2e-05,
"loss": 0.6874,
"step": 1360
},
{
"epoch": 0.12226684515841142,
"grad_norm": 0.35508838295936584,
"learning_rate": 2e-05,
"loss": 0.7588,
"step": 1370
},
{
"epoch": 0.12315930388219545,
"grad_norm": 0.3983374238014221,
"learning_rate": 2e-05,
"loss": 0.7383,
"step": 1380
},
{
"epoch": 0.12405176260597947,
"grad_norm": 0.35641518235206604,
"learning_rate": 2e-05,
"loss": 0.7357,
"step": 1390
},
{
"epoch": 0.1249442213297635,
"grad_norm": 0.41379478573799133,
"learning_rate": 2e-05,
"loss": 0.7257,
"step": 1400
},
{
"epoch": 0.12583668005354753,
"grad_norm": 0.39988917112350464,
"learning_rate": 2e-05,
"loss": 0.7272,
"step": 1410
},
{
"epoch": 0.12672913877733155,
"grad_norm": 0.3463815152645111,
"learning_rate": 2e-05,
"loss": 0.7595,
"step": 1420
},
{
"epoch": 0.12762159750111557,
"grad_norm": 0.36326804757118225,
"learning_rate": 2e-05,
"loss": 0.6967,
"step": 1430
},
{
"epoch": 0.1285140562248996,
"grad_norm": 0.3950536251068115,
"learning_rate": 2e-05,
"loss": 0.686,
"step": 1440
},
{
"epoch": 0.12940651494868363,
"grad_norm": 0.43041136860847473,
"learning_rate": 2e-05,
"loss": 0.7122,
"step": 1450
},
{
"epoch": 0.13029897367246765,
"grad_norm": 0.40778934955596924,
"learning_rate": 2e-05,
"loss": 0.7107,
"step": 1460
},
{
"epoch": 0.13119143239625167,
"grad_norm": 0.37620630860328674,
"learning_rate": 2e-05,
"loss": 0.7352,
"step": 1470
},
{
"epoch": 0.13208389112003568,
"grad_norm": 0.34521961212158203,
"learning_rate": 2e-05,
"loss": 0.725,
"step": 1480
},
{
"epoch": 0.13297634984381973,
"grad_norm": 0.4491102397441864,
"learning_rate": 2e-05,
"loss": 0.7313,
"step": 1490
},
{
"epoch": 0.13386880856760375,
"grad_norm": 0.3915207087993622,
"learning_rate": 2e-05,
"loss": 0.7185,
"step": 1500
},
{
"epoch": 0.13476126729138777,
"grad_norm": 0.40829235315322876,
"learning_rate": 2e-05,
"loss": 0.7266,
"step": 1510
},
{
"epoch": 0.1356537260151718,
"grad_norm": 0.4085201323032379,
"learning_rate": 2e-05,
"loss": 0.7142,
"step": 1520
},
{
"epoch": 0.13654618473895583,
"grad_norm": 0.3529062569141388,
"learning_rate": 2e-05,
"loss": 0.7092,
"step": 1530
},
{
"epoch": 0.13743864346273985,
"grad_norm": 0.360169917345047,
"learning_rate": 2e-05,
"loss": 0.7402,
"step": 1540
},
{
"epoch": 0.13833110218652386,
"grad_norm": 0.4295094907283783,
"learning_rate": 2e-05,
"loss": 0.7528,
"step": 1550
},
{
"epoch": 0.1392235609103079,
"grad_norm": 0.38765519857406616,
"learning_rate": 2e-05,
"loss": 0.7173,
"step": 1560
},
{
"epoch": 0.14011601963409193,
"grad_norm": 0.4022582769393921,
"learning_rate": 2e-05,
"loss": 0.6994,
"step": 1570
},
{
"epoch": 0.14100847835787594,
"grad_norm": 0.39251431822776794,
"learning_rate": 2e-05,
"loss": 0.7394,
"step": 1580
},
{
"epoch": 0.14190093708165996,
"grad_norm": 0.4118332862854004,
"learning_rate": 2e-05,
"loss": 0.7361,
"step": 1590
},
{
"epoch": 0.142793395805444,
"grad_norm": 0.39799195528030396,
"learning_rate": 2e-05,
"loss": 0.6995,
"step": 1600
},
{
"epoch": 0.14368585452922802,
"grad_norm": 0.35336437821388245,
"learning_rate": 2e-05,
"loss": 0.755,
"step": 1610
},
{
"epoch": 0.14457831325301204,
"grad_norm": 0.39616140723228455,
"learning_rate": 2e-05,
"loss": 0.7043,
"step": 1620
},
{
"epoch": 0.14547077197679606,
"grad_norm": 0.3775366246700287,
"learning_rate": 2e-05,
"loss": 0.723,
"step": 1630
},
{
"epoch": 0.1463632307005801,
"grad_norm": 0.38130348920822144,
"learning_rate": 2e-05,
"loss": 0.7029,
"step": 1640
},
{
"epoch": 0.14725568942436412,
"grad_norm": 0.7423177361488342,
"learning_rate": 2e-05,
"loss": 0.7276,
"step": 1650
},
{
"epoch": 0.14814814814814814,
"grad_norm": 0.3703177273273468,
"learning_rate": 2e-05,
"loss": 0.7094,
"step": 1660
},
{
"epoch": 0.14904060687193219,
"grad_norm": 0.36464789509773254,
"learning_rate": 2e-05,
"loss": 0.6968,
"step": 1670
},
{
"epoch": 0.1499330655957162,
"grad_norm": 0.3765050172805786,
"learning_rate": 2e-05,
"loss": 0.73,
"step": 1680
},
{
"epoch": 0.15082552431950022,
"grad_norm": 0.36146077513694763,
"learning_rate": 2e-05,
"loss": 0.6911,
"step": 1690
},
{
"epoch": 0.15171798304328424,
"grad_norm": 0.3474405109882355,
"learning_rate": 2e-05,
"loss": 0.7045,
"step": 1700
},
{
"epoch": 0.15261044176706828,
"grad_norm": 0.396933913230896,
"learning_rate": 2e-05,
"loss": 0.7363,
"step": 1710
},
{
"epoch": 0.1535029004908523,
"grad_norm": 0.37580183148384094,
"learning_rate": 2e-05,
"loss": 0.7219,
"step": 1720
},
{
"epoch": 0.15439535921463632,
"grad_norm": 0.3710784614086151,
"learning_rate": 2e-05,
"loss": 0.7089,
"step": 1730
},
{
"epoch": 0.15528781793842034,
"grad_norm": 0.36403852701187134,
"learning_rate": 2e-05,
"loss": 0.7111,
"step": 1740
},
{
"epoch": 0.15618027666220438,
"grad_norm": 0.5121102333068848,
"learning_rate": 2e-05,
"loss": 0.7,
"step": 1750
},
{
"epoch": 0.1570727353859884,
"grad_norm": 0.38486865162849426,
"learning_rate": 2e-05,
"loss": 0.7475,
"step": 1760
},
{
"epoch": 0.15796519410977242,
"grad_norm": 0.35487449169158936,
"learning_rate": 2e-05,
"loss": 0.7121,
"step": 1770
},
{
"epoch": 0.15885765283355643,
"grad_norm": 0.36509183049201965,
"learning_rate": 2e-05,
"loss": 0.7385,
"step": 1780
},
{
"epoch": 0.15975011155734048,
"grad_norm": 0.43019792437553406,
"learning_rate": 2e-05,
"loss": 0.7413,
"step": 1790
},
{
"epoch": 0.1606425702811245,
"grad_norm": 0.3725093901157379,
"learning_rate": 2e-05,
"loss": 0.7075,
"step": 1800
},
{
"epoch": 0.16153502900490851,
"grad_norm": 0.4121997356414795,
"learning_rate": 2e-05,
"loss": 0.7195,
"step": 1810
},
{
"epoch": 0.16242748772869256,
"grad_norm": 0.36837446689605713,
"learning_rate": 2e-05,
"loss": 0.7398,
"step": 1820
},
{
"epoch": 0.16331994645247658,
"grad_norm": 0.3591003715991974,
"learning_rate": 2e-05,
"loss": 0.7011,
"step": 1830
},
{
"epoch": 0.1642124051762606,
"grad_norm": 0.38240692019462585,
"learning_rate": 2e-05,
"loss": 0.7141,
"step": 1840
},
{
"epoch": 0.1651048639000446,
"grad_norm": 0.3967023491859436,
"learning_rate": 2e-05,
"loss": 0.7348,
"step": 1850
},
{
"epoch": 0.16599732262382866,
"grad_norm": 0.5831686854362488,
"learning_rate": 2e-05,
"loss": 0.7106,
"step": 1860
},
{
"epoch": 0.16688978134761268,
"grad_norm": 0.3728710412979126,
"learning_rate": 2e-05,
"loss": 0.6938,
"step": 1870
},
{
"epoch": 0.1677822400713967,
"grad_norm": 0.4233781695365906,
"learning_rate": 2e-05,
"loss": 0.7282,
"step": 1880
},
{
"epoch": 0.1686746987951807,
"grad_norm": 0.38467922806739807,
"learning_rate": 2e-05,
"loss": 0.7001,
"step": 1890
},
{
"epoch": 0.16956715751896476,
"grad_norm": 0.35904461145401,
"learning_rate": 2e-05,
"loss": 0.713,
"step": 1900
},
{
"epoch": 0.17045961624274877,
"grad_norm": 0.3828829526901245,
"learning_rate": 2e-05,
"loss": 0.6828,
"step": 1910
},
{
"epoch": 0.1713520749665328,
"grad_norm": 0.35955435037612915,
"learning_rate": 2e-05,
"loss": 0.7209,
"step": 1920
},
{
"epoch": 0.17224453369031684,
"grad_norm": 0.3535810708999634,
"learning_rate": 2e-05,
"loss": 0.7072,
"step": 1930
},
{
"epoch": 0.17313699241410085,
"grad_norm": 0.3620419502258301,
"learning_rate": 2e-05,
"loss": 0.7045,
"step": 1940
},
{
"epoch": 0.17402945113788487,
"grad_norm": 0.37288907170295715,
"learning_rate": 2e-05,
"loss": 0.7701,
"step": 1950
},
{
"epoch": 0.1749219098616689,
"grad_norm": 0.36177289485931396,
"learning_rate": 2e-05,
"loss": 0.695,
"step": 1960
},
{
"epoch": 0.17581436858545293,
"grad_norm": 0.46705108880996704,
"learning_rate": 2e-05,
"loss": 0.7036,
"step": 1970
},
{
"epoch": 0.17670682730923695,
"grad_norm": 0.38864728808403015,
"learning_rate": 2e-05,
"loss": 0.695,
"step": 1980
},
{
"epoch": 0.17759928603302097,
"grad_norm": 0.3607434332370758,
"learning_rate": 2e-05,
"loss": 0.7111,
"step": 1990
},
{
"epoch": 0.178491744756805,
"grad_norm": 0.36717599630355835,
"learning_rate": 2e-05,
"loss": 0.691,
"step": 2000
},
{
"epoch": 0.17938420348058903,
"grad_norm": 0.36441174149513245,
"learning_rate": 2e-05,
"loss": 0.6795,
"step": 2010
},
{
"epoch": 0.18027666220437305,
"grad_norm": 0.42372533679008484,
"learning_rate": 2e-05,
"loss": 0.7215,
"step": 2020
},
{
"epoch": 0.18116912092815707,
"grad_norm": 0.41000911593437195,
"learning_rate": 2e-05,
"loss": 0.7257,
"step": 2030
},
{
"epoch": 0.18206157965194109,
"grad_norm": 0.40014421939849854,
"learning_rate": 2e-05,
"loss": 0.702,
"step": 2040
},
{
"epoch": 0.18295403837572513,
"grad_norm": 0.3575685918331146,
"learning_rate": 2e-05,
"loss": 0.7076,
"step": 2050
},
{
"epoch": 0.18384649709950915,
"grad_norm": 0.3880053460597992,
"learning_rate": 2e-05,
"loss": 0.6628,
"step": 2060
},
{
"epoch": 0.18473895582329317,
"grad_norm": 0.3879825472831726,
"learning_rate": 2e-05,
"loss": 0.711,
"step": 2070
},
{
"epoch": 0.1856314145470772,
"grad_norm": 0.3911679983139038,
"learning_rate": 2e-05,
"loss": 0.7285,
"step": 2080
},
{
"epoch": 0.18652387327086123,
"grad_norm": 0.35667601227760315,
"learning_rate": 2e-05,
"loss": 0.7385,
"step": 2090
},
{
"epoch": 0.18741633199464525,
"grad_norm": 0.4055507779121399,
"learning_rate": 2e-05,
"loss": 0.7087,
"step": 2100
},
{
"epoch": 0.18830879071842926,
"grad_norm": 0.34139570593833923,
"learning_rate": 2e-05,
"loss": 0.7122,
"step": 2110
},
{
"epoch": 0.1892012494422133,
"grad_norm": 0.40417465567588806,
"learning_rate": 2e-05,
"loss": 0.7251,
"step": 2120
},
{
"epoch": 0.19009370816599733,
"grad_norm": 0.41374412178993225,
"learning_rate": 2e-05,
"loss": 0.6949,
"step": 2130
},
{
"epoch": 0.19098616688978134,
"grad_norm": 0.3738286793231964,
"learning_rate": 2e-05,
"loss": 0.6991,
"step": 2140
},
{
"epoch": 0.19187862561356536,
"grad_norm": 0.36283162236213684,
"learning_rate": 2e-05,
"loss": 0.7033,
"step": 2150
},
{
"epoch": 0.1927710843373494,
"grad_norm": 0.40305814146995544,
"learning_rate": 2e-05,
"loss": 0.7036,
"step": 2160
},
{
"epoch": 0.19366354306113343,
"grad_norm": 0.4250462055206299,
"learning_rate": 2e-05,
"loss": 0.7248,
"step": 2170
},
{
"epoch": 0.19455600178491744,
"grad_norm": 0.3769831359386444,
"learning_rate": 2e-05,
"loss": 0.7055,
"step": 2180
},
{
"epoch": 0.19544846050870146,
"grad_norm": 0.35918813943862915,
"learning_rate": 2e-05,
"loss": 0.676,
"step": 2190
},
{
"epoch": 0.1963409192324855,
"grad_norm": 0.3661561906337738,
"learning_rate": 2e-05,
"loss": 0.7058,
"step": 2200
},
{
"epoch": 0.19723337795626952,
"grad_norm": 0.32479768991470337,
"learning_rate": 2e-05,
"loss": 0.6975,
"step": 2210
},
{
"epoch": 0.19812583668005354,
"grad_norm": 0.36116334795951843,
"learning_rate": 2e-05,
"loss": 0.7006,
"step": 2220
},
{
"epoch": 0.1990182954038376,
"grad_norm": 0.3757176995277405,
"learning_rate": 2e-05,
"loss": 0.6867,
"step": 2230
},
{
"epoch": 0.1999107541276216,
"grad_norm": 0.3349403440952301,
"learning_rate": 2e-05,
"loss": 0.7119,
"step": 2240
},
{
"epoch": 0.20080321285140562,
"grad_norm": 0.41477563977241516,
"learning_rate": 2e-05,
"loss": 0.6737,
"step": 2250
},
{
"epoch": 0.20169567157518964,
"grad_norm": 0.7723550796508789,
"learning_rate": 2e-05,
"loss": 0.7063,
"step": 2260
},
{
"epoch": 0.20258813029897368,
"grad_norm": 0.3693602979183197,
"learning_rate": 2e-05,
"loss": 0.7431,
"step": 2270
},
{
"epoch": 0.2034805890227577,
"grad_norm": 0.4255744218826294,
"learning_rate": 2e-05,
"loss": 0.7051,
"step": 2280
},
{
"epoch": 0.20437304774654172,
"grad_norm": 0.3678276836872101,
"learning_rate": 2e-05,
"loss": 0.6955,
"step": 2290
},
{
"epoch": 0.20526550647032574,
"grad_norm": 0.39403510093688965,
"learning_rate": 2e-05,
"loss": 0.6889,
"step": 2300
},
{
"epoch": 0.20615796519410978,
"grad_norm": 0.3570137023925781,
"learning_rate": 2e-05,
"loss": 0.7089,
"step": 2310
},
{
"epoch": 0.2070504239178938,
"grad_norm": 0.3645356297492981,
"learning_rate": 2e-05,
"loss": 0.7132,
"step": 2320
},
{
"epoch": 0.20794288264167782,
"grad_norm": 0.36887142062187195,
"learning_rate": 2e-05,
"loss": 0.7095,
"step": 2330
},
{
"epoch": 0.20883534136546184,
"grad_norm": 0.3418295085430145,
"learning_rate": 2e-05,
"loss": 0.7006,
"step": 2340
},
{
"epoch": 0.20972780008924588,
"grad_norm": 0.3889702260494232,
"learning_rate": 2e-05,
"loss": 0.7043,
"step": 2350
},
{
"epoch": 0.2106202588130299,
"grad_norm": 0.3959186375141144,
"learning_rate": 2e-05,
"loss": 0.7222,
"step": 2360
},
{
"epoch": 0.21151271753681392,
"grad_norm": 0.34344956278800964,
"learning_rate": 2e-05,
"loss": 0.708,
"step": 2370
},
{
"epoch": 0.21240517626059796,
"grad_norm": 0.3525504171848297,
"learning_rate": 2e-05,
"loss": 0.7142,
"step": 2380
},
{
"epoch": 0.21329763498438198,
"grad_norm": 0.36897340416908264,
"learning_rate": 2e-05,
"loss": 0.7233,
"step": 2390
},
{
"epoch": 0.214190093708166,
"grad_norm": 0.3377510607242584,
"learning_rate": 2e-05,
"loss": 0.72,
"step": 2400
},
{
"epoch": 0.21508255243195,
"grad_norm": 0.39910000562667847,
"learning_rate": 2e-05,
"loss": 0.7211,
"step": 2410
},
{
"epoch": 0.21597501115573406,
"grad_norm": 0.3923272490501404,
"learning_rate": 2e-05,
"loss": 0.6979,
"step": 2420
},
{
"epoch": 0.21686746987951808,
"grad_norm": 0.4154103398323059,
"learning_rate": 2e-05,
"loss": 0.7031,
"step": 2430
},
{
"epoch": 0.2177599286033021,
"grad_norm": 0.40713241696357727,
"learning_rate": 2e-05,
"loss": 0.6988,
"step": 2440
},
{
"epoch": 0.2186523873270861,
"grad_norm": 0.3655557930469513,
"learning_rate": 2e-05,
"loss": 0.6843,
"step": 2450
},
{
"epoch": 0.21954484605087016,
"grad_norm": 0.3539635241031647,
"learning_rate": 2e-05,
"loss": 0.7085,
"step": 2460
},
{
"epoch": 0.22043730477465417,
"grad_norm": 0.41050246357917786,
"learning_rate": 2e-05,
"loss": 0.6647,
"step": 2470
},
{
"epoch": 0.2213297634984382,
"grad_norm": 0.36172372102737427,
"learning_rate": 2e-05,
"loss": 0.706,
"step": 2480
},
{
"epoch": 0.2222222222222222,
"grad_norm": 0.5249997973442078,
"learning_rate": 2e-05,
"loss": 0.7144,
"step": 2490
},
{
"epoch": 0.22311468094600626,
"grad_norm": 0.3864399194717407,
"learning_rate": 2e-05,
"loss": 0.7189,
"step": 2500
},
{
"epoch": 0.22400713966979027,
"grad_norm": 0.4319363236427307,
"learning_rate": 2e-05,
"loss": 0.7015,
"step": 2510
},
{
"epoch": 0.2248995983935743,
"grad_norm": 0.3635087013244629,
"learning_rate": 2e-05,
"loss": 0.6695,
"step": 2520
},
{
"epoch": 0.22579205711735834,
"grad_norm": 0.35824811458587646,
"learning_rate": 2e-05,
"loss": 0.6949,
"step": 2530
},
{
"epoch": 0.22668451584114235,
"grad_norm": 0.375846803188324,
"learning_rate": 2e-05,
"loss": 0.7237,
"step": 2540
},
{
"epoch": 0.22757697456492637,
"grad_norm": 0.35899844765663147,
"learning_rate": 2e-05,
"loss": 0.6959,
"step": 2550
},
{
"epoch": 0.2284694332887104,
"grad_norm": 0.3737565279006958,
"learning_rate": 2e-05,
"loss": 0.7104,
"step": 2560
},
{
"epoch": 0.22936189201249443,
"grad_norm": 0.35111722350120544,
"learning_rate": 2e-05,
"loss": 0.6941,
"step": 2570
},
{
"epoch": 0.23025435073627845,
"grad_norm": 0.3938366770744324,
"learning_rate": 2e-05,
"loss": 0.7205,
"step": 2580
},
{
"epoch": 0.23114680946006247,
"grad_norm": 0.35663139820098877,
"learning_rate": 2e-05,
"loss": 0.7184,
"step": 2590
},
{
"epoch": 0.2320392681838465,
"grad_norm": 0.42633557319641113,
"learning_rate": 2e-05,
"loss": 0.7065,
"step": 2600
},
{
"epoch": 0.23293172690763053,
"grad_norm": 0.4921680986881256,
"learning_rate": 2e-05,
"loss": 0.706,
"step": 2610
},
{
"epoch": 0.23382418563141455,
"grad_norm": 0.3506428301334381,
"learning_rate": 2e-05,
"loss": 0.721,
"step": 2620
},
{
"epoch": 0.23471664435519857,
"grad_norm": 0.34051036834716797,
"learning_rate": 2e-05,
"loss": 0.6939,
"step": 2630
},
{
"epoch": 0.23560910307898258,
"grad_norm": 0.36223891377449036,
"learning_rate": 2e-05,
"loss": 0.7122,
"step": 2640
},
{
"epoch": 0.23650156180276663,
"grad_norm": 0.35965049266815186,
"learning_rate": 2e-05,
"loss": 0.709,
"step": 2650
},
{
"epoch": 0.23739402052655065,
"grad_norm": 0.3486102223396301,
"learning_rate": 2e-05,
"loss": 0.693,
"step": 2660
},
{
"epoch": 0.23828647925033467,
"grad_norm": 0.38577350974082947,
"learning_rate": 2e-05,
"loss": 0.7067,
"step": 2670
},
{
"epoch": 0.2391789379741187,
"grad_norm": 0.40134578943252563,
"learning_rate": 2e-05,
"loss": 0.7132,
"step": 2680
},
{
"epoch": 0.24007139669790273,
"grad_norm": 0.41890060901641846,
"learning_rate": 2e-05,
"loss": 0.7044,
"step": 2690
},
{
"epoch": 0.24096385542168675,
"grad_norm": 0.3403701186180115,
"learning_rate": 2e-05,
"loss": 0.7058,
"step": 2700
},
{
"epoch": 0.24185631414547076,
"grad_norm": 0.33793163299560547,
"learning_rate": 2e-05,
"loss": 0.7181,
"step": 2710
},
{
"epoch": 0.2427487728692548,
"grad_norm": 0.5403984785079956,
"learning_rate": 2e-05,
"loss": 0.7062,
"step": 2720
},
{
"epoch": 0.24364123159303883,
"grad_norm": 0.4084964394569397,
"learning_rate": 2e-05,
"loss": 0.6615,
"step": 2730
},
{
"epoch": 0.24453369031682284,
"grad_norm": 0.3381352722644806,
"learning_rate": 2e-05,
"loss": 0.7106,
"step": 2740
},
{
"epoch": 0.24542614904060686,
"grad_norm": 0.38011088967323303,
"learning_rate": 2e-05,
"loss": 0.6913,
"step": 2750
},
{
"epoch": 0.2463186077643909,
"grad_norm": 0.3438170552253723,
"learning_rate": 2e-05,
"loss": 0.6822,
"step": 2760
},
{
"epoch": 0.24721106648817492,
"grad_norm": 0.35488688945770264,
"learning_rate": 2e-05,
"loss": 0.7069,
"step": 2770
},
{
"epoch": 0.24810352521195894,
"grad_norm": 0.3474864661693573,
"learning_rate": 2e-05,
"loss": 0.6961,
"step": 2780
},
{
"epoch": 0.24899598393574296,
"grad_norm": 0.37238046526908875,
"learning_rate": 2e-05,
"loss": 0.6934,
"step": 2790
},
{
"epoch": 0.249888442659527,
"grad_norm": 0.361629456281662,
"learning_rate": 2e-05,
"loss": 0.7176,
"step": 2800
},
{
"epoch": 0.250780901383311,
"grad_norm": 0.36093610525131226,
"learning_rate": 2e-05,
"loss": 0.6631,
"step": 2810
},
{
"epoch": 0.25167336010709507,
"grad_norm": 0.354215145111084,
"learning_rate": 2e-05,
"loss": 0.685,
"step": 2820
},
{
"epoch": 0.2525658188308791,
"grad_norm": 0.3703426122665405,
"learning_rate": 2e-05,
"loss": 0.6811,
"step": 2830
},
{
"epoch": 0.2534582775546631,
"grad_norm": 0.3834165036678314,
"learning_rate": 2e-05,
"loss": 0.7128,
"step": 2840
},
{
"epoch": 0.2543507362784471,
"grad_norm": 0.35115286707878113,
"learning_rate": 2e-05,
"loss": 0.6888,
"step": 2850
},
{
"epoch": 0.25524319500223114,
"grad_norm": 0.3497035503387451,
"learning_rate": 2e-05,
"loss": 0.6511,
"step": 2860
},
{
"epoch": 0.25613565372601516,
"grad_norm": 0.3738860487937927,
"learning_rate": 2e-05,
"loss": 0.7181,
"step": 2870
},
{
"epoch": 0.2570281124497992,
"grad_norm": 0.3604569733142853,
"learning_rate": 2e-05,
"loss": 0.6982,
"step": 2880
},
{
"epoch": 0.25792057117358325,
"grad_norm": 0.3718276917934418,
"learning_rate": 2e-05,
"loss": 0.7142,
"step": 2890
},
{
"epoch": 0.25881302989736726,
"grad_norm": 0.3611880838871002,
"learning_rate": 2e-05,
"loss": 0.702,
"step": 2900
},
{
"epoch": 0.2597054886211513,
"grad_norm": 0.33287131786346436,
"learning_rate": 2e-05,
"loss": 0.684,
"step": 2910
},
{
"epoch": 0.2605979473449353,
"grad_norm": 0.40636178851127625,
"learning_rate": 2e-05,
"loss": 0.6977,
"step": 2920
},
{
"epoch": 0.2614904060687193,
"grad_norm": 0.3703216016292572,
"learning_rate": 2e-05,
"loss": 0.6841,
"step": 2930
},
{
"epoch": 0.26238286479250333,
"grad_norm": 0.3907012343406677,
"learning_rate": 2e-05,
"loss": 0.6648,
"step": 2940
},
{
"epoch": 0.26327532351628735,
"grad_norm": 0.357471764087677,
"learning_rate": 2e-05,
"loss": 0.6518,
"step": 2950
},
{
"epoch": 0.26416778224007137,
"grad_norm": 0.38111019134521484,
"learning_rate": 2e-05,
"loss": 0.7083,
"step": 2960
},
{
"epoch": 0.26506024096385544,
"grad_norm": 0.3443157970905304,
"learning_rate": 2e-05,
"loss": 0.68,
"step": 2970
},
{
"epoch": 0.26595269968763946,
"grad_norm": 0.3853066563606262,
"learning_rate": 2e-05,
"loss": 0.7192,
"step": 2980
},
{
"epoch": 0.2668451584114235,
"grad_norm": 0.43045032024383545,
"learning_rate": 2e-05,
"loss": 0.7119,
"step": 2990
},
{
"epoch": 0.2677376171352075,
"grad_norm": 0.46091946959495544,
"learning_rate": 2e-05,
"loss": 0.6947,
"step": 3000
},
{
"epoch": 0.2686300758589915,
"grad_norm": 0.3609314262866974,
"learning_rate": 2e-05,
"loss": 0.6636,
"step": 3010
},
{
"epoch": 0.26952253458277553,
"grad_norm": 0.3863031268119812,
"learning_rate": 2e-05,
"loss": 0.6821,
"step": 3020
},
{
"epoch": 0.27041499330655955,
"grad_norm": 0.4071292579174042,
"learning_rate": 2e-05,
"loss": 0.7093,
"step": 3030
},
{
"epoch": 0.2713074520303436,
"grad_norm": 0.34357038140296936,
"learning_rate": 2e-05,
"loss": 0.7139,
"step": 3040
},
{
"epoch": 0.27219991075412764,
"grad_norm": 0.4047830402851105,
"learning_rate": 2e-05,
"loss": 0.6868,
"step": 3050
},
{
"epoch": 0.27309236947791166,
"grad_norm": 0.37571510672569275,
"learning_rate": 2e-05,
"loss": 0.6568,
"step": 3060
},
{
"epoch": 0.2739848282016957,
"grad_norm": 0.339928537607193,
"learning_rate": 2e-05,
"loss": 0.6987,
"step": 3070
},
{
"epoch": 0.2748772869254797,
"grad_norm": 0.36671870946884155,
"learning_rate": 2e-05,
"loss": 0.706,
"step": 3080
},
{
"epoch": 0.2757697456492637,
"grad_norm": 0.3619630038738251,
"learning_rate": 2e-05,
"loss": 0.6936,
"step": 3090
},
{
"epoch": 0.2766622043730477,
"grad_norm": 0.3525165915489197,
"learning_rate": 2e-05,
"loss": 0.7032,
"step": 3100
},
{
"epoch": 0.27755466309683174,
"grad_norm": 0.3450978100299835,
"learning_rate": 2e-05,
"loss": 0.7087,
"step": 3110
},
{
"epoch": 0.2784471218206158,
"grad_norm": 0.3459194600582123,
"learning_rate": 2e-05,
"loss": 0.6823,
"step": 3120
},
{
"epoch": 0.27933958054439983,
"grad_norm": 0.38839390873908997,
"learning_rate": 2e-05,
"loss": 0.6859,
"step": 3130
},
{
"epoch": 0.28023203926818385,
"grad_norm": 0.3918834328651428,
"learning_rate": 2e-05,
"loss": 0.7154,
"step": 3140
},
{
"epoch": 0.28112449799196787,
"grad_norm": 0.36024022102355957,
"learning_rate": 2e-05,
"loss": 0.6795,
"step": 3150
},
{
"epoch": 0.2820169567157519,
"grad_norm": 0.36553332209587097,
"learning_rate": 2e-05,
"loss": 0.651,
"step": 3160
},
{
"epoch": 0.2829094154395359,
"grad_norm": 0.3750966787338257,
"learning_rate": 2e-05,
"loss": 0.6676,
"step": 3170
},
{
"epoch": 0.2838018741633199,
"grad_norm": 0.36494848132133484,
"learning_rate": 2e-05,
"loss": 0.6919,
"step": 3180
},
{
"epoch": 0.284694332887104,
"grad_norm": 0.42444247007369995,
"learning_rate": 2e-05,
"loss": 0.697,
"step": 3190
},
{
"epoch": 0.285586791610888,
"grad_norm": 0.4227437973022461,
"learning_rate": 2e-05,
"loss": 0.6557,
"step": 3200
},
{
"epoch": 0.28647925033467203,
"grad_norm": 0.3764297068119049,
"learning_rate": 2e-05,
"loss": 0.6852,
"step": 3210
},
{
"epoch": 0.28737170905845605,
"grad_norm": 0.36593905091285706,
"learning_rate": 2e-05,
"loss": 0.6957,
"step": 3220
},
{
"epoch": 0.28826416778224007,
"grad_norm": 0.3768455684185028,
"learning_rate": 2e-05,
"loss": 0.6956,
"step": 3230
},
{
"epoch": 0.2891566265060241,
"grad_norm": 0.3834182024002075,
"learning_rate": 2e-05,
"loss": 0.6837,
"step": 3240
},
{
"epoch": 0.2900490852298081,
"grad_norm": 0.37360700964927673,
"learning_rate": 2e-05,
"loss": 0.6778,
"step": 3250
},
{
"epoch": 0.2909415439535921,
"grad_norm": 0.3748886287212372,
"learning_rate": 2e-05,
"loss": 0.6962,
"step": 3260
},
{
"epoch": 0.2918340026773762,
"grad_norm": 0.36913779377937317,
"learning_rate": 2e-05,
"loss": 0.7171,
"step": 3270
},
{
"epoch": 0.2927264614011602,
"grad_norm": 0.4049180746078491,
"learning_rate": 2e-05,
"loss": 0.6959,
"step": 3280
},
{
"epoch": 0.2936189201249442,
"grad_norm": 0.4105624258518219,
"learning_rate": 2e-05,
"loss": 0.669,
"step": 3290
},
{
"epoch": 0.29451137884872824,
"grad_norm": 0.36357712745666504,
"learning_rate": 2e-05,
"loss": 0.7103,
"step": 3300
},
{
"epoch": 0.29540383757251226,
"grad_norm": 0.3372548520565033,
"learning_rate": 2e-05,
"loss": 0.669,
"step": 3310
},
{
"epoch": 0.2962962962962963,
"grad_norm": 0.360275000333786,
"learning_rate": 2e-05,
"loss": 0.7128,
"step": 3320
},
{
"epoch": 0.2971887550200803,
"grad_norm": 0.36750873923301697,
"learning_rate": 2e-05,
"loss": 0.7159,
"step": 3330
},
{
"epoch": 0.29808121374386437,
"grad_norm": 0.3744310140609741,
"learning_rate": 2e-05,
"loss": 0.6991,
"step": 3340
},
{
"epoch": 0.2989736724676484,
"grad_norm": 0.36482685804367065,
"learning_rate": 2e-05,
"loss": 0.6761,
"step": 3350
},
{
"epoch": 0.2998661311914324,
"grad_norm": 0.4055212438106537,
"learning_rate": 2e-05,
"loss": 0.6832,
"step": 3360
},
{
"epoch": 0.3007585899152164,
"grad_norm": 0.3472900390625,
"learning_rate": 2e-05,
"loss": 0.657,
"step": 3370
},
{
"epoch": 0.30165104863900044,
"grad_norm": 0.41277948021888733,
"learning_rate": 2e-05,
"loss": 0.7004,
"step": 3380
},
{
"epoch": 0.30254350736278446,
"grad_norm": 0.5707241892814636,
"learning_rate": 2e-05,
"loss": 0.6946,
"step": 3390
},
{
"epoch": 0.3034359660865685,
"grad_norm": 0.37944552302360535,
"learning_rate": 2e-05,
"loss": 0.7048,
"step": 3400
},
{
"epoch": 0.3043284248103525,
"grad_norm": 0.40345481038093567,
"learning_rate": 2e-05,
"loss": 0.6784,
"step": 3410
},
{
"epoch": 0.30522088353413657,
"grad_norm": 0.36031800508499146,
"learning_rate": 2e-05,
"loss": 0.6687,
"step": 3420
},
{
"epoch": 0.3061133422579206,
"grad_norm": 0.3758523762226105,
"learning_rate": 2e-05,
"loss": 0.713,
"step": 3430
},
{
"epoch": 0.3070058009817046,
"grad_norm": 0.5176293849945068,
"learning_rate": 2e-05,
"loss": 0.6768,
"step": 3440
},
{
"epoch": 0.3078982597054886,
"grad_norm": 0.3904946744441986,
"learning_rate": 2e-05,
"loss": 0.7088,
"step": 3450
},
{
"epoch": 0.30879071842927264,
"grad_norm": 0.3160179555416107,
"learning_rate": 2e-05,
"loss": 0.6631,
"step": 3460
},
{
"epoch": 0.30968317715305665,
"grad_norm": 0.45626139640808105,
"learning_rate": 2e-05,
"loss": 0.6798,
"step": 3470
},
{
"epoch": 0.31057563587684067,
"grad_norm": 0.3389970064163208,
"learning_rate": 2e-05,
"loss": 0.685,
"step": 3480
},
{
"epoch": 0.31146809460062475,
"grad_norm": 0.37763211131095886,
"learning_rate": 2e-05,
"loss": 0.6879,
"step": 3490
},
{
"epoch": 0.31236055332440876,
"grad_norm": 0.374933123588562,
"learning_rate": 2e-05,
"loss": 0.6715,
"step": 3500
},
{
"epoch": 0.3132530120481928,
"grad_norm": 0.37782981991767883,
"learning_rate": 2e-05,
"loss": 0.6852,
"step": 3510
},
{
"epoch": 0.3141454707719768,
"grad_norm": 0.4102741479873657,
"learning_rate": 2e-05,
"loss": 0.7064,
"step": 3520
},
{
"epoch": 0.3150379294957608,
"grad_norm": 0.36353591084480286,
"learning_rate": 2e-05,
"loss": 0.6669,
"step": 3530
},
{
"epoch": 0.31593038821954483,
"grad_norm": 0.4682978391647339,
"learning_rate": 2e-05,
"loss": 0.6849,
"step": 3540
},
{
"epoch": 0.31682284694332885,
"grad_norm": 0.35799211263656616,
"learning_rate": 2e-05,
"loss": 0.6638,
"step": 3550
},
{
"epoch": 0.31771530566711287,
"grad_norm": 0.35494521260261536,
"learning_rate": 2e-05,
"loss": 0.7194,
"step": 3560
},
{
"epoch": 0.31860776439089694,
"grad_norm": 0.3495546877384186,
"learning_rate": 2e-05,
"loss": 0.7101,
"step": 3570
},
{
"epoch": 0.31950022311468096,
"grad_norm": 0.42559295892715454,
"learning_rate": 2e-05,
"loss": 0.729,
"step": 3580
},
{
"epoch": 0.320392681838465,
"grad_norm": 0.40502825379371643,
"learning_rate": 2e-05,
"loss": 0.6711,
"step": 3590
},
{
"epoch": 0.321285140562249,
"grad_norm": 0.39933738112449646,
"learning_rate": 2e-05,
"loss": 0.6846,
"step": 3600
},
{
"epoch": 0.322177599286033,
"grad_norm": 0.39374107122421265,
"learning_rate": 2e-05,
"loss": 0.6934,
"step": 3610
},
{
"epoch": 0.32307005800981703,
"grad_norm": 0.3833998739719391,
"learning_rate": 2e-05,
"loss": 0.7001,
"step": 3620
},
{
"epoch": 0.32396251673360105,
"grad_norm": 0.4226708710193634,
"learning_rate": 2e-05,
"loss": 0.7118,
"step": 3630
},
{
"epoch": 0.3248549754573851,
"grad_norm": 0.3613390028476715,
"learning_rate": 2e-05,
"loss": 0.6712,
"step": 3640
},
{
"epoch": 0.32574743418116914,
"grad_norm": 0.32615116238594055,
"learning_rate": 2e-05,
"loss": 0.6761,
"step": 3650
},
{
"epoch": 0.32663989290495316,
"grad_norm": 0.36767154932022095,
"learning_rate": 2e-05,
"loss": 0.6738,
"step": 3660
},
{
"epoch": 0.3275323516287372,
"grad_norm": 0.3822571635246277,
"learning_rate": 2e-05,
"loss": 0.6959,
"step": 3670
},
{
"epoch": 0.3284248103525212,
"grad_norm": 0.3931572139263153,
"learning_rate": 2e-05,
"loss": 0.7079,
"step": 3680
},
{
"epoch": 0.3293172690763052,
"grad_norm": 0.3877595365047455,
"learning_rate": 2e-05,
"loss": 0.6933,
"step": 3690
},
{
"epoch": 0.3302097278000892,
"grad_norm": 0.3704959750175476,
"learning_rate": 2e-05,
"loss": 0.6628,
"step": 3700
},
{
"epoch": 0.33110218652387324,
"grad_norm": 0.3556361198425293,
"learning_rate": 2e-05,
"loss": 0.6704,
"step": 3710
},
{
"epoch": 0.3319946452476573,
"grad_norm": 0.362934410572052,
"learning_rate": 2e-05,
"loss": 0.6598,
"step": 3720
},
{
"epoch": 0.33288710397144133,
"grad_norm": 0.3868967890739441,
"learning_rate": 2e-05,
"loss": 0.7028,
"step": 3730
},
{
"epoch": 0.33377956269522535,
"grad_norm": 0.38233718276023865,
"learning_rate": 2e-05,
"loss": 0.6698,
"step": 3740
},
{
"epoch": 0.33467202141900937,
"grad_norm": 0.3984028398990631,
"learning_rate": 2e-05,
"loss": 0.6998,
"step": 3750
},
{
"epoch": 0.3355644801427934,
"grad_norm": 0.3509763777256012,
"learning_rate": 2e-05,
"loss": 0.6784,
"step": 3760
},
{
"epoch": 0.3364569388665774,
"grad_norm": 0.3608149588108063,
"learning_rate": 2e-05,
"loss": 0.6694,
"step": 3770
},
{
"epoch": 0.3373493975903614,
"grad_norm": 0.3655262291431427,
"learning_rate": 2e-05,
"loss": 0.6604,
"step": 3780
},
{
"epoch": 0.3382418563141455,
"grad_norm": 0.3790647089481354,
"learning_rate": 2e-05,
"loss": 0.6651,
"step": 3790
},
{
"epoch": 0.3391343150379295,
"grad_norm": 0.35572123527526855,
"learning_rate": 2e-05,
"loss": 0.7299,
"step": 3800
},
{
"epoch": 0.34002677376171353,
"grad_norm": 0.3570621609687805,
"learning_rate": 2e-05,
"loss": 0.681,
"step": 3810
},
{
"epoch": 0.34091923248549755,
"grad_norm": 0.3663609027862549,
"learning_rate": 2e-05,
"loss": 0.6557,
"step": 3820
},
{
"epoch": 0.34181169120928157,
"grad_norm": 0.37612035870552063,
"learning_rate": 2e-05,
"loss": 0.6829,
"step": 3830
},
{
"epoch": 0.3427041499330656,
"grad_norm": 0.3695187568664551,
"learning_rate": 2e-05,
"loss": 0.6792,
"step": 3840
},
{
"epoch": 0.3435966086568496,
"grad_norm": 0.3543972671031952,
"learning_rate": 2e-05,
"loss": 0.6603,
"step": 3850
},
{
"epoch": 0.3444890673806337,
"grad_norm": 0.3484421372413635,
"learning_rate": 2e-05,
"loss": 0.6412,
"step": 3860
},
{
"epoch": 0.3453815261044177,
"grad_norm": 0.636989414691925,
"learning_rate": 2e-05,
"loss": 0.6685,
"step": 3870
},
{
"epoch": 0.3462739848282017,
"grad_norm": 0.353354275226593,
"learning_rate": 2e-05,
"loss": 0.6816,
"step": 3880
},
{
"epoch": 0.3471664435519857,
"grad_norm": 0.399431049823761,
"learning_rate": 2e-05,
"loss": 0.6821,
"step": 3890
},
{
"epoch": 0.34805890227576974,
"grad_norm": 0.3725152909755707,
"learning_rate": 2e-05,
"loss": 0.6705,
"step": 3900
},
{
"epoch": 0.34895136099955376,
"grad_norm": 0.3697719871997833,
"learning_rate": 2e-05,
"loss": 0.6736,
"step": 3910
},
{
"epoch": 0.3498438197233378,
"grad_norm": 0.37048324942588806,
"learning_rate": 2e-05,
"loss": 0.6881,
"step": 3920
},
{
"epoch": 0.3507362784471218,
"grad_norm": 0.4095633029937744,
"learning_rate": 2e-05,
"loss": 0.6529,
"step": 3930
},
{
"epoch": 0.35162873717090587,
"grad_norm": 0.35396143794059753,
"learning_rate": 2e-05,
"loss": 0.7209,
"step": 3940
},
{
"epoch": 0.3525211958946899,
"grad_norm": 0.3832853436470032,
"learning_rate": 2e-05,
"loss": 0.6959,
"step": 3950
},
{
"epoch": 0.3534136546184739,
"grad_norm": 0.37400299310684204,
"learning_rate": 2e-05,
"loss": 0.6638,
"step": 3960
},
{
"epoch": 0.3543061133422579,
"grad_norm": 0.7657487988471985,
"learning_rate": 2e-05,
"loss": 0.6751,
"step": 3970
},
{
"epoch": 0.35519857206604194,
"grad_norm": 0.3688769042491913,
"learning_rate": 2e-05,
"loss": 0.6851,
"step": 3980
},
{
"epoch": 0.35609103078982596,
"grad_norm": 0.3446170389652252,
"learning_rate": 2e-05,
"loss": 0.6704,
"step": 3990
},
{
"epoch": 0.35698348951361,
"grad_norm": 0.38899853825569153,
"learning_rate": 2e-05,
"loss": 0.6728,
"step": 4000
},
{
"epoch": 0.35787594823739405,
"grad_norm": 0.3742004930973053,
"learning_rate": 2e-05,
"loss": 0.6821,
"step": 4010
},
{
"epoch": 0.35876840696117807,
"grad_norm": 0.36814481019973755,
"learning_rate": 2e-05,
"loss": 0.6905,
"step": 4020
},
{
"epoch": 0.3596608656849621,
"grad_norm": 0.3448152542114258,
"learning_rate": 2e-05,
"loss": 0.6751,
"step": 4030
},
{
"epoch": 0.3605533244087461,
"grad_norm": 0.3532841205596924,
"learning_rate": 2e-05,
"loss": 0.6663,
"step": 4040
},
{
"epoch": 0.3614457831325301,
"grad_norm": 0.390525758266449,
"learning_rate": 2e-05,
"loss": 0.6676,
"step": 4050
},
{
"epoch": 0.36233824185631414,
"grad_norm": 0.41043761372566223,
"learning_rate": 2e-05,
"loss": 0.6865,
"step": 4060
},
{
"epoch": 0.36323070058009815,
"grad_norm": 0.32364386320114136,
"learning_rate": 2e-05,
"loss": 0.6736,
"step": 4070
},
{
"epoch": 0.36412315930388217,
"grad_norm": 0.39562374353408813,
"learning_rate": 2e-05,
"loss": 0.6816,
"step": 4080
},
{
"epoch": 0.36501561802766624,
"grad_norm": 0.38002610206604004,
"learning_rate": 2e-05,
"loss": 0.6635,
"step": 4090
},
{
"epoch": 0.36590807675145026,
"grad_norm": 0.34306979179382324,
"learning_rate": 2e-05,
"loss": 0.7087,
"step": 4100
},
{
"epoch": 0.3668005354752343,
"grad_norm": 0.36761438846588135,
"learning_rate": 2e-05,
"loss": 0.6806,
"step": 4110
},
{
"epoch": 0.3676929941990183,
"grad_norm": 0.39585381746292114,
"learning_rate": 2e-05,
"loss": 0.6927,
"step": 4120
},
{
"epoch": 0.3685854529228023,
"grad_norm": 0.38605520129203796,
"learning_rate": 2e-05,
"loss": 0.6897,
"step": 4130
},
{
"epoch": 0.36947791164658633,
"grad_norm": 0.3497367799282074,
"learning_rate": 2e-05,
"loss": 0.6812,
"step": 4140
},
{
"epoch": 0.37037037037037035,
"grad_norm": 4.066261291503906,
"learning_rate": 2e-05,
"loss": 0.7264,
"step": 4150
},
{
"epoch": 0.3712628290941544,
"grad_norm": 0.40141093730926514,
"learning_rate": 2e-05,
"loss": 0.693,
"step": 4160
},
{
"epoch": 0.37215528781793844,
"grad_norm": 0.3579643666744232,
"learning_rate": 2e-05,
"loss": 0.7018,
"step": 4170
},
{
"epoch": 0.37304774654172246,
"grad_norm": 0.3658234775066376,
"learning_rate": 2e-05,
"loss": 0.6767,
"step": 4180
},
{
"epoch": 0.3739402052655065,
"grad_norm": 0.4451167583465576,
"learning_rate": 2e-05,
"loss": 0.7064,
"step": 4190
},
{
"epoch": 0.3748326639892905,
"grad_norm": 0.3791666328907013,
"learning_rate": 2e-05,
"loss": 0.6824,
"step": 4200
},
{
"epoch": 0.3757251227130745,
"grad_norm": 0.4027309715747833,
"learning_rate": 2e-05,
"loss": 0.6778,
"step": 4210
},
{
"epoch": 0.37661758143685853,
"grad_norm": 0.3656576871871948,
"learning_rate": 2e-05,
"loss": 0.6654,
"step": 4220
},
{
"epoch": 0.37751004016064255,
"grad_norm": 0.3933909237384796,
"learning_rate": 2e-05,
"loss": 0.6497,
"step": 4230
},
{
"epoch": 0.3784024988844266,
"grad_norm": 0.36298003792762756,
"learning_rate": 2e-05,
"loss": 0.6643,
"step": 4240
},
{
"epoch": 0.37929495760821064,
"grad_norm": 0.41185012459754944,
"learning_rate": 2e-05,
"loss": 0.6787,
"step": 4250
},
{
"epoch": 0.38018741633199465,
"grad_norm": 0.40756914019584656,
"learning_rate": 2e-05,
"loss": 0.716,
"step": 4260
},
{
"epoch": 0.38107987505577867,
"grad_norm": 0.4002636671066284,
"learning_rate": 2e-05,
"loss": 0.6634,
"step": 4270
},
{
"epoch": 0.3819723337795627,
"grad_norm": 0.35606589913368225,
"learning_rate": 2e-05,
"loss": 0.6638,
"step": 4280
},
{
"epoch": 0.3828647925033467,
"grad_norm": 0.36240053176879883,
"learning_rate": 2e-05,
"loss": 0.6598,
"step": 4290
},
{
"epoch": 0.3837572512271307,
"grad_norm": 0.3612985610961914,
"learning_rate": 2e-05,
"loss": 0.6844,
"step": 4300
},
{
"epoch": 0.3846497099509148,
"grad_norm": 0.873512864112854,
"learning_rate": 2e-05,
"loss": 0.6547,
"step": 4310
},
{
"epoch": 0.3855421686746988,
"grad_norm": 0.3159959614276886,
"learning_rate": 2e-05,
"loss": 0.6505,
"step": 4320
},
{
"epoch": 0.38643462739848283,
"grad_norm": 0.3532978892326355,
"learning_rate": 2e-05,
"loss": 0.6909,
"step": 4330
},
{
"epoch": 0.38732708612226685,
"grad_norm": 0.3583095669746399,
"learning_rate": 2e-05,
"loss": 0.6779,
"step": 4340
},
{
"epoch": 0.38821954484605087,
"grad_norm": 0.407150000333786,
"learning_rate": 2e-05,
"loss": 0.6786,
"step": 4350
},
{
"epoch": 0.3891120035698349,
"grad_norm": 0.3659987449645996,
"learning_rate": 2e-05,
"loss": 0.6788,
"step": 4360
},
{
"epoch": 0.3900044622936189,
"grad_norm": 0.3716491460800171,
"learning_rate": 2e-05,
"loss": 0.668,
"step": 4370
},
{
"epoch": 0.3908969210174029,
"grad_norm": 0.38405466079711914,
"learning_rate": 2e-05,
"loss": 0.6684,
"step": 4380
},
{
"epoch": 0.391789379741187,
"grad_norm": 0.3628016710281372,
"learning_rate": 2e-05,
"loss": 0.6983,
"step": 4390
},
{
"epoch": 0.392681838464971,
"grad_norm": 0.39058199524879456,
"learning_rate": 2e-05,
"loss": 0.6593,
"step": 4400
},
{
"epoch": 0.39357429718875503,
"grad_norm": 0.3607003390789032,
"learning_rate": 2e-05,
"loss": 0.6737,
"step": 4410
},
{
"epoch": 0.39446675591253905,
"grad_norm": 0.49269410967826843,
"learning_rate": 2e-05,
"loss": 0.6588,
"step": 4420
},
{
"epoch": 0.39535921463632306,
"grad_norm": 0.37630751729011536,
"learning_rate": 2e-05,
"loss": 0.6647,
"step": 4430
},
{
"epoch": 0.3962516733601071,
"grad_norm": 0.38567686080932617,
"learning_rate": 2e-05,
"loss": 0.6516,
"step": 4440
},
{
"epoch": 0.3971441320838911,
"grad_norm": 0.3609790802001953,
"learning_rate": 2e-05,
"loss": 0.6845,
"step": 4450
},
{
"epoch": 0.3980365908076752,
"grad_norm": 0.3757692277431488,
"learning_rate": 2e-05,
"loss": 0.6646,
"step": 4460
},
{
"epoch": 0.3989290495314592,
"grad_norm": 0.35269299149513245,
"learning_rate": 2e-05,
"loss": 0.6779,
"step": 4470
},
{
"epoch": 0.3998215082552432,
"grad_norm": 0.3557558059692383,
"learning_rate": 2e-05,
"loss": 0.6973,
"step": 4480
},
{
"epoch": 0.4007139669790272,
"grad_norm": 0.3537740707397461,
"learning_rate": 2e-05,
"loss": 0.6511,
"step": 4490
},
{
"epoch": 0.40160642570281124,
"grad_norm": 0.3563501834869385,
"learning_rate": 2e-05,
"loss": 0.6701,
"step": 4500
},
{
"epoch": 0.40249888442659526,
"grad_norm": 0.3577269911766052,
"learning_rate": 2e-05,
"loss": 0.6839,
"step": 4510
},
{
"epoch": 0.4033913431503793,
"grad_norm": 0.34676194190979004,
"learning_rate": 2e-05,
"loss": 0.6549,
"step": 4520
},
{
"epoch": 0.4042838018741633,
"grad_norm": 0.40689483284950256,
"learning_rate": 2e-05,
"loss": 0.6689,
"step": 4530
},
{
"epoch": 0.40517626059794737,
"grad_norm": 0.35380804538726807,
"learning_rate": 2e-05,
"loss": 0.6631,
"step": 4540
},
{
"epoch": 0.4060687193217314,
"grad_norm": 0.4036043882369995,
"learning_rate": 2e-05,
"loss": 0.6916,
"step": 4550
},
{
"epoch": 0.4069611780455154,
"grad_norm": 0.39215508103370667,
"learning_rate": 2e-05,
"loss": 0.6759,
"step": 4560
},
{
"epoch": 0.4078536367692994,
"grad_norm": 0.33775123953819275,
"learning_rate": 2e-05,
"loss": 0.6527,
"step": 4570
},
{
"epoch": 0.40874609549308344,
"grad_norm": 0.35432910919189453,
"learning_rate": 2e-05,
"loss": 0.6624,
"step": 4580
},
{
"epoch": 0.40963855421686746,
"grad_norm": 0.47398561239242554,
"learning_rate": 2e-05,
"loss": 0.669,
"step": 4590
},
{
"epoch": 0.4105310129406515,
"grad_norm": 0.3641202449798584,
"learning_rate": 2e-05,
"loss": 0.6768,
"step": 4600
},
{
"epoch": 0.41142347166443555,
"grad_norm": 0.3806946277618408,
"learning_rate": 2e-05,
"loss": 0.6915,
"step": 4610
},
{
"epoch": 0.41231593038821956,
"grad_norm": 0.39436906576156616,
"learning_rate": 2e-05,
"loss": 0.6989,
"step": 4620
},
{
"epoch": 0.4132083891120036,
"grad_norm": 0.39246389269828796,
"learning_rate": 2e-05,
"loss": 0.6684,
"step": 4630
},
{
"epoch": 0.4141008478357876,
"grad_norm": 0.36079880595207214,
"learning_rate": 2e-05,
"loss": 0.6804,
"step": 4640
},
{
"epoch": 0.4149933065595716,
"grad_norm": 0.3715951144695282,
"learning_rate": 2e-05,
"loss": 0.6908,
"step": 4650
},
{
"epoch": 0.41588576528335564,
"grad_norm": 0.35639339685440063,
"learning_rate": 2e-05,
"loss": 0.6645,
"step": 4660
},
{
"epoch": 0.41677822400713965,
"grad_norm": 0.37775149941444397,
"learning_rate": 2e-05,
"loss": 0.6581,
"step": 4670
},
{
"epoch": 0.41767068273092367,
"grad_norm": 0.3476824462413788,
"learning_rate": 2e-05,
"loss": 0.6469,
"step": 4680
},
{
"epoch": 0.41856314145470774,
"grad_norm": 0.33308857679367065,
"learning_rate": 2e-05,
"loss": 0.6528,
"step": 4690
},
{
"epoch": 0.41945560017849176,
"grad_norm": 0.3618086278438568,
"learning_rate": 2e-05,
"loss": 0.6824,
"step": 4700
},
{
"epoch": 0.4203480589022758,
"grad_norm": 0.36656132340431213,
"learning_rate": 2e-05,
"loss": 0.6754,
"step": 4710
},
{
"epoch": 0.4212405176260598,
"grad_norm": 0.36235707998275757,
"learning_rate": 2e-05,
"loss": 0.6905,
"step": 4720
},
{
"epoch": 0.4221329763498438,
"grad_norm": 0.35832539200782776,
"learning_rate": 2e-05,
"loss": 0.6703,
"step": 4730
},
{
"epoch": 0.42302543507362783,
"grad_norm": 0.4274637699127197,
"learning_rate": 2e-05,
"loss": 0.6881,
"step": 4740
},
{
"epoch": 0.42391789379741185,
"grad_norm": 0.3612465560436249,
"learning_rate": 2e-05,
"loss": 0.6648,
"step": 4750
},
{
"epoch": 0.4248103525211959,
"grad_norm": 0.3838100731372833,
"learning_rate": 2e-05,
"loss": 0.6885,
"step": 4760
},
{
"epoch": 0.42570281124497994,
"grad_norm": 0.3913135230541229,
"learning_rate": 2e-05,
"loss": 0.678,
"step": 4770
},
{
"epoch": 0.42659526996876396,
"grad_norm": 0.3443652391433716,
"learning_rate": 2e-05,
"loss": 0.6725,
"step": 4780
},
{
"epoch": 0.427487728692548,
"grad_norm": 0.3562873899936676,
"learning_rate": 2e-05,
"loss": 0.6989,
"step": 4790
},
{
"epoch": 0.428380187416332,
"grad_norm": 0.5659394264221191,
"learning_rate": 2e-05,
"loss": 0.6778,
"step": 4800
},
{
"epoch": 0.429272646140116,
"grad_norm": 0.350859135389328,
"learning_rate": 2e-05,
"loss": 0.6428,
"step": 4810
},
{
"epoch": 0.4301651048639,
"grad_norm": 0.4072927236557007,
"learning_rate": 2e-05,
"loss": 0.6619,
"step": 4820
},
{
"epoch": 0.43105756358768405,
"grad_norm": 0.39504697918891907,
"learning_rate": 2e-05,
"loss": 0.6648,
"step": 4830
},
{
"epoch": 0.4319500223114681,
"grad_norm": 0.3588836193084717,
"learning_rate": 2e-05,
"loss": 0.6775,
"step": 4840
},
{
"epoch": 0.43284248103525214,
"grad_norm": 0.34355223178863525,
"learning_rate": 2e-05,
"loss": 0.6492,
"step": 4850
},
{
"epoch": 0.43373493975903615,
"grad_norm": 0.3690549433231354,
"learning_rate": 2e-05,
"loss": 0.7112,
"step": 4860
},
{
"epoch": 0.43462739848282017,
"grad_norm": 0.40262696146965027,
"learning_rate": 2e-05,
"loss": 0.6977,
"step": 4870
},
{
"epoch": 0.4355198572066042,
"grad_norm": 0.3697252571582794,
"learning_rate": 2e-05,
"loss": 0.6673,
"step": 4880
},
{
"epoch": 0.4364123159303882,
"grad_norm": 0.3683331310749054,
"learning_rate": 2e-05,
"loss": 0.6588,
"step": 4890
},
{
"epoch": 0.4373047746541722,
"grad_norm": 0.35332024097442627,
"learning_rate": 2e-05,
"loss": 0.6573,
"step": 4900
},
{
"epoch": 0.4381972333779563,
"grad_norm": 0.33469337224960327,
"learning_rate": 2e-05,
"loss": 0.6429,
"step": 4910
},
{
"epoch": 0.4390896921017403,
"grad_norm": 0.34541958570480347,
"learning_rate": 2e-05,
"loss": 0.6413,
"step": 4920
},
{
"epoch": 0.43998215082552433,
"grad_norm": 0.39203688502311707,
"learning_rate": 2e-05,
"loss": 0.6642,
"step": 4930
},
{
"epoch": 0.44087460954930835,
"grad_norm": 0.3529221713542938,
"learning_rate": 2e-05,
"loss": 0.6416,
"step": 4940
},
{
"epoch": 0.44176706827309237,
"grad_norm": 0.35118046402931213,
"learning_rate": 2e-05,
"loss": 0.6432,
"step": 4950
},
{
"epoch": 0.4426595269968764,
"grad_norm": 0.3619842231273651,
"learning_rate": 2e-05,
"loss": 0.6691,
"step": 4960
},
{
"epoch": 0.4435519857206604,
"grad_norm": 0.3873862028121948,
"learning_rate": 2e-05,
"loss": 0.6572,
"step": 4970
},
{
"epoch": 0.4444444444444444,
"grad_norm": 0.37688902020454407,
"learning_rate": 2e-05,
"loss": 0.6723,
"step": 4980
},
{
"epoch": 0.4453369031682285,
"grad_norm": 0.353566437959671,
"learning_rate": 2e-05,
"loss": 0.6676,
"step": 4990
},
{
"epoch": 0.4462293618920125,
"grad_norm": 0.35387760400772095,
"learning_rate": 2e-05,
"loss": 0.6553,
"step": 5000
},
{
"epoch": 0.44712182061579653,
"grad_norm": 0.41578125953674316,
"learning_rate": 2e-05,
"loss": 0.679,
"step": 5010
},
{
"epoch": 0.44801427933958055,
"grad_norm": 0.389415979385376,
"learning_rate": 2e-05,
"loss": 0.6602,
"step": 5020
},
{
"epoch": 0.44890673806336456,
"grad_norm": 0.40956026315689087,
"learning_rate": 2e-05,
"loss": 0.6733,
"step": 5030
},
{
"epoch": 0.4497991967871486,
"grad_norm": 0.38854891061782837,
"learning_rate": 2e-05,
"loss": 0.6591,
"step": 5040
},
{
"epoch": 0.4506916555109326,
"grad_norm": 0.35887807607650757,
"learning_rate": 2e-05,
"loss": 0.6565,
"step": 5050
},
{
"epoch": 0.45158411423471667,
"grad_norm": 0.3465573489665985,
"learning_rate": 2e-05,
"loss": 0.695,
"step": 5060
},
{
"epoch": 0.4524765729585007,
"grad_norm": 0.37553462386131287,
"learning_rate": 2e-05,
"loss": 0.6736,
"step": 5070
},
{
"epoch": 0.4533690316822847,
"grad_norm": 0.38836538791656494,
"learning_rate": 2e-05,
"loss": 0.653,
"step": 5080
},
{
"epoch": 0.4542614904060687,
"grad_norm": 0.7373122572898865,
"learning_rate": 2e-05,
"loss": 0.6423,
"step": 5090
},
{
"epoch": 0.45515394912985274,
"grad_norm": 0.3776000738143921,
"learning_rate": 2e-05,
"loss": 0.6697,
"step": 5100
},
{
"epoch": 0.45604640785363676,
"grad_norm": 0.31693071126937866,
"learning_rate": 2e-05,
"loss": 0.6656,
"step": 5110
},
{
"epoch": 0.4569388665774208,
"grad_norm": 0.3468279540538788,
"learning_rate": 2e-05,
"loss": 0.6723,
"step": 5120
},
{
"epoch": 0.4578313253012048,
"grad_norm": 0.36441564559936523,
"learning_rate": 2e-05,
"loss": 0.6581,
"step": 5130
},
{
"epoch": 0.45872378402498887,
"grad_norm": 0.34191110730171204,
"learning_rate": 2e-05,
"loss": 0.66,
"step": 5140
},
{
"epoch": 0.4596162427487729,
"grad_norm": 0.382263720035553,
"learning_rate": 2e-05,
"loss": 0.701,
"step": 5150
},
{
"epoch": 0.4605087014725569,
"grad_norm": 0.4101616144180298,
"learning_rate": 2e-05,
"loss": 0.6678,
"step": 5160
},
{
"epoch": 0.4614011601963409,
"grad_norm": 0.35307857394218445,
"learning_rate": 2e-05,
"loss": 0.6295,
"step": 5170
},
{
"epoch": 0.46229361892012494,
"grad_norm": 0.41348662972450256,
"learning_rate": 2e-05,
"loss": 0.676,
"step": 5180
},
{
"epoch": 0.46318607764390896,
"grad_norm": 0.3474131226539612,
"learning_rate": 2e-05,
"loss": 0.6836,
"step": 5190
},
{
"epoch": 0.464078536367693,
"grad_norm": 0.34295785427093506,
"learning_rate": 2e-05,
"loss": 0.6663,
"step": 5200
},
{
"epoch": 0.46497099509147705,
"grad_norm": 0.3485386073589325,
"learning_rate": 2e-05,
"loss": 0.6796,
"step": 5210
},
{
"epoch": 0.46586345381526106,
"grad_norm": 0.36912795901298523,
"learning_rate": 2e-05,
"loss": 0.6464,
"step": 5220
},
{
"epoch": 0.4667559125390451,
"grad_norm": 0.38085198402404785,
"learning_rate": 2e-05,
"loss": 0.662,
"step": 5230
},
{
"epoch": 0.4676483712628291,
"grad_norm": 0.5402212142944336,
"learning_rate": 2e-05,
"loss": 0.667,
"step": 5240
},
{
"epoch": 0.4685408299866131,
"grad_norm": 0.3647153377532959,
"learning_rate": 2e-05,
"loss": 0.6656,
"step": 5250
},
{
"epoch": 0.46943328871039713,
"grad_norm": 0.347307950258255,
"learning_rate": 2e-05,
"loss": 0.6622,
"step": 5260
},
{
"epoch": 0.47032574743418115,
"grad_norm": 0.34363237023353577,
"learning_rate": 2e-05,
"loss": 0.6848,
"step": 5270
},
{
"epoch": 0.47121820615796517,
"grad_norm": 0.3889744281768799,
"learning_rate": 2e-05,
"loss": 0.6832,
"step": 5280
},
{
"epoch": 0.47211066488174924,
"grad_norm": 0.47765013575553894,
"learning_rate": 2e-05,
"loss": 0.6474,
"step": 5290
},
{
"epoch": 0.47300312360553326,
"grad_norm": 0.37653648853302,
"learning_rate": 2e-05,
"loss": 0.6632,
"step": 5300
},
{
"epoch": 0.4738955823293173,
"grad_norm": 0.3738003075122833,
"learning_rate": 2e-05,
"loss": 0.7,
"step": 5310
},
{
"epoch": 0.4747880410531013,
"grad_norm": 0.3545479476451874,
"learning_rate": 2e-05,
"loss": 0.6572,
"step": 5320
},
{
"epoch": 0.4756804997768853,
"grad_norm": 0.4097460210323334,
"learning_rate": 2e-05,
"loss": 0.6638,
"step": 5330
},
{
"epoch": 0.47657295850066933,
"grad_norm": 0.4064861834049225,
"learning_rate": 2e-05,
"loss": 0.6675,
"step": 5340
},
{
"epoch": 0.47746541722445335,
"grad_norm": 0.4148159325122833,
"learning_rate": 2e-05,
"loss": 0.6868,
"step": 5350
},
{
"epoch": 0.4783578759482374,
"grad_norm": 0.3503594994544983,
"learning_rate": 2e-05,
"loss": 0.631,
"step": 5360
},
{
"epoch": 0.47925033467202144,
"grad_norm": 0.40914788842201233,
"learning_rate": 2e-05,
"loss": 0.6845,
"step": 5370
},
{
"epoch": 0.48014279339580546,
"grad_norm": 0.3585137724876404,
"learning_rate": 2e-05,
"loss": 0.658,
"step": 5380
},
{
"epoch": 0.4810352521195895,
"grad_norm": 0.35773351788520813,
"learning_rate": 2e-05,
"loss": 0.6432,
"step": 5390
},
{
"epoch": 0.4819277108433735,
"grad_norm": 0.38882124423980713,
"learning_rate": 2e-05,
"loss": 0.6645,
"step": 5400
},
{
"epoch": 0.4828201695671575,
"grad_norm": 0.42651259899139404,
"learning_rate": 2e-05,
"loss": 0.6497,
"step": 5410
},
{
"epoch": 0.4837126282909415,
"grad_norm": 0.36548325419425964,
"learning_rate": 2e-05,
"loss": 0.6572,
"step": 5420
},
{
"epoch": 0.48460508701472554,
"grad_norm": 0.33452707529067993,
"learning_rate": 2e-05,
"loss": 0.6854,
"step": 5430
},
{
"epoch": 0.4854975457385096,
"grad_norm": 0.3678087890148163,
"learning_rate": 2e-05,
"loss": 0.6626,
"step": 5440
},
{
"epoch": 0.48639000446229363,
"grad_norm": 0.40957334637641907,
"learning_rate": 2e-05,
"loss": 0.6867,
"step": 5450
},
{
"epoch": 0.48728246318607765,
"grad_norm": 0.367035835981369,
"learning_rate": 2e-05,
"loss": 0.651,
"step": 5460
},
{
"epoch": 0.48817492190986167,
"grad_norm": 0.37794142961502075,
"learning_rate": 2e-05,
"loss": 0.6654,
"step": 5470
},
{
"epoch": 0.4890673806336457,
"grad_norm": 0.39220210909843445,
"learning_rate": 2e-05,
"loss": 0.654,
"step": 5480
},
{
"epoch": 0.4899598393574297,
"grad_norm": 0.4127984344959259,
"learning_rate": 2e-05,
"loss": 0.6582,
"step": 5490
},
{
"epoch": 0.4908522980812137,
"grad_norm": 0.3525770306587219,
"learning_rate": 2e-05,
"loss": 0.6444,
"step": 5500
},
{
"epoch": 0.4917447568049978,
"grad_norm": 0.37988531589508057,
"learning_rate": 2e-05,
"loss": 0.6795,
"step": 5510
},
{
"epoch": 0.4926372155287818,
"grad_norm": 0.40696239471435547,
"learning_rate": 2e-05,
"loss": 0.6829,
"step": 5520
},
{
"epoch": 0.49352967425256583,
"grad_norm": 0.3252825438976288,
"learning_rate": 2e-05,
"loss": 0.6472,
"step": 5530
},
{
"epoch": 0.49442213297634985,
"grad_norm": 0.3405821919441223,
"learning_rate": 2e-05,
"loss": 0.6847,
"step": 5540
},
{
"epoch": 0.49531459170013387,
"grad_norm": 0.3719472885131836,
"learning_rate": 2e-05,
"loss": 0.6364,
"step": 5550
},
{
"epoch": 0.4962070504239179,
"grad_norm": 0.3792165517807007,
"learning_rate": 2e-05,
"loss": 0.624,
"step": 5560
},
{
"epoch": 0.4970995091477019,
"grad_norm": 0.3495136797428131,
"learning_rate": 2e-05,
"loss": 0.6582,
"step": 5570
},
{
"epoch": 0.4979919678714859,
"grad_norm": 0.3685084879398346,
"learning_rate": 2e-05,
"loss": 0.6633,
"step": 5580
},
{
"epoch": 0.49888442659527,
"grad_norm": 0.35136640071868896,
"learning_rate": 2e-05,
"loss": 0.6446,
"step": 5590
},
{
"epoch": 0.499776885319054,
"grad_norm": 0.4077424108982086,
"learning_rate": 2e-05,
"loss": 0.6826,
"step": 5600
},
{
"epoch": 0.500669344042838,
"grad_norm": 0.342560350894928,
"learning_rate": 2e-05,
"loss": 0.6413,
"step": 5610
},
{
"epoch": 0.501561802766622,
"grad_norm": 0.3729529082775116,
"learning_rate": 2e-05,
"loss": 0.6533,
"step": 5620
},
{
"epoch": 0.5024542614904061,
"grad_norm": 0.3485109210014343,
"learning_rate": 2e-05,
"loss": 0.6805,
"step": 5630
},
{
"epoch": 0.5033467202141901,
"grad_norm": 0.3356485664844513,
"learning_rate": 2e-05,
"loss": 0.6771,
"step": 5640
},
{
"epoch": 0.5042391789379741,
"grad_norm": 0.38243138790130615,
"learning_rate": 2e-05,
"loss": 0.6675,
"step": 5650
},
{
"epoch": 0.5051316376617582,
"grad_norm": 0.37277427315711975,
"learning_rate": 2e-05,
"loss": 0.641,
"step": 5660
},
{
"epoch": 0.5060240963855421,
"grad_norm": 0.3976978659629822,
"learning_rate": 2e-05,
"loss": 0.6711,
"step": 5670
},
{
"epoch": 0.5069165551093262,
"grad_norm": 0.35143548250198364,
"learning_rate": 2e-05,
"loss": 0.6357,
"step": 5680
},
{
"epoch": 0.5078090138331102,
"grad_norm": 0.37111008167266846,
"learning_rate": 2e-05,
"loss": 0.6504,
"step": 5690
},
{
"epoch": 0.5087014725568942,
"grad_norm": 0.41470929980278015,
"learning_rate": 2e-05,
"loss": 0.6633,
"step": 5700
},
{
"epoch": 0.5095939312806783,
"grad_norm": 0.3423355221748352,
"learning_rate": 2e-05,
"loss": 0.6614,
"step": 5710
},
{
"epoch": 0.5104863900044623,
"grad_norm": 0.39969611167907715,
"learning_rate": 2e-05,
"loss": 0.665,
"step": 5720
},
{
"epoch": 0.5113788487282463,
"grad_norm": 0.4176351726055145,
"learning_rate": 2e-05,
"loss": 0.624,
"step": 5730
},
{
"epoch": 0.5122713074520303,
"grad_norm": 0.368865430355072,
"learning_rate": 2e-05,
"loss": 0.6886,
"step": 5740
},
{
"epoch": 0.5131637661758144,
"grad_norm": 0.37808871269226074,
"learning_rate": 2e-05,
"loss": 0.6506,
"step": 5750
},
{
"epoch": 0.5140562248995983,
"grad_norm": 0.3877156972885132,
"learning_rate": 2e-05,
"loss": 0.6576,
"step": 5760
},
{
"epoch": 0.5149486836233824,
"grad_norm": 0.4622533917427063,
"learning_rate": 2e-05,
"loss": 0.6882,
"step": 5770
},
{
"epoch": 0.5158411423471665,
"grad_norm": 0.3736531138420105,
"learning_rate": 2e-05,
"loss": 0.6514,
"step": 5780
},
{
"epoch": 0.5167336010709505,
"grad_norm": 0.3759421110153198,
"learning_rate": 2e-05,
"loss": 0.6495,
"step": 5790
},
{
"epoch": 0.5176260597947345,
"grad_norm": 0.38427674770355225,
"learning_rate": 2e-05,
"loss": 0.6694,
"step": 5800
},
{
"epoch": 0.5185185185185185,
"grad_norm": 0.34168484807014465,
"learning_rate": 2e-05,
"loss": 0.6208,
"step": 5810
},
{
"epoch": 0.5194109772423026,
"grad_norm": 0.3361280560493469,
"learning_rate": 2e-05,
"loss": 0.6634,
"step": 5820
},
{
"epoch": 0.5203034359660865,
"grad_norm": 0.34314724802970886,
"learning_rate": 2e-05,
"loss": 0.6604,
"step": 5830
},
{
"epoch": 0.5211958946898706,
"grad_norm": 0.3676067292690277,
"learning_rate": 2e-05,
"loss": 0.647,
"step": 5840
},
{
"epoch": 0.5220883534136547,
"grad_norm": 0.3909711241722107,
"learning_rate": 2e-05,
"loss": 0.6598,
"step": 5850
},
{
"epoch": 0.5229808121374386,
"grad_norm": 0.3700374364852905,
"learning_rate": 2e-05,
"loss": 0.6624,
"step": 5860
},
{
"epoch": 0.5238732708612227,
"grad_norm": 0.3496149778366089,
"learning_rate": 2e-05,
"loss": 0.659,
"step": 5870
},
{
"epoch": 0.5247657295850067,
"grad_norm": 0.39002978801727295,
"learning_rate": 2e-05,
"loss": 0.6423,
"step": 5880
},
{
"epoch": 0.5256581883087907,
"grad_norm": 0.3534677028656006,
"learning_rate": 2e-05,
"loss": 0.678,
"step": 5890
},
{
"epoch": 0.5265506470325747,
"grad_norm": 0.3787784278392792,
"learning_rate": 2e-05,
"loss": 0.6776,
"step": 5900
},
{
"epoch": 0.5274431057563588,
"grad_norm": 0.372121661901474,
"learning_rate": 2e-05,
"loss": 0.6507,
"step": 5910
},
{
"epoch": 0.5283355644801427,
"grad_norm": 0.3725496232509613,
"learning_rate": 2e-05,
"loss": 0.6716,
"step": 5920
},
{
"epoch": 0.5292280232039268,
"grad_norm": 0.3385017216205597,
"learning_rate": 2e-05,
"loss": 0.6516,
"step": 5930
},
{
"epoch": 0.5301204819277109,
"grad_norm": 0.35288533568382263,
"learning_rate": 2e-05,
"loss": 0.6485,
"step": 5940
},
{
"epoch": 0.5310129406514948,
"grad_norm": 0.3737861216068268,
"learning_rate": 2e-05,
"loss": 0.6612,
"step": 5950
},
{
"epoch": 0.5319053993752789,
"grad_norm": 0.3486451506614685,
"learning_rate": 2e-05,
"loss": 0.6317,
"step": 5960
},
{
"epoch": 0.5327978580990629,
"grad_norm": 0.37649545073509216,
"learning_rate": 2e-05,
"loss": 0.6738,
"step": 5970
},
{
"epoch": 0.533690316822847,
"grad_norm": 0.40644797682762146,
"learning_rate": 2e-05,
"loss": 0.6269,
"step": 5980
},
{
"epoch": 0.5345827755466309,
"grad_norm": 0.40873983502388,
"learning_rate": 2e-05,
"loss": 0.6353,
"step": 5990
},
{
"epoch": 0.535475234270415,
"grad_norm": 0.3289964199066162,
"learning_rate": 2e-05,
"loss": 0.6079,
"step": 6000
},
{
"epoch": 0.5363676929941991,
"grad_norm": 0.32475483417510986,
"learning_rate": 2e-05,
"loss": 0.6475,
"step": 6010
},
{
"epoch": 0.537260151717983,
"grad_norm": 0.35270053148269653,
"learning_rate": 2e-05,
"loss": 0.6419,
"step": 6020
},
{
"epoch": 0.5381526104417671,
"grad_norm": 0.34637442231178284,
"learning_rate": 2e-05,
"loss": 0.6581,
"step": 6030
},
{
"epoch": 0.5390450691655511,
"grad_norm": 0.3699469268321991,
"learning_rate": 2e-05,
"loss": 0.6262,
"step": 6040
},
{
"epoch": 0.5399375278893351,
"grad_norm": 0.3830867409706116,
"learning_rate": 2e-05,
"loss": 0.6517,
"step": 6050
},
{
"epoch": 0.5408299866131191,
"grad_norm": 0.38110360503196716,
"learning_rate": 2e-05,
"loss": 0.6227,
"step": 6060
},
{
"epoch": 0.5417224453369032,
"grad_norm": 0.3710538148880005,
"learning_rate": 2e-05,
"loss": 0.6749,
"step": 6070
},
{
"epoch": 0.5426149040606872,
"grad_norm": 0.32121920585632324,
"learning_rate": 2e-05,
"loss": 0.6167,
"step": 6080
},
{
"epoch": 0.5435073627844712,
"grad_norm": 0.354740709066391,
"learning_rate": 2e-05,
"loss": 0.6731,
"step": 6090
},
{
"epoch": 0.5443998215082553,
"grad_norm": 0.3399162292480469,
"learning_rate": 2e-05,
"loss": 0.6298,
"step": 6100
},
{
"epoch": 0.5452922802320392,
"grad_norm": 0.36772987246513367,
"learning_rate": 2e-05,
"loss": 0.6517,
"step": 6110
},
{
"epoch": 0.5461847389558233,
"grad_norm": 0.32623496651649475,
"learning_rate": 2e-05,
"loss": 0.6198,
"step": 6120
},
{
"epoch": 0.5470771976796073,
"grad_norm": 0.39266809821128845,
"learning_rate": 2e-05,
"loss": 0.6608,
"step": 6130
},
{
"epoch": 0.5479696564033913,
"grad_norm": 0.3569527566432953,
"learning_rate": 2e-05,
"loss": 0.6364,
"step": 6140
},
{
"epoch": 0.5488621151271754,
"grad_norm": 0.41820159554481506,
"learning_rate": 2e-05,
"loss": 0.6368,
"step": 6150
},
{
"epoch": 0.5497545738509594,
"grad_norm": 0.36492493748664856,
"learning_rate": 2e-05,
"loss": 0.6525,
"step": 6160
},
{
"epoch": 0.5506470325747435,
"grad_norm": 0.386701375246048,
"learning_rate": 2e-05,
"loss": 0.6373,
"step": 6170
},
{
"epoch": 0.5515394912985274,
"grad_norm": 0.3586895763874054,
"learning_rate": 2e-05,
"loss": 0.6479,
"step": 6180
},
{
"epoch": 0.5524319500223115,
"grad_norm": 0.39232516288757324,
"learning_rate": 2e-05,
"loss": 0.663,
"step": 6190
},
{
"epoch": 0.5533244087460955,
"grad_norm": 0.326825886964798,
"learning_rate": 2e-05,
"loss": 0.6282,
"step": 6200
},
{
"epoch": 0.5542168674698795,
"grad_norm": 0.4082288146018982,
"learning_rate": 2e-05,
"loss": 0.6576,
"step": 6210
},
{
"epoch": 0.5551093261936635,
"grad_norm": 0.3908236622810364,
"learning_rate": 2e-05,
"loss": 0.6671,
"step": 6220
},
{
"epoch": 0.5560017849174476,
"grad_norm": 0.37259408831596375,
"learning_rate": 2e-05,
"loss": 0.6605,
"step": 6230
},
{
"epoch": 0.5568942436412316,
"grad_norm": 0.39755138754844666,
"learning_rate": 2e-05,
"loss": 0.636,
"step": 6240
},
{
"epoch": 0.5577867023650156,
"grad_norm": 0.38658297061920166,
"learning_rate": 2e-05,
"loss": 0.656,
"step": 6250
},
{
"epoch": 0.5586791610887997,
"grad_norm": 0.3339689075946808,
"learning_rate": 2e-05,
"loss": 0.6313,
"step": 6260
},
{
"epoch": 0.5595716198125836,
"grad_norm": 0.33873316645622253,
"learning_rate": 2e-05,
"loss": 0.6737,
"step": 6270
},
{
"epoch": 0.5604640785363677,
"grad_norm": 0.33827605843544006,
"learning_rate": 2e-05,
"loss": 0.6392,
"step": 6280
},
{
"epoch": 0.5613565372601517,
"grad_norm": 0.3628009259700775,
"learning_rate": 2e-05,
"loss": 0.6775,
"step": 6290
},
{
"epoch": 0.5622489959839357,
"grad_norm": 0.34019726514816284,
"learning_rate": 2e-05,
"loss": 0.6922,
"step": 6300
},
{
"epoch": 0.5631414547077198,
"grad_norm": 0.3830169141292572,
"learning_rate": 2e-05,
"loss": 0.6963,
"step": 6310
},
{
"epoch": 0.5640339134315038,
"grad_norm": 0.3492322564125061,
"learning_rate": 2e-05,
"loss": 0.6481,
"step": 6320
},
{
"epoch": 0.5649263721552878,
"grad_norm": 0.3648815155029297,
"learning_rate": 2e-05,
"loss": 0.627,
"step": 6330
},
{
"epoch": 0.5658188308790718,
"grad_norm": 0.6144285202026367,
"learning_rate": 2e-05,
"loss": 0.667,
"step": 6340
},
{
"epoch": 0.5667112896028559,
"grad_norm": 0.35637691617012024,
"learning_rate": 2e-05,
"loss": 0.6501,
"step": 6350
},
{
"epoch": 0.5676037483266398,
"grad_norm": 0.35367274284362793,
"learning_rate": 2e-05,
"loss": 0.6307,
"step": 6360
},
{
"epoch": 0.5684962070504239,
"grad_norm": 0.4123179614543915,
"learning_rate": 2e-05,
"loss": 0.6682,
"step": 6370
},
{
"epoch": 0.569388665774208,
"grad_norm": 0.39732566475868225,
"learning_rate": 2e-05,
"loss": 0.6488,
"step": 6380
},
{
"epoch": 0.570281124497992,
"grad_norm": 0.3471108078956604,
"learning_rate": 2e-05,
"loss": 0.6415,
"step": 6390
},
{
"epoch": 0.571173583221776,
"grad_norm": 0.35157427191734314,
"learning_rate": 2e-05,
"loss": 0.6251,
"step": 6400
},
{
"epoch": 0.57206604194556,
"grad_norm": 0.3665190637111664,
"learning_rate": 2e-05,
"loss": 0.6532,
"step": 6410
},
{
"epoch": 0.5729585006693441,
"grad_norm": 0.39863625168800354,
"learning_rate": 2e-05,
"loss": 0.6802,
"step": 6420
},
{
"epoch": 0.573850959393128,
"grad_norm": 0.37718063592910767,
"learning_rate": 2e-05,
"loss": 0.6575,
"step": 6430
},
{
"epoch": 0.5747434181169121,
"grad_norm": 0.3465448021888733,
"learning_rate": 2e-05,
"loss": 0.6419,
"step": 6440
},
{
"epoch": 0.5756358768406962,
"grad_norm": 0.3486118018627167,
"learning_rate": 2e-05,
"loss": 0.669,
"step": 6450
},
{
"epoch": 0.5765283355644801,
"grad_norm": 0.38347044587135315,
"learning_rate": 2e-05,
"loss": 0.6548,
"step": 6460
},
{
"epoch": 0.5774207942882642,
"grad_norm": 0.36011189222335815,
"learning_rate": 2e-05,
"loss": 0.6352,
"step": 6470
},
{
"epoch": 0.5783132530120482,
"grad_norm": 0.3930314779281616,
"learning_rate": 2e-05,
"loss": 0.6838,
"step": 6480
},
{
"epoch": 0.5792057117358322,
"grad_norm": 0.356662392616272,
"learning_rate": 2e-05,
"loss": 0.6403,
"step": 6490
},
{
"epoch": 0.5800981704596162,
"grad_norm": 0.36029770970344543,
"learning_rate": 2e-05,
"loss": 0.6547,
"step": 6500
},
{
"epoch": 0.5809906291834003,
"grad_norm": 0.36168232560157776,
"learning_rate": 2e-05,
"loss": 0.621,
"step": 6510
},
{
"epoch": 0.5818830879071842,
"grad_norm": 0.37506598234176636,
"learning_rate": 2e-05,
"loss": 0.6479,
"step": 6520
},
{
"epoch": 0.5827755466309683,
"grad_norm": 0.3930968940258026,
"learning_rate": 2e-05,
"loss": 0.6325,
"step": 6530
},
{
"epoch": 0.5836680053547524,
"grad_norm": 0.3708667755126953,
"learning_rate": 2e-05,
"loss": 0.6449,
"step": 6540
},
{
"epoch": 0.5845604640785363,
"grad_norm": 0.36663392186164856,
"learning_rate": 2e-05,
"loss": 0.6424,
"step": 6550
},
{
"epoch": 0.5854529228023204,
"grad_norm": 0.3694658875465393,
"learning_rate": 2e-05,
"loss": 0.627,
"step": 6560
},
{
"epoch": 0.5863453815261044,
"grad_norm": 0.41160261631011963,
"learning_rate": 2e-05,
"loss": 0.6364,
"step": 6570
},
{
"epoch": 0.5872378402498885,
"grad_norm": 0.4105084538459778,
"learning_rate": 2e-05,
"loss": 0.6726,
"step": 6580
},
{
"epoch": 0.5881302989736724,
"grad_norm": 0.3616373836994171,
"learning_rate": 2e-05,
"loss": 0.6294,
"step": 6590
},
{
"epoch": 0.5890227576974565,
"grad_norm": 0.3613976538181305,
"learning_rate": 2e-05,
"loss": 0.6428,
"step": 6600
},
{
"epoch": 0.5899152164212406,
"grad_norm": 0.3835005760192871,
"learning_rate": 2e-05,
"loss": 0.6187,
"step": 6610
},
{
"epoch": 0.5908076751450245,
"grad_norm": 0.32900547981262207,
"learning_rate": 2e-05,
"loss": 0.6242,
"step": 6620
},
{
"epoch": 0.5917001338688086,
"grad_norm": 0.3713598847389221,
"learning_rate": 2e-05,
"loss": 0.6568,
"step": 6630
},
{
"epoch": 0.5925925925925926,
"grad_norm": 0.3687555193901062,
"learning_rate": 2e-05,
"loss": 0.6559,
"step": 6640
},
{
"epoch": 0.5934850513163766,
"grad_norm": 0.35752445459365845,
"learning_rate": 2e-05,
"loss": 0.6366,
"step": 6650
},
{
"epoch": 0.5943775100401606,
"grad_norm": 0.3643396198749542,
"learning_rate": 2e-05,
"loss": 0.6376,
"step": 6660
},
{
"epoch": 0.5952699687639447,
"grad_norm": 0.40656864643096924,
"learning_rate": 2e-05,
"loss": 0.6635,
"step": 6670
},
{
"epoch": 0.5961624274877287,
"grad_norm": 0.3739723861217499,
"learning_rate": 2e-05,
"loss": 0.6871,
"step": 6680
},
{
"epoch": 0.5970548862115127,
"grad_norm": 0.3461340069770813,
"learning_rate": 2e-05,
"loss": 0.6471,
"step": 6690
},
{
"epoch": 0.5979473449352968,
"grad_norm": 0.37061694264411926,
"learning_rate": 2e-05,
"loss": 0.6373,
"step": 6700
},
{
"epoch": 0.5988398036590807,
"grad_norm": 0.383504182100296,
"learning_rate": 2e-05,
"loss": 0.6575,
"step": 6710
},
{
"epoch": 0.5997322623828648,
"grad_norm": 0.37076982855796814,
"learning_rate": 2e-05,
"loss": 0.6172,
"step": 6720
},
{
"epoch": 0.6006247211066488,
"grad_norm": 0.3490729331970215,
"learning_rate": 2e-05,
"loss": 0.6527,
"step": 6730
},
{
"epoch": 0.6015171798304328,
"grad_norm": 0.36137017607688904,
"learning_rate": 2e-05,
"loss": 0.641,
"step": 6740
},
{
"epoch": 0.6024096385542169,
"grad_norm": 0.44374004006385803,
"learning_rate": 2e-05,
"loss": 0.6657,
"step": 6750
},
{
"epoch": 0.6033020972780009,
"grad_norm": 0.37671053409576416,
"learning_rate": 2e-05,
"loss": 0.6354,
"step": 6760
},
{
"epoch": 0.604194556001785,
"grad_norm": 0.3474961221218109,
"learning_rate": 2e-05,
"loss": 0.611,
"step": 6770
},
{
"epoch": 0.6050870147255689,
"grad_norm": 0.35777968168258667,
"learning_rate": 2e-05,
"loss": 0.6341,
"step": 6780
},
{
"epoch": 0.605979473449353,
"grad_norm": 0.39478209614753723,
"learning_rate": 2e-05,
"loss": 0.6299,
"step": 6790
},
{
"epoch": 0.606871932173137,
"grad_norm": 0.37285494804382324,
"learning_rate": 2e-05,
"loss": 0.6442,
"step": 6800
},
{
"epoch": 0.607764390896921,
"grad_norm": 0.36982327699661255,
"learning_rate": 2e-05,
"loss": 0.6216,
"step": 6810
},
{
"epoch": 0.608656849620705,
"grad_norm": 0.36921244859695435,
"learning_rate": 2e-05,
"loss": 0.647,
"step": 6820
},
{
"epoch": 0.6095493083444891,
"grad_norm": 0.4001862406730652,
"learning_rate": 2e-05,
"loss": 0.6489,
"step": 6830
},
{
"epoch": 0.6104417670682731,
"grad_norm": 0.37241610884666443,
"learning_rate": 2e-05,
"loss": 0.6621,
"step": 6840
},
{
"epoch": 0.6113342257920571,
"grad_norm": 0.38561350107192993,
"learning_rate": 2e-05,
"loss": 0.635,
"step": 6850
},
{
"epoch": 0.6122266845158412,
"grad_norm": 0.34888726472854614,
"learning_rate": 2e-05,
"loss": 0.6562,
"step": 6860
},
{
"epoch": 0.6131191432396251,
"grad_norm": 0.3733842372894287,
"learning_rate": 2e-05,
"loss": 0.6599,
"step": 6870
},
{
"epoch": 0.6140116019634092,
"grad_norm": 0.33748945593833923,
"learning_rate": 2e-05,
"loss": 0.6338,
"step": 6880
},
{
"epoch": 0.6149040606871932,
"grad_norm": 0.4345172345638275,
"learning_rate": 2e-05,
"loss": 0.6463,
"step": 6890
},
{
"epoch": 0.6157965194109772,
"grad_norm": 0.3841955065727234,
"learning_rate": 2e-05,
"loss": 0.6451,
"step": 6900
},
{
"epoch": 0.6166889781347613,
"grad_norm": 0.36685696244239807,
"learning_rate": 2e-05,
"loss": 0.6636,
"step": 6910
},
{
"epoch": 0.6175814368585453,
"grad_norm": 0.3804943263530731,
"learning_rate": 2e-05,
"loss": 0.6309,
"step": 6920
},
{
"epoch": 0.6184738955823293,
"grad_norm": 0.41180241107940674,
"learning_rate": 2e-05,
"loss": 0.6579,
"step": 6930
},
{
"epoch": 0.6193663543061133,
"grad_norm": 0.37410253286361694,
"learning_rate": 2e-05,
"loss": 0.6312,
"step": 6940
},
{
"epoch": 0.6202588130298974,
"grad_norm": 0.39086076617240906,
"learning_rate": 2e-05,
"loss": 0.6572,
"step": 6950
},
{
"epoch": 0.6211512717536813,
"grad_norm": 0.36655816435813904,
"learning_rate": 2e-05,
"loss": 0.6239,
"step": 6960
},
{
"epoch": 0.6220437304774654,
"grad_norm": 0.36375167965888977,
"learning_rate": 2e-05,
"loss": 0.6653,
"step": 6970
},
{
"epoch": 0.6229361892012495,
"grad_norm": 0.3411877751350403,
"learning_rate": 2e-05,
"loss": 0.6491,
"step": 6980
},
{
"epoch": 0.6238286479250335,
"grad_norm": 0.43325725197792053,
"learning_rate": 2e-05,
"loss": 0.665,
"step": 6990
},
{
"epoch": 0.6247211066488175,
"grad_norm": 0.3501139283180237,
"learning_rate": 2e-05,
"loss": 0.6636,
"step": 7000
},
{
"epoch": 0.6256135653726015,
"grad_norm": 0.3959539532661438,
"learning_rate": 2e-05,
"loss": 0.6178,
"step": 7010
},
{
"epoch": 0.6265060240963856,
"grad_norm": 0.3225207030773163,
"learning_rate": 2e-05,
"loss": 0.6414,
"step": 7020
},
{
"epoch": 0.6273984828201695,
"grad_norm": 0.36039894819259644,
"learning_rate": 2e-05,
"loss": 0.6312,
"step": 7030
},
{
"epoch": 0.6282909415439536,
"grad_norm": 0.351453572511673,
"learning_rate": 2e-05,
"loss": 0.6567,
"step": 7040
},
{
"epoch": 0.6291834002677377,
"grad_norm": 0.3850865960121155,
"learning_rate": 2e-05,
"loss": 0.666,
"step": 7050
},
{
"epoch": 0.6300758589915216,
"grad_norm": 0.3699142038822174,
"learning_rate": 2e-05,
"loss": 0.6547,
"step": 7060
},
{
"epoch": 0.6309683177153057,
"grad_norm": 0.36317190527915955,
"learning_rate": 2e-05,
"loss": 0.6549,
"step": 7070
},
{
"epoch": 0.6318607764390897,
"grad_norm": 0.3556196391582489,
"learning_rate": 2e-05,
"loss": 0.6674,
"step": 7080
},
{
"epoch": 0.6327532351628737,
"grad_norm": 0.37361249327659607,
"learning_rate": 2e-05,
"loss": 0.6085,
"step": 7090
},
{
"epoch": 0.6336456938866577,
"grad_norm": 0.3366241455078125,
"learning_rate": 2e-05,
"loss": 0.6659,
"step": 7100
},
{
"epoch": 0.6345381526104418,
"grad_norm": 0.35550394654273987,
"learning_rate": 2e-05,
"loss": 0.6532,
"step": 7110
},
{
"epoch": 0.6354306113342257,
"grad_norm": 0.3637809455394745,
"learning_rate": 2e-05,
"loss": 0.6418,
"step": 7120
},
{
"epoch": 0.6363230700580098,
"grad_norm": 0.38233086466789246,
"learning_rate": 2e-05,
"loss": 0.6513,
"step": 7130
},
{
"epoch": 0.6372155287817939,
"grad_norm": 0.7820004820823669,
"learning_rate": 2e-05,
"loss": 0.6642,
"step": 7140
},
{
"epoch": 0.6381079875055778,
"grad_norm": 0.370889276266098,
"learning_rate": 2e-05,
"loss": 0.6446,
"step": 7150
},
{
"epoch": 0.6390004462293619,
"grad_norm": 0.39864107966423035,
"learning_rate": 2e-05,
"loss": 0.6404,
"step": 7160
},
{
"epoch": 0.6398929049531459,
"grad_norm": 0.384749174118042,
"learning_rate": 2e-05,
"loss": 0.6664,
"step": 7170
},
{
"epoch": 0.64078536367693,
"grad_norm": 0.3626806437969208,
"learning_rate": 2e-05,
"loss": 0.6379,
"step": 7180
},
{
"epoch": 0.6416778224007139,
"grad_norm": 0.3334522545337677,
"learning_rate": 2e-05,
"loss": 0.6525,
"step": 7190
},
{
"epoch": 0.642570281124498,
"grad_norm": 0.34982267022132874,
"learning_rate": 2e-05,
"loss": 0.6154,
"step": 7200
},
{
"epoch": 0.6434627398482821,
"grad_norm": 0.3824388384819031,
"learning_rate": 2e-05,
"loss": 0.6855,
"step": 7210
},
{
"epoch": 0.644355198572066,
"grad_norm": 0.3233283460140228,
"learning_rate": 2e-05,
"loss": 0.6431,
"step": 7220
},
{
"epoch": 0.6452476572958501,
"grad_norm": 0.3989836275577545,
"learning_rate": 2e-05,
"loss": 0.6946,
"step": 7230
},
{
"epoch": 0.6461401160196341,
"grad_norm": 0.43236714601516724,
"learning_rate": 2e-05,
"loss": 0.6621,
"step": 7240
},
{
"epoch": 0.6470325747434181,
"grad_norm": 0.3799687623977661,
"learning_rate": 2e-05,
"loss": 0.6438,
"step": 7250
},
{
"epoch": 0.6479250334672021,
"grad_norm": 0.3717935383319855,
"learning_rate": 2e-05,
"loss": 0.6506,
"step": 7260
},
{
"epoch": 0.6488174921909862,
"grad_norm": 0.3626563847064972,
"learning_rate": 2e-05,
"loss": 0.6632,
"step": 7270
},
{
"epoch": 0.6497099509147702,
"grad_norm": 0.3770589828491211,
"learning_rate": 2e-05,
"loss": 0.6338,
"step": 7280
},
{
"epoch": 0.6506024096385542,
"grad_norm": 0.3650999069213867,
"learning_rate": 2e-05,
"loss": 0.6341,
"step": 7290
},
{
"epoch": 0.6514948683623383,
"grad_norm": 0.3675408661365509,
"learning_rate": 2e-05,
"loss": 0.6534,
"step": 7300
},
{
"epoch": 0.6523873270861222,
"grad_norm": 0.3976017236709595,
"learning_rate": 2e-05,
"loss": 0.6658,
"step": 7310
},
{
"epoch": 0.6532797858099063,
"grad_norm": 0.3467005789279938,
"learning_rate": 2e-05,
"loss": 0.6749,
"step": 7320
},
{
"epoch": 0.6541722445336903,
"grad_norm": 0.3584713935852051,
"learning_rate": 2e-05,
"loss": 0.6779,
"step": 7330
},
{
"epoch": 0.6550647032574743,
"grad_norm": 0.35010483860969543,
"learning_rate": 2e-05,
"loss": 0.6637,
"step": 7340
},
{
"epoch": 0.6559571619812584,
"grad_norm": 0.3644416630268097,
"learning_rate": 2e-05,
"loss": 0.6533,
"step": 7350
},
{
"epoch": 0.6568496207050424,
"grad_norm": 0.3614256978034973,
"learning_rate": 2e-05,
"loss": 0.6381,
"step": 7360
},
{
"epoch": 0.6577420794288265,
"grad_norm": 0.3577764332294464,
"learning_rate": 2e-05,
"loss": 0.6419,
"step": 7370
},
{
"epoch": 0.6586345381526104,
"grad_norm": 0.3804263174533844,
"learning_rate": 2e-05,
"loss": 0.6549,
"step": 7380
},
{
"epoch": 0.6595269968763945,
"grad_norm": 0.37790757417678833,
"learning_rate": 2e-05,
"loss": 0.6007,
"step": 7390
},
{
"epoch": 0.6604194556001785,
"grad_norm": 0.3633478581905365,
"learning_rate": 2e-05,
"loss": 0.6425,
"step": 7400
},
{
"epoch": 0.6613119143239625,
"grad_norm": 0.3643863797187805,
"learning_rate": 2e-05,
"loss": 0.6385,
"step": 7410
},
{
"epoch": 0.6622043730477465,
"grad_norm": 0.3877108693122864,
"learning_rate": 2e-05,
"loss": 0.6226,
"step": 7420
},
{
"epoch": 0.6630968317715306,
"grad_norm": 0.37192121148109436,
"learning_rate": 2e-05,
"loss": 0.6365,
"step": 7430
},
{
"epoch": 0.6639892904953146,
"grad_norm": 0.3512563109397888,
"learning_rate": 2e-05,
"loss": 0.6139,
"step": 7440
},
{
"epoch": 0.6648817492190986,
"grad_norm": 0.3617221713066101,
"learning_rate": 2e-05,
"loss": 0.6312,
"step": 7450
},
{
"epoch": 0.6657742079428827,
"grad_norm": 0.38665178418159485,
"learning_rate": 2e-05,
"loss": 0.6435,
"step": 7460
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.3535751402378082,
"learning_rate": 2e-05,
"loss": 0.6327,
"step": 7470
},
{
"epoch": 0.6675591253904507,
"grad_norm": 0.4813151955604553,
"learning_rate": 2e-05,
"loss": 0.6255,
"step": 7480
},
{
"epoch": 0.6684515841142347,
"grad_norm": 0.35549283027648926,
"learning_rate": 2e-05,
"loss": 0.6451,
"step": 7490
},
{
"epoch": 0.6693440428380187,
"grad_norm": 0.3726365864276886,
"learning_rate": 2e-05,
"loss": 0.6432,
"step": 7500
},
{
"epoch": 0.6702365015618028,
"grad_norm": 0.34098222851753235,
"learning_rate": 2e-05,
"loss": 0.6456,
"step": 7510
},
{
"epoch": 0.6711289602855868,
"grad_norm": 0.5256399512290955,
"learning_rate": 2e-05,
"loss": 0.6473,
"step": 7520
},
{
"epoch": 0.6720214190093708,
"grad_norm": 0.3453484773635864,
"learning_rate": 2e-05,
"loss": 0.6507,
"step": 7530
},
{
"epoch": 0.6729138777331548,
"grad_norm": 0.36325860023498535,
"learning_rate": 2e-05,
"loss": 0.6077,
"step": 7540
},
{
"epoch": 0.6738063364569389,
"grad_norm": 0.41058191657066345,
"learning_rate": 2e-05,
"loss": 0.652,
"step": 7550
},
{
"epoch": 0.6746987951807228,
"grad_norm": 0.3669188320636749,
"learning_rate": 2e-05,
"loss": 0.6404,
"step": 7560
},
{
"epoch": 0.6755912539045069,
"grad_norm": 0.3991318941116333,
"learning_rate": 2e-05,
"loss": 0.6129,
"step": 7570
},
{
"epoch": 0.676483712628291,
"grad_norm": 0.38861116766929626,
"learning_rate": 2e-05,
"loss": 0.637,
"step": 7580
},
{
"epoch": 0.677376171352075,
"grad_norm": 0.3536396622657776,
"learning_rate": 2e-05,
"loss": 0.6345,
"step": 7590
},
{
"epoch": 0.678268630075859,
"grad_norm": 0.3620068430900574,
"learning_rate": 2e-05,
"loss": 0.6199,
"step": 7600
},
{
"epoch": 0.679161088799643,
"grad_norm": 0.342059850692749,
"learning_rate": 2e-05,
"loss": 0.6312,
"step": 7610
},
{
"epoch": 0.6800535475234271,
"grad_norm": 1.9499003887176514,
"learning_rate": 2e-05,
"loss": 0.6676,
"step": 7620
},
{
"epoch": 0.680946006247211,
"grad_norm": 0.38469621539115906,
"learning_rate": 2e-05,
"loss": 0.644,
"step": 7630
},
{
"epoch": 0.6818384649709951,
"grad_norm": 0.33616894483566284,
"learning_rate": 2e-05,
"loss": 0.6413,
"step": 7640
},
{
"epoch": 0.6827309236947792,
"grad_norm": 0.34228286147117615,
"learning_rate": 2e-05,
"loss": 0.6117,
"step": 7650
},
{
"epoch": 0.6836233824185631,
"grad_norm": 0.38736626505851746,
"learning_rate": 2e-05,
"loss": 0.6284,
"step": 7660
},
{
"epoch": 0.6845158411423472,
"grad_norm": 0.32073092460632324,
"learning_rate": 2e-05,
"loss": 0.6175,
"step": 7670
},
{
"epoch": 0.6854082998661312,
"grad_norm": 0.35504892468452454,
"learning_rate": 2e-05,
"loss": 0.6122,
"step": 7680
},
{
"epoch": 0.6863007585899152,
"grad_norm": 0.3640560805797577,
"learning_rate": 2e-05,
"loss": 0.6834,
"step": 7690
},
{
"epoch": 0.6871932173136992,
"grad_norm": 0.33724644780158997,
"learning_rate": 2e-05,
"loss": 0.6312,
"step": 7700
},
{
"epoch": 0.6880856760374833,
"grad_norm": 0.3776415288448334,
"learning_rate": 2e-05,
"loss": 0.6468,
"step": 7710
},
{
"epoch": 0.6889781347612673,
"grad_norm": 0.336077481508255,
"learning_rate": 2e-05,
"loss": 0.6044,
"step": 7720
},
{
"epoch": 0.6898705934850513,
"grad_norm": 0.3467625379562378,
"learning_rate": 2e-05,
"loss": 0.6525,
"step": 7730
},
{
"epoch": 0.6907630522088354,
"grad_norm": 0.3360276222229004,
"learning_rate": 2e-05,
"loss": 0.6613,
"step": 7740
},
{
"epoch": 0.6916555109326193,
"grad_norm": 0.37104010581970215,
"learning_rate": 2e-05,
"loss": 0.6614,
"step": 7750
},
{
"epoch": 0.6925479696564034,
"grad_norm": 0.348202109336853,
"learning_rate": 2e-05,
"loss": 0.6311,
"step": 7760
},
{
"epoch": 0.6934404283801874,
"grad_norm": 0.35366103053092957,
"learning_rate": 2e-05,
"loss": 0.6561,
"step": 7770
},
{
"epoch": 0.6943328871039715,
"grad_norm": 0.33663704991340637,
"learning_rate": 2e-05,
"loss": 0.6139,
"step": 7780
},
{
"epoch": 0.6952253458277554,
"grad_norm": 0.3673596680164337,
"learning_rate": 2e-05,
"loss": 0.6374,
"step": 7790
},
{
"epoch": 0.6961178045515395,
"grad_norm": 0.34689071774482727,
"learning_rate": 2e-05,
"loss": 0.6516,
"step": 7800
},
{
"epoch": 0.6970102632753236,
"grad_norm": 0.3599478602409363,
"learning_rate": 2e-05,
"loss": 0.6185,
"step": 7810
},
{
"epoch": 0.6979027219991075,
"grad_norm": 0.410500168800354,
"learning_rate": 2e-05,
"loss": 0.667,
"step": 7820
},
{
"epoch": 0.6987951807228916,
"grad_norm": 0.36490246653556824,
"learning_rate": 2e-05,
"loss": 0.6204,
"step": 7830
},
{
"epoch": 0.6996876394466756,
"grad_norm": 0.3675346374511719,
"learning_rate": 2e-05,
"loss": 0.6436,
"step": 7840
},
{
"epoch": 0.7005800981704596,
"grad_norm": 0.346149206161499,
"learning_rate": 2e-05,
"loss": 0.6558,
"step": 7850
},
{
"epoch": 0.7014725568942436,
"grad_norm": 0.32325688004493713,
"learning_rate": 2e-05,
"loss": 0.6651,
"step": 7860
},
{
"epoch": 0.7023650156180277,
"grad_norm": 0.3264862298965454,
"learning_rate": 2e-05,
"loss": 0.6103,
"step": 7870
},
{
"epoch": 0.7032574743418117,
"grad_norm": 0.36970004439353943,
"learning_rate": 2e-05,
"loss": 0.6315,
"step": 7880
},
{
"epoch": 0.7041499330655957,
"grad_norm": 0.39608097076416016,
"learning_rate": 2e-05,
"loss": 0.6503,
"step": 7890
},
{
"epoch": 0.7050423917893798,
"grad_norm": 0.35610708594322205,
"learning_rate": 2e-05,
"loss": 0.6334,
"step": 7900
},
{
"epoch": 0.7059348505131637,
"grad_norm": 0.40980538725852966,
"learning_rate": 2e-05,
"loss": 0.6323,
"step": 7910
},
{
"epoch": 0.7068273092369478,
"grad_norm": 0.3704054653644562,
"learning_rate": 2e-05,
"loss": 0.6378,
"step": 7920
},
{
"epoch": 0.7077197679607318,
"grad_norm": 0.3645652234554291,
"learning_rate": 2e-05,
"loss": 0.6313,
"step": 7930
},
{
"epoch": 0.7086122266845158,
"grad_norm": 0.37894171476364136,
"learning_rate": 2e-05,
"loss": 0.6478,
"step": 7940
},
{
"epoch": 0.7095046854082999,
"grad_norm": 0.39392492175102234,
"learning_rate": 2e-05,
"loss": 0.5948,
"step": 7950
},
{
"epoch": 0.7103971441320839,
"grad_norm": 0.39752423763275146,
"learning_rate": 2e-05,
"loss": 0.6386,
"step": 7960
},
{
"epoch": 0.711289602855868,
"grad_norm": 0.3843719959259033,
"learning_rate": 2e-05,
"loss": 0.6458,
"step": 7970
},
{
"epoch": 0.7121820615796519,
"grad_norm": 0.4077357351779938,
"learning_rate": 2e-05,
"loss": 0.6563,
"step": 7980
},
{
"epoch": 0.713074520303436,
"grad_norm": 0.39332854747772217,
"learning_rate": 2e-05,
"loss": 0.6452,
"step": 7990
},
{
"epoch": 0.71396697902722,
"grad_norm": 0.3695387840270996,
"learning_rate": 2e-05,
"loss": 0.6239,
"step": 8000
},
{
"epoch": 0.714859437751004,
"grad_norm": 0.352400004863739,
"learning_rate": 2e-05,
"loss": 0.6512,
"step": 8010
},
{
"epoch": 0.7157518964747881,
"grad_norm": 0.3909405469894409,
"learning_rate": 2e-05,
"loss": 0.6605,
"step": 8020
},
{
"epoch": 0.7166443551985721,
"grad_norm": 0.3437958061695099,
"learning_rate": 2e-05,
"loss": 0.5833,
"step": 8030
},
{
"epoch": 0.7175368139223561,
"grad_norm": 0.37089890241622925,
"learning_rate": 2e-05,
"loss": 0.6348,
"step": 8040
},
{
"epoch": 0.7184292726461401,
"grad_norm": 0.3495701849460602,
"learning_rate": 2e-05,
"loss": 0.6545,
"step": 8050
},
{
"epoch": 0.7193217313699242,
"grad_norm": 0.3881834149360657,
"learning_rate": 2e-05,
"loss": 0.6404,
"step": 8060
},
{
"epoch": 0.7202141900937081,
"grad_norm": 0.3843727707862854,
"learning_rate": 2e-05,
"loss": 0.6768,
"step": 8070
},
{
"epoch": 0.7211066488174922,
"grad_norm": 0.3623158931732178,
"learning_rate": 2e-05,
"loss": 0.6231,
"step": 8080
},
{
"epoch": 0.7219991075412762,
"grad_norm": 0.3612702786922455,
"learning_rate": 2e-05,
"loss": 0.6358,
"step": 8090
},
{
"epoch": 0.7228915662650602,
"grad_norm": 0.3244030177593231,
"learning_rate": 2e-05,
"loss": 0.5904,
"step": 8100
},
{
"epoch": 0.7237840249888443,
"grad_norm": 0.3844699561595917,
"learning_rate": 2e-05,
"loss": 0.6569,
"step": 8110
},
{
"epoch": 0.7246764837126283,
"grad_norm": 0.4768036901950836,
"learning_rate": 2e-05,
"loss": 0.6569,
"step": 8120
},
{
"epoch": 0.7255689424364123,
"grad_norm": 0.44165143370628357,
"learning_rate": 2e-05,
"loss": 0.6634,
"step": 8130
},
{
"epoch": 0.7264614011601963,
"grad_norm": 0.40429961681365967,
"learning_rate": 2e-05,
"loss": 0.6272,
"step": 8140
},
{
"epoch": 0.7273538598839804,
"grad_norm": 0.4306611120700836,
"learning_rate": 2e-05,
"loss": 0.6528,
"step": 8150
},
{
"epoch": 0.7282463186077643,
"grad_norm": 0.3734756112098694,
"learning_rate": 2e-05,
"loss": 0.617,
"step": 8160
},
{
"epoch": 0.7291387773315484,
"grad_norm": 0.40359383821487427,
"learning_rate": 2e-05,
"loss": 0.6483,
"step": 8170
},
{
"epoch": 0.7300312360553325,
"grad_norm": 0.36413565278053284,
"learning_rate": 2e-05,
"loss": 0.6368,
"step": 8180
},
{
"epoch": 0.7309236947791165,
"grad_norm": 0.37381213903427124,
"learning_rate": 2e-05,
"loss": 0.6447,
"step": 8190
},
{
"epoch": 0.7318161535029005,
"grad_norm": 0.33702579140663147,
"learning_rate": 2e-05,
"loss": 0.6189,
"step": 8200
},
{
"epoch": 0.7327086122266845,
"grad_norm": 0.3796248137950897,
"learning_rate": 2e-05,
"loss": 0.6623,
"step": 8210
},
{
"epoch": 0.7336010709504686,
"grad_norm": 0.3743330240249634,
"learning_rate": 2e-05,
"loss": 0.6203,
"step": 8220
},
{
"epoch": 0.7344935296742525,
"grad_norm": 0.3532598614692688,
"learning_rate": 2e-05,
"loss": 0.6315,
"step": 8230
},
{
"epoch": 0.7353859883980366,
"grad_norm": 0.43246474862098694,
"learning_rate": 2e-05,
"loss": 0.6363,
"step": 8240
},
{
"epoch": 0.7362784471218207,
"grad_norm": 0.3675767481327057,
"learning_rate": 2e-05,
"loss": 0.6192,
"step": 8250
},
{
"epoch": 0.7371709058456046,
"grad_norm": 0.4110357165336609,
"learning_rate": 2e-05,
"loss": 0.6376,
"step": 8260
},
{
"epoch": 0.7380633645693887,
"grad_norm": 0.35468590259552,
"learning_rate": 2e-05,
"loss": 0.6101,
"step": 8270
},
{
"epoch": 0.7389558232931727,
"grad_norm": 0.3875008523464203,
"learning_rate": 2e-05,
"loss": 0.6336,
"step": 8280
},
{
"epoch": 0.7398482820169567,
"grad_norm": 0.3486942946910858,
"learning_rate": 2e-05,
"loss": 0.6607,
"step": 8290
},
{
"epoch": 0.7407407407407407,
"grad_norm": 0.33507025241851807,
"learning_rate": 2e-05,
"loss": 0.6265,
"step": 8300
},
{
"epoch": 0.7416331994645248,
"grad_norm": 0.3795264959335327,
"learning_rate": 2e-05,
"loss": 0.6558,
"step": 8310
},
{
"epoch": 0.7425256581883088,
"grad_norm": 0.37040022015571594,
"learning_rate": 2e-05,
"loss": 0.6529,
"step": 8320
},
{
"epoch": 0.7434181169120928,
"grad_norm": 0.3661496043205261,
"learning_rate": 2e-05,
"loss": 0.6349,
"step": 8330
},
{
"epoch": 0.7443105756358769,
"grad_norm": 0.34654492139816284,
"learning_rate": 2e-05,
"loss": 0.6051,
"step": 8340
},
{
"epoch": 0.7452030343596608,
"grad_norm": 1.4594160318374634,
"learning_rate": 2e-05,
"loss": 0.6381,
"step": 8350
},
{
"epoch": 0.7460954930834449,
"grad_norm": 0.3718035817146301,
"learning_rate": 2e-05,
"loss": 0.6145,
"step": 8360
},
{
"epoch": 0.7469879518072289,
"grad_norm": 0.3533289432525635,
"learning_rate": 2e-05,
"loss": 0.6268,
"step": 8370
},
{
"epoch": 0.747880410531013,
"grad_norm": 0.3960415720939636,
"learning_rate": 2e-05,
"loss": 0.614,
"step": 8380
},
{
"epoch": 0.7487728692547969,
"grad_norm": 0.36679884791374207,
"learning_rate": 2e-05,
"loss": 0.6067,
"step": 8390
},
{
"epoch": 0.749665327978581,
"grad_norm": 0.4344695806503296,
"learning_rate": 2e-05,
"loss": 0.6484,
"step": 8400
},
{
"epoch": 0.7505577867023651,
"grad_norm": 0.3955872654914856,
"learning_rate": 2e-05,
"loss": 0.6308,
"step": 8410
},
{
"epoch": 0.751450245426149,
"grad_norm": 0.33813098073005676,
"learning_rate": 2e-05,
"loss": 0.6584,
"step": 8420
},
{
"epoch": 0.7523427041499331,
"grad_norm": 0.3696398437023163,
"learning_rate": 2e-05,
"loss": 0.6337,
"step": 8430
},
{
"epoch": 0.7532351628737171,
"grad_norm": 0.35776013135910034,
"learning_rate": 2e-05,
"loss": 0.6088,
"step": 8440
},
{
"epoch": 0.7541276215975011,
"grad_norm": 0.3539564311504364,
"learning_rate": 2e-05,
"loss": 0.6312,
"step": 8450
},
{
"epoch": 0.7550200803212851,
"grad_norm": 0.39548131823539734,
"learning_rate": 2e-05,
"loss": 0.6088,
"step": 8460
},
{
"epoch": 0.7559125390450692,
"grad_norm": 0.3738992512226105,
"learning_rate": 2e-05,
"loss": 0.6174,
"step": 8470
},
{
"epoch": 0.7568049977688532,
"grad_norm": 0.36003831028938293,
"learning_rate": 2e-05,
"loss": 0.6231,
"step": 8480
},
{
"epoch": 0.7576974564926372,
"grad_norm": 0.407076895236969,
"learning_rate": 2e-05,
"loss": 0.6379,
"step": 8490
},
{
"epoch": 0.7585899152164213,
"grad_norm": 0.38533586263656616,
"learning_rate": 2e-05,
"loss": 0.6527,
"step": 8500
},
{
"epoch": 0.7594823739402052,
"grad_norm": 0.3441564738750458,
"learning_rate": 2e-05,
"loss": 0.5972,
"step": 8510
},
{
"epoch": 0.7603748326639893,
"grad_norm": 0.33874499797821045,
"learning_rate": 2e-05,
"loss": 0.616,
"step": 8520
},
{
"epoch": 0.7612672913877733,
"grad_norm": 0.35387542843818665,
"learning_rate": 2e-05,
"loss": 0.6676,
"step": 8530
},
{
"epoch": 0.7621597501115573,
"grad_norm": 0.3653339445590973,
"learning_rate": 2e-05,
"loss": 0.6312,
"step": 8540
},
{
"epoch": 0.7630522088353414,
"grad_norm": 0.32299816608428955,
"learning_rate": 2e-05,
"loss": 0.6334,
"step": 8550
},
{
"epoch": 0.7639446675591254,
"grad_norm": 0.3464934229850769,
"learning_rate": 2e-05,
"loss": 0.6641,
"step": 8560
},
{
"epoch": 0.7648371262829095,
"grad_norm": 0.37227317690849304,
"learning_rate": 2e-05,
"loss": 0.6194,
"step": 8570
},
{
"epoch": 0.7657295850066934,
"grad_norm": 0.3686710000038147,
"learning_rate": 2e-05,
"loss": 0.6147,
"step": 8580
},
{
"epoch": 0.7666220437304775,
"grad_norm": 0.373597115278244,
"learning_rate": 2e-05,
"loss": 0.5967,
"step": 8590
},
{
"epoch": 0.7675145024542614,
"grad_norm": 0.33288809657096863,
"learning_rate": 2e-05,
"loss": 0.6206,
"step": 8600
},
{
"epoch": 0.7684069611780455,
"grad_norm": 0.3427422344684601,
"learning_rate": 2e-05,
"loss": 0.6251,
"step": 8610
},
{
"epoch": 0.7692994199018296,
"grad_norm": 0.38359037041664124,
"learning_rate": 2e-05,
"loss": 0.6625,
"step": 8620
},
{
"epoch": 0.7701918786256136,
"grad_norm": 0.3536847233772278,
"learning_rate": 2e-05,
"loss": 0.6504,
"step": 8630
},
{
"epoch": 0.7710843373493976,
"grad_norm": 0.3672263026237488,
"learning_rate": 2e-05,
"loss": 0.6449,
"step": 8640
},
{
"epoch": 0.7719767960731816,
"grad_norm": 0.4250284731388092,
"learning_rate": 2e-05,
"loss": 0.6443,
"step": 8650
},
{
"epoch": 0.7728692547969657,
"grad_norm": 0.3516312837600708,
"learning_rate": 2e-05,
"loss": 0.6057,
"step": 8660
},
{
"epoch": 0.7737617135207496,
"grad_norm": 0.3861185610294342,
"learning_rate": 2e-05,
"loss": 0.6603,
"step": 8670
},
{
"epoch": 0.7746541722445337,
"grad_norm": 0.3534548580646515,
"learning_rate": 2e-05,
"loss": 0.6199,
"step": 8680
},
{
"epoch": 0.7755466309683177,
"grad_norm": 0.39039257168769836,
"learning_rate": 2e-05,
"loss": 0.6181,
"step": 8690
},
{
"epoch": 0.7764390896921017,
"grad_norm": 0.3589833378791809,
"learning_rate": 2e-05,
"loss": 0.6193,
"step": 8700
},
{
"epoch": 0.7773315484158858,
"grad_norm": 0.40167734026908875,
"learning_rate": 2e-05,
"loss": 0.6193,
"step": 8710
},
{
"epoch": 0.7782240071396698,
"grad_norm": 0.38521915674209595,
"learning_rate": 2e-05,
"loss": 0.6233,
"step": 8720
},
{
"epoch": 0.7791164658634538,
"grad_norm": 0.3585764169692993,
"learning_rate": 2e-05,
"loss": 0.6298,
"step": 8730
},
{
"epoch": 0.7800089245872378,
"grad_norm": 0.38784846663475037,
"learning_rate": 2e-05,
"loss": 0.6401,
"step": 8740
},
{
"epoch": 0.7809013833110219,
"grad_norm": 0.3346785604953766,
"learning_rate": 2e-05,
"loss": 0.6251,
"step": 8750
},
{
"epoch": 0.7817938420348058,
"grad_norm": 0.36054345965385437,
"learning_rate": 2e-05,
"loss": 0.6421,
"step": 8760
},
{
"epoch": 0.7826863007585899,
"grad_norm": 0.337555468082428,
"learning_rate": 2e-05,
"loss": 0.6215,
"step": 8770
},
{
"epoch": 0.783578759482374,
"grad_norm": 1.3613266944885254,
"learning_rate": 2e-05,
"loss": 0.6109,
"step": 8780
},
{
"epoch": 0.784471218206158,
"grad_norm": 0.34960684180259705,
"learning_rate": 2e-05,
"loss": 0.6175,
"step": 8790
},
{
"epoch": 0.785363676929942,
"grad_norm": 0.35623908042907715,
"learning_rate": 2e-05,
"loss": 0.643,
"step": 8800
},
{
"epoch": 0.786256135653726,
"grad_norm": 0.3679932653903961,
"learning_rate": 2e-05,
"loss": 0.6309,
"step": 8810
},
{
"epoch": 0.7871485943775101,
"grad_norm": 0.33791545033454895,
"learning_rate": 2e-05,
"loss": 0.6538,
"step": 8820
},
{
"epoch": 0.788041053101294,
"grad_norm": 0.3487846851348877,
"learning_rate": 2e-05,
"loss": 0.612,
"step": 8830
},
{
"epoch": 0.7889335118250781,
"grad_norm": 0.35549217462539673,
"learning_rate": 2e-05,
"loss": 0.6301,
"step": 8840
},
{
"epoch": 0.7898259705488622,
"grad_norm": 0.3861076831817627,
"learning_rate": 2e-05,
"loss": 0.6043,
"step": 8850
},
{
"epoch": 0.7907184292726461,
"grad_norm": 0.36030107736587524,
"learning_rate": 2e-05,
"loss": 0.6269,
"step": 8860
},
{
"epoch": 0.7916108879964302,
"grad_norm": 0.4166125953197479,
"learning_rate": 2e-05,
"loss": 0.6732,
"step": 8870
},
{
"epoch": 0.7925033467202142,
"grad_norm": 0.33864039182662964,
"learning_rate": 2e-05,
"loss": 0.6322,
"step": 8880
},
{
"epoch": 0.7933958054439982,
"grad_norm": 0.36620956659317017,
"learning_rate": 2e-05,
"loss": 0.6105,
"step": 8890
},
{
"epoch": 0.7942882641677822,
"grad_norm": 0.3513573706150055,
"learning_rate": 2e-05,
"loss": 0.6453,
"step": 8900
},
{
"epoch": 0.7951807228915663,
"grad_norm": 0.37508857250213623,
"learning_rate": 2e-05,
"loss": 0.6143,
"step": 8910
},
{
"epoch": 0.7960731816153503,
"grad_norm": 0.3583836555480957,
"learning_rate": 2e-05,
"loss": 0.6265,
"step": 8920
},
{
"epoch": 0.7969656403391343,
"grad_norm": 0.3793869614601135,
"learning_rate": 2e-05,
"loss": 0.6182,
"step": 8930
},
{
"epoch": 0.7978580990629184,
"grad_norm": 0.3591775596141815,
"learning_rate": 2e-05,
"loss": 0.6248,
"step": 8940
},
{
"epoch": 0.7987505577867023,
"grad_norm": 0.37659013271331787,
"learning_rate": 2e-05,
"loss": 0.6296,
"step": 8950
},
{
"epoch": 0.7996430165104864,
"grad_norm": 0.33787015080451965,
"learning_rate": 2e-05,
"loss": 0.6183,
"step": 8960
},
{
"epoch": 0.8005354752342704,
"grad_norm": 0.33152836561203003,
"learning_rate": 2e-05,
"loss": 0.6362,
"step": 8970
},
{
"epoch": 0.8014279339580545,
"grad_norm": 0.351147323846817,
"learning_rate": 2e-05,
"loss": 0.6198,
"step": 8980
},
{
"epoch": 0.8023203926818384,
"grad_norm": 0.3685293197631836,
"learning_rate": 2e-05,
"loss": 0.6561,
"step": 8990
},
{
"epoch": 0.8032128514056225,
"grad_norm": 0.3723013699054718,
"learning_rate": 2e-05,
"loss": 0.6189,
"step": 9000
},
{
"epoch": 0.8041053101294066,
"grad_norm": 0.37293747067451477,
"learning_rate": 2e-05,
"loss": 0.6051,
"step": 9010
},
{
"epoch": 0.8049977688531905,
"grad_norm": 0.3714136779308319,
"learning_rate": 2e-05,
"loss": 0.6373,
"step": 9020
},
{
"epoch": 0.8058902275769746,
"grad_norm": 0.36760061979293823,
"learning_rate": 2e-05,
"loss": 0.609,
"step": 9030
},
{
"epoch": 0.8067826863007586,
"grad_norm": 0.4301621615886688,
"learning_rate": 2e-05,
"loss": 0.6073,
"step": 9040
},
{
"epoch": 0.8076751450245426,
"grad_norm": 0.36239850521087646,
"learning_rate": 2e-05,
"loss": 0.644,
"step": 9050
},
{
"epoch": 0.8085676037483266,
"grad_norm": 0.400017648935318,
"learning_rate": 2e-05,
"loss": 0.6458,
"step": 9060
},
{
"epoch": 0.8094600624721107,
"grad_norm": 0.39437153935432434,
"learning_rate": 2e-05,
"loss": 0.6228,
"step": 9070
},
{
"epoch": 0.8103525211958947,
"grad_norm": 0.4264233112335205,
"learning_rate": 2e-05,
"loss": 0.6262,
"step": 9080
},
{
"epoch": 0.8112449799196787,
"grad_norm": 0.37684154510498047,
"learning_rate": 2e-05,
"loss": 0.6107,
"step": 9090
},
{
"epoch": 0.8121374386434628,
"grad_norm": 0.3752806484699249,
"learning_rate": 2e-05,
"loss": 0.6324,
"step": 9100
},
{
"epoch": 0.8130298973672467,
"grad_norm": 0.3934779763221741,
"learning_rate": 2e-05,
"loss": 0.6329,
"step": 9110
},
{
"epoch": 0.8139223560910308,
"grad_norm": 0.36012762784957886,
"learning_rate": 2e-05,
"loss": 0.6219,
"step": 9120
},
{
"epoch": 0.8148148148148148,
"grad_norm": 0.38915708661079407,
"learning_rate": 2e-05,
"loss": 0.6466,
"step": 9130
},
{
"epoch": 0.8157072735385988,
"grad_norm": 0.37535613775253296,
"learning_rate": 2e-05,
"loss": 0.6456,
"step": 9140
},
{
"epoch": 0.8165997322623829,
"grad_norm": 0.3604534864425659,
"learning_rate": 2e-05,
"loss": 0.6365,
"step": 9150
},
{
"epoch": 0.8174921909861669,
"grad_norm": 0.3851489722728729,
"learning_rate": 2e-05,
"loss": 0.6413,
"step": 9160
},
{
"epoch": 0.818384649709951,
"grad_norm": 0.3508491516113281,
"learning_rate": 2e-05,
"loss": 0.6186,
"step": 9170
},
{
"epoch": 0.8192771084337349,
"grad_norm": 0.3768831491470337,
"learning_rate": 2e-05,
"loss": 0.6234,
"step": 9180
},
{
"epoch": 0.820169567157519,
"grad_norm": 0.3987121284008026,
"learning_rate": 2e-05,
"loss": 0.6079,
"step": 9190
},
{
"epoch": 0.821062025881303,
"grad_norm": 0.38579994440078735,
"learning_rate": 2e-05,
"loss": 0.6396,
"step": 9200
},
{
"epoch": 0.821954484605087,
"grad_norm": 0.3479354679584503,
"learning_rate": 2e-05,
"loss": 0.6232,
"step": 9210
},
{
"epoch": 0.8228469433288711,
"grad_norm": 0.36894768476486206,
"learning_rate": 2e-05,
"loss": 0.6387,
"step": 9220
},
{
"epoch": 0.8237394020526551,
"grad_norm": 0.3829409182071686,
"learning_rate": 2e-05,
"loss": 0.595,
"step": 9230
},
{
"epoch": 0.8246318607764391,
"grad_norm": 0.38592830300331116,
"learning_rate": 2e-05,
"loss": 0.6665,
"step": 9240
},
{
"epoch": 0.8255243195002231,
"grad_norm": 0.35907185077667236,
"learning_rate": 2e-05,
"loss": 0.6181,
"step": 9250
},
{
"epoch": 0.8264167782240072,
"grad_norm": 0.3805224299430847,
"learning_rate": 2e-05,
"loss": 0.6446,
"step": 9260
},
{
"epoch": 0.8273092369477911,
"grad_norm": 0.33057451248168945,
"learning_rate": 2e-05,
"loss": 0.6255,
"step": 9270
},
{
"epoch": 0.8282016956715752,
"grad_norm": 0.39051002264022827,
"learning_rate": 2e-05,
"loss": 0.6337,
"step": 9280
},
{
"epoch": 0.8290941543953592,
"grad_norm": 0.3585379719734192,
"learning_rate": 2e-05,
"loss": 0.6384,
"step": 9290
},
{
"epoch": 0.8299866131191432,
"grad_norm": 0.6728903651237488,
"learning_rate": 2e-05,
"loss": 0.6237,
"step": 9300
},
{
"epoch": 0.8308790718429273,
"grad_norm": 0.3884449303150177,
"learning_rate": 2e-05,
"loss": 0.6086,
"step": 9310
},
{
"epoch": 0.8317715305667113,
"grad_norm": 0.35533463954925537,
"learning_rate": 2e-05,
"loss": 0.6082,
"step": 9320
},
{
"epoch": 0.8326639892904953,
"grad_norm": 0.3803737759590149,
"learning_rate": 2e-05,
"loss": 0.61,
"step": 9330
},
{
"epoch": 0.8335564480142793,
"grad_norm": 0.9017601609230042,
"learning_rate": 2e-05,
"loss": 0.6262,
"step": 9340
},
{
"epoch": 0.8344489067380634,
"grad_norm": 0.3875792920589447,
"learning_rate": 2e-05,
"loss": 0.5821,
"step": 9350
},
{
"epoch": 0.8353413654618473,
"grad_norm": 0.38558685779571533,
"learning_rate": 2e-05,
"loss": 0.6382,
"step": 9360
},
{
"epoch": 0.8362338241856314,
"grad_norm": 0.3616545796394348,
"learning_rate": 2e-05,
"loss": 0.6151,
"step": 9370
},
{
"epoch": 0.8371262829094155,
"grad_norm": 0.48823440074920654,
"learning_rate": 2e-05,
"loss": 0.6007,
"step": 9380
},
{
"epoch": 0.8380187416331994,
"grad_norm": 0.40082624554634094,
"learning_rate": 2e-05,
"loss": 0.609,
"step": 9390
},
{
"epoch": 0.8389112003569835,
"grad_norm": 0.39392322301864624,
"learning_rate": 2e-05,
"loss": 0.6515,
"step": 9400
},
{
"epoch": 0.8398036590807675,
"grad_norm": 0.3339507281780243,
"learning_rate": 2e-05,
"loss": 0.6217,
"step": 9410
},
{
"epoch": 0.8406961178045516,
"grad_norm": 0.4271765351295471,
"learning_rate": 2e-05,
"loss": 0.5934,
"step": 9420
},
{
"epoch": 0.8415885765283355,
"grad_norm": 0.5515242218971252,
"learning_rate": 2e-05,
"loss": 0.5644,
"step": 9430
},
{
"epoch": 0.8424810352521196,
"grad_norm": 0.34122082591056824,
"learning_rate": 2e-05,
"loss": 0.6374,
"step": 9440
},
{
"epoch": 0.8433734939759037,
"grad_norm": 0.3861217796802521,
"learning_rate": 2e-05,
"loss": 0.6198,
"step": 9450
},
{
"epoch": 0.8442659526996876,
"grad_norm": 0.3957724869251251,
"learning_rate": 2e-05,
"loss": 0.6214,
"step": 9460
},
{
"epoch": 0.8451584114234717,
"grad_norm": 0.38469135761260986,
"learning_rate": 2e-05,
"loss": 0.6134,
"step": 9470
},
{
"epoch": 0.8460508701472557,
"grad_norm": 0.353278249502182,
"learning_rate": 2e-05,
"loss": 0.6351,
"step": 9480
},
{
"epoch": 0.8469433288710397,
"grad_norm": 0.3535063862800598,
"learning_rate": 2e-05,
"loss": 0.6313,
"step": 9490
},
{
"epoch": 0.8478357875948237,
"grad_norm": 0.33216315507888794,
"learning_rate": 2e-05,
"loss": 0.6295,
"step": 9500
},
{
"epoch": 0.8487282463186078,
"grad_norm": 0.38016945123672485,
"learning_rate": 2e-05,
"loss": 0.6169,
"step": 9510
},
{
"epoch": 0.8496207050423918,
"grad_norm": 0.37464439868927,
"learning_rate": 2e-05,
"loss": 0.6166,
"step": 9520
},
{
"epoch": 0.8505131637661758,
"grad_norm": 0.369200199842453,
"learning_rate": 2e-05,
"loss": 0.6173,
"step": 9530
},
{
"epoch": 0.8514056224899599,
"grad_norm": 0.3673664927482605,
"learning_rate": 2e-05,
"loss": 0.6332,
"step": 9540
},
{
"epoch": 0.8522980812137438,
"grad_norm": 0.3803843855857849,
"learning_rate": 2e-05,
"loss": 0.6089,
"step": 9550
},
{
"epoch": 0.8531905399375279,
"grad_norm": 0.3628324270248413,
"learning_rate": 2e-05,
"loss": 0.6521,
"step": 9560
},
{
"epoch": 0.8540829986613119,
"grad_norm": 0.3493793308734894,
"learning_rate": 2e-05,
"loss": 0.6109,
"step": 9570
},
{
"epoch": 0.854975457385096,
"grad_norm": 0.39917269349098206,
"learning_rate": 2e-05,
"loss": 0.6183,
"step": 9580
},
{
"epoch": 0.8558679161088799,
"grad_norm": 0.38868650794029236,
"learning_rate": 2e-05,
"loss": 0.599,
"step": 9590
},
{
"epoch": 0.856760374832664,
"grad_norm": 0.38541194796562195,
"learning_rate": 2e-05,
"loss": 0.6016,
"step": 9600
},
{
"epoch": 0.8576528335564481,
"grad_norm": 0.43350282311439514,
"learning_rate": 2e-05,
"loss": 0.6351,
"step": 9610
},
{
"epoch": 0.858545292280232,
"grad_norm": 0.4161338210105896,
"learning_rate": 2e-05,
"loss": 0.6154,
"step": 9620
},
{
"epoch": 0.8594377510040161,
"grad_norm": 0.38455066084861755,
"learning_rate": 2e-05,
"loss": 0.609,
"step": 9630
},
{
"epoch": 0.8603302097278,
"grad_norm": 0.3522926867008209,
"learning_rate": 2e-05,
"loss": 0.6191,
"step": 9640
},
{
"epoch": 0.8612226684515841,
"grad_norm": 0.36186689138412476,
"learning_rate": 2e-05,
"loss": 0.5689,
"step": 9650
},
{
"epoch": 0.8621151271753681,
"grad_norm": 0.4799335300922394,
"learning_rate": 2e-05,
"loss": 0.6443,
"step": 9660
},
{
"epoch": 0.8630075858991522,
"grad_norm": 0.34810033440589905,
"learning_rate": 2e-05,
"loss": 0.6174,
"step": 9670
},
{
"epoch": 0.8639000446229362,
"grad_norm": 0.4124077260494232,
"learning_rate": 2e-05,
"loss": 0.618,
"step": 9680
},
{
"epoch": 0.8647925033467202,
"grad_norm": 0.35452476143836975,
"learning_rate": 2e-05,
"loss": 0.6113,
"step": 9690
},
{
"epoch": 0.8656849620705043,
"grad_norm": 0.3950854539871216,
"learning_rate": 2e-05,
"loss": 0.6346,
"step": 9700
},
{
"epoch": 0.8665774207942882,
"grad_norm": 0.3903513252735138,
"learning_rate": 2e-05,
"loss": 0.6329,
"step": 9710
},
{
"epoch": 0.8674698795180723,
"grad_norm": 0.3830397129058838,
"learning_rate": 2e-05,
"loss": 0.6266,
"step": 9720
},
{
"epoch": 0.8683623382418563,
"grad_norm": 0.3720979690551758,
"learning_rate": 2e-05,
"loss": 0.6339,
"step": 9730
},
{
"epoch": 0.8692547969656403,
"grad_norm": 0.38329318165779114,
"learning_rate": 2e-05,
"loss": 0.6171,
"step": 9740
},
{
"epoch": 0.8701472556894244,
"grad_norm": 0.35977301001548767,
"learning_rate": 2e-05,
"loss": 0.5923,
"step": 9750
},
{
"epoch": 0.8710397144132084,
"grad_norm": 0.3920813202857971,
"learning_rate": 2e-05,
"loss": 0.6018,
"step": 9760
},
{
"epoch": 0.8719321731369924,
"grad_norm": 0.35237017273902893,
"learning_rate": 2e-05,
"loss": 0.632,
"step": 9770
},
{
"epoch": 0.8728246318607764,
"grad_norm": 0.3926961123943329,
"learning_rate": 2e-05,
"loss": 0.6047,
"step": 9780
},
{
"epoch": 0.8737170905845605,
"grad_norm": 0.33182623982429504,
"learning_rate": 2e-05,
"loss": 0.5797,
"step": 9790
},
{
"epoch": 0.8746095493083444,
"grad_norm": 0.3521885275840759,
"learning_rate": 2e-05,
"loss": 0.615,
"step": 9800
},
{
"epoch": 0.8755020080321285,
"grad_norm": 0.37236177921295166,
"learning_rate": 2e-05,
"loss": 0.6352,
"step": 9810
},
{
"epoch": 0.8763944667559126,
"grad_norm": 0.3450852632522583,
"learning_rate": 2e-05,
"loss": 0.592,
"step": 9820
},
{
"epoch": 0.8772869254796966,
"grad_norm": 0.4200640320777893,
"learning_rate": 2e-05,
"loss": 0.6056,
"step": 9830
},
{
"epoch": 0.8781793842034806,
"grad_norm": 0.35741138458251953,
"learning_rate": 2e-05,
"loss": 0.6024,
"step": 9840
},
{
"epoch": 0.8790718429272646,
"grad_norm": 0.3525106906890869,
"learning_rate": 2e-05,
"loss": 0.5964,
"step": 9850
},
{
"epoch": 0.8799643016510487,
"grad_norm": 0.3489421010017395,
"learning_rate": 2e-05,
"loss": 0.634,
"step": 9860
},
{
"epoch": 0.8808567603748326,
"grad_norm": 0.3646111786365509,
"learning_rate": 2e-05,
"loss": 0.5924,
"step": 9870
},
{
"epoch": 0.8817492190986167,
"grad_norm": 0.37145110964775085,
"learning_rate": 2e-05,
"loss": 0.6189,
"step": 9880
},
{
"epoch": 0.8826416778224007,
"grad_norm": 0.3439500033855438,
"learning_rate": 2e-05,
"loss": 0.6253,
"step": 9890
},
{
"epoch": 0.8835341365461847,
"grad_norm": 0.3616589605808258,
"learning_rate": 2e-05,
"loss": 0.592,
"step": 9900
},
{
"epoch": 0.8844265952699688,
"grad_norm": 0.37503954768180847,
"learning_rate": 2e-05,
"loss": 0.6174,
"step": 9910
},
{
"epoch": 0.8853190539937528,
"grad_norm": 0.34467074275016785,
"learning_rate": 2e-05,
"loss": 0.6421,
"step": 9920
},
{
"epoch": 0.8862115127175368,
"grad_norm": 0.33880603313446045,
"learning_rate": 2e-05,
"loss": 0.5966,
"step": 9930
},
{
"epoch": 0.8871039714413208,
"grad_norm": 0.37716859579086304,
"learning_rate": 2e-05,
"loss": 0.6199,
"step": 9940
},
{
"epoch": 0.8879964301651049,
"grad_norm": 0.40070945024490356,
"learning_rate": 2e-05,
"loss": 0.6379,
"step": 9950
},
{
"epoch": 0.8888888888888888,
"grad_norm": 0.37700626254081726,
"learning_rate": 2e-05,
"loss": 0.615,
"step": 9960
},
{
"epoch": 0.8897813476126729,
"grad_norm": 0.3722045421600342,
"learning_rate": 2e-05,
"loss": 0.6153,
"step": 9970
},
{
"epoch": 0.890673806336457,
"grad_norm": 0.3589438498020172,
"learning_rate": 2e-05,
"loss": 0.6097,
"step": 9980
},
{
"epoch": 0.891566265060241,
"grad_norm": 0.3535745143890381,
"learning_rate": 2e-05,
"loss": 0.5494,
"step": 9990
},
{
"epoch": 0.892458723784025,
"grad_norm": 0.3482585549354553,
"learning_rate": 2e-05,
"loss": 0.6312,
"step": 10000
},
{
"epoch": 0.893351182507809,
"grad_norm": 0.3461279571056366,
"learning_rate": 2e-05,
"loss": 0.5913,
"step": 10010
},
{
"epoch": 0.8942436412315931,
"grad_norm": 0.5033317804336548,
"learning_rate": 2e-05,
"loss": 0.6109,
"step": 10020
},
{
"epoch": 0.895136099955377,
"grad_norm": 0.34654584527015686,
"learning_rate": 2e-05,
"loss": 0.6448,
"step": 10030
},
{
"epoch": 0.8960285586791611,
"grad_norm": 0.3693196773529053,
"learning_rate": 2e-05,
"loss": 0.6239,
"step": 10040
},
{
"epoch": 0.8969210174029452,
"grad_norm": 0.3849048912525177,
"learning_rate": 2e-05,
"loss": 0.6516,
"step": 10050
},
{
"epoch": 0.8978134761267291,
"grad_norm": 0.3809046745300293,
"learning_rate": 2e-05,
"loss": 0.6035,
"step": 10060
},
{
"epoch": 0.8987059348505132,
"grad_norm": 0.34524375200271606,
"learning_rate": 2e-05,
"loss": 0.6016,
"step": 10070
},
{
"epoch": 0.8995983935742972,
"grad_norm": 0.35845518112182617,
"learning_rate": 2e-05,
"loss": 0.6049,
"step": 10080
},
{
"epoch": 0.9004908522980812,
"grad_norm": 0.3985752463340759,
"learning_rate": 2e-05,
"loss": 0.6137,
"step": 10090
},
{
"epoch": 0.9013833110218652,
"grad_norm": 0.3505628705024719,
"learning_rate": 2e-05,
"loss": 0.5879,
"step": 10100
},
{
"epoch": 0.9022757697456493,
"grad_norm": 0.3667459189891815,
"learning_rate": 2e-05,
"loss": 0.6318,
"step": 10110
},
{
"epoch": 0.9031682284694333,
"grad_norm": 0.3778235614299774,
"learning_rate": 2e-05,
"loss": 0.6016,
"step": 10120
},
{
"epoch": 0.9040606871932173,
"grad_norm": 0.4845481812953949,
"learning_rate": 2e-05,
"loss": 0.6007,
"step": 10130
},
{
"epoch": 0.9049531459170014,
"grad_norm": 0.3549792170524597,
"learning_rate": 2e-05,
"loss": 0.6011,
"step": 10140
},
{
"epoch": 0.9058456046407853,
"grad_norm": 0.36095544695854187,
"learning_rate": 2e-05,
"loss": 0.602,
"step": 10150
},
{
"epoch": 0.9067380633645694,
"grad_norm": 0.35801881551742554,
"learning_rate": 2e-05,
"loss": 0.5978,
"step": 10160
},
{
"epoch": 0.9076305220883534,
"grad_norm": 0.36918237805366516,
"learning_rate": 2e-05,
"loss": 0.6304,
"step": 10170
},
{
"epoch": 0.9085229808121374,
"grad_norm": 0.35014456510543823,
"learning_rate": 1.999957358086795e-05,
"loss": 0.6012,
"step": 10180
},
{
"epoch": 0.9094154395359214,
"grad_norm": 0.35047101974487305,
"learning_rate": 1.9991993813020483e-05,
"loss": 0.6006,
"step": 10190
},
{
"epoch": 0.9103078982597055,
"grad_norm": 0.38929077982902527,
"learning_rate": 1.9974946373028628e-05,
"loss": 0.5732,
"step": 10200
},
{
"epoch": 0.9112003569834896,
"grad_norm": 0.36206427216529846,
"learning_rate": 1.994844749501764e-05,
"loss": 0.608,
"step": 10210
},
{
"epoch": 0.9120928157072735,
"grad_norm": 0.3739660382270813,
"learning_rate": 1.9912522413632988e-05,
"loss": 0.6278,
"step": 10220
},
{
"epoch": 0.9129852744310576,
"grad_norm": 0.42990395426750183,
"learning_rate": 1.9867205340009656e-05,
"loss": 0.6449,
"step": 10230
},
{
"epoch": 0.9138777331548416,
"grad_norm": 0.4061349332332611,
"learning_rate": 1.9812539429193164e-05,
"loss": 0.6423,
"step": 10240
},
{
"epoch": 0.9147701918786256,
"grad_norm": 0.3416290283203125,
"learning_rate": 1.9748576739043423e-05,
"loss": 0.5971,
"step": 10250
},
{
"epoch": 0.9156626506024096,
"grad_norm": 0.36104583740234375,
"learning_rate": 1.967537818066047e-05,
"loss": 0.6077,
"step": 10260
},
{
"epoch": 0.9165551093261937,
"grad_norm": 0.3769310712814331,
"learning_rate": 1.959301346037941e-05,
"loss": 0.5671,
"step": 10270
},
{
"epoch": 0.9174475680499777,
"grad_norm": 0.3740551173686981,
"learning_rate": 1.9501561013389646e-05,
"loss": 0.622,
"step": 10280
},
{
"epoch": 0.9183400267737617,
"grad_norm": 0.4391929805278778,
"learning_rate": 1.9401107929041795e-05,
"loss": 0.6062,
"step": 10290
},
{
"epoch": 0.9192324854975458,
"grad_norm": 0.3468918800354004,
"learning_rate": 1.9291749867913225e-05,
"loss": 0.6297,
"step": 10300
},
{
"epoch": 0.9201249442213297,
"grad_norm": 0.3624332845211029,
"learning_rate": 1.91735909707114e-05,
"loss": 0.6029,
"step": 10310
},
{
"epoch": 0.9210174029451138,
"grad_norm": 0.36448609828948975,
"learning_rate": 1.9046743759101545e-05,
"loss": 0.5969,
"step": 10320
},
{
"epoch": 0.9219098616688978,
"grad_norm": 0.3732825219631195,
"learning_rate": 1.8911329028553324e-05,
"loss": 0.6233,
"step": 10330
},
{
"epoch": 0.9228023203926818,
"grad_norm": 0.36012694239616394,
"learning_rate": 1.876747573330835e-05,
"loss": 0.5995,
"step": 10340
},
{
"epoch": 0.9236947791164659,
"grad_norm": 0.36623698472976685,
"learning_rate": 1.8615320863578244e-05,
"loss": 0.6442,
"step": 10350
},
{
"epoch": 0.9245872378402499,
"grad_norm": 0.4014148712158203,
"learning_rate": 1.8455009315090036e-05,
"loss": 0.611,
"step": 10360
},
{
"epoch": 0.925479696564034,
"grad_norm": 0.3628361225128174,
"learning_rate": 1.8286693751103294e-05,
"loss": 0.6104,
"step": 10370
},
{
"epoch": 0.9263721552878179,
"grad_norm": 0.34941187500953674,
"learning_rate": 1.811053445703024e-05,
"loss": 0.6138,
"step": 10380
},
{
"epoch": 0.927264614011602,
"grad_norm": 0.4069834053516388,
"learning_rate": 1.7926699187797375e-05,
"loss": 0.6355,
"step": 10390
},
{
"epoch": 0.928157072735386,
"grad_norm": 0.35099998116493225,
"learning_rate": 1.7735363008093995e-05,
"loss": 0.6261,
"step": 10400
},
{
"epoch": 0.92904953145917,
"grad_norm": 0.3818628191947937,
"learning_rate": 1.7536708125659577e-05,
"loss": 0.6076,
"step": 10410
},
{
"epoch": 0.9299419901829541,
"grad_norm": 0.40360206365585327,
"learning_rate": 1.733092371776905e-05,
"loss": 0.5788,
"step": 10420
},
{
"epoch": 0.930834448906738,
"grad_norm": 0.40806108713150024,
"learning_rate": 1.7118205751080915e-05,
"loss": 0.6244,
"step": 10430
},
{
"epoch": 0.9317269076305221,
"grad_norm": 0.37131550908088684,
"learning_rate": 1.6898756795019935e-05,
"loss": 0.5685,
"step": 10440
},
{
"epoch": 0.9326193663543061,
"grad_norm": 0.35844001173973083,
"learning_rate": 1.667278582887211e-05,
"loss": 0.594,
"step": 10450
},
{
"epoch": 0.9335118250780902,
"grad_norm": 0.3987446427345276,
"learning_rate": 1.6440508042775545e-05,
"loss": 0.6338,
"step": 10460
},
{
"epoch": 0.9344042838018741,
"grad_norm": 0.3822847306728363,
"learning_rate": 1.6202144632796796e-05,
"loss": 0.5733,
"step": 10470
},
{
"epoch": 0.9352967425256582,
"grad_norm": 0.3593252897262573,
"learning_rate": 1.595792259028783e-05,
"loss": 0.5836,
"step": 10480
},
{
"epoch": 0.9361892012494422,
"grad_norm": 0.3746921122074127,
"learning_rate": 1.570807448572419e-05,
"loss": 0.5704,
"step": 10490
},
{
"epoch": 0.9370816599732262,
"grad_norm": 0.36186739802360535,
"learning_rate": 1.5452838247230197e-05,
"loss": 0.6347,
"step": 10500
},
{
"epoch": 0.9379741186970103,
"grad_norm": 0.35661041736602783,
"learning_rate": 1.5192456934002106e-05,
"loss": 0.5975,
"step": 10510
},
{
"epoch": 0.9388665774207943,
"grad_norm": 0.5992140769958496,
"learning_rate": 1.492717850484502e-05,
"loss": 0.6058,
"step": 10520
},
{
"epoch": 0.9397590361445783,
"grad_norm": 0.3280079662799835,
"learning_rate": 1.4657255582043904e-05,
"loss": 0.5908,
"step": 10530
},
{
"epoch": 0.9406514948683623,
"grad_norm": 0.36672094464302063,
"learning_rate": 1.4382945210793663e-05,
"loss": 0.6141,
"step": 10540
},
{
"epoch": 0.9415439535921464,
"grad_norm": 0.3416384160518646,
"learning_rate": 1.4104508614417267e-05,
"loss": 0.6,
"step": 10550
},
{
"epoch": 0.9424364123159303,
"grad_norm": 0.3936033248901367,
"learning_rate": 1.382221094560512e-05,
"loss": 0.6191,
"step": 10560
},
{
"epoch": 0.9433288710397144,
"grad_norm": 0.3451262414455414,
"learning_rate": 1.3536321033912506e-05,
"loss": 0.5764,
"step": 10570
},
{
"epoch": 0.9442213297634985,
"grad_norm": 0.36703693866729736,
"learning_rate": 1.3247111129755609e-05,
"loss": 0.6179,
"step": 10580
},
{
"epoch": 0.9451137884872824,
"grad_norm": 0.3471667170524597,
"learning_rate": 1.2954856645149868e-05,
"loss": 0.6136,
"step": 10590
},
{
"epoch": 0.9460062472110665,
"grad_norm": 0.3940487504005432,
"learning_rate": 1.2659835891437553e-05,
"loss": 0.5901,
"step": 10600
},
{
"epoch": 0.9468987059348505,
"grad_norm": 0.4237748980522156,
"learning_rate": 1.236232981425436e-05,
"loss": 0.5834,
"step": 10610
},
{
"epoch": 0.9477911646586346,
"grad_norm": 0.37984493374824524,
"learning_rate": 1.2062621725987402e-05,
"loss": 0.5893,
"step": 10620
},
{
"epoch": 0.9486836233824185,
"grad_norm": 0.3261927366256714,
"learning_rate": 1.1760997035979318e-05,
"loss": 0.5871,
"step": 10630
},
{
"epoch": 0.9495760821062026,
"grad_norm": 0.33754071593284607,
"learning_rate": 1.1457742978735514e-05,
"loss": 0.6045,
"step": 10640
},
{
"epoch": 0.9504685408299867,
"grad_norm": 0.3280695378780365,
"learning_rate": 1.1153148340393298e-05,
"loss": 0.5752,
"step": 10650
},
{
"epoch": 0.9513609995537706,
"grad_norm": 0.3338243365287781,
"learning_rate": 1.0847503183713424e-05,
"loss": 0.6055,
"step": 10660
},
{
"epoch": 0.9522534582775547,
"grad_norm": 0.4393932819366455,
"learning_rate": 1.0541098571855896e-05,
"loss": 0.5895,
"step": 10670
},
{
"epoch": 0.9531459170013387,
"grad_norm": 0.39193621277809143,
"learning_rate": 1.0234226291203123e-05,
"loss": 0.5994,
"step": 10680
},
{
"epoch": 0.9540383757251227,
"grad_norm": 0.36276116967201233,
"learning_rate": 9.927178573494333e-06,
"loss": 0.6056,
"step": 10690
},
{
"epoch": 0.9549308344489067,
"grad_norm": 0.33743754029273987,
"learning_rate": 9.620247817535902e-06,
"loss": 0.6146,
"step": 10700
},
{
"epoch": 0.9558232931726908,
"grad_norm": 0.3383070230484009,
"learning_rate": 9.313726310752581e-06,
"loss": 0.5862,
"step": 10710
},
{
"epoch": 0.9567157518964748,
"grad_norm": 0.35390374064445496,
"learning_rate": 9.00790595084477e-06,
"loss": 0.5832,
"step": 10720
},
{
"epoch": 0.9576082106202588,
"grad_norm": 0.3209785223007202,
"learning_rate": 8.703077967816944e-06,
"loss": 0.5929,
"step": 10730
},
{
"epoch": 0.9585006693440429,
"grad_norm": 0.38426336646080017,
"learning_rate": 8.39953264664192e-06,
"loss": 0.5986,
"step": 10740
},
{
"epoch": 0.9593931280678268,
"grad_norm": 0.3510819971561432,
"learning_rate": 8.097559050825058e-06,
"loss": 0.5958,
"step": 10750
},
{
"epoch": 0.9602855867916109,
"grad_norm": 0.3880379796028137,
"learning_rate": 7.79744474713166e-06,
"loss": 0.5683,
"step": 10760
},
{
"epoch": 0.9611780455153949,
"grad_norm": 0.35356783866882324,
"learning_rate": 7.499475531739696e-06,
"loss": 0.6009,
"step": 10770
},
{
"epoch": 0.962070504239179,
"grad_norm": 0.33149874210357666,
"learning_rate": 7.203935158078662e-06,
"loss": 0.5768,
"step": 10780
},
{
"epoch": 0.9629629629629629,
"grad_norm": 0.4101981818675995,
"learning_rate": 6.911105066613709e-06,
"loss": 0.6079,
"step": 10790
},
{
"epoch": 0.963855421686747,
"grad_norm": 0.37781646847724915,
"learning_rate": 6.621264116832394e-06,
"loss": 0.5778,
"step": 10800
},
{
"epoch": 0.9647478804105311,
"grad_norm": 0.3336600661277771,
"learning_rate": 6.334688321689274e-06,
"loss": 0.5945,
"step": 10810
},
{
"epoch": 0.965640339134315,
"grad_norm": 0.3808899521827698,
"learning_rate": 6.051650584761237e-06,
"loss": 0.6149,
"step": 10820
},
{
"epoch": 0.9665327978580991,
"grad_norm": 0.3518933057785034,
"learning_rate": 5.772420440363841e-06,
"loss": 0.5681,
"step": 10830
},
{
"epoch": 0.967425256581883,
"grad_norm": 0.32728177309036255,
"learning_rate": 5.497263796876207e-06,
"loss": 0.593,
"step": 10840
},
{
"epoch": 0.9683177153056671,
"grad_norm": 0.36615872383117676,
"learning_rate": 5.226442683518813e-06,
"loss": 0.589,
"step": 10850
},
{
"epoch": 0.9692101740294511,
"grad_norm": 0.3780212998390198,
"learning_rate": 4.960215000825432e-06,
"loss": 0.581,
"step": 10860
},
{
"epoch": 0.9701026327532352,
"grad_norm": 0.3941071033477783,
"learning_rate": 4.698834275046711e-06,
"loss": 0.5705,
"step": 10870
},
{
"epoch": 0.9709950914770192,
"grad_norm": 0.3820596933364868,
"learning_rate": 4.442549416719423e-06,
"loss": 0.6023,
"step": 10880
},
{
"epoch": 0.9718875502008032,
"grad_norm": 0.40901729464530945,
"learning_rate": 4.1916044836311565e-06,
"loss": 0.5978,
"step": 10890
},
{
"epoch": 0.9727800089245873,
"grad_norm": 0.39374688267707825,
"learning_rate": 3.94623844840626e-06,
"loss": 0.5883,
"step": 10900
},
{
"epoch": 0.9736724676483712,
"grad_norm": 0.36094120144844055,
"learning_rate": 3.7066849709343467e-06,
"loss": 0.612,
"step": 10910
},
{
"epoch": 0.9745649263721553,
"grad_norm": 0.36163845658302307,
"learning_rate": 3.473172175858059e-06,
"loss": 0.5961,
"step": 10920
},
{
"epoch": 0.9754573850959393,
"grad_norm": 0.36990347504615784,
"learning_rate": 3.2459224353320046e-06,
"loss": 0.6076,
"step": 10930
},
{
"epoch": 0.9763498438197233,
"grad_norm": 0.3423275351524353,
"learning_rate": 3.025152157259735e-06,
"loss": 0.6078,
"step": 10940
},
{
"epoch": 0.9772423025435074,
"grad_norm": 0.3716829717159271,
"learning_rate": 2.811071579210425e-06,
"loss": 0.573,
"step": 10950
},
{
"epoch": 0.9781347612672914,
"grad_norm": 0.3452274799346924,
"learning_rate": 2.603884568211513e-06,
"loss": 0.5495,
"step": 10960
},
{
"epoch": 0.9790272199910754,
"grad_norm": 0.36534741520881653,
"learning_rate": 2.4037884266079434e-06,
"loss": 0.5912,
"step": 10970
},
{
"epoch": 0.9799196787148594,
"grad_norm": 0.3491140902042389,
"learning_rate": 2.2109737041728955e-06,
"loss": 0.5734,
"step": 10980
},
{
"epoch": 0.9808121374386435,
"grad_norm": 0.5794815421104431,
"learning_rate": 2.0256240166489454e-06,
"loss": 0.5741,
"step": 10990
},
{
"epoch": 0.9817045961624274,
"grad_norm": 0.3869876563549042,
"learning_rate": 1.847915870892413e-06,
"loss": 0.587,
"step": 11000
},
{
"epoch": 0.9825970548862115,
"grad_norm": 0.38850685954093933,
"learning_rate": 1.6780184967874715e-06,
"loss": 0.5575,
"step": 11010
},
{
"epoch": 0.9834895136099956,
"grad_norm": 0.3412823975086212,
"learning_rate": 1.5160936860900294e-06,
"loss": 0.5955,
"step": 11020
},
{
"epoch": 0.9843819723337796,
"grad_norm": 0.3528998792171478,
"learning_rate": 1.3622956383548762e-06,
"loss": 0.6284,
"step": 11030
},
{
"epoch": 0.9852744310575636,
"grad_norm": 0.3793332874774933,
"learning_rate": 1.216770814092834e-06,
"loss": 0.6048,
"step": 11040
},
{
"epoch": 0.9861668897813476,
"grad_norm": 0.3675083816051483,
"learning_rate": 1.0796577952977013e-06,
"loss": 0.5924,
"step": 11050
},
{
"epoch": 0.9870593485051317,
"grad_norm": 0.3536325991153717,
"learning_rate": 9.510871534758705e-07,
"loss": 0.5972,
"step": 11060
},
{
"epoch": 0.9879518072289156,
"grad_norm": 0.3966204524040222,
"learning_rate": 8.311813253042334e-07,
"loss": 0.6427,
"step": 11070
},
{
"epoch": 0.9888442659526997,
"grad_norm": 0.7368773221969604,
"learning_rate": 7.200544960348308e-07,
"loss": 0.6186,
"step": 11080
},
{
"epoch": 0.9897367246764837,
"grad_norm": 0.3751795291900635,
"learning_rate": 6.178124907572545e-07,
"loss": 0.5679,
"step": 11090
},
{
"epoch": 0.9906291834002677,
"grad_norm": 0.4560701847076416,
"learning_rate": 5.245526736223528e-07,
"loss": 0.5836,
"step": 11100
},
{
"epoch": 0.9915216421240518,
"grad_norm": 0.3626096248626709,
"learning_rate": 4.403638551232205e-07,
"loss": 0.6028,
"step": 11110
},
{
"epoch": 0.9924141008478358,
"grad_norm": 0.32997241616249084,
"learning_rate": 3.6532620752175616e-07,
"loss": 0.5988,
"step": 11120
},
{
"epoch": 0.9933065595716198,
"grad_norm": 0.37923938035964966,
"learning_rate": 2.9951118850133247e-07,
"loss": 0.5888,
"step": 11130
},
{
"epoch": 0.9941990182954038,
"grad_norm": 0.33107107877731323,
"learning_rate": 2.429814731182774e-07,
"loss": 0.5895,
"step": 11140
},
{
"epoch": 0.9950914770191879,
"grad_norm": 0.3522332012653351,
"learning_rate": 1.957908941169813e-07,
"loss": 0.5822,
"step": 11150
},
{
"epoch": 0.9959839357429718,
"grad_norm": 0.333924800157547,
"learning_rate": 1.5798439066545254e-07,
"loss": 0.6043,
"step": 11160
},
{
"epoch": 0.9968763944667559,
"grad_norm": 0.3580850064754486,
"learning_rate": 1.2959796556014471e-07,
"loss": 0.5939,
"step": 11170
},
{
"epoch": 0.99776885319054,
"grad_norm": 0.3551585078239441,
"learning_rate": 1.1065865094081884e-07,
"loss": 0.5816,
"step": 11180
},
{
"epoch": 0.998661311914324,
"grad_norm": 0.38049548864364624,
"learning_rate": 1.011844825480734e-07,
"loss": 0.5576,
"step": 11190
},
{
"epoch": 0.9990182954038376,
"step": 11194,
"total_flos": 4.547514943786923e+19,
"train_loss": 0.0032895751482507085,
"train_runtime": 620.1021,
"train_samples_per_second": 216.622,
"train_steps_per_second": 18.052
}
],
"logging_steps": 10,
"max_steps": 11194,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 159,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.547514943786923e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}