rqadri's picture
Add files using upload-large-folder tool
d9e781c verified
Raw History Blame Contribute Delete
180 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9369716246756508,
"eval_steps": 500,
"global_step": 11194,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008370302167908262,
"grad_norm": 5.156661510467529,
"learning_rate": 1.1061797752808989e-06,
"loss": 1.5667,
"step": 10
},
{
"epoch": 0.0016740604335816524,
"grad_norm": 2.557840347290039,
"learning_rate": 2.2241573033707866e-06,
"loss": 1.3469,
"step": 20
},
{
"epoch": 0.0025110906503724786,
"grad_norm": 1.6066818237304688,
"learning_rate": 3.342134831460675e-06,
"loss": 1.2057,
"step": 30
},
{
"epoch": 0.0033481208671633047,
"grad_norm": 1.1234897375106812,
"learning_rate": 4.4601123595505624e-06,
"loss": 1.0592,
"step": 40
},
{
"epoch": 0.004185151083954131,
"grad_norm": 1.0128376483917236,
"learning_rate": 5.5780898876404495e-06,
"loss": 0.9068,
"step": 50
},
{
"epoch": 0.005022181300744957,
"grad_norm": 0.7160766124725342,
"learning_rate": 6.6960674157303374e-06,
"loss": 0.8015,
"step": 60
},
{
"epoch": 0.005859211517535783,
"grad_norm": 0.47716090083122253,
"learning_rate": 7.814044943820226e-06,
"loss": 0.8152,
"step": 70
},
{
"epoch": 0.006696241734326609,
"grad_norm": 0.5273013114929199,
"learning_rate": 8.932022471910112e-06,
"loss": 0.7991,
"step": 80
},
{
"epoch": 0.007533271951117435,
"grad_norm": 0.4626390039920807,
"learning_rate": 1.005e-05,
"loss": 0.7387,
"step": 90
},
{
"epoch": 0.008370302167908262,
"grad_norm": 0.5121504664421082,
"learning_rate": 1.1167977528089888e-05,
"loss": 0.7605,
"step": 100
},
{
"epoch": 0.009207332384699087,
"grad_norm": 0.4082605540752411,
"learning_rate": 1.2285955056179776e-05,
"loss": 0.7623,
"step": 110
},
{
"epoch": 0.010044362601489915,
"grad_norm": 0.5059930682182312,
"learning_rate": 1.3403932584269664e-05,
"loss": 0.764,
"step": 120
},
{
"epoch": 0.01088139281828074,
"grad_norm": 0.751139223575592,
"learning_rate": 1.4521910112359552e-05,
"loss": 0.7645,
"step": 130
},
{
"epoch": 0.011718423035071566,
"grad_norm": 0.492674320936203,
"learning_rate": 1.563988764044944e-05,
"loss": 0.781,
"step": 140
},
{
"epoch": 0.012555453251862391,
"grad_norm": 0.566781222820282,
"learning_rate": 1.6757865168539328e-05,
"loss": 0.7548,
"step": 150
},
{
"epoch": 0.013392483468653219,
"grad_norm": 0.5136772990226746,
"learning_rate": 1.7875842696629214e-05,
"loss": 0.7799,
"step": 160
},
{
"epoch": 0.014229513685444044,
"grad_norm": 0.40454524755477905,
"learning_rate": 1.89938202247191e-05,
"loss": 0.7748,
"step": 170
},
{
"epoch": 0.01506654390223487,
"grad_norm": 0.4504382014274597,
"learning_rate": 2e-05,
"loss": 0.7757,
"step": 180
},
{
"epoch": 0.015903574119025696,
"grad_norm": 0.5842396020889282,
"learning_rate": 2e-05,
"loss": 0.7491,
"step": 190
},
{
"epoch": 0.016740604335816523,
"grad_norm": 0.42499402165412903,
"learning_rate": 2e-05,
"loss": 0.7533,
"step": 200
},
{
"epoch": 0.01757763455260735,
"grad_norm": 0.4922196567058563,
"learning_rate": 2e-05,
"loss": 0.7639,
"step": 210
},
{
"epoch": 0.018414664769398174,
"grad_norm": 0.4512643814086914,
"learning_rate": 2e-05,
"loss": 0.7663,
"step": 220
},
{
"epoch": 0.019251694986189002,
"grad_norm": 0.4370189607143402,
"learning_rate": 2e-05,
"loss": 0.765,
"step": 230
},
{
"epoch": 0.02008872520297983,
"grad_norm": 0.41970548033714294,
"learning_rate": 2e-05,
"loss": 0.745,
"step": 240
},
{
"epoch": 0.020925755419770653,
"grad_norm": 0.45108288526535034,
"learning_rate": 2e-05,
"loss": 0.7364,
"step": 250
},
{
"epoch": 0.02176278563656148,
"grad_norm": 0.42641422152519226,
"learning_rate": 2e-05,
"loss": 0.732,
"step": 260
},
{
"epoch": 0.022599815853352308,
"grad_norm": 0.3930014371871948,
"learning_rate": 2e-05,
"loss": 0.7634,
"step": 270
},
{
"epoch": 0.02343684607014313,
"grad_norm": 0.43919554352760315,
"learning_rate": 2e-05,
"loss": 0.7621,
"step": 280
},
{
"epoch": 0.02427387628693396,
"grad_norm": 0.4371900260448456,
"learning_rate": 2e-05,
"loss": 0.7379,
"step": 290
},
{
"epoch": 0.025110906503724783,
"grad_norm": 0.4431065618991852,
"learning_rate": 2e-05,
"loss": 0.7306,
"step": 300
},
{
"epoch": 0.02594793672051561,
"grad_norm": 0.4054403603076935,
"learning_rate": 2e-05,
"loss": 0.7532,
"step": 310
},
{
"epoch": 0.026784966937306438,
"grad_norm": 0.43971535563468933,
"learning_rate": 2e-05,
"loss": 0.7527,
"step": 320
},
{
"epoch": 0.02762199715409726,
"grad_norm": 1.0866317749023438,
"learning_rate": 2e-05,
"loss": 0.7705,
"step": 330
},
{
"epoch": 0.02845902737088809,
"grad_norm": 0.4061005115509033,
"learning_rate": 2e-05,
"loss": 0.7739,
"step": 340
},
{
"epoch": 0.029296057587678916,
"grad_norm": 0.5896549820899963,
"learning_rate": 2e-05,
"loss": 0.7655,
"step": 350
},
{
"epoch": 0.03013308780446974,
"grad_norm": 0.44174519181251526,
"learning_rate": 2e-05,
"loss": 0.7502,
"step": 360
},
{
"epoch": 0.030970118021260568,
"grad_norm": 0.4336935877799988,
"learning_rate": 2e-05,
"loss": 0.7119,
"step": 370
},
{
"epoch": 0.03180714823805139,
"grad_norm": 0.43263721466064453,
"learning_rate": 2e-05,
"loss": 0.7308,
"step": 380
},
{
"epoch": 0.03264417845484222,
"grad_norm": 0.4120350480079651,
"learning_rate": 2e-05,
"loss": 0.7464,
"step": 390
},
{
"epoch": 0.033481208671633046,
"grad_norm": 0.4036485254764557,
"learning_rate": 2e-05,
"loss": 0.7601,
"step": 400
},
{
"epoch": 0.03431823888842387,
"grad_norm": 0.41021424531936646,
"learning_rate": 2e-05,
"loss": 0.7281,
"step": 410
},
{
"epoch": 0.0351552691052147,
"grad_norm": 0.4482649564743042,
"learning_rate": 2e-05,
"loss": 0.7316,
"step": 420
},
{
"epoch": 0.035992299322005525,
"grad_norm": 0.4150967299938202,
"learning_rate": 2e-05,
"loss": 0.7365,
"step": 430
},
{
"epoch": 0.03682932953879635,
"grad_norm": 0.3876197934150696,
"learning_rate": 2e-05,
"loss": 0.7511,
"step": 440
},
{
"epoch": 0.03766635975558718,
"grad_norm": 0.40040096640586853,
"learning_rate": 2e-05,
"loss": 0.793,
"step": 450
},
{
"epoch": 0.038503389972378003,
"grad_norm": 0.4496796727180481,
"learning_rate": 2e-05,
"loss": 0.7423,
"step": 460
},
{
"epoch": 0.03934042018916883,
"grad_norm": 0.4478641152381897,
"learning_rate": 2e-05,
"loss": 0.7485,
"step": 470
},
{
"epoch": 0.04017745040595966,
"grad_norm": 0.4376203715801239,
"learning_rate": 2e-05,
"loss": 0.7909,
"step": 480
},
{
"epoch": 0.04101448062275048,
"grad_norm": 0.42852625250816345,
"learning_rate": 2e-05,
"loss": 0.7159,
"step": 490
},
{
"epoch": 0.041851510839541306,
"grad_norm": 0.42360687255859375,
"learning_rate": 2e-05,
"loss": 0.7401,
"step": 500
},
{
"epoch": 0.04268854105633214,
"grad_norm": 0.38901394605636597,
"learning_rate": 2e-05,
"loss": 0.7284,
"step": 510
},
{
"epoch": 0.04352557127312296,
"grad_norm": 0.4375343322753906,
"learning_rate": 2e-05,
"loss": 0.738,
"step": 520
},
{
"epoch": 0.044362601489913785,
"grad_norm": 0.44532549381256104,
"learning_rate": 2e-05,
"loss": 0.7469,
"step": 530
},
{
"epoch": 0.045199631706704615,
"grad_norm": 0.46848392486572266,
"learning_rate": 2e-05,
"loss": 0.7366,
"step": 540
},
{
"epoch": 0.04603666192349544,
"grad_norm": 0.3851851224899292,
"learning_rate": 2e-05,
"loss": 0.7335,
"step": 550
},
{
"epoch": 0.04687369214028626,
"grad_norm": 0.40839746594429016,
"learning_rate": 2e-05,
"loss": 0.7053,
"step": 560
},
{
"epoch": 0.04771072235707709,
"grad_norm": 0.4012123644351959,
"learning_rate": 2e-05,
"loss": 0.7137,
"step": 570
},
{
"epoch": 0.04854775257386792,
"grad_norm": 0.3855404555797577,
"learning_rate": 2e-05,
"loss": 0.7133,
"step": 580
},
{
"epoch": 0.04938478279065874,
"grad_norm": 0.3988204002380371,
"learning_rate": 2e-05,
"loss": 0.7541,
"step": 590
},
{
"epoch": 0.050221813007449566,
"grad_norm": 0.4450335204601288,
"learning_rate": 2e-05,
"loss": 0.7238,
"step": 600
},
{
"epoch": 0.0510588432242404,
"grad_norm": 0.4375969469547272,
"learning_rate": 2e-05,
"loss": 0.7044,
"step": 610
},
{
"epoch": 0.05189587344103122,
"grad_norm": 0.4379328787326813,
"learning_rate": 2e-05,
"loss": 0.726,
"step": 620
},
{
"epoch": 0.052732903657822044,
"grad_norm": 0.39580798149108887,
"learning_rate": 2e-05,
"loss": 0.7463,
"step": 630
},
{
"epoch": 0.053569933874612875,
"grad_norm": 0.41373711824417114,
"learning_rate": 2e-05,
"loss": 0.7499,
"step": 640
},
{
"epoch": 0.0544069640914037,
"grad_norm": 0.4301176369190216,
"learning_rate": 2e-05,
"loss": 0.7341,
"step": 650
},
{
"epoch": 0.05524399430819452,
"grad_norm": 0.45098692178726196,
"learning_rate": 2e-05,
"loss": 0.7318,
"step": 660
},
{
"epoch": 0.056081024524985354,
"grad_norm": 0.4196617305278778,
"learning_rate": 2e-05,
"loss": 0.734,
"step": 670
},
{
"epoch": 0.05691805474177618,
"grad_norm": 0.4272335171699524,
"learning_rate": 2e-05,
"loss": 0.7083,
"step": 680
},
{
"epoch": 0.057755084958567,
"grad_norm": 0.4190222918987274,
"learning_rate": 2e-05,
"loss": 0.7272,
"step": 690
},
{
"epoch": 0.05859211517535783,
"grad_norm": 0.42260268330574036,
"learning_rate": 2e-05,
"loss": 0.7266,
"step": 700
},
{
"epoch": 0.059429145392148656,
"grad_norm": 0.3979990780353546,
"learning_rate": 2e-05,
"loss": 0.7265,
"step": 710
},
{
"epoch": 0.06026617560893948,
"grad_norm": 0.41610896587371826,
"learning_rate": 2e-05,
"loss": 0.7308,
"step": 720
},
{
"epoch": 0.06110320582573031,
"grad_norm": 0.44141194224357605,
"learning_rate": 2e-05,
"loss": 0.752,
"step": 730
},
{
"epoch": 0.061940236042521135,
"grad_norm": 0.40890923142433167,
"learning_rate": 2e-05,
"loss": 0.7552,
"step": 740
},
{
"epoch": 0.06277726625931196,
"grad_norm": 0.37664929032325745,
"learning_rate": 2e-05,
"loss": 0.7363,
"step": 750
},
{
"epoch": 0.06361429647610278,
"grad_norm": 0.3718191683292389,
"learning_rate": 2e-05,
"loss": 0.7458,
"step": 760
},
{
"epoch": 0.0644513266928936,
"grad_norm": 0.4162319004535675,
"learning_rate": 2e-05,
"loss": 0.7587,
"step": 770
},
{
"epoch": 0.06528835690968444,
"grad_norm": 0.5250889658927917,
"learning_rate": 2e-05,
"loss": 0.733,
"step": 780
},
{
"epoch": 0.06612538712647527,
"grad_norm": 0.3899112343788147,
"learning_rate": 2e-05,
"loss": 0.731,
"step": 790
},
{
"epoch": 0.06696241734326609,
"grad_norm": 0.39714515209198,
"learning_rate": 2e-05,
"loss": 0.7397,
"step": 800
},
{
"epoch": 0.06779944756005692,
"grad_norm": 0.4384140372276306,
"learning_rate": 2e-05,
"loss": 0.7334,
"step": 810
},
{
"epoch": 0.06863647777684774,
"grad_norm": 0.37715354561805725,
"learning_rate": 2e-05,
"loss": 0.7442,
"step": 820
},
{
"epoch": 0.06947350799363856,
"grad_norm": 0.4676320552825928,
"learning_rate": 2e-05,
"loss": 0.729,
"step": 830
},
{
"epoch": 0.0703105382104294,
"grad_norm": 0.4101060926914215,
"learning_rate": 2e-05,
"loss": 0.7412,
"step": 840
},
{
"epoch": 0.07114756842722023,
"grad_norm": 0.40823832154273987,
"learning_rate": 2e-05,
"loss": 0.7404,
"step": 850
},
{
"epoch": 0.07198459864401105,
"grad_norm": 0.35889768600463867,
"learning_rate": 2e-05,
"loss": 0.7301,
"step": 860
},
{
"epoch": 0.07282162886080187,
"grad_norm": 0.35591280460357666,
"learning_rate": 2e-05,
"loss": 0.7434,
"step": 870
},
{
"epoch": 0.0736586590775927,
"grad_norm": 0.3851705491542816,
"learning_rate": 2e-05,
"loss": 0.7002,
"step": 880
},
{
"epoch": 0.07449568929438352,
"grad_norm": 0.3983948230743408,
"learning_rate": 2e-05,
"loss": 0.7274,
"step": 890
},
{
"epoch": 0.07533271951117436,
"grad_norm": 0.3635563254356384,
"learning_rate": 2e-05,
"loss": 0.6975,
"step": 900
},
{
"epoch": 0.07616974972796518,
"grad_norm": 0.3900563418865204,
"learning_rate": 2e-05,
"loss": 0.7467,
"step": 910
},
{
"epoch": 0.07700677994475601,
"grad_norm": 0.4121996760368347,
"learning_rate": 2e-05,
"loss": 0.7181,
"step": 920
},
{
"epoch": 0.07784381016154683,
"grad_norm": 0.35744690895080566,
"learning_rate": 2e-05,
"loss": 0.72,
"step": 930
},
{
"epoch": 0.07868084037833765,
"grad_norm": 0.44155263900756836,
"learning_rate": 2e-05,
"loss": 0.714,
"step": 940
},
{
"epoch": 0.07951787059512848,
"grad_norm": 0.415809690952301,
"learning_rate": 2e-05,
"loss": 0.7518,
"step": 950
},
{
"epoch": 0.08035490081191932,
"grad_norm": 0.3967406153678894,
"learning_rate": 2e-05,
"loss": 0.7445,
"step": 960
},
{
"epoch": 0.08119193102871014,
"grad_norm": 0.4007624089717865,
"learning_rate": 2e-05,
"loss": 0.747,
"step": 970
},
{
"epoch": 0.08202896124550096,
"grad_norm": 0.38344693183898926,
"learning_rate": 2e-05,
"loss": 0.7295,
"step": 980
},
{
"epoch": 0.08286599146229179,
"grad_norm": 0.45661893486976624,
"learning_rate": 2e-05,
"loss": 0.7111,
"step": 990
},
{
"epoch": 0.08370302167908261,
"grad_norm": 0.4255678951740265,
"learning_rate": 2e-05,
"loss": 0.775,
"step": 1000
},
{
"epoch": 0.08454005189587344,
"grad_norm": 0.49089524149894714,
"learning_rate": 2e-05,
"loss": 0.7387,
"step": 1010
},
{
"epoch": 0.08537708211266427,
"grad_norm": 0.3930380642414093,
"learning_rate": 2e-05,
"loss": 0.7601,
"step": 1020
},
{
"epoch": 0.0862141123294551,
"grad_norm": 0.4231725037097931,
"learning_rate": 2e-05,
"loss": 0.6822,
"step": 1030
},
{
"epoch": 0.08705114254624592,
"grad_norm": 0.39020201563835144,
"learning_rate": 2e-05,
"loss": 0.7325,
"step": 1040
},
{
"epoch": 0.08788817276303675,
"grad_norm": 0.429443359375,
"learning_rate": 2e-05,
"loss": 0.7194,
"step": 1050
},
{
"epoch": 0.08872520297982757,
"grad_norm": 0.38595613837242126,
"learning_rate": 2e-05,
"loss": 0.7336,
"step": 1060
},
{
"epoch": 0.0895622331966184,
"grad_norm": 0.371380090713501,
"learning_rate": 2e-05,
"loss": 0.7325,
"step": 1070
},
{
"epoch": 0.09039926341340923,
"grad_norm": 0.396846204996109,
"learning_rate": 2e-05,
"loss": 0.7281,
"step": 1080
},
{
"epoch": 0.09123629363020005,
"grad_norm": 0.42279285192489624,
"learning_rate": 2e-05,
"loss": 0.7383,
"step": 1090
},
{
"epoch": 0.09207332384699088,
"grad_norm": 0.41259169578552246,
"learning_rate": 2e-05,
"loss": 0.7398,
"step": 1100
},
{
"epoch": 0.0929103540637817,
"grad_norm": 0.43002089858055115,
"learning_rate": 2e-05,
"loss": 0.7323,
"step": 1110
},
{
"epoch": 0.09374738428057253,
"grad_norm": 0.4018864929676056,
"learning_rate": 2e-05,
"loss": 0.7542,
"step": 1120
},
{
"epoch": 0.09458441449736335,
"grad_norm": 0.3879416882991791,
"learning_rate": 2e-05,
"loss": 0.724,
"step": 1130
},
{
"epoch": 0.09542144471415417,
"grad_norm": 0.40612295269966125,
"learning_rate": 2e-05,
"loss": 0.7181,
"step": 1140
},
{
"epoch": 0.09625847493094501,
"grad_norm": 0.3889906406402588,
"learning_rate": 2e-05,
"loss": 0.7206,
"step": 1150
},
{
"epoch": 0.09709550514773584,
"grad_norm": 0.3631397783756256,
"learning_rate": 2e-05,
"loss": 0.7608,
"step": 1160
},
{
"epoch": 0.09793253536452666,
"grad_norm": 0.3583589494228363,
"learning_rate": 2e-05,
"loss": 0.7257,
"step": 1170
},
{
"epoch": 0.09876956558131748,
"grad_norm": 0.38138115406036377,
"learning_rate": 2e-05,
"loss": 0.7296,
"step": 1180
},
{
"epoch": 0.09960659579810831,
"grad_norm": 0.381708025932312,
"learning_rate": 2e-05,
"loss": 0.7275,
"step": 1190
},
{
"epoch": 0.10044362601489913,
"grad_norm": 0.3952488601207733,
"learning_rate": 2e-05,
"loss": 0.7211,
"step": 1200
},
{
"epoch": 0.10128065623168997,
"grad_norm": 0.369489848613739,
"learning_rate": 2e-05,
"loss": 0.6827,
"step": 1210
},
{
"epoch": 0.1021176864484808,
"grad_norm": 0.3854788541793823,
"learning_rate": 2e-05,
"loss": 0.7141,
"step": 1220
},
{
"epoch": 0.10295471666527162,
"grad_norm": 0.44547921419143677,
"learning_rate": 2e-05,
"loss": 0.7465,
"step": 1230
},
{
"epoch": 0.10379174688206244,
"grad_norm": 0.3807377219200134,
"learning_rate": 2e-05,
"loss": 0.6965,
"step": 1240
},
{
"epoch": 0.10462877709885327,
"grad_norm": 1.0734481811523438,
"learning_rate": 2e-05,
"loss": 0.7228,
"step": 1250
},
{
"epoch": 0.10546580731564409,
"grad_norm": 0.3832617700099945,
"learning_rate": 2e-05,
"loss": 0.76,
"step": 1260
},
{
"epoch": 0.10630283753243493,
"grad_norm": 0.4228065013885498,
"learning_rate": 2e-05,
"loss": 0.7379,
"step": 1270
},
{
"epoch": 0.10713986774922575,
"grad_norm": 0.39900723099708557,
"learning_rate": 2e-05,
"loss": 0.6866,
"step": 1280
},
{
"epoch": 0.10797689796601657,
"grad_norm": 0.5197460055351257,
"learning_rate": 2e-05,
"loss": 0.6915,
"step": 1290
},
{
"epoch": 0.1088139281828074,
"grad_norm": 0.6023410558700562,
"learning_rate": 2e-05,
"loss": 0.7019,
"step": 1300
},
{
"epoch": 0.10965095839959822,
"grad_norm": 0.4066433310508728,
"learning_rate": 2e-05,
"loss": 0.7001,
"step": 1310
},
{
"epoch": 0.11048798861638905,
"grad_norm": 0.382357656955719,
"learning_rate": 2e-05,
"loss": 0.7287,
"step": 1320
},
{
"epoch": 0.11132501883317988,
"grad_norm": 0.3749663829803467,
"learning_rate": 2e-05,
"loss": 0.7429,
"step": 1330
},
{
"epoch": 0.11216204904997071,
"grad_norm": 0.3689495325088501,
"learning_rate": 2e-05,
"loss": 0.6842,
"step": 1340
},
{
"epoch": 0.11299907926676153,
"grad_norm": 0.41168835759162903,
"learning_rate": 2e-05,
"loss": 0.7533,
"step": 1350
},
{
"epoch": 0.11383610948355236,
"grad_norm": 0.39960694313049316,
"learning_rate": 2e-05,
"loss": 0.7312,
"step": 1360
},
{
"epoch": 0.11467313970034318,
"grad_norm": 0.3908539414405823,
"learning_rate": 2e-05,
"loss": 0.7085,
"step": 1370
},
{
"epoch": 0.115510169917134,
"grad_norm": 0.38182100653648376,
"learning_rate": 2e-05,
"loss": 0.7271,
"step": 1380
},
{
"epoch": 0.11634720013392484,
"grad_norm": 0.405620276927948,
"learning_rate": 2e-05,
"loss": 0.7235,
"step": 1390
},
{
"epoch": 0.11718423035071567,
"grad_norm": 0.3966982364654541,
"learning_rate": 2e-05,
"loss": 0.7371,
"step": 1400
},
{
"epoch": 0.11802126056750649,
"grad_norm": 0.3768328130245209,
"learning_rate": 2e-05,
"loss": 0.7172,
"step": 1410
},
{
"epoch": 0.11885829078429731,
"grad_norm": 0.4282349944114685,
"learning_rate": 2e-05,
"loss": 0.7318,
"step": 1420
},
{
"epoch": 0.11969532100108814,
"grad_norm": 0.39045482873916626,
"learning_rate": 2e-05,
"loss": 0.704,
"step": 1430
},
{
"epoch": 0.12053235121787896,
"grad_norm": 0.3846886456012726,
"learning_rate": 2e-05,
"loss": 0.7069,
"step": 1440
},
{
"epoch": 0.12136938143466978,
"grad_norm": 0.3845898509025574,
"learning_rate": 2e-05,
"loss": 0.703,
"step": 1450
},
{
"epoch": 0.12220641165146062,
"grad_norm": 0.4043080508708954,
"learning_rate": 2e-05,
"loss": 0.7329,
"step": 1460
},
{
"epoch": 0.12304344186825145,
"grad_norm": 0.353148877620697,
"learning_rate": 2e-05,
"loss": 0.7039,
"step": 1470
},
{
"epoch": 0.12388047208504227,
"grad_norm": 0.3626961410045624,
"learning_rate": 2e-05,
"loss": 0.7125,
"step": 1480
},
{
"epoch": 0.1247175023018331,
"grad_norm": 0.40537577867507935,
"learning_rate": 2e-05,
"loss": 0.6874,
"step": 1490
},
{
"epoch": 0.12555453251862392,
"grad_norm": 0.38374269008636475,
"learning_rate": 2e-05,
"loss": 0.7166,
"step": 1500
},
{
"epoch": 0.12639156273541474,
"grad_norm": 0.3687508702278137,
"learning_rate": 2e-05,
"loss": 0.7042,
"step": 1510
},
{
"epoch": 0.12722859295220557,
"grad_norm": 0.38297727704048157,
"learning_rate": 2e-05,
"loss": 0.7276,
"step": 1520
},
{
"epoch": 0.1280656231689964,
"grad_norm": 0.40739986300468445,
"learning_rate": 2e-05,
"loss": 0.7352,
"step": 1530
},
{
"epoch": 0.1289026533857872,
"grad_norm": 0.5073732733726501,
"learning_rate": 2e-05,
"loss": 0.7407,
"step": 1540
},
{
"epoch": 0.12973968360257807,
"grad_norm": 0.3655388653278351,
"learning_rate": 2e-05,
"loss": 0.707,
"step": 1550
},
{
"epoch": 0.1305767138193689,
"grad_norm": 0.38478103280067444,
"learning_rate": 2e-05,
"loss": 0.7155,
"step": 1560
},
{
"epoch": 0.1314137440361597,
"grad_norm": 0.3790566027164459,
"learning_rate": 2e-05,
"loss": 0.7048,
"step": 1570
},
{
"epoch": 0.13225077425295054,
"grad_norm": 0.3985552489757538,
"learning_rate": 2e-05,
"loss": 0.7469,
"step": 1580
},
{
"epoch": 0.13308780446974136,
"grad_norm": 0.3573896586894989,
"learning_rate": 2e-05,
"loss": 0.7128,
"step": 1590
},
{
"epoch": 0.13392483468653218,
"grad_norm": 0.3679613471031189,
"learning_rate": 2e-05,
"loss": 0.7063,
"step": 1600
},
{
"epoch": 0.134761864903323,
"grad_norm": 0.4195422828197479,
"learning_rate": 2e-05,
"loss": 0.7214,
"step": 1610
},
{
"epoch": 0.13559889512011383,
"grad_norm": 0.4262971878051758,
"learning_rate": 2e-05,
"loss": 0.7214,
"step": 1620
},
{
"epoch": 0.13643592533690466,
"grad_norm": 0.3953056335449219,
"learning_rate": 2e-05,
"loss": 0.7457,
"step": 1630
},
{
"epoch": 0.13727295555369548,
"grad_norm": 0.3896598517894745,
"learning_rate": 2e-05,
"loss": 0.68,
"step": 1640
},
{
"epoch": 0.1381099857704863,
"grad_norm": 0.39134523272514343,
"learning_rate": 2e-05,
"loss": 0.7233,
"step": 1650
},
{
"epoch": 0.13894701598727713,
"grad_norm": 0.38543522357940674,
"learning_rate": 2e-05,
"loss": 0.7078,
"step": 1660
},
{
"epoch": 0.13978404620406798,
"grad_norm": 0.37859565019607544,
"learning_rate": 2e-05,
"loss": 0.7141,
"step": 1670
},
{
"epoch": 0.1406210764208588,
"grad_norm": 0.3654524087905884,
"learning_rate": 2e-05,
"loss": 0.6817,
"step": 1680
},
{
"epoch": 0.14145810663764963,
"grad_norm": 0.3827599585056305,
"learning_rate": 2e-05,
"loss": 0.6995,
"step": 1690
},
{
"epoch": 0.14229513685444045,
"grad_norm": 0.3548571467399597,
"learning_rate": 2e-05,
"loss": 0.7106,
"step": 1700
},
{
"epoch": 0.14313216707123128,
"grad_norm": 0.4650750756263733,
"learning_rate": 2e-05,
"loss": 0.7498,
"step": 1710
},
{
"epoch": 0.1439691972880221,
"grad_norm": 0.38478001952171326,
"learning_rate": 2e-05,
"loss": 0.7699,
"step": 1720
},
{
"epoch": 0.14480622750481292,
"grad_norm": 0.37154585123062134,
"learning_rate": 2e-05,
"loss": 0.6941,
"step": 1730
},
{
"epoch": 0.14564325772160375,
"grad_norm": 0.38709065318107605,
"learning_rate": 2e-05,
"loss": 0.7337,
"step": 1740
},
{
"epoch": 0.14648028793839457,
"grad_norm": 1.7314486503601074,
"learning_rate": 2e-05,
"loss": 0.7005,
"step": 1750
},
{
"epoch": 0.1473173181551854,
"grad_norm": 0.3551817834377289,
"learning_rate": 2e-05,
"loss": 0.7132,
"step": 1760
},
{
"epoch": 0.14815434837197622,
"grad_norm": 0.3846317529678345,
"learning_rate": 2e-05,
"loss": 0.6762,
"step": 1770
},
{
"epoch": 0.14899137858876704,
"grad_norm": 0.37913134694099426,
"learning_rate": 2e-05,
"loss": 0.7101,
"step": 1780
},
{
"epoch": 0.1498284088055579,
"grad_norm": 0.3794521391391754,
"learning_rate": 2e-05,
"loss": 0.7327,
"step": 1790
},
{
"epoch": 0.15066543902234872,
"grad_norm": 0.3727302551269531,
"learning_rate": 2e-05,
"loss": 0.7198,
"step": 1800
},
{
"epoch": 0.15150246923913954,
"grad_norm": 0.39975666999816895,
"learning_rate": 2e-05,
"loss": 0.7283,
"step": 1810
},
{
"epoch": 0.15233949945593037,
"grad_norm": 0.37394288182258606,
"learning_rate": 2e-05,
"loss": 0.6815,
"step": 1820
},
{
"epoch": 0.1531765296727212,
"grad_norm": 0.38191404938697815,
"learning_rate": 2e-05,
"loss": 0.723,
"step": 1830
},
{
"epoch": 0.15401355988951201,
"grad_norm": 0.3914385437965393,
"learning_rate": 2e-05,
"loss": 0.6959,
"step": 1840
},
{
"epoch": 0.15485059010630284,
"grad_norm": 0.36960726976394653,
"learning_rate": 2e-05,
"loss": 0.6981,
"step": 1850
},
{
"epoch": 0.15568762032309366,
"grad_norm": 0.4533153474330902,
"learning_rate": 2e-05,
"loss": 0.7042,
"step": 1860
},
{
"epoch": 0.15652465053988449,
"grad_norm": 0.390516459941864,
"learning_rate": 2e-05,
"loss": 0.7285,
"step": 1870
},
{
"epoch": 0.1573616807566753,
"grad_norm": 0.36687996983528137,
"learning_rate": 2e-05,
"loss": 0.7039,
"step": 1880
},
{
"epoch": 0.15819871097346613,
"grad_norm": 0.3998259902000427,
"learning_rate": 2e-05,
"loss": 0.7045,
"step": 1890
},
{
"epoch": 0.15903574119025696,
"grad_norm": 0.3630969226360321,
"learning_rate": 2e-05,
"loss": 0.7156,
"step": 1900
},
{
"epoch": 0.15987277140704778,
"grad_norm": 0.49144166707992554,
"learning_rate": 2e-05,
"loss": 0.7492,
"step": 1910
},
{
"epoch": 0.16070980162383863,
"grad_norm": 0.3666890263557434,
"learning_rate": 2e-05,
"loss": 0.6957,
"step": 1920
},
{
"epoch": 0.16154683184062946,
"grad_norm": 0.36240652203559875,
"learning_rate": 2e-05,
"loss": 0.7208,
"step": 1930
},
{
"epoch": 0.16238386205742028,
"grad_norm": 0.37068548798561096,
"learning_rate": 2e-05,
"loss": 0.7593,
"step": 1940
},
{
"epoch": 0.1632208922742111,
"grad_norm": 0.38422319293022156,
"learning_rate": 2e-05,
"loss": 0.718,
"step": 1950
},
{
"epoch": 0.16405792249100193,
"grad_norm": 0.4526020884513855,
"learning_rate": 2e-05,
"loss": 0.7152,
"step": 1960
},
{
"epoch": 0.16489495270779275,
"grad_norm": 0.42693546414375305,
"learning_rate": 2e-05,
"loss": 0.7031,
"step": 1970
},
{
"epoch": 0.16573198292458358,
"grad_norm": 0.352283239364624,
"learning_rate": 2e-05,
"loss": 0.6788,
"step": 1980
},
{
"epoch": 0.1665690131413744,
"grad_norm": 0.4254308342933655,
"learning_rate": 2e-05,
"loss": 0.7004,
"step": 1990
},
{
"epoch": 0.16740604335816522,
"grad_norm": 0.37109827995300293,
"learning_rate": 2e-05,
"loss": 0.7183,
"step": 2000
},
{
"epoch": 0.16824307357495605,
"grad_norm": 0.3963578939437866,
"learning_rate": 2e-05,
"loss": 0.7152,
"step": 2010
},
{
"epoch": 0.16908010379174687,
"grad_norm": 0.4323606491088867,
"learning_rate": 2e-05,
"loss": 0.7275,
"step": 2020
},
{
"epoch": 0.1699171340085377,
"grad_norm": 0.38154488801956177,
"learning_rate": 2e-05,
"loss": 0.7043,
"step": 2030
},
{
"epoch": 0.17075416422532855,
"grad_norm": 0.37403401732444763,
"learning_rate": 2e-05,
"loss": 0.6961,
"step": 2040
},
{
"epoch": 0.17159119444211937,
"grad_norm": 0.4297429919242859,
"learning_rate": 2e-05,
"loss": 0.7279,
"step": 2050
},
{
"epoch": 0.1724282246589102,
"grad_norm": 0.3764204978942871,
"learning_rate": 2e-05,
"loss": 0.7169,
"step": 2060
},
{
"epoch": 0.17326525487570102,
"grad_norm": 0.4536464512348175,
"learning_rate": 2e-05,
"loss": 0.7076,
"step": 2070
},
{
"epoch": 0.17410228509249184,
"grad_norm": 0.3891889750957489,
"learning_rate": 2e-05,
"loss": 0.6937,
"step": 2080
},
{
"epoch": 0.17493931530928267,
"grad_norm": 0.3979426920413971,
"learning_rate": 2e-05,
"loss": 0.7117,
"step": 2090
},
{
"epoch": 0.1757763455260735,
"grad_norm": 0.33533552289009094,
"learning_rate": 2e-05,
"loss": 0.6911,
"step": 2100
},
{
"epoch": 0.17661337574286431,
"grad_norm": 0.4086405038833618,
"learning_rate": 2e-05,
"loss": 0.6961,
"step": 2110
},
{
"epoch": 0.17745040595965514,
"grad_norm": 0.32550907135009766,
"learning_rate": 2e-05,
"loss": 0.7189,
"step": 2120
},
{
"epoch": 0.17828743617644596,
"grad_norm": 0.41129428148269653,
"learning_rate": 2e-05,
"loss": 0.7132,
"step": 2130
},
{
"epoch": 0.1791244663932368,
"grad_norm": 0.38379132747650146,
"learning_rate": 2e-05,
"loss": 0.7083,
"step": 2140
},
{
"epoch": 0.1799614966100276,
"grad_norm": 0.33447548747062683,
"learning_rate": 2e-05,
"loss": 0.6957,
"step": 2150
},
{
"epoch": 0.18079852682681846,
"grad_norm": 0.36413493752479553,
"learning_rate": 2e-05,
"loss": 0.6845,
"step": 2160
},
{
"epoch": 0.18163555704360929,
"grad_norm": 0.3704940676689148,
"learning_rate": 2e-05,
"loss": 0.7045,
"step": 2170
},
{
"epoch": 0.1824725872604001,
"grad_norm": 0.37158524990081787,
"learning_rate": 2e-05,
"loss": 0.6945,
"step": 2180
},
{
"epoch": 0.18330961747719093,
"grad_norm": 0.37925466895103455,
"learning_rate": 2e-05,
"loss": 0.7088,
"step": 2190
},
{
"epoch": 0.18414664769398176,
"grad_norm": 0.3649779260158539,
"learning_rate": 2e-05,
"loss": 0.7342,
"step": 2200
},
{
"epoch": 0.18498367791077258,
"grad_norm": 0.38125574588775635,
"learning_rate": 2e-05,
"loss": 0.7045,
"step": 2210
},
{
"epoch": 0.1858207081275634,
"grad_norm": 0.4088246524333954,
"learning_rate": 2e-05,
"loss": 0.7006,
"step": 2220
},
{
"epoch": 0.18665773834435423,
"grad_norm": 0.4514538645744324,
"learning_rate": 2e-05,
"loss": 0.7126,
"step": 2230
},
{
"epoch": 0.18749476856114505,
"grad_norm": 0.3832446336746216,
"learning_rate": 2e-05,
"loss": 0.6912,
"step": 2240
},
{
"epoch": 0.18833179877793588,
"grad_norm": 0.37790173292160034,
"learning_rate": 2e-05,
"loss": 0.6738,
"step": 2250
},
{
"epoch": 0.1891688289947267,
"grad_norm": 0.3716677129268646,
"learning_rate": 2e-05,
"loss": 0.7122,
"step": 2260
},
{
"epoch": 0.19000585921151752,
"grad_norm": 0.3565468490123749,
"learning_rate": 2e-05,
"loss": 0.679,
"step": 2270
},
{
"epoch": 0.19084288942830835,
"grad_norm": 0.37897953391075134,
"learning_rate": 2e-05,
"loss": 0.6941,
"step": 2280
},
{
"epoch": 0.1916799196450992,
"grad_norm": 0.3777736723423004,
"learning_rate": 2e-05,
"loss": 0.7166,
"step": 2290
},
{
"epoch": 0.19251694986189002,
"grad_norm": 0.3585146367549896,
"learning_rate": 2e-05,
"loss": 0.6928,
"step": 2300
},
{
"epoch": 0.19335398007868085,
"grad_norm": 0.3698466122150421,
"learning_rate": 2e-05,
"loss": 0.6937,
"step": 2310
},
{
"epoch": 0.19419101029547167,
"grad_norm": 0.3647162914276123,
"learning_rate": 2e-05,
"loss": 0.7128,
"step": 2320
},
{
"epoch": 0.1950280405122625,
"grad_norm": 0.4572893977165222,
"learning_rate": 2e-05,
"loss": 0.6978,
"step": 2330
},
{
"epoch": 0.19586507072905332,
"grad_norm": 0.42052674293518066,
"learning_rate": 2e-05,
"loss": 0.6901,
"step": 2340
},
{
"epoch": 0.19670210094584414,
"grad_norm": 0.4102165102958679,
"learning_rate": 2e-05,
"loss": 0.7097,
"step": 2350
},
{
"epoch": 0.19753913116263497,
"grad_norm": 0.3792290687561035,
"learning_rate": 2e-05,
"loss": 0.6917,
"step": 2360
},
{
"epoch": 0.1983761613794258,
"grad_norm": 0.41515079140663147,
"learning_rate": 2e-05,
"loss": 0.7033,
"step": 2370
},
{
"epoch": 0.19921319159621662,
"grad_norm": 0.44105610251426697,
"learning_rate": 2e-05,
"loss": 0.7093,
"step": 2380
},
{
"epoch": 0.20005022181300744,
"grad_norm": 0.3615840971469879,
"learning_rate": 2e-05,
"loss": 0.7512,
"step": 2390
},
{
"epoch": 0.20088725202979826,
"grad_norm": 0.3563784062862396,
"learning_rate": 2e-05,
"loss": 0.7046,
"step": 2400
},
{
"epoch": 0.20172428224658911,
"grad_norm": 0.3593883216381073,
"learning_rate": 2e-05,
"loss": 0.7143,
"step": 2410
},
{
"epoch": 0.20256131246337994,
"grad_norm": 0.375445157289505,
"learning_rate": 2e-05,
"loss": 0.678,
"step": 2420
},
{
"epoch": 0.20339834268017076,
"grad_norm": 0.3783409595489502,
"learning_rate": 2e-05,
"loss": 0.6926,
"step": 2430
},
{
"epoch": 0.2042353728969616,
"grad_norm": 0.3709818720817566,
"learning_rate": 2e-05,
"loss": 0.6974,
"step": 2440
},
{
"epoch": 0.2050724031137524,
"grad_norm": 0.3591563403606415,
"learning_rate": 2e-05,
"loss": 0.7022,
"step": 2450
},
{
"epoch": 0.20590943333054323,
"grad_norm": 0.42944005131721497,
"learning_rate": 2e-05,
"loss": 0.7151,
"step": 2460
},
{
"epoch": 0.20674646354733406,
"grad_norm": 0.36380648612976074,
"learning_rate": 2e-05,
"loss": 0.6938,
"step": 2470
},
{
"epoch": 0.20758349376412488,
"grad_norm": 0.3823877274990082,
"learning_rate": 2e-05,
"loss": 0.6853,
"step": 2480
},
{
"epoch": 0.2084205239809157,
"grad_norm": 0.40340110659599304,
"learning_rate": 2e-05,
"loss": 0.6983,
"step": 2490
},
{
"epoch": 0.20925755419770653,
"grad_norm": 0.3656036853790283,
"learning_rate": 2e-05,
"loss": 0.6927,
"step": 2500
},
{
"epoch": 0.21009458441449735,
"grad_norm": 0.3953785002231598,
"learning_rate": 2e-05,
"loss": 0.6779,
"step": 2510
},
{
"epoch": 0.21093161463128818,
"grad_norm": 0.40045875310897827,
"learning_rate": 2e-05,
"loss": 0.6812,
"step": 2520
},
{
"epoch": 0.211768644848079,
"grad_norm": 0.3604848086833954,
"learning_rate": 2e-05,
"loss": 0.6908,
"step": 2530
},
{
"epoch": 0.21260567506486985,
"grad_norm": 0.40517356991767883,
"learning_rate": 2e-05,
"loss": 0.7074,
"step": 2540
},
{
"epoch": 0.21344270528166068,
"grad_norm": 0.3920334279537201,
"learning_rate": 2e-05,
"loss": 0.7021,
"step": 2550
},
{
"epoch": 0.2142797354984515,
"grad_norm": 0.35391831398010254,
"learning_rate": 2e-05,
"loss": 0.704,
"step": 2560
},
{
"epoch": 0.21511676571524233,
"grad_norm": 0.33125635981559753,
"learning_rate": 2e-05,
"loss": 0.6751,
"step": 2570
},
{
"epoch": 0.21595379593203315,
"grad_norm": 0.3804548382759094,
"learning_rate": 2e-05,
"loss": 0.6929,
"step": 2580
},
{
"epoch": 0.21679082614882397,
"grad_norm": 0.41652804613113403,
"learning_rate": 2e-05,
"loss": 0.7224,
"step": 2590
},
{
"epoch": 0.2176278563656148,
"grad_norm": 0.37819674611091614,
"learning_rate": 2e-05,
"loss": 0.6942,
"step": 2600
},
{
"epoch": 0.21846488658240562,
"grad_norm": 0.3700343668460846,
"learning_rate": 2e-05,
"loss": 0.6922,
"step": 2610
},
{
"epoch": 0.21930191679919644,
"grad_norm": 0.39303967356681824,
"learning_rate": 2e-05,
"loss": 0.6836,
"step": 2620
},
{
"epoch": 0.22013894701598727,
"grad_norm": 0.3704970180988312,
"learning_rate": 2e-05,
"loss": 0.6656,
"step": 2630
},
{
"epoch": 0.2209759772327781,
"grad_norm": 0.35388532280921936,
"learning_rate": 2e-05,
"loss": 0.7203,
"step": 2640
},
{
"epoch": 0.22181300744956892,
"grad_norm": 0.3718905746936798,
"learning_rate": 2e-05,
"loss": 0.6942,
"step": 2650
},
{
"epoch": 0.22265003766635977,
"grad_norm": 0.36480191349983215,
"learning_rate": 2e-05,
"loss": 0.7213,
"step": 2660
},
{
"epoch": 0.2234870678831506,
"grad_norm": 0.5288359522819519,
"learning_rate": 2e-05,
"loss": 0.7045,
"step": 2670
},
{
"epoch": 0.22432409809994142,
"grad_norm": 0.3652160167694092,
"learning_rate": 2e-05,
"loss": 0.708,
"step": 2680
},
{
"epoch": 0.22516112831673224,
"grad_norm": 0.36390116810798645,
"learning_rate": 2e-05,
"loss": 0.6881,
"step": 2690
},
{
"epoch": 0.22599815853352306,
"grad_norm": 0.3840753734111786,
"learning_rate": 2e-05,
"loss": 0.6633,
"step": 2700
},
{
"epoch": 0.2268351887503139,
"grad_norm": 0.3530333638191223,
"learning_rate": 2e-05,
"loss": 0.7124,
"step": 2710
},
{
"epoch": 0.2276722189671047,
"grad_norm": 0.342545747756958,
"learning_rate": 2e-05,
"loss": 0.697,
"step": 2720
},
{
"epoch": 0.22850924918389554,
"grad_norm": 0.5206401348114014,
"learning_rate": 2e-05,
"loss": 0.6976,
"step": 2730
},
{
"epoch": 0.22934627940068636,
"grad_norm": 0.3752775192260742,
"learning_rate": 2e-05,
"loss": 0.7146,
"step": 2740
},
{
"epoch": 0.23018330961747718,
"grad_norm": 0.3544803857803345,
"learning_rate": 2e-05,
"loss": 0.7199,
"step": 2750
},
{
"epoch": 0.231020339834268,
"grad_norm": 0.47715863585472107,
"learning_rate": 2e-05,
"loss": 0.7116,
"step": 2760
},
{
"epoch": 0.23185737005105883,
"grad_norm": 0.3936082720756531,
"learning_rate": 2e-05,
"loss": 0.7104,
"step": 2770
},
{
"epoch": 0.23269440026784968,
"grad_norm": 0.3845888376235962,
"learning_rate": 2e-05,
"loss": 0.7153,
"step": 2780
},
{
"epoch": 0.2335314304846405,
"grad_norm": 0.3471842110157013,
"learning_rate": 2e-05,
"loss": 0.6582,
"step": 2790
},
{
"epoch": 0.23436846070143133,
"grad_norm": 0.3849339485168457,
"learning_rate": 2e-05,
"loss": 0.7134,
"step": 2800
},
{
"epoch": 0.23520549091822215,
"grad_norm": 0.4041845500469208,
"learning_rate": 2e-05,
"loss": 0.6917,
"step": 2810
},
{
"epoch": 0.23604252113501298,
"grad_norm": 0.347912460565567,
"learning_rate": 2e-05,
"loss": 0.7065,
"step": 2820
},
{
"epoch": 0.2368795513518038,
"grad_norm": 0.383291631937027,
"learning_rate": 2e-05,
"loss": 0.7237,
"step": 2830
},
{
"epoch": 0.23771658156859463,
"grad_norm": 0.3993476927280426,
"learning_rate": 2e-05,
"loss": 0.7263,
"step": 2840
},
{
"epoch": 0.23855361178538545,
"grad_norm": 0.364463210105896,
"learning_rate": 2e-05,
"loss": 0.6825,
"step": 2850
},
{
"epoch": 0.23939064200217627,
"grad_norm": 0.3854297697544098,
"learning_rate": 2e-05,
"loss": 0.6828,
"step": 2860
},
{
"epoch": 0.2402276722189671,
"grad_norm": 0.4553110599517822,
"learning_rate": 2e-05,
"loss": 0.6841,
"step": 2870
},
{
"epoch": 0.24106470243575792,
"grad_norm": 0.3404019773006439,
"learning_rate": 2e-05,
"loss": 0.6824,
"step": 2880
},
{
"epoch": 0.24190173265254875,
"grad_norm": 0.3552730679512024,
"learning_rate": 2e-05,
"loss": 0.705,
"step": 2890
},
{
"epoch": 0.24273876286933957,
"grad_norm": 0.6009185910224915,
"learning_rate": 2e-05,
"loss": 0.6872,
"step": 2900
},
{
"epoch": 0.24357579308613042,
"grad_norm": 0.3935545086860657,
"learning_rate": 2e-05,
"loss": 0.6606,
"step": 2910
},
{
"epoch": 0.24441282330292124,
"grad_norm": 0.3839946389198303,
"learning_rate": 2e-05,
"loss": 0.6758,
"step": 2920
},
{
"epoch": 0.24524985351971207,
"grad_norm": 0.49954575300216675,
"learning_rate": 2e-05,
"loss": 0.6747,
"step": 2930
},
{
"epoch": 0.2460868837365029,
"grad_norm": 0.3401426672935486,
"learning_rate": 2e-05,
"loss": 0.6798,
"step": 2940
},
{
"epoch": 0.24692391395329372,
"grad_norm": 0.38917040824890137,
"learning_rate": 2e-05,
"loss": 0.6955,
"step": 2950
},
{
"epoch": 0.24776094417008454,
"grad_norm": 0.3529467284679413,
"learning_rate": 2e-05,
"loss": 0.6733,
"step": 2960
},
{
"epoch": 0.24859797438687536,
"grad_norm": 0.3835350275039673,
"learning_rate": 2e-05,
"loss": 0.7163,
"step": 2970
},
{
"epoch": 0.2494350046036662,
"grad_norm": 0.34143391251564026,
"learning_rate": 2e-05,
"loss": 0.7019,
"step": 2980
},
{
"epoch": 0.250272034820457,
"grad_norm": 0.39724600315093994,
"learning_rate": 2e-05,
"loss": 0.6812,
"step": 2990
},
{
"epoch": 0.25110906503724784,
"grad_norm": 0.3517789840698242,
"learning_rate": 2e-05,
"loss": 0.6866,
"step": 3000
},
{
"epoch": 0.25194609525403866,
"grad_norm": 0.457095742225647,
"learning_rate": 2e-05,
"loss": 0.6892,
"step": 3010
},
{
"epoch": 0.2527831254708295,
"grad_norm": 0.3822527825832367,
"learning_rate": 2e-05,
"loss": 0.7063,
"step": 3020
},
{
"epoch": 0.2536201556876203,
"grad_norm": 0.39527907967567444,
"learning_rate": 2e-05,
"loss": 0.6757,
"step": 3030
},
{
"epoch": 0.25445718590441113,
"grad_norm": 0.36703014373779297,
"learning_rate": 2e-05,
"loss": 0.6991,
"step": 3040
},
{
"epoch": 0.25529421612120196,
"grad_norm": 0.5913490056991577,
"learning_rate": 2e-05,
"loss": 0.6808,
"step": 3050
},
{
"epoch": 0.2561312463379928,
"grad_norm": 0.6630072593688965,
"learning_rate": 2e-05,
"loss": 0.7075,
"step": 3060
},
{
"epoch": 0.2569682765547836,
"grad_norm": 0.3538056015968323,
"learning_rate": 2e-05,
"loss": 0.7061,
"step": 3070
},
{
"epoch": 0.2578053067715744,
"grad_norm": 0.4272959530353546,
"learning_rate": 2e-05,
"loss": 0.6843,
"step": 3080
},
{
"epoch": 0.2586423369883653,
"grad_norm": 0.396391898393631,
"learning_rate": 2e-05,
"loss": 0.6751,
"step": 3090
},
{
"epoch": 0.25947936720515613,
"grad_norm": 0.3552750051021576,
"learning_rate": 2e-05,
"loss": 0.7147,
"step": 3100
},
{
"epoch": 0.26031639742194695,
"grad_norm": 0.3866838216781616,
"learning_rate": 2e-05,
"loss": 0.736,
"step": 3110
},
{
"epoch": 0.2611534276387378,
"grad_norm": 0.37459060549736023,
"learning_rate": 2e-05,
"loss": 0.6848,
"step": 3120
},
{
"epoch": 0.2619904578555286,
"grad_norm": 0.3690750300884247,
"learning_rate": 2e-05,
"loss": 0.6834,
"step": 3130
},
{
"epoch": 0.2628274880723194,
"grad_norm": 0.4790518879890442,
"learning_rate": 2e-05,
"loss": 0.6947,
"step": 3140
},
{
"epoch": 0.26366451828911025,
"grad_norm": 0.3825061023235321,
"learning_rate": 2e-05,
"loss": 0.7086,
"step": 3150
},
{
"epoch": 0.2645015485059011,
"grad_norm": 0.43931442499160767,
"learning_rate": 2e-05,
"loss": 0.7131,
"step": 3160
},
{
"epoch": 0.2653385787226919,
"grad_norm": 0.36091071367263794,
"learning_rate": 2e-05,
"loss": 0.6678,
"step": 3170
},
{
"epoch": 0.2661756089394827,
"grad_norm": 0.35754019021987915,
"learning_rate": 2e-05,
"loss": 0.6757,
"step": 3180
},
{
"epoch": 0.26701263915627355,
"grad_norm": 0.34211859107017517,
"learning_rate": 2e-05,
"loss": 0.6844,
"step": 3190
},
{
"epoch": 0.26784966937306437,
"grad_norm": 0.3811708390712738,
"learning_rate": 2e-05,
"loss": 0.6752,
"step": 3200
},
{
"epoch": 0.2686866995898552,
"grad_norm": 0.37679523229599,
"learning_rate": 2e-05,
"loss": 0.6768,
"step": 3210
},
{
"epoch": 0.269523729806646,
"grad_norm": 0.3931836187839508,
"learning_rate": 2e-05,
"loss": 0.7104,
"step": 3220
},
{
"epoch": 0.27036076002343684,
"grad_norm": 0.4057767689228058,
"learning_rate": 2e-05,
"loss": 0.6791,
"step": 3230
},
{
"epoch": 0.27119779024022767,
"grad_norm": 0.33529049158096313,
"learning_rate": 2e-05,
"loss": 0.6784,
"step": 3240
},
{
"epoch": 0.2720348204570185,
"grad_norm": 0.34509772062301636,
"learning_rate": 2e-05,
"loss": 0.7474,
"step": 3250
},
{
"epoch": 0.2728718506738093,
"grad_norm": 0.3847754895687103,
"learning_rate": 2e-05,
"loss": 0.6765,
"step": 3260
},
{
"epoch": 0.27370888089060014,
"grad_norm": 0.38386350870132446,
"learning_rate": 2e-05,
"loss": 0.6782,
"step": 3270
},
{
"epoch": 0.27454591110739096,
"grad_norm": 0.4805894196033478,
"learning_rate": 2e-05,
"loss": 0.6864,
"step": 3280
},
{
"epoch": 0.2753829413241818,
"grad_norm": 0.46428972482681274,
"learning_rate": 2e-05,
"loss": 0.6901,
"step": 3290
},
{
"epoch": 0.2762199715409726,
"grad_norm": 0.3913302719593048,
"learning_rate": 2e-05,
"loss": 0.7239,
"step": 3300
},
{
"epoch": 0.27705700175776343,
"grad_norm": 0.3995335102081299,
"learning_rate": 2e-05,
"loss": 0.6828,
"step": 3310
},
{
"epoch": 0.27789403197455426,
"grad_norm": 0.36607876420021057,
"learning_rate": 2e-05,
"loss": 0.6621,
"step": 3320
},
{
"epoch": 0.2787310621913451,
"grad_norm": 0.38472291827201843,
"learning_rate": 2e-05,
"loss": 0.6712,
"step": 3330
},
{
"epoch": 0.27956809240813596,
"grad_norm": 0.34564754366874695,
"learning_rate": 2e-05,
"loss": 0.6863,
"step": 3340
},
{
"epoch": 0.2804051226249268,
"grad_norm": 0.3804911673069,
"learning_rate": 2e-05,
"loss": 0.7107,
"step": 3350
},
{
"epoch": 0.2812421528417176,
"grad_norm": 0.3177351653575897,
"learning_rate": 2e-05,
"loss": 0.6595,
"step": 3360
},
{
"epoch": 0.28207918305850843,
"grad_norm": 0.3490181863307953,
"learning_rate": 2e-05,
"loss": 0.6671,
"step": 3370
},
{
"epoch": 0.28291621327529926,
"grad_norm": 0.5247802734375,
"learning_rate": 2e-05,
"loss": 0.6614,
"step": 3380
},
{
"epoch": 0.2837532434920901,
"grad_norm": 0.36323365569114685,
"learning_rate": 2e-05,
"loss": 0.684,
"step": 3390
},
{
"epoch": 0.2845902737088809,
"grad_norm": 0.359318345785141,
"learning_rate": 2e-05,
"loss": 0.661,
"step": 3400
},
{
"epoch": 0.2854273039256717,
"grad_norm": 0.3711358308792114,
"learning_rate": 2e-05,
"loss": 0.6748,
"step": 3410
},
{
"epoch": 0.28626433414246255,
"grad_norm": 0.36873385310173035,
"learning_rate": 2e-05,
"loss": 0.6655,
"step": 3420
},
{
"epoch": 0.2871013643592534,
"grad_norm": 0.398560494184494,
"learning_rate": 2e-05,
"loss": 0.6624,
"step": 3430
},
{
"epoch": 0.2879383945760442,
"grad_norm": 0.48586469888687134,
"learning_rate": 2e-05,
"loss": 0.6993,
"step": 3440
},
{
"epoch": 0.288775424792835,
"grad_norm": 0.3617458641529083,
"learning_rate": 2e-05,
"loss": 0.6928,
"step": 3450
},
{
"epoch": 0.28961245500962585,
"grad_norm": 0.3452693521976471,
"learning_rate": 2e-05,
"loss": 0.6965,
"step": 3460
},
{
"epoch": 0.29044948522641667,
"grad_norm": 0.39020127058029175,
"learning_rate": 2e-05,
"loss": 0.691,
"step": 3470
},
{
"epoch": 0.2912865154432075,
"grad_norm": 0.38490548729896545,
"learning_rate": 2e-05,
"loss": 0.6824,
"step": 3480
},
{
"epoch": 0.2921235456599983,
"grad_norm": 0.3624000549316406,
"learning_rate": 2e-05,
"loss": 0.6849,
"step": 3490
},
{
"epoch": 0.29296057587678914,
"grad_norm": 0.40137097239494324,
"learning_rate": 2e-05,
"loss": 0.6779,
"step": 3500
},
{
"epoch": 0.29379760609357997,
"grad_norm": 0.3723010718822479,
"learning_rate": 2e-05,
"loss": 0.6639,
"step": 3510
},
{
"epoch": 0.2946346363103708,
"grad_norm": 0.33410966396331787,
"learning_rate": 2e-05,
"loss": 0.6849,
"step": 3520
},
{
"epoch": 0.2954716665271616,
"grad_norm": 0.4087796211242676,
"learning_rate": 2e-05,
"loss": 0.7198,
"step": 3530
},
{
"epoch": 0.29630869674395244,
"grad_norm": 0.3803013265132904,
"learning_rate": 2e-05,
"loss": 0.6705,
"step": 3540
},
{
"epoch": 0.29714572696074326,
"grad_norm": 0.38683268427848816,
"learning_rate": 2e-05,
"loss": 0.6848,
"step": 3550
},
{
"epoch": 0.2979827571775341,
"grad_norm": 0.3987625241279602,
"learning_rate": 2e-05,
"loss": 0.693,
"step": 3560
},
{
"epoch": 0.2988197873943249,
"grad_norm": 0.3848333954811096,
"learning_rate": 2e-05,
"loss": 0.691,
"step": 3570
},
{
"epoch": 0.2996568176111158,
"grad_norm": 0.3905976116657257,
"learning_rate": 2e-05,
"loss": 0.6745,
"step": 3580
},
{
"epoch": 0.3004938478279066,
"grad_norm": 0.36275070905685425,
"learning_rate": 2e-05,
"loss": 0.6693,
"step": 3590
},
{
"epoch": 0.30133087804469744,
"grad_norm": 0.3495936691761017,
"learning_rate": 2e-05,
"loss": 0.6845,
"step": 3600
},
{
"epoch": 0.30216790826148826,
"grad_norm": 0.36721131205558777,
"learning_rate": 2e-05,
"loss": 0.6807,
"step": 3610
},
{
"epoch": 0.3030049384782791,
"grad_norm": 0.42015427350997925,
"learning_rate": 2e-05,
"loss": 0.6934,
"step": 3620
},
{
"epoch": 0.3038419686950699,
"grad_norm": 0.41565388441085815,
"learning_rate": 2e-05,
"loss": 0.6817,
"step": 3630
},
{
"epoch": 0.30467899891186073,
"grad_norm": 0.3864046633243561,
"learning_rate": 2e-05,
"loss": 0.6972,
"step": 3640
},
{
"epoch": 0.30551602912865156,
"grad_norm": 0.3387700021266937,
"learning_rate": 2e-05,
"loss": 0.6753,
"step": 3650
},
{
"epoch": 0.3063530593454424,
"grad_norm": 0.37594422698020935,
"learning_rate": 2e-05,
"loss": 0.6808,
"step": 3660
},
{
"epoch": 0.3071900895622332,
"grad_norm": 0.3680058419704437,
"learning_rate": 2e-05,
"loss": 0.6924,
"step": 3670
},
{
"epoch": 0.30802711977902403,
"grad_norm": 0.37362930178642273,
"learning_rate": 2e-05,
"loss": 0.6598,
"step": 3680
},
{
"epoch": 0.30886414999581485,
"grad_norm": 0.3793889880180359,
"learning_rate": 2e-05,
"loss": 0.6754,
"step": 3690
},
{
"epoch": 0.3097011802126057,
"grad_norm": 0.35503870248794556,
"learning_rate": 2e-05,
"loss": 0.6834,
"step": 3700
},
{
"epoch": 0.3105382104293965,
"grad_norm": 0.3719038665294647,
"learning_rate": 2e-05,
"loss": 0.6721,
"step": 3710
},
{
"epoch": 0.3113752406461873,
"grad_norm": 0.38428905606269836,
"learning_rate": 2e-05,
"loss": 0.6499,
"step": 3720
},
{
"epoch": 0.31221227086297815,
"grad_norm": 0.374455988407135,
"learning_rate": 2e-05,
"loss": 0.657,
"step": 3730
},
{
"epoch": 0.31304930107976897,
"grad_norm": 0.37055298686027527,
"learning_rate": 2e-05,
"loss": 0.691,
"step": 3740
},
{
"epoch": 0.3138863312965598,
"grad_norm": 0.37087371945381165,
"learning_rate": 2e-05,
"loss": 0.6859,
"step": 3750
},
{
"epoch": 0.3147233615133506,
"grad_norm": 0.44824519753456116,
"learning_rate": 2e-05,
"loss": 0.689,
"step": 3760
},
{
"epoch": 0.31556039173014144,
"grad_norm": 0.40546661615371704,
"learning_rate": 2e-05,
"loss": 0.6715,
"step": 3770
},
{
"epoch": 0.31639742194693227,
"grad_norm": 0.39258283376693726,
"learning_rate": 2e-05,
"loss": 0.6877,
"step": 3780
},
{
"epoch": 0.3172344521637231,
"grad_norm": 0.36289212107658386,
"learning_rate": 2e-05,
"loss": 0.6668,
"step": 3790
},
{
"epoch": 0.3180714823805139,
"grad_norm": 0.40301036834716797,
"learning_rate": 2e-05,
"loss": 0.6785,
"step": 3800
},
{
"epoch": 0.31890851259730474,
"grad_norm": 0.3613869249820709,
"learning_rate": 2e-05,
"loss": 0.6792,
"step": 3810
},
{
"epoch": 0.31974554281409556,
"grad_norm": 0.3650999069213867,
"learning_rate": 2e-05,
"loss": 0.6548,
"step": 3820
},
{
"epoch": 0.32058257303088644,
"grad_norm": 0.38625913858413696,
"learning_rate": 2e-05,
"loss": 0.63,
"step": 3830
},
{
"epoch": 0.32141960324767727,
"grad_norm": 0.35693198442459106,
"learning_rate": 2e-05,
"loss": 0.6974,
"step": 3840
},
{
"epoch": 0.3222566334644681,
"grad_norm": 0.3826311230659485,
"learning_rate": 2e-05,
"loss": 0.6842,
"step": 3850
},
{
"epoch": 0.3230936636812589,
"grad_norm": 0.3499303162097931,
"learning_rate": 2e-05,
"loss": 0.667,
"step": 3860
},
{
"epoch": 0.32393069389804974,
"grad_norm": 0.33624884486198425,
"learning_rate": 2e-05,
"loss": 0.6643,
"step": 3870
},
{
"epoch": 0.32476772411484056,
"grad_norm": 0.4605383574962616,
"learning_rate": 2e-05,
"loss": 0.6631,
"step": 3880
},
{
"epoch": 0.3256047543316314,
"grad_norm": 0.3703138828277588,
"learning_rate": 2e-05,
"loss": 0.7092,
"step": 3890
},
{
"epoch": 0.3264417845484222,
"grad_norm": 0.3547705411911011,
"learning_rate": 2e-05,
"loss": 0.674,
"step": 3900
},
{
"epoch": 0.32727881476521303,
"grad_norm": 0.38592010736465454,
"learning_rate": 2e-05,
"loss": 0.729,
"step": 3910
},
{
"epoch": 0.32811584498200386,
"grad_norm": 0.38469675183296204,
"learning_rate": 2e-05,
"loss": 0.6379,
"step": 3920
},
{
"epoch": 0.3289528751987947,
"grad_norm": 0.38590508699417114,
"learning_rate": 2e-05,
"loss": 0.6671,
"step": 3930
},
{
"epoch": 0.3297899054155855,
"grad_norm": 0.4092082381248474,
"learning_rate": 2e-05,
"loss": 0.7011,
"step": 3940
},
{
"epoch": 0.33062693563237633,
"grad_norm": 0.3793179988861084,
"learning_rate": 2e-05,
"loss": 0.6973,
"step": 3950
},
{
"epoch": 0.33146396584916715,
"grad_norm": 0.38254857063293457,
"learning_rate": 2e-05,
"loss": 0.6909,
"step": 3960
},
{
"epoch": 0.332300996065958,
"grad_norm": 0.3839905261993408,
"learning_rate": 2e-05,
"loss": 0.6891,
"step": 3970
},
{
"epoch": 0.3331380262827488,
"grad_norm": 0.38743963837623596,
"learning_rate": 2e-05,
"loss": 0.7079,
"step": 3980
},
{
"epoch": 0.3339750564995396,
"grad_norm": 0.381570965051651,
"learning_rate": 2e-05,
"loss": 0.7051,
"step": 3990
},
{
"epoch": 0.33481208671633045,
"grad_norm": 0.3812105059623718,
"learning_rate": 2e-05,
"loss": 0.6781,
"step": 4000
},
{
"epoch": 0.33564911693312127,
"grad_norm": 0.3621882200241089,
"learning_rate": 2e-05,
"loss": 0.6923,
"step": 4010
},
{
"epoch": 0.3364861471499121,
"grad_norm": 0.35323214530944824,
"learning_rate": 2e-05,
"loss": 0.6851,
"step": 4020
},
{
"epoch": 0.3373231773667029,
"grad_norm": 0.35751551389694214,
"learning_rate": 2e-05,
"loss": 0.6655,
"step": 4030
},
{
"epoch": 0.33816020758349374,
"grad_norm": 0.3949991464614868,
"learning_rate": 2e-05,
"loss": 0.6621,
"step": 4040
},
{
"epoch": 0.33899723780028457,
"grad_norm": 0.3553832173347473,
"learning_rate": 2e-05,
"loss": 0.7026,
"step": 4050
},
{
"epoch": 0.3398342680170754,
"grad_norm": 0.39129525423049927,
"learning_rate": 2e-05,
"loss": 0.6727,
"step": 4060
},
{
"epoch": 0.3406712982338662,
"grad_norm": 0.39109840989112854,
"learning_rate": 2e-05,
"loss": 0.692,
"step": 4070
},
{
"epoch": 0.3415083284506571,
"grad_norm": 0.384739488363266,
"learning_rate": 2e-05,
"loss": 0.6578,
"step": 4080
},
{
"epoch": 0.3423453586674479,
"grad_norm": 0.34750863909721375,
"learning_rate": 2e-05,
"loss": 0.6972,
"step": 4090
},
{
"epoch": 0.34318238888423874,
"grad_norm": 0.3817720115184784,
"learning_rate": 2e-05,
"loss": 0.6563,
"step": 4100
},
{
"epoch": 0.34401941910102957,
"grad_norm": 0.38964515924453735,
"learning_rate": 2e-05,
"loss": 0.6591,
"step": 4110
},
{
"epoch": 0.3448564493178204,
"grad_norm": 0.38531047105789185,
"learning_rate": 2e-05,
"loss": 0.6475,
"step": 4120
},
{
"epoch": 0.3456934795346112,
"grad_norm": 0.4181869626045227,
"learning_rate": 2e-05,
"loss": 0.6746,
"step": 4130
},
{
"epoch": 0.34653050975140204,
"grad_norm": 0.36208441853523254,
"learning_rate": 2e-05,
"loss": 0.6825,
"step": 4140
},
{
"epoch": 0.34736753996819286,
"grad_norm": 0.3654119074344635,
"learning_rate": 2e-05,
"loss": 0.6887,
"step": 4150
},
{
"epoch": 0.3482045701849837,
"grad_norm": 0.39477288722991943,
"learning_rate": 2e-05,
"loss": 0.6977,
"step": 4160
},
{
"epoch": 0.3490416004017745,
"grad_norm": 0.36870384216308594,
"learning_rate": 2e-05,
"loss": 0.6725,
"step": 4170
},
{
"epoch": 0.34987863061856533,
"grad_norm": 0.35877320170402527,
"learning_rate": 2e-05,
"loss": 0.679,
"step": 4180
},
{
"epoch": 0.35071566083535616,
"grad_norm": 0.5562852621078491,
"learning_rate": 2e-05,
"loss": 0.6439,
"step": 4190
},
{
"epoch": 0.351552691052147,
"grad_norm": 0.40305373072624207,
"learning_rate": 2e-05,
"loss": 0.703,
"step": 4200
},
{
"epoch": 0.3523897212689378,
"grad_norm": 0.41178417205810547,
"learning_rate": 2e-05,
"loss": 0.6618,
"step": 4210
},
{
"epoch": 0.35322675148572863,
"grad_norm": 0.3854200541973114,
"learning_rate": 2e-05,
"loss": 0.6662,
"step": 4220
},
{
"epoch": 0.35406378170251945,
"grad_norm": 0.3953651487827301,
"learning_rate": 2e-05,
"loss": 0.7133,
"step": 4230
},
{
"epoch": 0.3549008119193103,
"grad_norm": 0.3878295123577118,
"learning_rate": 2e-05,
"loss": 0.701,
"step": 4240
},
{
"epoch": 0.3557378421361011,
"grad_norm": 0.36245018243789673,
"learning_rate": 2e-05,
"loss": 0.6104,
"step": 4250
},
{
"epoch": 0.3565748723528919,
"grad_norm": 0.3872743844985962,
"learning_rate": 2e-05,
"loss": 0.6878,
"step": 4260
},
{
"epoch": 0.35741190256968275,
"grad_norm": 0.4376787543296814,
"learning_rate": 2e-05,
"loss": 0.6741,
"step": 4270
},
{
"epoch": 0.3582489327864736,
"grad_norm": 0.5118808150291443,
"learning_rate": 2e-05,
"loss": 0.7126,
"step": 4280
},
{
"epoch": 0.3590859630032644,
"grad_norm": 0.35995811223983765,
"learning_rate": 2e-05,
"loss": 0.6814,
"step": 4290
},
{
"epoch": 0.3599229932200552,
"grad_norm": 0.32932382822036743,
"learning_rate": 2e-05,
"loss": 0.6686,
"step": 4300
},
{
"epoch": 0.36076002343684604,
"grad_norm": 0.3927007019519806,
"learning_rate": 2e-05,
"loss": 0.6526,
"step": 4310
},
{
"epoch": 0.3615970536536369,
"grad_norm": 0.3740251958370209,
"learning_rate": 2e-05,
"loss": 0.6658,
"step": 4320
},
{
"epoch": 0.36243408387042775,
"grad_norm": 0.3808770477771759,
"learning_rate": 2e-05,
"loss": 0.6923,
"step": 4330
},
{
"epoch": 0.36327111408721857,
"grad_norm": 0.3733738660812378,
"learning_rate": 2e-05,
"loss": 0.6758,
"step": 4340
},
{
"epoch": 0.3641081443040094,
"grad_norm": 0.36265361309051514,
"learning_rate": 2e-05,
"loss": 0.6714,
"step": 4350
},
{
"epoch": 0.3649451745208002,
"grad_norm": 0.37637802958488464,
"learning_rate": 2e-05,
"loss": 0.7047,
"step": 4360
},
{
"epoch": 0.36578220473759104,
"grad_norm": 0.3615052402019501,
"learning_rate": 2e-05,
"loss": 0.6887,
"step": 4370
},
{
"epoch": 0.36661923495438187,
"grad_norm": 0.3507406413555145,
"learning_rate": 2e-05,
"loss": 0.6817,
"step": 4380
},
{
"epoch": 0.3674562651711727,
"grad_norm": 0.3859863579273224,
"learning_rate": 2e-05,
"loss": 0.6908,
"step": 4390
},
{
"epoch": 0.3682932953879635,
"grad_norm": 0.5150337815284729,
"learning_rate": 2e-05,
"loss": 0.6829,
"step": 4400
},
{
"epoch": 0.36913032560475434,
"grad_norm": 0.3702976107597351,
"learning_rate": 2e-05,
"loss": 0.6628,
"step": 4410
},
{
"epoch": 0.36996735582154516,
"grad_norm": 0.36254793405532837,
"learning_rate": 2e-05,
"loss": 0.6735,
"step": 4420
},
{
"epoch": 0.370804386038336,
"grad_norm": 0.3495381474494934,
"learning_rate": 2e-05,
"loss": 0.6815,
"step": 4430
},
{
"epoch": 0.3716414162551268,
"grad_norm": 0.3943999707698822,
"learning_rate": 2e-05,
"loss": 0.6797,
"step": 4440
},
{
"epoch": 0.37247844647191763,
"grad_norm": 0.3715941905975342,
"learning_rate": 2e-05,
"loss": 0.6615,
"step": 4450
},
{
"epoch": 0.37331547668870846,
"grad_norm": 0.47644540667533875,
"learning_rate": 2e-05,
"loss": 0.6901,
"step": 4460
},
{
"epoch": 0.3741525069054993,
"grad_norm": 0.40302789211273193,
"learning_rate": 2e-05,
"loss": 0.6556,
"step": 4470
},
{
"epoch": 0.3749895371222901,
"grad_norm": 0.366240531206131,
"learning_rate": 2e-05,
"loss": 0.6787,
"step": 4480
},
{
"epoch": 0.37582656733908093,
"grad_norm": 0.3775447607040405,
"learning_rate": 2e-05,
"loss": 0.6518,
"step": 4490
},
{
"epoch": 0.37666359755587175,
"grad_norm": 0.3555198609828949,
"learning_rate": 2e-05,
"loss": 0.6844,
"step": 4500
},
{
"epoch": 0.3775006277726626,
"grad_norm": 0.40677034854888916,
"learning_rate": 2e-05,
"loss": 0.6899,
"step": 4510
},
{
"epoch": 0.3783376579894534,
"grad_norm": 0.33568084239959717,
"learning_rate": 2e-05,
"loss": 0.6329,
"step": 4520
},
{
"epoch": 0.3791746882062442,
"grad_norm": 0.4298158586025238,
"learning_rate": 2e-05,
"loss": 0.6856,
"step": 4530
},
{
"epoch": 0.38001171842303505,
"grad_norm": 0.3619917333126068,
"learning_rate": 2e-05,
"loss": 0.655,
"step": 4540
},
{
"epoch": 0.3808487486398259,
"grad_norm": 0.34173473715782166,
"learning_rate": 2e-05,
"loss": 0.6386,
"step": 4550
},
{
"epoch": 0.3816857788566167,
"grad_norm": 0.41530799865722656,
"learning_rate": 2e-05,
"loss": 0.6436,
"step": 4560
},
{
"epoch": 0.3825228090734076,
"grad_norm": 0.3594314455986023,
"learning_rate": 2e-05,
"loss": 0.6765,
"step": 4570
},
{
"epoch": 0.3833598392901984,
"grad_norm": 0.3838607370853424,
"learning_rate": 2e-05,
"loss": 0.656,
"step": 4580
},
{
"epoch": 0.3841968695069892,
"grad_norm": 0.3307185769081116,
"learning_rate": 2e-05,
"loss": 0.6976,
"step": 4590
},
{
"epoch": 0.38503389972378005,
"grad_norm": 0.4034730792045593,
"learning_rate": 2e-05,
"loss": 0.6824,
"step": 4600
},
{
"epoch": 0.3858709299405709,
"grad_norm": 0.38577455282211304,
"learning_rate": 2e-05,
"loss": 0.6516,
"step": 4610
},
{
"epoch": 0.3867079601573617,
"grad_norm": 0.3357555568218231,
"learning_rate": 2e-05,
"loss": 0.645,
"step": 4620
},
{
"epoch": 0.3875449903741525,
"grad_norm": 0.37598440051078796,
"learning_rate": 2e-05,
"loss": 0.7059,
"step": 4630
},
{
"epoch": 0.38838202059094334,
"grad_norm": 0.3609393239021301,
"learning_rate": 2e-05,
"loss": 0.669,
"step": 4640
},
{
"epoch": 0.38921905080773417,
"grad_norm": 0.3757115304470062,
"learning_rate": 2e-05,
"loss": 0.6395,
"step": 4650
},
{
"epoch": 0.390056081024525,
"grad_norm": 0.36719217896461487,
"learning_rate": 2e-05,
"loss": 0.6744,
"step": 4660
},
{
"epoch": 0.3908931112413158,
"grad_norm": 0.36577510833740234,
"learning_rate": 2e-05,
"loss": 0.6851,
"step": 4670
},
{
"epoch": 0.39173014145810664,
"grad_norm": 0.36640894412994385,
"learning_rate": 2e-05,
"loss": 0.6627,
"step": 4680
},
{
"epoch": 0.39256717167489746,
"grad_norm": 0.3786374628543854,
"learning_rate": 2e-05,
"loss": 0.6888,
"step": 4690
},
{
"epoch": 0.3934042018916883,
"grad_norm": 0.3693200349807739,
"learning_rate": 2e-05,
"loss": 0.6608,
"step": 4700
},
{
"epoch": 0.3942412321084791,
"grad_norm": 0.35623887181282043,
"learning_rate": 2e-05,
"loss": 0.6913,
"step": 4710
},
{
"epoch": 0.39507826232526994,
"grad_norm": 0.37266993522644043,
"learning_rate": 2e-05,
"loss": 0.6216,
"step": 4720
},
{
"epoch": 0.39591529254206076,
"grad_norm": 0.48957139253616333,
"learning_rate": 2e-05,
"loss": 0.6577,
"step": 4730
},
{
"epoch": 0.3967523227588516,
"grad_norm": 0.361542284488678,
"learning_rate": 2e-05,
"loss": 0.6707,
"step": 4740
},
{
"epoch": 0.3975893529756424,
"grad_norm": 0.3781006932258606,
"learning_rate": 2e-05,
"loss": 0.6729,
"step": 4750
},
{
"epoch": 0.39842638319243323,
"grad_norm": 0.3931069076061249,
"learning_rate": 2e-05,
"loss": 0.6626,
"step": 4760
},
{
"epoch": 0.39926341340922405,
"grad_norm": 0.3622207045555115,
"learning_rate": 2e-05,
"loss": 0.6719,
"step": 4770
},
{
"epoch": 0.4001004436260149,
"grad_norm": 0.43951886892318726,
"learning_rate": 2e-05,
"loss": 0.6866,
"step": 4780
},
{
"epoch": 0.4009374738428057,
"grad_norm": 0.36725106835365295,
"learning_rate": 2e-05,
"loss": 0.6412,
"step": 4790
},
{
"epoch": 0.4017745040595965,
"grad_norm": 0.3468758761882782,
"learning_rate": 2e-05,
"loss": 0.656,
"step": 4800
},
{
"epoch": 0.40261153427638735,
"grad_norm": 0.3753811717033386,
"learning_rate": 2e-05,
"loss": 0.674,
"step": 4810
},
{
"epoch": 0.40344856449317823,
"grad_norm": 0.35826578736305237,
"learning_rate": 2e-05,
"loss": 0.6671,
"step": 4820
},
{
"epoch": 0.40428559470996905,
"grad_norm": 0.5122092962265015,
"learning_rate": 2e-05,
"loss": 0.68,
"step": 4830
},
{
"epoch": 0.4051226249267599,
"grad_norm": 0.34622722864151,
"learning_rate": 2e-05,
"loss": 0.6371,
"step": 4840
},
{
"epoch": 0.4059596551435507,
"grad_norm": 0.354408323764801,
"learning_rate": 2e-05,
"loss": 0.6516,
"step": 4850
},
{
"epoch": 0.4067966853603415,
"grad_norm": 0.3598283529281616,
"learning_rate": 2e-05,
"loss": 0.6357,
"step": 4860
},
{
"epoch": 0.40763371557713235,
"grad_norm": 0.34254366159439087,
"learning_rate": 2e-05,
"loss": 0.6617,
"step": 4870
},
{
"epoch": 0.4084707457939232,
"grad_norm": 0.4542747437953949,
"learning_rate": 2e-05,
"loss": 0.6532,
"step": 4880
},
{
"epoch": 0.409307776010714,
"grad_norm": 0.35308054089546204,
"learning_rate": 2e-05,
"loss": 0.6558,
"step": 4890
},
{
"epoch": 0.4101448062275048,
"grad_norm": 0.37054240703582764,
"learning_rate": 2e-05,
"loss": 0.6681,
"step": 4900
},
{
"epoch": 0.41098183644429565,
"grad_norm": 0.3926886022090912,
"learning_rate": 2e-05,
"loss": 0.6739,
"step": 4910
},
{
"epoch": 0.41181886666108647,
"grad_norm": 0.4271712601184845,
"learning_rate": 2e-05,
"loss": 0.655,
"step": 4920
},
{
"epoch": 0.4126558968778773,
"grad_norm": 0.4078362286090851,
"learning_rate": 2e-05,
"loss": 0.5931,
"step": 4930
},
{
"epoch": 0.4134929270946681,
"grad_norm": 0.3612181544303894,
"learning_rate": 2e-05,
"loss": 0.6747,
"step": 4940
},
{
"epoch": 0.41432995731145894,
"grad_norm": 0.36205559968948364,
"learning_rate": 2e-05,
"loss": 0.6643,
"step": 4950
},
{
"epoch": 0.41516698752824976,
"grad_norm": 0.33852431178092957,
"learning_rate": 2e-05,
"loss": 0.6516,
"step": 4960
},
{
"epoch": 0.4160040177450406,
"grad_norm": 0.360599160194397,
"learning_rate": 2e-05,
"loss": 0.6424,
"step": 4970
},
{
"epoch": 0.4168410479618314,
"grad_norm": 0.3367842733860016,
"learning_rate": 2e-05,
"loss": 0.6583,
"step": 4980
},
{
"epoch": 0.41767807817862224,
"grad_norm": 0.37129393219947815,
"learning_rate": 2e-05,
"loss": 0.6406,
"step": 4990
},
{
"epoch": 0.41851510839541306,
"grad_norm": 0.40336930751800537,
"learning_rate": 2e-05,
"loss": 0.6615,
"step": 5000
},
{
"epoch": 0.4193521386122039,
"grad_norm": 0.3625902831554413,
"learning_rate": 2e-05,
"loss": 0.6726,
"step": 5010
},
{
"epoch": 0.4201891688289947,
"grad_norm": 0.3696928322315216,
"learning_rate": 2e-05,
"loss": 0.6929,
"step": 5020
},
{
"epoch": 0.42102619904578553,
"grad_norm": 0.35005995631217957,
"learning_rate": 2e-05,
"loss": 0.6734,
"step": 5030
},
{
"epoch": 0.42186322926257636,
"grad_norm": 0.3266897201538086,
"learning_rate": 2e-05,
"loss": 0.6882,
"step": 5040
},
{
"epoch": 0.4227002594793672,
"grad_norm": 0.4611261188983917,
"learning_rate": 2e-05,
"loss": 0.7007,
"step": 5050
},
{
"epoch": 0.423537289696158,
"grad_norm": 0.39426982402801514,
"learning_rate": 2e-05,
"loss": 0.6638,
"step": 5060
},
{
"epoch": 0.4243743199129489,
"grad_norm": 0.3529796302318573,
"learning_rate": 2e-05,
"loss": 0.6559,
"step": 5070
},
{
"epoch": 0.4252113501297397,
"grad_norm": 0.39787614345550537,
"learning_rate": 2e-05,
"loss": 0.6387,
"step": 5080
},
{
"epoch": 0.42604838034653053,
"grad_norm": 0.3513227701187134,
"learning_rate": 2e-05,
"loss": 0.6614,
"step": 5090
},
{
"epoch": 0.42688541056332135,
"grad_norm": 0.39367735385894775,
"learning_rate": 2e-05,
"loss": 0.6512,
"step": 5100
},
{
"epoch": 0.4277224407801122,
"grad_norm": 0.39242255687713623,
"learning_rate": 2e-05,
"loss": 0.6726,
"step": 5110
},
{
"epoch": 0.428559470996903,
"grad_norm": 0.39294275641441345,
"learning_rate": 2e-05,
"loss": 0.6721,
"step": 5120
},
{
"epoch": 0.4293965012136938,
"grad_norm": 0.4447023570537567,
"learning_rate": 2e-05,
"loss": 0.6925,
"step": 5130
},
{
"epoch": 0.43023353143048465,
"grad_norm": 0.5347163677215576,
"learning_rate": 2e-05,
"loss": 0.6567,
"step": 5140
},
{
"epoch": 0.4310705616472755,
"grad_norm": 0.37236112356185913,
"learning_rate": 2e-05,
"loss": 0.6532,
"step": 5150
},
{
"epoch": 0.4319075918640663,
"grad_norm": 0.3528517484664917,
"learning_rate": 2e-05,
"loss": 0.6436,
"step": 5160
},
{
"epoch": 0.4327446220808571,
"grad_norm": 0.4381149709224701,
"learning_rate": 2e-05,
"loss": 0.6462,
"step": 5170
},
{
"epoch": 0.43358165229764795,
"grad_norm": 0.34845399856567383,
"learning_rate": 2e-05,
"loss": 0.6879,
"step": 5180
},
{
"epoch": 0.43441868251443877,
"grad_norm": 0.3650329113006592,
"learning_rate": 2e-05,
"loss": 0.6796,
"step": 5190
},
{
"epoch": 0.4352557127312296,
"grad_norm": 0.3584339916706085,
"learning_rate": 2e-05,
"loss": 0.6738,
"step": 5200
},
{
"epoch": 0.4360927429480204,
"grad_norm": 0.3829450309276581,
"learning_rate": 2e-05,
"loss": 0.642,
"step": 5210
},
{
"epoch": 0.43692977316481124,
"grad_norm": 0.3501336872577667,
"learning_rate": 2e-05,
"loss": 0.6659,
"step": 5220
},
{
"epoch": 0.43776680338160207,
"grad_norm": 0.36899852752685547,
"learning_rate": 2e-05,
"loss": 0.6634,
"step": 5230
},
{
"epoch": 0.4386038335983929,
"grad_norm": 0.35678166151046753,
"learning_rate": 2e-05,
"loss": 0.6384,
"step": 5240
},
{
"epoch": 0.4394408638151837,
"grad_norm": 0.3652724027633667,
"learning_rate": 2e-05,
"loss": 0.6173,
"step": 5250
},
{
"epoch": 0.44027789403197454,
"grad_norm": 0.38767310976982117,
"learning_rate": 2e-05,
"loss": 0.6758,
"step": 5260
},
{
"epoch": 0.44111492424876536,
"grad_norm": 0.33291152119636536,
"learning_rate": 2e-05,
"loss": 0.6699,
"step": 5270
},
{
"epoch": 0.4419519544655562,
"grad_norm": 0.35918429493904114,
"learning_rate": 2e-05,
"loss": 0.6709,
"step": 5280
},
{
"epoch": 0.442788984682347,
"grad_norm": 0.35800132155418396,
"learning_rate": 2e-05,
"loss": 0.6714,
"step": 5290
},
{
"epoch": 0.44362601489913783,
"grad_norm": 0.35795432329177856,
"learning_rate": 2e-05,
"loss": 0.6521,
"step": 5300
},
{
"epoch": 0.4444630451159287,
"grad_norm": 0.3649119734764099,
"learning_rate": 2e-05,
"loss": 0.651,
"step": 5310
},
{
"epoch": 0.44530007533271954,
"grad_norm": 0.6159412264823914,
"learning_rate": 2e-05,
"loss": 0.6632,
"step": 5320
},
{
"epoch": 0.44613710554951036,
"grad_norm": 0.3722281754016876,
"learning_rate": 2e-05,
"loss": 0.6651,
"step": 5330
},
{
"epoch": 0.4469741357663012,
"grad_norm": 0.34443187713623047,
"learning_rate": 2e-05,
"loss": 0.633,
"step": 5340
},
{
"epoch": 0.447811165983092,
"grad_norm": 0.3489256799221039,
"learning_rate": 2e-05,
"loss": 0.6692,
"step": 5350
},
{
"epoch": 0.44864819619988283,
"grad_norm": 0.3537524938583374,
"learning_rate": 2e-05,
"loss": 0.6598,
"step": 5360
},
{
"epoch": 0.44948522641667366,
"grad_norm": 0.35627481341362,
"learning_rate": 2e-05,
"loss": 0.6573,
"step": 5370
},
{
"epoch": 0.4503222566334645,
"grad_norm": 0.3463481068611145,
"learning_rate": 2e-05,
"loss": 0.6825,
"step": 5380
},
{
"epoch": 0.4511592868502553,
"grad_norm": 0.3670712411403656,
"learning_rate": 2e-05,
"loss": 0.6482,
"step": 5390
},
{
"epoch": 0.4519963170670461,
"grad_norm": 0.5201845169067383,
"learning_rate": 2e-05,
"loss": 0.6882,
"step": 5400
},
{
"epoch": 0.45283334728383695,
"grad_norm": 0.3747744858264923,
"learning_rate": 2e-05,
"loss": 0.6782,
"step": 5410
},
{
"epoch": 0.4536703775006278,
"grad_norm": 0.37223178148269653,
"learning_rate": 2e-05,
"loss": 0.6764,
"step": 5420
},
{
"epoch": 0.4545074077174186,
"grad_norm": 0.40864551067352295,
"learning_rate": 2e-05,
"loss": 0.6666,
"step": 5430
},
{
"epoch": 0.4553444379342094,
"grad_norm": 0.36135533452033997,
"learning_rate": 2e-05,
"loss": 0.6409,
"step": 5440
},
{
"epoch": 0.45618146815100025,
"grad_norm": 0.3873385190963745,
"learning_rate": 2e-05,
"loss": 0.6865,
"step": 5450
},
{
"epoch": 0.45701849836779107,
"grad_norm": 0.3834053874015808,
"learning_rate": 2e-05,
"loss": 0.6489,
"step": 5460
},
{
"epoch": 0.4578555285845819,
"grad_norm": 0.3461966812610626,
"learning_rate": 2e-05,
"loss": 0.6953,
"step": 5470
},
{
"epoch": 0.4586925588013727,
"grad_norm": 0.38454338908195496,
"learning_rate": 2e-05,
"loss": 0.6603,
"step": 5480
},
{
"epoch": 0.45952958901816354,
"grad_norm": 0.3803924024105072,
"learning_rate": 2e-05,
"loss": 0.6822,
"step": 5490
},
{
"epoch": 0.46036661923495437,
"grad_norm": 0.38291850686073303,
"learning_rate": 2e-05,
"loss": 0.6249,
"step": 5500
},
{
"epoch": 0.4612036494517452,
"grad_norm": 0.3552491366863251,
"learning_rate": 2e-05,
"loss": 0.6551,
"step": 5510
},
{
"epoch": 0.462040679668536,
"grad_norm": 0.3963458836078644,
"learning_rate": 2e-05,
"loss": 0.6142,
"step": 5520
},
{
"epoch": 0.46287770988532684,
"grad_norm": 0.3606397807598114,
"learning_rate": 2e-05,
"loss": 0.6279,
"step": 5530
},
{
"epoch": 0.46371474010211766,
"grad_norm": 0.3819950819015503,
"learning_rate": 2e-05,
"loss": 0.6335,
"step": 5540
},
{
"epoch": 0.4645517703189085,
"grad_norm": 0.3351725935935974,
"learning_rate": 2e-05,
"loss": 0.6544,
"step": 5550
},
{
"epoch": 0.46538880053569937,
"grad_norm": 0.5290308594703674,
"learning_rate": 2e-05,
"loss": 0.6792,
"step": 5560
},
{
"epoch": 0.4662258307524902,
"grad_norm": 0.35919585824012756,
"learning_rate": 2e-05,
"loss": 0.6633,
"step": 5570
},
{
"epoch": 0.467062860969281,
"grad_norm": 0.37764254212379456,
"learning_rate": 2e-05,
"loss": 0.6464,
"step": 5580
},
{
"epoch": 0.46789989118607184,
"grad_norm": 0.3419042229652405,
"learning_rate": 2e-05,
"loss": 0.6482,
"step": 5590
},
{
"epoch": 0.46873692140286266,
"grad_norm": 0.36101606488227844,
"learning_rate": 2e-05,
"loss": 0.638,
"step": 5600
},
{
"epoch": 0.4695739516196535,
"grad_norm": 0.38443782925605774,
"learning_rate": 2e-05,
"loss": 0.6505,
"step": 5610
},
{
"epoch": 0.4704109818364443,
"grad_norm": 0.6685389280319214,
"learning_rate": 2e-05,
"loss": 0.6319,
"step": 5620
},
{
"epoch": 0.47124801205323513,
"grad_norm": 0.37761780619621277,
"learning_rate": 2e-05,
"loss": 0.6383,
"step": 5630
},
{
"epoch": 0.47208504227002596,
"grad_norm": 0.47527140378952026,
"learning_rate": 2e-05,
"loss": 0.6663,
"step": 5640
},
{
"epoch": 0.4729220724868168,
"grad_norm": 0.35319945216178894,
"learning_rate": 2e-05,
"loss": 0.6447,
"step": 5650
},
{
"epoch": 0.4737591027036076,
"grad_norm": 0.3519211411476135,
"learning_rate": 2e-05,
"loss": 0.6716,
"step": 5660
},
{
"epoch": 0.47459613292039843,
"grad_norm": 0.35968127846717834,
"learning_rate": 2e-05,
"loss": 0.6622,
"step": 5670
},
{
"epoch": 0.47543316313718925,
"grad_norm": 0.3681982457637787,
"learning_rate": 2e-05,
"loss": 0.6462,
"step": 5680
},
{
"epoch": 0.4762701933539801,
"grad_norm": 0.3889543414115906,
"learning_rate": 2e-05,
"loss": 0.6846,
"step": 5690
},
{
"epoch": 0.4771072235707709,
"grad_norm": 0.35321757197380066,
"learning_rate": 2e-05,
"loss": 0.6627,
"step": 5700
},
{
"epoch": 0.4779442537875617,
"grad_norm": 0.4116288721561432,
"learning_rate": 2e-05,
"loss": 0.6756,
"step": 5710
},
{
"epoch": 0.47878128400435255,
"grad_norm": 0.35536208748817444,
"learning_rate": 2e-05,
"loss": 0.6553,
"step": 5720
},
{
"epoch": 0.47961831422114337,
"grad_norm": 0.4066528081893921,
"learning_rate": 2e-05,
"loss": 0.6814,
"step": 5730
},
{
"epoch": 0.4804553444379342,
"grad_norm": 0.37721550464630127,
"learning_rate": 2e-05,
"loss": 0.6775,
"step": 5740
},
{
"epoch": 0.481292374654725,
"grad_norm": 0.35653671622276306,
"learning_rate": 2e-05,
"loss": 0.6605,
"step": 5750
},
{
"epoch": 0.48212940487151584,
"grad_norm": 0.34860867261886597,
"learning_rate": 2e-05,
"loss": 0.6523,
"step": 5760
},
{
"epoch": 0.48296643508830667,
"grad_norm": 0.47001925110816956,
"learning_rate": 2e-05,
"loss": 0.631,
"step": 5770
},
{
"epoch": 0.4838034653050975,
"grad_norm": 0.3418459892272949,
"learning_rate": 2e-05,
"loss": 0.6297,
"step": 5780
},
{
"epoch": 0.4846404955218883,
"grad_norm": 0.360967218875885,
"learning_rate": 2e-05,
"loss": 0.6264,
"step": 5790
},
{
"epoch": 0.48547752573867914,
"grad_norm": 0.3304743468761444,
"learning_rate": 2e-05,
"loss": 0.6555,
"step": 5800
},
{
"epoch": 0.48631455595547,
"grad_norm": 0.3925345540046692,
"learning_rate": 2e-05,
"loss": 0.666,
"step": 5810
},
{
"epoch": 0.48715158617226084,
"grad_norm": 0.4329330325126648,
"learning_rate": 2e-05,
"loss": 0.6844,
"step": 5820
},
{
"epoch": 0.48798861638905167,
"grad_norm": 0.35020846128463745,
"learning_rate": 2e-05,
"loss": 0.6724,
"step": 5830
},
{
"epoch": 0.4888256466058425,
"grad_norm": 0.3561979830265045,
"learning_rate": 2e-05,
"loss": 0.6577,
"step": 5840
},
{
"epoch": 0.4896626768226333,
"grad_norm": 0.38194599747657776,
"learning_rate": 2e-05,
"loss": 0.6604,
"step": 5850
},
{
"epoch": 0.49049970703942414,
"grad_norm": 0.36795371770858765,
"learning_rate": 2e-05,
"loss": 0.6936,
"step": 5860
},
{
"epoch": 0.49133673725621496,
"grad_norm": 0.3567444980144501,
"learning_rate": 2e-05,
"loss": 0.647,
"step": 5870
},
{
"epoch": 0.4921737674730058,
"grad_norm": 0.3601284325122833,
"learning_rate": 2e-05,
"loss": 0.6537,
"step": 5880
},
{
"epoch": 0.4930107976897966,
"grad_norm": 0.40184250473976135,
"learning_rate": 2e-05,
"loss": 0.6765,
"step": 5890
},
{
"epoch": 0.49384782790658743,
"grad_norm": 0.4098629653453827,
"learning_rate": 2e-05,
"loss": 0.6563,
"step": 5900
},
{
"epoch": 0.49468485812337826,
"grad_norm": 0.3989146053791046,
"learning_rate": 2e-05,
"loss": 0.6738,
"step": 5910
},
{
"epoch": 0.4955218883401691,
"grad_norm": 0.3967300057411194,
"learning_rate": 2e-05,
"loss": 0.6618,
"step": 5920
},
{
"epoch": 0.4963589185569599,
"grad_norm": 0.35535138845443726,
"learning_rate": 2e-05,
"loss": 0.6466,
"step": 5930
},
{
"epoch": 0.49719594877375073,
"grad_norm": 0.36962181329727173,
"learning_rate": 2e-05,
"loss": 0.6388,
"step": 5940
},
{
"epoch": 0.49803297899054155,
"grad_norm": 0.40621426701545715,
"learning_rate": 2e-05,
"loss": 0.6631,
"step": 5950
},
{
"epoch": 0.4988700092073324,
"grad_norm": 0.35730671882629395,
"learning_rate": 2e-05,
"loss": 0.6521,
"step": 5960
},
{
"epoch": 0.4997070394241232,
"grad_norm": 0.3682115077972412,
"learning_rate": 2e-05,
"loss": 0.647,
"step": 5970
},
{
"epoch": 0.500544069640914,
"grad_norm": 0.3790656328201294,
"learning_rate": 2e-05,
"loss": 0.6541,
"step": 5980
},
{
"epoch": 0.5013810998577048,
"grad_norm": 0.37468239665031433,
"learning_rate": 2e-05,
"loss": 0.6547,
"step": 5990
},
{
"epoch": 0.5022181300744957,
"grad_norm": 0.3356288969516754,
"learning_rate": 2e-05,
"loss": 0.6329,
"step": 6000
},
{
"epoch": 0.5030551602912865,
"grad_norm": 0.34511512517929077,
"learning_rate": 2e-05,
"loss": 0.6447,
"step": 6010
},
{
"epoch": 0.5038921905080773,
"grad_norm": 0.35576921701431274,
"learning_rate": 2e-05,
"loss": 0.6326,
"step": 6020
},
{
"epoch": 0.5047292207248681,
"grad_norm": 0.3609001338481903,
"learning_rate": 2e-05,
"loss": 0.6516,
"step": 6030
},
{
"epoch": 0.505566250941659,
"grad_norm": 0.3582797646522522,
"learning_rate": 2e-05,
"loss": 0.6685,
"step": 6040
},
{
"epoch": 0.5064032811584498,
"grad_norm": 0.34268200397491455,
"learning_rate": 2e-05,
"loss": 0.6524,
"step": 6050
},
{
"epoch": 0.5072403113752406,
"grad_norm": 0.3530672490596771,
"learning_rate": 2e-05,
"loss": 0.6696,
"step": 6060
},
{
"epoch": 0.5080773415920314,
"grad_norm": 0.34003183245658875,
"learning_rate": 2e-05,
"loss": 0.6457,
"step": 6070
},
{
"epoch": 0.5089143718088223,
"grad_norm": 0.3780054450035095,
"learning_rate": 2e-05,
"loss": 0.6252,
"step": 6080
},
{
"epoch": 0.5097514020256131,
"grad_norm": 0.43377479910850525,
"learning_rate": 2e-05,
"loss": 0.6606,
"step": 6090
},
{
"epoch": 0.5105884322424039,
"grad_norm": 0.37533921003341675,
"learning_rate": 2e-05,
"loss": 0.6162,
"step": 6100
},
{
"epoch": 0.5114254624591947,
"grad_norm": 0.34509313106536865,
"learning_rate": 2e-05,
"loss": 0.6542,
"step": 6110
},
{
"epoch": 0.5122624926759856,
"grad_norm": 0.39592641592025757,
"learning_rate": 2e-05,
"loss": 0.6309,
"step": 6120
},
{
"epoch": 0.5130995228927764,
"grad_norm": 0.3516509234905243,
"learning_rate": 2e-05,
"loss": 0.6412,
"step": 6130
},
{
"epoch": 0.5139365531095672,
"grad_norm": 0.35252875089645386,
"learning_rate": 2e-05,
"loss": 0.6741,
"step": 6140
},
{
"epoch": 0.514773583326358,
"grad_norm": 0.3630253076553345,
"learning_rate": 2e-05,
"loss": 0.67,
"step": 6150
},
{
"epoch": 0.5156106135431489,
"grad_norm": 0.4943890869617462,
"learning_rate": 2e-05,
"loss": 0.6496,
"step": 6160
},
{
"epoch": 0.5164476437599397,
"grad_norm": 0.38662484288215637,
"learning_rate": 2e-05,
"loss": 0.6599,
"step": 6170
},
{
"epoch": 0.5172846739767306,
"grad_norm": 0.39891964197158813,
"learning_rate": 2e-05,
"loss": 0.6473,
"step": 6180
},
{
"epoch": 0.5181217041935214,
"grad_norm": 0.3752380609512329,
"learning_rate": 2e-05,
"loss": 0.6669,
"step": 6190
},
{
"epoch": 0.5189587344103123,
"grad_norm": 0.3734413981437683,
"learning_rate": 2e-05,
"loss": 0.6671,
"step": 6200
},
{
"epoch": 0.5197957646271031,
"grad_norm": 0.3842720687389374,
"learning_rate": 2e-05,
"loss": 0.6205,
"step": 6210
},
{
"epoch": 0.5206327948438939,
"grad_norm": 0.3729918599128723,
"learning_rate": 2e-05,
"loss": 0.6299,
"step": 6220
},
{
"epoch": 0.5214698250606847,
"grad_norm": 0.3549349904060364,
"learning_rate": 2e-05,
"loss": 0.6658,
"step": 6230
},
{
"epoch": 0.5223068552774756,
"grad_norm": 0.3492337763309479,
"learning_rate": 2e-05,
"loss": 0.6511,
"step": 6240
},
{
"epoch": 0.5231438854942664,
"grad_norm": 0.3354603350162506,
"learning_rate": 2e-05,
"loss": 0.6369,
"step": 6250
},
{
"epoch": 0.5239809157110572,
"grad_norm": 0.36312589049339294,
"learning_rate": 2e-05,
"loss": 0.6517,
"step": 6260
},
{
"epoch": 0.524817945927848,
"grad_norm": 0.33643534779548645,
"learning_rate": 2e-05,
"loss": 0.631,
"step": 6270
},
{
"epoch": 0.5256549761446389,
"grad_norm": 0.3987065553665161,
"learning_rate": 2e-05,
"loss": 0.6539,
"step": 6280
},
{
"epoch": 0.5264920063614297,
"grad_norm": 0.3580562472343445,
"learning_rate": 2e-05,
"loss": 0.6565,
"step": 6290
},
{
"epoch": 0.5273290365782205,
"grad_norm": 0.39528289437294006,
"learning_rate": 2e-05,
"loss": 0.6317,
"step": 6300
},
{
"epoch": 0.5281660667950113,
"grad_norm": 0.35878393054008484,
"learning_rate": 2e-05,
"loss": 0.6521,
"step": 6310
},
{
"epoch": 0.5290030970118021,
"grad_norm": 0.3379558324813843,
"learning_rate": 2e-05,
"loss": 0.6624,
"step": 6320
},
{
"epoch": 0.529840127228593,
"grad_norm": 0.3982899785041809,
"learning_rate": 2e-05,
"loss": 0.6403,
"step": 6330
},
{
"epoch": 0.5306771574453838,
"grad_norm": 0.3709496259689331,
"learning_rate": 2e-05,
"loss": 0.6903,
"step": 6340
},
{
"epoch": 0.5315141876621746,
"grad_norm": 0.38068562746047974,
"learning_rate": 2e-05,
"loss": 0.6671,
"step": 6350
},
{
"epoch": 0.5323512178789654,
"grad_norm": 0.3703364133834839,
"learning_rate": 2e-05,
"loss": 0.6536,
"step": 6360
},
{
"epoch": 0.5331882480957563,
"grad_norm": 0.3773478865623474,
"learning_rate": 2e-05,
"loss": 0.6275,
"step": 6370
},
{
"epoch": 0.5340252783125471,
"grad_norm": 0.35488447546958923,
"learning_rate": 2e-05,
"loss": 0.6249,
"step": 6380
},
{
"epoch": 0.5348623085293379,
"grad_norm": 0.39066097140312195,
"learning_rate": 2e-05,
"loss": 0.6598,
"step": 6390
},
{
"epoch": 0.5356993387461287,
"grad_norm": 0.42319586873054504,
"learning_rate": 2e-05,
"loss": 0.6383,
"step": 6400
},
{
"epoch": 0.5365363689629196,
"grad_norm": 0.37875017523765564,
"learning_rate": 2e-05,
"loss": 0.6643,
"step": 6410
},
{
"epoch": 0.5373733991797104,
"grad_norm": 0.36670878529548645,
"learning_rate": 2e-05,
"loss": 0.6442,
"step": 6420
},
{
"epoch": 0.5382104293965012,
"grad_norm": 0.40315425395965576,
"learning_rate": 2e-05,
"loss": 0.6288,
"step": 6430
},
{
"epoch": 0.539047459613292,
"grad_norm": 0.37048014998435974,
"learning_rate": 2e-05,
"loss": 0.6387,
"step": 6440
},
{
"epoch": 0.5398844898300829,
"grad_norm": 0.34068137407302856,
"learning_rate": 2e-05,
"loss": 0.6582,
"step": 6450
},
{
"epoch": 0.5407215200468737,
"grad_norm": 0.4085431396961212,
"learning_rate": 2e-05,
"loss": 0.692,
"step": 6460
},
{
"epoch": 0.5415585502636645,
"grad_norm": 0.37911438941955566,
"learning_rate": 2e-05,
"loss": 0.6398,
"step": 6470
},
{
"epoch": 0.5423955804804553,
"grad_norm": 0.3791961371898651,
"learning_rate": 2e-05,
"loss": 0.6816,
"step": 6480
},
{
"epoch": 0.5432326106972462,
"grad_norm": 0.36386221647262573,
"learning_rate": 2e-05,
"loss": 0.6829,
"step": 6490
},
{
"epoch": 0.544069640914037,
"grad_norm": 0.3571239709854126,
"learning_rate": 2e-05,
"loss": 0.6275,
"step": 6500
},
{
"epoch": 0.5449066711308278,
"grad_norm": 0.3513040244579315,
"learning_rate": 2e-05,
"loss": 0.685,
"step": 6510
},
{
"epoch": 0.5457437013476186,
"grad_norm": 0.40488460659980774,
"learning_rate": 2e-05,
"loss": 0.6239,
"step": 6520
},
{
"epoch": 0.5465807315644094,
"grad_norm": 0.3723262846469879,
"learning_rate": 2e-05,
"loss": 0.6262,
"step": 6530
},
{
"epoch": 0.5474177617812003,
"grad_norm": 0.3982182443141937,
"learning_rate": 2e-05,
"loss": 0.6476,
"step": 6540
},
{
"epoch": 0.5482547919979911,
"grad_norm": 0.3855936527252197,
"learning_rate": 2e-05,
"loss": 0.6487,
"step": 6550
},
{
"epoch": 0.5490918222147819,
"grad_norm": 0.39931339025497437,
"learning_rate": 2e-05,
"loss": 0.6555,
"step": 6560
},
{
"epoch": 0.5499288524315727,
"grad_norm": 0.3838026821613312,
"learning_rate": 2e-05,
"loss": 0.614,
"step": 6570
},
{
"epoch": 0.5507658826483636,
"grad_norm": 0.3357454538345337,
"learning_rate": 2e-05,
"loss": 0.6312,
"step": 6580
},
{
"epoch": 0.5516029128651544,
"grad_norm": 0.32106679677963257,
"learning_rate": 2e-05,
"loss": 0.675,
"step": 6590
},
{
"epoch": 0.5524399430819452,
"grad_norm": 0.3373437523841858,
"learning_rate": 2e-05,
"loss": 0.631,
"step": 6600
},
{
"epoch": 0.553276973298736,
"grad_norm": 0.3836980164051056,
"learning_rate": 2e-05,
"loss": 0.6201,
"step": 6610
},
{
"epoch": 0.5541140035155269,
"grad_norm": 0.37900593876838684,
"learning_rate": 2e-05,
"loss": 0.6579,
"step": 6620
},
{
"epoch": 0.5549510337323177,
"grad_norm": 0.39630722999572754,
"learning_rate": 2e-05,
"loss": 0.6795,
"step": 6630
},
{
"epoch": 0.5557880639491085,
"grad_norm": 0.5832887291908264,
"learning_rate": 2e-05,
"loss": 0.6235,
"step": 6640
},
{
"epoch": 0.5566250941658993,
"grad_norm": 0.34389233589172363,
"learning_rate": 2e-05,
"loss": 0.642,
"step": 6650
},
{
"epoch": 0.5574621243826902,
"grad_norm": 0.44017985463142395,
"learning_rate": 2e-05,
"loss": 0.5899,
"step": 6660
},
{
"epoch": 0.5582991545994811,
"grad_norm": 0.3805539608001709,
"learning_rate": 2e-05,
"loss": 0.6636,
"step": 6670
},
{
"epoch": 0.5591361848162719,
"grad_norm": 0.4991150498390198,
"learning_rate": 2e-05,
"loss": 0.6334,
"step": 6680
},
{
"epoch": 0.5599732150330627,
"grad_norm": 0.3494931161403656,
"learning_rate": 2e-05,
"loss": 0.6725,
"step": 6690
},
{
"epoch": 0.5608102452498536,
"grad_norm": 0.3774120807647705,
"learning_rate": 2e-05,
"loss": 0.6431,
"step": 6700
},
{
"epoch": 0.5616472754666444,
"grad_norm": 0.3690647780895233,
"learning_rate": 2e-05,
"loss": 0.6669,
"step": 6710
},
{
"epoch": 0.5624843056834352,
"grad_norm": 0.3637116551399231,
"learning_rate": 2e-05,
"loss": 0.6754,
"step": 6720
},
{
"epoch": 0.563321335900226,
"grad_norm": 0.5737238526344299,
"learning_rate": 2e-05,
"loss": 0.6405,
"step": 6730
},
{
"epoch": 0.5641583661170169,
"grad_norm": 0.3776264488697052,
"learning_rate": 2e-05,
"loss": 0.6398,
"step": 6740
},
{
"epoch": 0.5649953963338077,
"grad_norm": 0.3660067319869995,
"learning_rate": 2e-05,
"loss": 0.615,
"step": 6750
},
{
"epoch": 0.5658324265505985,
"grad_norm": 0.335502952337265,
"learning_rate": 2e-05,
"loss": 0.6448,
"step": 6760
},
{
"epoch": 0.5666694567673893,
"grad_norm": 0.38001254200935364,
"learning_rate": 2e-05,
"loss": 0.6449,
"step": 6770
},
{
"epoch": 0.5675064869841802,
"grad_norm": 0.3713911473751068,
"learning_rate": 2e-05,
"loss": 0.6467,
"step": 6780
},
{
"epoch": 0.568343517200971,
"grad_norm": 0.3704918324947357,
"learning_rate": 2e-05,
"loss": 0.6654,
"step": 6790
},
{
"epoch": 0.5691805474177618,
"grad_norm": 0.343713641166687,
"learning_rate": 2e-05,
"loss": 0.6458,
"step": 6800
},
{
"epoch": 0.5700175776345526,
"grad_norm": 0.36956989765167236,
"learning_rate": 2e-05,
"loss": 0.6476,
"step": 6810
},
{
"epoch": 0.5708546078513435,
"grad_norm": 0.3819212019443512,
"learning_rate": 2e-05,
"loss": 0.6374,
"step": 6820
},
{
"epoch": 0.5716916380681343,
"grad_norm": 0.34743985533714294,
"learning_rate": 2e-05,
"loss": 0.6244,
"step": 6830
},
{
"epoch": 0.5725286682849251,
"grad_norm": 0.34101831912994385,
"learning_rate": 2e-05,
"loss": 0.6229,
"step": 6840
},
{
"epoch": 0.5733656985017159,
"grad_norm": 0.4011986553668976,
"learning_rate": 2e-05,
"loss": 0.6389,
"step": 6850
},
{
"epoch": 0.5742027287185067,
"grad_norm": 0.34482240676879883,
"learning_rate": 2e-05,
"loss": 0.6672,
"step": 6860
},
{
"epoch": 0.5750397589352976,
"grad_norm": 0.360812783241272,
"learning_rate": 2e-05,
"loss": 0.6835,
"step": 6870
},
{
"epoch": 0.5758767891520884,
"grad_norm": 0.5191910862922668,
"learning_rate": 2e-05,
"loss": 0.6367,
"step": 6880
},
{
"epoch": 0.5767138193688792,
"grad_norm": 0.3681277334690094,
"learning_rate": 2e-05,
"loss": 0.6618,
"step": 6890
},
{
"epoch": 0.57755084958567,
"grad_norm": 0.4177042543888092,
"learning_rate": 2e-05,
"loss": 0.6503,
"step": 6900
},
{
"epoch": 0.5783878798024609,
"grad_norm": 0.37461766600608826,
"learning_rate": 2e-05,
"loss": 0.6378,
"step": 6910
},
{
"epoch": 0.5792249100192517,
"grad_norm": 0.34315815567970276,
"learning_rate": 2e-05,
"loss": 0.6263,
"step": 6920
},
{
"epoch": 0.5800619402360425,
"grad_norm": 0.37280896306037903,
"learning_rate": 2e-05,
"loss": 0.6495,
"step": 6930
},
{
"epoch": 0.5808989704528333,
"grad_norm": 0.3597322702407837,
"learning_rate": 2e-05,
"loss": 0.6392,
"step": 6940
},
{
"epoch": 0.5817360006696242,
"grad_norm": 0.3935507833957672,
"learning_rate": 2e-05,
"loss": 0.6519,
"step": 6950
},
{
"epoch": 0.582573030886415,
"grad_norm": 0.473751038312912,
"learning_rate": 2e-05,
"loss": 0.6441,
"step": 6960
},
{
"epoch": 0.5834100611032058,
"grad_norm": 0.36001309752464294,
"learning_rate": 2e-05,
"loss": 0.647,
"step": 6970
},
{
"epoch": 0.5842470913199966,
"grad_norm": 0.3589722216129303,
"learning_rate": 2e-05,
"loss": 0.6381,
"step": 6980
},
{
"epoch": 0.5850841215367875,
"grad_norm": 0.3798554837703705,
"learning_rate": 2e-05,
"loss": 0.6471,
"step": 6990
},
{
"epoch": 0.5859211517535783,
"grad_norm": 0.3698202967643738,
"learning_rate": 2e-05,
"loss": 0.6444,
"step": 7000
},
{
"epoch": 0.5867581819703691,
"grad_norm": 0.38922882080078125,
"learning_rate": 2e-05,
"loss": 0.6623,
"step": 7010
},
{
"epoch": 0.5875952121871599,
"grad_norm": 0.3997010290622711,
"learning_rate": 2e-05,
"loss": 0.657,
"step": 7020
},
{
"epoch": 0.5884322424039508,
"grad_norm": 0.3831057846546173,
"learning_rate": 2e-05,
"loss": 0.6417,
"step": 7030
},
{
"epoch": 0.5892692726207416,
"grad_norm": 0.3822855055332184,
"learning_rate": 2e-05,
"loss": 0.6465,
"step": 7040
},
{
"epoch": 0.5901063028375324,
"grad_norm": 0.35025328397750854,
"learning_rate": 2e-05,
"loss": 0.6719,
"step": 7050
},
{
"epoch": 0.5909433330543232,
"grad_norm": 0.38824155926704407,
"learning_rate": 2e-05,
"loss": 0.6658,
"step": 7060
},
{
"epoch": 0.591780363271114,
"grad_norm": 0.35230553150177,
"learning_rate": 2e-05,
"loss": 0.6515,
"step": 7070
},
{
"epoch": 0.5926173934879049,
"grad_norm": 0.369748055934906,
"learning_rate": 2e-05,
"loss": 0.6125,
"step": 7080
},
{
"epoch": 0.5934544237046957,
"grad_norm": 0.37262609601020813,
"learning_rate": 2e-05,
"loss": 0.6568,
"step": 7090
},
{
"epoch": 0.5942914539214865,
"grad_norm": 0.4075169265270233,
"learning_rate": 2e-05,
"loss": 0.6407,
"step": 7100
},
{
"epoch": 0.5951284841382773,
"grad_norm": 0.35482028126716614,
"learning_rate": 2e-05,
"loss": 0.6446,
"step": 7110
},
{
"epoch": 0.5959655143550682,
"grad_norm": 0.37759819626808167,
"learning_rate": 2e-05,
"loss": 0.6359,
"step": 7120
},
{
"epoch": 0.596802544571859,
"grad_norm": 0.3791484832763672,
"learning_rate": 2e-05,
"loss": 0.6462,
"step": 7130
},
{
"epoch": 0.5976395747886498,
"grad_norm": 0.360541433095932,
"learning_rate": 2e-05,
"loss": 0.6734,
"step": 7140
},
{
"epoch": 0.5984766050054406,
"grad_norm": 0.8784747123718262,
"learning_rate": 2e-05,
"loss": 0.6533,
"step": 7150
},
{
"epoch": 0.5993136352222316,
"grad_norm": 0.4028649926185608,
"learning_rate": 2e-05,
"loss": 0.6878,
"step": 7160
},
{
"epoch": 0.6001506654390224,
"grad_norm": 0.3939493000507355,
"learning_rate": 2e-05,
"loss": 0.6343,
"step": 7170
},
{
"epoch": 0.6009876956558132,
"grad_norm": 0.33013269305229187,
"learning_rate": 2e-05,
"loss": 0.6208,
"step": 7180
},
{
"epoch": 0.601824725872604,
"grad_norm": 0.3637343943119049,
"learning_rate": 2e-05,
"loss": 0.67,
"step": 7190
},
{
"epoch": 0.6026617560893949,
"grad_norm": 0.4331212043762207,
"learning_rate": 2e-05,
"loss": 0.6325,
"step": 7200
},
{
"epoch": 0.6034987863061857,
"grad_norm": 0.3568844497203827,
"learning_rate": 2e-05,
"loss": 0.6407,
"step": 7210
},
{
"epoch": 0.6043358165229765,
"grad_norm": 0.36737126111984253,
"learning_rate": 2e-05,
"loss": 0.6369,
"step": 7220
},
{
"epoch": 0.6051728467397673,
"grad_norm": 0.37844184041023254,
"learning_rate": 2e-05,
"loss": 0.6334,
"step": 7230
},
{
"epoch": 0.6060098769565582,
"grad_norm": 0.36976346373558044,
"learning_rate": 2e-05,
"loss": 0.6469,
"step": 7240
},
{
"epoch": 0.606846907173349,
"grad_norm": 0.34516632556915283,
"learning_rate": 2e-05,
"loss": 0.7494,
"step": 7250
},
{
"epoch": 0.6076839373901398,
"grad_norm": 0.36559611558914185,
"learning_rate": 2e-05,
"loss": 0.6203,
"step": 7260
},
{
"epoch": 0.6085209676069306,
"grad_norm": 0.41558602452278137,
"learning_rate": 2e-05,
"loss": 0.6477,
"step": 7270
},
{
"epoch": 0.6093579978237215,
"grad_norm": 0.33512237668037415,
"learning_rate": 2e-05,
"loss": 0.6311,
"step": 7280
},
{
"epoch": 0.6101950280405123,
"grad_norm": 0.355272501707077,
"learning_rate": 2e-05,
"loss": 0.6369,
"step": 7290
},
{
"epoch": 0.6110320582573031,
"grad_norm": 0.42383986711502075,
"learning_rate": 2e-05,
"loss": 0.6656,
"step": 7300
},
{
"epoch": 0.6118690884740939,
"grad_norm": 0.37551674246788025,
"learning_rate": 2e-05,
"loss": 0.6193,
"step": 7310
},
{
"epoch": 0.6127061186908848,
"grad_norm": 0.33307281136512756,
"learning_rate": 2e-05,
"loss": 0.6288,
"step": 7320
},
{
"epoch": 0.6135431489076756,
"grad_norm": 0.3674827218055725,
"learning_rate": 2e-05,
"loss": 0.6242,
"step": 7330
},
{
"epoch": 0.6143801791244664,
"grad_norm": 0.37685728073120117,
"learning_rate": 2e-05,
"loss": 0.6263,
"step": 7340
},
{
"epoch": 0.6152172093412572,
"grad_norm": 0.40486040711402893,
"learning_rate": 2e-05,
"loss": 0.6273,
"step": 7350
},
{
"epoch": 0.6160542395580481,
"grad_norm": 0.36861538887023926,
"learning_rate": 2e-05,
"loss": 0.6369,
"step": 7360
},
{
"epoch": 0.6168912697748389,
"grad_norm": 0.38653436303138733,
"learning_rate": 2e-05,
"loss": 0.6399,
"step": 7370
},
{
"epoch": 0.6177282999916297,
"grad_norm": 0.3330835700035095,
"learning_rate": 2e-05,
"loss": 0.6446,
"step": 7380
},
{
"epoch": 0.6185653302084205,
"grad_norm": 0.3681088089942932,
"learning_rate": 2e-05,
"loss": 0.6752,
"step": 7390
},
{
"epoch": 0.6194023604252114,
"grad_norm": 0.3649876117706299,
"learning_rate": 2e-05,
"loss": 0.6528,
"step": 7400
},
{
"epoch": 0.6202393906420022,
"grad_norm": 0.37088438868522644,
"learning_rate": 2e-05,
"loss": 0.6222,
"step": 7410
},
{
"epoch": 0.621076420858793,
"grad_norm": 0.44030991196632385,
"learning_rate": 2e-05,
"loss": 0.6149,
"step": 7420
},
{
"epoch": 0.6219134510755838,
"grad_norm": 0.36003291606903076,
"learning_rate": 2e-05,
"loss": 0.6295,
"step": 7430
},
{
"epoch": 0.6227504812923746,
"grad_norm": 0.3467269539833069,
"learning_rate": 2e-05,
"loss": 0.6698,
"step": 7440
},
{
"epoch": 0.6235875115091655,
"grad_norm": 0.384486585855484,
"learning_rate": 2e-05,
"loss": 0.6266,
"step": 7450
},
{
"epoch": 0.6244245417259563,
"grad_norm": 0.33349546790122986,
"learning_rate": 2e-05,
"loss": 0.6162,
"step": 7460
},
{
"epoch": 0.6252615719427471,
"grad_norm": 0.4121619164943695,
"learning_rate": 2e-05,
"loss": 0.626,
"step": 7470
},
{
"epoch": 0.6260986021595379,
"grad_norm": 0.41288620233535767,
"learning_rate": 2e-05,
"loss": 0.6234,
"step": 7480
},
{
"epoch": 0.6269356323763288,
"grad_norm": 0.3818019926548004,
"learning_rate": 2e-05,
"loss": 0.6455,
"step": 7490
},
{
"epoch": 0.6277726625931196,
"grad_norm": 0.37027862668037415,
"learning_rate": 2e-05,
"loss": 0.6469,
"step": 7500
},
{
"epoch": 0.6286096928099104,
"grad_norm": 0.3822766840457916,
"learning_rate": 2e-05,
"loss": 0.6347,
"step": 7510
},
{
"epoch": 0.6294467230267012,
"grad_norm": 0.41255244612693787,
"learning_rate": 2e-05,
"loss": 0.6175,
"step": 7520
},
{
"epoch": 0.6302837532434921,
"grad_norm": 0.3520616888999939,
"learning_rate": 2e-05,
"loss": 0.6438,
"step": 7530
},
{
"epoch": 0.6311207834602829,
"grad_norm": 0.38395896553993225,
"learning_rate": 2e-05,
"loss": 0.6681,
"step": 7540
},
{
"epoch": 0.6319578136770737,
"grad_norm": 0.381974458694458,
"learning_rate": 2e-05,
"loss": 0.6115,
"step": 7550
},
{
"epoch": 0.6327948438938645,
"grad_norm": 0.3589411973953247,
"learning_rate": 2e-05,
"loss": 0.6311,
"step": 7560
},
{
"epoch": 0.6336318741106554,
"grad_norm": 0.372006356716156,
"learning_rate": 2e-05,
"loss": 0.6289,
"step": 7570
},
{
"epoch": 0.6344689043274462,
"grad_norm": 0.42437031865119934,
"learning_rate": 2e-05,
"loss": 0.652,
"step": 7580
},
{
"epoch": 0.635305934544237,
"grad_norm": 0.3619164824485779,
"learning_rate": 2e-05,
"loss": 0.6473,
"step": 7590
},
{
"epoch": 0.6361429647610278,
"grad_norm": 0.3945671617984772,
"learning_rate": 2e-05,
"loss": 0.6514,
"step": 7600
},
{
"epoch": 0.6369799949778187,
"grad_norm": 0.37704697251319885,
"learning_rate": 2e-05,
"loss": 0.5996,
"step": 7610
},
{
"epoch": 0.6378170251946095,
"grad_norm": 0.9980588555335999,
"learning_rate": 2e-05,
"loss": 0.6487,
"step": 7620
},
{
"epoch": 0.6386540554114003,
"grad_norm": 0.38779252767562866,
"learning_rate": 2e-05,
"loss": 0.6435,
"step": 7630
},
{
"epoch": 0.6394910856281911,
"grad_norm": 0.37917718291282654,
"learning_rate": 2e-05,
"loss": 0.6768,
"step": 7640
},
{
"epoch": 0.640328115844982,
"grad_norm": 0.39834779500961304,
"learning_rate": 2e-05,
"loss": 0.6871,
"step": 7650
},
{
"epoch": 0.6411651460617729,
"grad_norm": 0.3755333125591278,
"learning_rate": 2e-05,
"loss": 0.6558,
"step": 7660
},
{
"epoch": 0.6420021762785637,
"grad_norm": 0.3637411296367645,
"learning_rate": 2e-05,
"loss": 0.6231,
"step": 7670
},
{
"epoch": 0.6428392064953545,
"grad_norm": 0.36118972301483154,
"learning_rate": 2e-05,
"loss": 0.6269,
"step": 7680
},
{
"epoch": 0.6436762367121454,
"grad_norm": 0.402189701795578,
"learning_rate": 2e-05,
"loss": 0.6712,
"step": 7690
},
{
"epoch": 0.6445132669289362,
"grad_norm": 0.3748190701007843,
"learning_rate": 2e-05,
"loss": 0.6511,
"step": 7700
},
{
"epoch": 0.645350297145727,
"grad_norm": 0.37605899572372437,
"learning_rate": 2e-05,
"loss": 0.6827,
"step": 7710
},
{
"epoch": 0.6461873273625178,
"grad_norm": 0.37820547819137573,
"learning_rate": 2e-05,
"loss": 0.6232,
"step": 7720
},
{
"epoch": 0.6470243575793087,
"grad_norm": 0.328792005777359,
"learning_rate": 2e-05,
"loss": 0.655,
"step": 7730
},
{
"epoch": 0.6478613877960995,
"grad_norm": 0.3954271972179413,
"learning_rate": 2e-05,
"loss": 0.6809,
"step": 7740
},
{
"epoch": 0.6486984180128903,
"grad_norm": 0.3670234680175781,
"learning_rate": 2e-05,
"loss": 0.6532,
"step": 7750
},
{
"epoch": 0.6495354482296811,
"grad_norm": 0.3692343831062317,
"learning_rate": 2e-05,
"loss": 0.6131,
"step": 7760
},
{
"epoch": 0.650372478446472,
"grad_norm": 0.35789957642555237,
"learning_rate": 2e-05,
"loss": 0.622,
"step": 7770
},
{
"epoch": 0.6512095086632628,
"grad_norm": 0.35526564717292786,
"learning_rate": 2e-05,
"loss": 0.627,
"step": 7780
},
{
"epoch": 0.6520465388800536,
"grad_norm": 0.3509477376937866,
"learning_rate": 2e-05,
"loss": 0.653,
"step": 7790
},
{
"epoch": 0.6528835690968444,
"grad_norm": 0.373808354139328,
"learning_rate": 2e-05,
"loss": 0.6638,
"step": 7800
},
{
"epoch": 0.6537205993136352,
"grad_norm": 0.37063848972320557,
"learning_rate": 2e-05,
"loss": 0.6376,
"step": 7810
},
{
"epoch": 0.6545576295304261,
"grad_norm": 0.37798410654067993,
"learning_rate": 2e-05,
"loss": 0.6411,
"step": 7820
},
{
"epoch": 0.6553946597472169,
"grad_norm": 0.38672247529029846,
"learning_rate": 2e-05,
"loss": 0.6571,
"step": 7830
},
{
"epoch": 0.6562316899640077,
"grad_norm": 0.3556165099143982,
"learning_rate": 2e-05,
"loss": 0.6689,
"step": 7840
},
{
"epoch": 0.6570687201807985,
"grad_norm": 0.42970338463783264,
"learning_rate": 2e-05,
"loss": 0.6446,
"step": 7850
},
{
"epoch": 0.6579057503975894,
"grad_norm": 0.35523146390914917,
"learning_rate": 2e-05,
"loss": 0.6285,
"step": 7860
},
{
"epoch": 0.6587427806143802,
"grad_norm": 0.3626030385494232,
"learning_rate": 2e-05,
"loss": 0.6452,
"step": 7870
},
{
"epoch": 0.659579810831171,
"grad_norm": 0.3713902533054352,
"learning_rate": 2e-05,
"loss": 0.6309,
"step": 7880
},
{
"epoch": 0.6604168410479618,
"grad_norm": 0.34307995438575745,
"learning_rate": 2e-05,
"loss": 0.6351,
"step": 7890
},
{
"epoch": 0.6612538712647527,
"grad_norm": 0.37593090534210205,
"learning_rate": 2e-05,
"loss": 0.6358,
"step": 7900
},
{
"epoch": 0.6620909014815435,
"grad_norm": 0.3647778630256653,
"learning_rate": 2e-05,
"loss": 0.6154,
"step": 7910
},
{
"epoch": 0.6629279316983343,
"grad_norm": 0.3892625570297241,
"learning_rate": 2e-05,
"loss": 0.6123,
"step": 7920
},
{
"epoch": 0.6637649619151251,
"grad_norm": 0.3764898478984833,
"learning_rate": 2e-05,
"loss": 0.6604,
"step": 7930
},
{
"epoch": 0.664601992131916,
"grad_norm": 0.38851094245910645,
"learning_rate": 2e-05,
"loss": 0.6304,
"step": 7940
},
{
"epoch": 0.6654390223487068,
"grad_norm": 0.3928258419036865,
"learning_rate": 2e-05,
"loss": 0.6047,
"step": 7950
},
{
"epoch": 0.6662760525654976,
"grad_norm": 0.5227580070495605,
"learning_rate": 2e-05,
"loss": 0.6587,
"step": 7960
},
{
"epoch": 0.6671130827822884,
"grad_norm": 0.3499297499656677,
"learning_rate": 2e-05,
"loss": 0.6145,
"step": 7970
},
{
"epoch": 0.6679501129990792,
"grad_norm": 0.40670010447502136,
"learning_rate": 2e-05,
"loss": 0.6427,
"step": 7980
},
{
"epoch": 0.6687871432158701,
"grad_norm": 0.3574115037918091,
"learning_rate": 2e-05,
"loss": 0.6564,
"step": 7990
},
{
"epoch": 0.6696241734326609,
"grad_norm": 0.3581046462059021,
"learning_rate": 2e-05,
"loss": 0.6443,
"step": 8000
},
{
"epoch": 0.6704612036494517,
"grad_norm": 0.357467383146286,
"learning_rate": 2e-05,
"loss": 0.6521,
"step": 8010
},
{
"epoch": 0.6712982338662425,
"grad_norm": 0.41289180517196655,
"learning_rate": 2e-05,
"loss": 0.6606,
"step": 8020
},
{
"epoch": 0.6721352640830334,
"grad_norm": 0.3704478144645691,
"learning_rate": 2e-05,
"loss": 0.6854,
"step": 8030
},
{
"epoch": 0.6729722942998242,
"grad_norm": 0.3519052565097809,
"learning_rate": 2e-05,
"loss": 0.6309,
"step": 8040
},
{
"epoch": 0.673809324516615,
"grad_norm": 0.35991206765174866,
"learning_rate": 2e-05,
"loss": 0.6313,
"step": 8050
},
{
"epoch": 0.6746463547334058,
"grad_norm": 0.35568827390670776,
"learning_rate": 2e-05,
"loss": 0.6472,
"step": 8060
},
{
"epoch": 0.6754833849501967,
"grad_norm": 0.33062511682510376,
"learning_rate": 2e-05,
"loss": 0.6197,
"step": 8070
},
{
"epoch": 0.6763204151669875,
"grad_norm": 0.38448452949523926,
"learning_rate": 2e-05,
"loss": 0.649,
"step": 8080
},
{
"epoch": 0.6771574453837783,
"grad_norm": 0.3624459505081177,
"learning_rate": 2e-05,
"loss": 0.6208,
"step": 8090
},
{
"epoch": 0.6779944756005691,
"grad_norm": 0.3570438027381897,
"learning_rate": 2e-05,
"loss": 0.6659,
"step": 8100
},
{
"epoch": 0.67883150581736,
"grad_norm": 0.37720203399658203,
"learning_rate": 2e-05,
"loss": 0.6278,
"step": 8110
},
{
"epoch": 0.6796685360341508,
"grad_norm": 0.3522493243217468,
"learning_rate": 2e-05,
"loss": 0.6336,
"step": 8120
},
{
"epoch": 0.6805055662509416,
"grad_norm": 0.362285852432251,
"learning_rate": 2e-05,
"loss": 0.6605,
"step": 8130
},
{
"epoch": 0.6813425964677324,
"grad_norm": 0.4146277904510498,
"learning_rate": 2e-05,
"loss": 0.6718,
"step": 8140
},
{
"epoch": 0.6821796266845234,
"grad_norm": 0.37331175804138184,
"learning_rate": 2e-05,
"loss": 0.6294,
"step": 8150
},
{
"epoch": 0.6830166569013142,
"grad_norm": 0.36368969082832336,
"learning_rate": 2e-05,
"loss": 0.6144,
"step": 8160
},
{
"epoch": 0.683853687118105,
"grad_norm": 0.33885619044303894,
"learning_rate": 2e-05,
"loss": 0.6408,
"step": 8170
},
{
"epoch": 0.6846907173348958,
"grad_norm": 0.3416866362094879,
"learning_rate": 2e-05,
"loss": 0.6413,
"step": 8180
},
{
"epoch": 0.6855277475516867,
"grad_norm": 0.36033281683921814,
"learning_rate": 2e-05,
"loss": 0.6143,
"step": 8190
},
{
"epoch": 0.6863647777684775,
"grad_norm": 0.364259272813797,
"learning_rate": 2e-05,
"loss": 0.6215,
"step": 8200
},
{
"epoch": 0.6872018079852683,
"grad_norm": 0.3732483386993408,
"learning_rate": 2e-05,
"loss": 0.6285,
"step": 8210
},
{
"epoch": 0.6880388382020591,
"grad_norm": 0.35848233103752136,
"learning_rate": 2e-05,
"loss": 0.6359,
"step": 8220
},
{
"epoch": 0.68887586841885,
"grad_norm": 0.39869287610054016,
"learning_rate": 2e-05,
"loss": 0.6016,
"step": 8230
},
{
"epoch": 0.6897128986356408,
"grad_norm": 0.3383026123046875,
"learning_rate": 2e-05,
"loss": 0.6375,
"step": 8240
},
{
"epoch": 0.6905499288524316,
"grad_norm": 0.36849716305732727,
"learning_rate": 2e-05,
"loss": 0.5938,
"step": 8250
},
{
"epoch": 0.6913869590692224,
"grad_norm": 0.37617143988609314,
"learning_rate": 2e-05,
"loss": 0.6488,
"step": 8260
},
{
"epoch": 0.6922239892860133,
"grad_norm": 0.35504791140556335,
"learning_rate": 2e-05,
"loss": 0.6181,
"step": 8270
},
{
"epoch": 0.6930610195028041,
"grad_norm": 0.3785565197467804,
"learning_rate": 2e-05,
"loss": 0.6387,
"step": 8280
},
{
"epoch": 0.6938980497195949,
"grad_norm": 0.35008254647254944,
"learning_rate": 2e-05,
"loss": 0.6238,
"step": 8290
},
{
"epoch": 0.6947350799363857,
"grad_norm": 0.3626289963722229,
"learning_rate": 2e-05,
"loss": 0.6407,
"step": 8300
},
{
"epoch": 0.6955721101531765,
"grad_norm": 0.4064772129058838,
"learning_rate": 2e-05,
"loss": 0.6351,
"step": 8310
},
{
"epoch": 0.6964091403699674,
"grad_norm": 0.37249740958213806,
"learning_rate": 2e-05,
"loss": 0.6109,
"step": 8320
},
{
"epoch": 0.6972461705867582,
"grad_norm": 0.37401044368743896,
"learning_rate": 2e-05,
"loss": 0.6495,
"step": 8330
},
{
"epoch": 0.698083200803549,
"grad_norm": 0.3611725866794586,
"learning_rate": 2e-05,
"loss": 0.5961,
"step": 8340
},
{
"epoch": 0.6989202310203398,
"grad_norm": 0.37362730503082275,
"learning_rate": 2e-05,
"loss": 0.6398,
"step": 8350
},
{
"epoch": 0.6997572612371307,
"grad_norm": 0.48868802189826965,
"learning_rate": 2e-05,
"loss": 0.6447,
"step": 8360
},
{
"epoch": 0.7005942914539215,
"grad_norm": 0.4603143334388733,
"learning_rate": 2e-05,
"loss": 0.6562,
"step": 8370
},
{
"epoch": 0.7014313216707123,
"grad_norm": 0.3333459794521332,
"learning_rate": 2e-05,
"loss": 0.614,
"step": 8380
},
{
"epoch": 0.7022683518875031,
"grad_norm": 0.336022287607193,
"learning_rate": 2e-05,
"loss": 0.6471,
"step": 8390
},
{
"epoch": 0.703105382104294,
"grad_norm": 0.3631014823913574,
"learning_rate": 2e-05,
"loss": 0.6237,
"step": 8400
},
{
"epoch": 0.7039424123210848,
"grad_norm": 0.3699735403060913,
"learning_rate": 2e-05,
"loss": 0.6498,
"step": 8410
},
{
"epoch": 0.7047794425378756,
"grad_norm": 0.3177425265312195,
"learning_rate": 2e-05,
"loss": 0.5785,
"step": 8420
},
{
"epoch": 0.7056164727546664,
"grad_norm": 0.38554540276527405,
"learning_rate": 2e-05,
"loss": 0.67,
"step": 8430
},
{
"epoch": 0.7064535029714573,
"grad_norm": 0.3833550810813904,
"learning_rate": 2e-05,
"loss": 0.6324,
"step": 8440
},
{
"epoch": 0.7072905331882481,
"grad_norm": 0.34186726808547974,
"learning_rate": 2e-05,
"loss": 0.6251,
"step": 8450
},
{
"epoch": 0.7081275634050389,
"grad_norm": 0.3434412181377411,
"learning_rate": 2e-05,
"loss": 0.6358,
"step": 8460
},
{
"epoch": 0.7089645936218297,
"grad_norm": 0.38122087717056274,
"learning_rate": 2e-05,
"loss": 0.6225,
"step": 8470
},
{
"epoch": 0.7098016238386206,
"grad_norm": 0.35209226608276367,
"learning_rate": 2e-05,
"loss": 0.6517,
"step": 8480
},
{
"epoch": 0.7106386540554114,
"grad_norm": 0.3892095386981964,
"learning_rate": 2e-05,
"loss": 0.6441,
"step": 8490
},
{
"epoch": 0.7114756842722022,
"grad_norm": 0.3626607358455658,
"learning_rate": 2e-05,
"loss": 0.6779,
"step": 8500
},
{
"epoch": 0.712312714488993,
"grad_norm": 0.3459932506084442,
"learning_rate": 2e-05,
"loss": 0.6281,
"step": 8510
},
{
"epoch": 0.7131497447057839,
"grad_norm": 0.4026942253112793,
"learning_rate": 2e-05,
"loss": 0.6188,
"step": 8520
},
{
"epoch": 0.7139867749225747,
"grad_norm": 0.38787296414375305,
"learning_rate": 2e-05,
"loss": 0.6138,
"step": 8530
},
{
"epoch": 0.7148238051393655,
"grad_norm": 0.38193342089653015,
"learning_rate": 2e-05,
"loss": 0.6733,
"step": 8540
},
{
"epoch": 0.7156608353561563,
"grad_norm": 0.4010123014450073,
"learning_rate": 2e-05,
"loss": 0.6577,
"step": 8550
},
{
"epoch": 0.7164978655729471,
"grad_norm": 0.40022245049476624,
"learning_rate": 2e-05,
"loss": 0.6375,
"step": 8560
},
{
"epoch": 0.717334895789738,
"grad_norm": 0.4041902422904968,
"learning_rate": 2e-05,
"loss": 0.6488,
"step": 8570
},
{
"epoch": 0.7181719260065288,
"grad_norm": 0.3369944989681244,
"learning_rate": 2e-05,
"loss": 0.5881,
"step": 8580
},
{
"epoch": 0.7190089562233196,
"grad_norm": 0.348461389541626,
"learning_rate": 2e-05,
"loss": 0.6144,
"step": 8590
},
{
"epoch": 0.7198459864401104,
"grad_norm": 0.3990456759929657,
"learning_rate": 2e-05,
"loss": 0.6419,
"step": 8600
},
{
"epoch": 0.7206830166569013,
"grad_norm": 0.3708956241607666,
"learning_rate": 2e-05,
"loss": 0.6176,
"step": 8610
},
{
"epoch": 0.7215200468736921,
"grad_norm": 0.3824920654296875,
"learning_rate": 2e-05,
"loss": 0.6044,
"step": 8620
},
{
"epoch": 0.7223570770904829,
"grad_norm": 0.34812334179878235,
"learning_rate": 2e-05,
"loss": 0.6414,
"step": 8630
},
{
"epoch": 0.7231941073072738,
"grad_norm": 0.3725791573524475,
"learning_rate": 2e-05,
"loss": 0.613,
"step": 8640
},
{
"epoch": 0.7240311375240647,
"grad_norm": 0.4005664587020874,
"learning_rate": 2e-05,
"loss": 0.6258,
"step": 8650
},
{
"epoch": 0.7248681677408555,
"grad_norm": 0.38495662808418274,
"learning_rate": 2e-05,
"loss": 0.6448,
"step": 8660
},
{
"epoch": 0.7257051979576463,
"grad_norm": 0.36874255537986755,
"learning_rate": 2e-05,
"loss": 0.6066,
"step": 8670
},
{
"epoch": 0.7265422281744371,
"grad_norm": 0.3951646089553833,
"learning_rate": 2e-05,
"loss": 0.6373,
"step": 8680
},
{
"epoch": 0.727379258391228,
"grad_norm": 0.37776291370391846,
"learning_rate": 2e-05,
"loss": 0.6228,
"step": 8690
},
{
"epoch": 0.7282162886080188,
"grad_norm": 0.39674872159957886,
"learning_rate": 2e-05,
"loss": 0.6199,
"step": 8700
},
{
"epoch": 0.7290533188248096,
"grad_norm": 0.35712602734565735,
"learning_rate": 2e-05,
"loss": 0.6265,
"step": 8710
},
{
"epoch": 0.7298903490416004,
"grad_norm": 0.3914978504180908,
"learning_rate": 2e-05,
"loss": 0.639,
"step": 8720
},
{
"epoch": 0.7307273792583913,
"grad_norm": 0.38332468271255493,
"learning_rate": 2e-05,
"loss": 0.6467,
"step": 8730
},
{
"epoch": 0.7315644094751821,
"grad_norm": 0.5695624351501465,
"learning_rate": 2e-05,
"loss": 0.6676,
"step": 8740
},
{
"epoch": 0.7324014396919729,
"grad_norm": 0.3501618206501007,
"learning_rate": 2e-05,
"loss": 0.6465,
"step": 8750
},
{
"epoch": 0.7332384699087637,
"grad_norm": 0.4172833263874054,
"learning_rate": 2e-05,
"loss": 0.6495,
"step": 8760
},
{
"epoch": 0.7340755001255546,
"grad_norm": 0.4131946265697479,
"learning_rate": 2e-05,
"loss": 0.6316,
"step": 8770
},
{
"epoch": 0.7349125303423454,
"grad_norm": 0.37521132826805115,
"learning_rate": 2e-05,
"loss": 0.6237,
"step": 8780
},
{
"epoch": 0.7357495605591362,
"grad_norm": 0.3829571306705475,
"learning_rate": 2e-05,
"loss": 0.605,
"step": 8790
},
{
"epoch": 0.736586590775927,
"grad_norm": 0.39805084466934204,
"learning_rate": 2e-05,
"loss": 0.6442,
"step": 8800
},
{
"epoch": 0.7374236209927179,
"grad_norm": 0.36277908086776733,
"learning_rate": 2e-05,
"loss": 0.6111,
"step": 8810
},
{
"epoch": 0.7382606512095087,
"grad_norm": 0.3767291307449341,
"learning_rate": 2e-05,
"loss": 0.6102,
"step": 8820
},
{
"epoch": 0.7390976814262995,
"grad_norm": 0.35881152749061584,
"learning_rate": 2e-05,
"loss": 0.6386,
"step": 8830
},
{
"epoch": 0.7399347116430903,
"grad_norm": 0.4228999614715576,
"learning_rate": 2e-05,
"loss": 0.6702,
"step": 8840
},
{
"epoch": 0.7407717418598811,
"grad_norm": 0.38206616044044495,
"learning_rate": 2e-05,
"loss": 0.63,
"step": 8850
},
{
"epoch": 0.741608772076672,
"grad_norm": 0.3692625164985657,
"learning_rate": 2e-05,
"loss": 0.6316,
"step": 8860
},
{
"epoch": 0.7424458022934628,
"grad_norm": 0.4151228368282318,
"learning_rate": 2e-05,
"loss": 0.6144,
"step": 8870
},
{
"epoch": 0.7432828325102536,
"grad_norm": 0.37447482347488403,
"learning_rate": 2e-05,
"loss": 0.6255,
"step": 8880
},
{
"epoch": 0.7441198627270444,
"grad_norm": 0.4272429347038269,
"learning_rate": 2e-05,
"loss": 0.6253,
"step": 8890
},
{
"epoch": 0.7449568929438353,
"grad_norm": 0.4338759481906891,
"learning_rate": 2e-05,
"loss": 0.6513,
"step": 8900
},
{
"epoch": 0.7457939231606261,
"grad_norm": 0.3489220440387726,
"learning_rate": 2e-05,
"loss": 0.6123,
"step": 8910
},
{
"epoch": 0.7466309533774169,
"grad_norm": 0.4269581437110901,
"learning_rate": 2e-05,
"loss": 0.6134,
"step": 8920
},
{
"epoch": 0.7474679835942077,
"grad_norm": 0.5574132800102234,
"learning_rate": 2e-05,
"loss": 0.6539,
"step": 8930
},
{
"epoch": 0.7483050138109986,
"grad_norm": 0.37711331248283386,
"learning_rate": 2e-05,
"loss": 0.5916,
"step": 8940
},
{
"epoch": 0.7491420440277894,
"grad_norm": 0.37575340270996094,
"learning_rate": 2e-05,
"loss": 0.6273,
"step": 8950
},
{
"epoch": 0.7499790742445802,
"grad_norm": 0.4214867055416107,
"learning_rate": 2e-05,
"loss": 0.6497,
"step": 8960
},
{
"epoch": 0.750816104461371,
"grad_norm": 0.3663678765296936,
"learning_rate": 2e-05,
"loss": 0.6312,
"step": 8970
},
{
"epoch": 0.7516531346781619,
"grad_norm": 0.3570701479911804,
"learning_rate": 2e-05,
"loss": 0.6228,
"step": 8980
},
{
"epoch": 0.7524901648949527,
"grad_norm": 0.3359588384628296,
"learning_rate": 2e-05,
"loss": 0.6244,
"step": 8990
},
{
"epoch": 0.7533271951117435,
"grad_norm": 0.40977218747138977,
"learning_rate": 2e-05,
"loss": 0.6458,
"step": 9000
},
{
"epoch": 0.7541642253285343,
"grad_norm": 0.42812758684158325,
"learning_rate": 2e-05,
"loss": 0.6253,
"step": 9010
},
{
"epoch": 0.7550012555453252,
"grad_norm": 0.39282578229904175,
"learning_rate": 2e-05,
"loss": 0.6222,
"step": 9020
},
{
"epoch": 0.755838285762116,
"grad_norm": 0.39099663496017456,
"learning_rate": 2e-05,
"loss": 0.6023,
"step": 9030
},
{
"epoch": 0.7566753159789068,
"grad_norm": 0.34671810269355774,
"learning_rate": 2e-05,
"loss": 0.6277,
"step": 9040
},
{
"epoch": 0.7575123461956976,
"grad_norm": 0.35134005546569824,
"learning_rate": 2e-05,
"loss": 0.6129,
"step": 9050
},
{
"epoch": 0.7583493764124885,
"grad_norm": 0.35226568579673767,
"learning_rate": 2e-05,
"loss": 0.5996,
"step": 9060
},
{
"epoch": 0.7591864066292793,
"grad_norm": 0.38973966240882874,
"learning_rate": 2e-05,
"loss": 0.6396,
"step": 9070
},
{
"epoch": 0.7600234368460701,
"grad_norm": 0.35773080587387085,
"learning_rate": 2e-05,
"loss": 0.639,
"step": 9080
},
{
"epoch": 0.7608604670628609,
"grad_norm": 0.3722341060638428,
"learning_rate": 2e-05,
"loss": 0.5893,
"step": 9090
},
{
"epoch": 0.7616974972796517,
"grad_norm": 0.36534038186073303,
"learning_rate": 2e-05,
"loss": 0.62,
"step": 9100
},
{
"epoch": 0.7625345274964426,
"grad_norm": 0.3434760272502899,
"learning_rate": 2e-05,
"loss": 0.6069,
"step": 9110
},
{
"epoch": 0.7633715577132334,
"grad_norm": 0.39537400007247925,
"learning_rate": 2e-05,
"loss": 0.5883,
"step": 9120
},
{
"epoch": 0.7642085879300242,
"grad_norm": 0.37340280413627625,
"learning_rate": 2e-05,
"loss": 0.5897,
"step": 9130
},
{
"epoch": 0.7650456181468152,
"grad_norm": 0.35823094844818115,
"learning_rate": 2e-05,
"loss": 0.6298,
"step": 9140
},
{
"epoch": 0.765882648363606,
"grad_norm": 0.37899595499038696,
"learning_rate": 2e-05,
"loss": 0.6107,
"step": 9150
},
{
"epoch": 0.7667196785803968,
"grad_norm": 0.4177338182926178,
"learning_rate": 2e-05,
"loss": 0.621,
"step": 9160
},
{
"epoch": 0.7675567087971876,
"grad_norm": 0.36833837628364563,
"learning_rate": 2e-05,
"loss": 0.603,
"step": 9170
},
{
"epoch": 0.7683937390139784,
"grad_norm": 0.390982985496521,
"learning_rate": 2e-05,
"loss": 0.6385,
"step": 9180
},
{
"epoch": 0.7692307692307693,
"grad_norm": 0.35779502987861633,
"learning_rate": 2e-05,
"loss": 0.6362,
"step": 9190
},
{
"epoch": 0.7700677994475601,
"grad_norm": 0.377236932516098,
"learning_rate": 2e-05,
"loss": 0.6085,
"step": 9200
},
{
"epoch": 0.7709048296643509,
"grad_norm": 0.3452379107475281,
"learning_rate": 2e-05,
"loss": 0.6225,
"step": 9210
},
{
"epoch": 0.7717418598811417,
"grad_norm": 0.39392876625061035,
"learning_rate": 2e-05,
"loss": 0.6277,
"step": 9220
},
{
"epoch": 0.7725788900979326,
"grad_norm": 0.3619462847709656,
"learning_rate": 2e-05,
"loss": 0.6312,
"step": 9230
},
{
"epoch": 0.7734159203147234,
"grad_norm": 0.4709945023059845,
"learning_rate": 2e-05,
"loss": 0.6515,
"step": 9240
},
{
"epoch": 0.7742529505315142,
"grad_norm": 0.4286535382270813,
"learning_rate": 2e-05,
"loss": 0.6158,
"step": 9250
},
{
"epoch": 0.775089980748305,
"grad_norm": 0.37350061535835266,
"learning_rate": 2e-05,
"loss": 0.6375,
"step": 9260
},
{
"epoch": 0.7759270109650959,
"grad_norm": 0.3267936706542969,
"learning_rate": 2e-05,
"loss": 0.6507,
"step": 9270
},
{
"epoch": 0.7767640411818867,
"grad_norm": 0.3860539495944977,
"learning_rate": 2e-05,
"loss": 0.6438,
"step": 9280
},
{
"epoch": 0.7776010713986775,
"grad_norm": 0.3778722286224365,
"learning_rate": 2e-05,
"loss": 0.5884,
"step": 9290
},
{
"epoch": 0.7784381016154683,
"grad_norm": 0.3919179439544678,
"learning_rate": 2e-05,
"loss": 0.6225,
"step": 9300
},
{
"epoch": 0.7792751318322592,
"grad_norm": 0.3830442428588867,
"learning_rate": 2e-05,
"loss": 0.6394,
"step": 9310
},
{
"epoch": 0.78011216204905,
"grad_norm": 0.33387279510498047,
"learning_rate": 2e-05,
"loss": 0.6287,
"step": 9320
},
{
"epoch": 0.7809491922658408,
"grad_norm": 0.3703407049179077,
"learning_rate": 2e-05,
"loss": 0.6111,
"step": 9330
},
{
"epoch": 0.7817862224826316,
"grad_norm": 0.36593103408813477,
"learning_rate": 2e-05,
"loss": 0.6385,
"step": 9340
},
{
"epoch": 0.7826232526994225,
"grad_norm": 0.3878519535064697,
"learning_rate": 2e-05,
"loss": 0.6219,
"step": 9350
},
{
"epoch": 0.7834602829162133,
"grad_norm": 0.351995050907135,
"learning_rate": 2e-05,
"loss": 0.6272,
"step": 9360
},
{
"epoch": 0.7842973131330041,
"grad_norm": 0.3645213842391968,
"learning_rate": 2e-05,
"loss": 0.6222,
"step": 9370
},
{
"epoch": 0.7851343433497949,
"grad_norm": 0.33696743845939636,
"learning_rate": 2e-05,
"loss": 0.585,
"step": 9380
},
{
"epoch": 0.7859713735665858,
"grad_norm": 0.3524693250656128,
"learning_rate": 2e-05,
"loss": 0.6145,
"step": 9390
},
{
"epoch": 0.7868084037833766,
"grad_norm": 0.3504578173160553,
"learning_rate": 2e-05,
"loss": 0.6162,
"step": 9400
},
{
"epoch": 0.7876454340001674,
"grad_norm": 0.3870294988155365,
"learning_rate": 2e-05,
"loss": 0.6249,
"step": 9410
},
{
"epoch": 0.7884824642169582,
"grad_norm": 0.4301256835460663,
"learning_rate": 2e-05,
"loss": 0.6127,
"step": 9420
},
{
"epoch": 0.789319494433749,
"grad_norm": 0.3780767619609833,
"learning_rate": 2e-05,
"loss": 0.6034,
"step": 9430
},
{
"epoch": 0.7901565246505399,
"grad_norm": 0.3460957109928131,
"learning_rate": 2e-05,
"loss": 0.6185,
"step": 9440
},
{
"epoch": 0.7909935548673307,
"grad_norm": 0.39352548122406006,
"learning_rate": 2e-05,
"loss": 0.6517,
"step": 9450
},
{
"epoch": 0.7918305850841215,
"grad_norm": 0.411136269569397,
"learning_rate": 2e-05,
"loss": 0.6431,
"step": 9460
},
{
"epoch": 0.7926676153009123,
"grad_norm": 0.3527356684207916,
"learning_rate": 2e-05,
"loss": 0.6158,
"step": 9470
},
{
"epoch": 0.7935046455177032,
"grad_norm": 0.38108116388320923,
"learning_rate": 2e-05,
"loss": 0.6196,
"step": 9480
},
{
"epoch": 0.794341675734494,
"grad_norm": 0.36168816685676575,
"learning_rate": 2e-05,
"loss": 0.6306,
"step": 9490
},
{
"epoch": 0.7951787059512848,
"grad_norm": 0.3753302991390228,
"learning_rate": 2e-05,
"loss": 0.6267,
"step": 9500
},
{
"epoch": 0.7960157361680756,
"grad_norm": 0.3463782072067261,
"learning_rate": 2e-05,
"loss": 0.6496,
"step": 9510
},
{
"epoch": 0.7968527663848665,
"grad_norm": 0.3713393211364746,
"learning_rate": 2e-05,
"loss": 0.6105,
"step": 9520
},
{
"epoch": 0.7976897966016573,
"grad_norm": 0.3766273260116577,
"learning_rate": 2e-05,
"loss": 0.6185,
"step": 9530
},
{
"epoch": 0.7985268268184481,
"grad_norm": 0.3587380349636078,
"learning_rate": 2e-05,
"loss": 0.6069,
"step": 9540
},
{
"epoch": 0.7993638570352389,
"grad_norm": 0.3560864329338074,
"learning_rate": 2e-05,
"loss": 0.5949,
"step": 9550
},
{
"epoch": 0.8002008872520298,
"grad_norm": 0.35435038805007935,
"learning_rate": 2e-05,
"loss": 0.6079,
"step": 9560
},
{
"epoch": 0.8010379174688206,
"grad_norm": 0.38286086916923523,
"learning_rate": 2e-05,
"loss": 0.6189,
"step": 9570
},
{
"epoch": 0.8018749476856114,
"grad_norm": 0.39769411087036133,
"learning_rate": 2e-05,
"loss": 0.6183,
"step": 9580
},
{
"epoch": 0.8027119779024022,
"grad_norm": 0.4291287958621979,
"learning_rate": 2e-05,
"loss": 0.6278,
"step": 9590
},
{
"epoch": 0.803549008119193,
"grad_norm": 0.3671792149543762,
"learning_rate": 2e-05,
"loss": 0.6154,
"step": 9600
},
{
"epoch": 0.8043860383359839,
"grad_norm": 0.40434497594833374,
"learning_rate": 2e-05,
"loss": 0.6054,
"step": 9610
},
{
"epoch": 0.8052230685527747,
"grad_norm": 0.41883158683776855,
"learning_rate": 2e-05,
"loss": 0.6208,
"step": 9620
},
{
"epoch": 0.8060600987695656,
"grad_norm": 0.38663536310195923,
"learning_rate": 2e-05,
"loss": 0.5956,
"step": 9630
},
{
"epoch": 0.8068971289863565,
"grad_norm": 0.35269322991371155,
"learning_rate": 2e-05,
"loss": 0.6574,
"step": 9640
},
{
"epoch": 0.8077341592031473,
"grad_norm": 0.40031880140304565,
"learning_rate": 2e-05,
"loss": 0.6274,
"step": 9650
},
{
"epoch": 0.8085711894199381,
"grad_norm": 0.3519479036331177,
"learning_rate": 2e-05,
"loss": 0.6344,
"step": 9660
},
{
"epoch": 0.8094082196367289,
"grad_norm": 0.36624595522880554,
"learning_rate": 2e-05,
"loss": 0.6317,
"step": 9670
},
{
"epoch": 0.8102452498535198,
"grad_norm": 0.3485221266746521,
"learning_rate": 2e-05,
"loss": 0.6153,
"step": 9680
},
{
"epoch": 0.8110822800703106,
"grad_norm": 0.3847684860229492,
"learning_rate": 2e-05,
"loss": 0.5969,
"step": 9690
},
{
"epoch": 0.8119193102871014,
"grad_norm": 0.5449545979499817,
"learning_rate": 2e-05,
"loss": 0.6346,
"step": 9700
},
{
"epoch": 0.8127563405038922,
"grad_norm": 0.3659104108810425,
"learning_rate": 2e-05,
"loss": 0.5829,
"step": 9710
},
{
"epoch": 0.813593370720683,
"grad_norm": 0.3642854690551758,
"learning_rate": 2e-05,
"loss": 0.6232,
"step": 9720
},
{
"epoch": 0.8144304009374739,
"grad_norm": 0.3828984498977661,
"learning_rate": 2e-05,
"loss": 0.6078,
"step": 9730
},
{
"epoch": 0.8152674311542647,
"grad_norm": 0.4159924387931824,
"learning_rate": 2e-05,
"loss": 0.629,
"step": 9740
},
{
"epoch": 0.8161044613710555,
"grad_norm": 0.36572638154029846,
"learning_rate": 2e-05,
"loss": 0.604,
"step": 9750
},
{
"epoch": 0.8169414915878463,
"grad_norm": 0.36739251017570496,
"learning_rate": 2e-05,
"loss": 0.6154,
"step": 9760
},
{
"epoch": 0.8177785218046372,
"grad_norm": 0.3697957694530487,
"learning_rate": 2e-05,
"loss": 0.6252,
"step": 9770
},
{
"epoch": 0.818615552021428,
"grad_norm": 0.3758239448070526,
"learning_rate": 2e-05,
"loss": 0.6254,
"step": 9780
},
{
"epoch": 0.8194525822382188,
"grad_norm": 0.39665308594703674,
"learning_rate": 2e-05,
"loss": 0.6467,
"step": 9790
},
{
"epoch": 0.8202896124550096,
"grad_norm": 0.36492836475372314,
"learning_rate": 2e-05,
"loss": 0.6109,
"step": 9800
},
{
"epoch": 0.8211266426718005,
"grad_norm": 0.3612421154975891,
"learning_rate": 2e-05,
"loss": 0.5614,
"step": 9810
},
{
"epoch": 0.8219636728885913,
"grad_norm": 0.49745631217956543,
"learning_rate": 2e-05,
"loss": 0.6106,
"step": 9820
},
{
"epoch": 0.8228007031053821,
"grad_norm": 0.37881478667259216,
"learning_rate": 2e-05,
"loss": 0.6104,
"step": 9830
},
{
"epoch": 0.8236377333221729,
"grad_norm": 0.39541590213775635,
"learning_rate": 2e-05,
"loss": 0.6018,
"step": 9840
},
{
"epoch": 0.8244747635389638,
"grad_norm": 0.35362669825553894,
"learning_rate": 2e-05,
"loss": 0.6126,
"step": 9850
},
{
"epoch": 0.8253117937557546,
"grad_norm": 0.39162972569465637,
"learning_rate": 2e-05,
"loss": 0.6291,
"step": 9860
},
{
"epoch": 0.8261488239725454,
"grad_norm": 0.38019391894340515,
"learning_rate": 2e-05,
"loss": 0.607,
"step": 9870
},
{
"epoch": 0.8269858541893362,
"grad_norm": 0.3479459583759308,
"learning_rate": 2e-05,
"loss": 0.6391,
"step": 9880
},
{
"epoch": 0.8278228844061271,
"grad_norm": 0.3999125063419342,
"learning_rate": 2e-05,
"loss": 0.6363,
"step": 9890
},
{
"epoch": 0.8286599146229179,
"grad_norm": 0.4058418273925781,
"learning_rate": 2e-05,
"loss": 0.6119,
"step": 9900
},
{
"epoch": 0.8294969448397087,
"grad_norm": 0.4318464696407318,
"learning_rate": 2e-05,
"loss": 0.6222,
"step": 9910
},
{
"epoch": 0.8303339750564995,
"grad_norm": 0.48508167266845703,
"learning_rate": 2e-05,
"loss": 0.6336,
"step": 9920
},
{
"epoch": 0.8311710052732904,
"grad_norm": 0.42082536220550537,
"learning_rate": 2e-05,
"loss": 0.6164,
"step": 9930
},
{
"epoch": 0.8320080354900812,
"grad_norm": 0.37225547432899475,
"learning_rate": 2e-05,
"loss": 0.6375,
"step": 9940
},
{
"epoch": 0.832845065706872,
"grad_norm": 0.4065360724925995,
"learning_rate": 2e-05,
"loss": 0.6103,
"step": 9950
},
{
"epoch": 0.8336820959236628,
"grad_norm": 0.3439057767391205,
"learning_rate": 2e-05,
"loss": 0.602,
"step": 9960
},
{
"epoch": 0.8345191261404536,
"grad_norm": 0.34860286116600037,
"learning_rate": 2e-05,
"loss": 0.6097,
"step": 9970
},
{
"epoch": 0.8353561563572445,
"grad_norm": 0.35745686292648315,
"learning_rate": 2e-05,
"loss": 0.6318,
"step": 9980
},
{
"epoch": 0.8361931865740353,
"grad_norm": 0.37750235199928284,
"learning_rate": 2e-05,
"loss": 0.6111,
"step": 9990
},
{
"epoch": 0.8370302167908261,
"grad_norm": 0.37214308977127075,
"learning_rate": 2e-05,
"loss": 0.5948,
"step": 10000
},
{
"epoch": 0.8378672470076169,
"grad_norm": 0.3304697573184967,
"learning_rate": 2e-05,
"loss": 0.6271,
"step": 10010
},
{
"epoch": 0.8387042772244078,
"grad_norm": 0.38082876801490784,
"learning_rate": 2e-05,
"loss": 0.5802,
"step": 10020
},
{
"epoch": 0.8395413074411986,
"grad_norm": 0.35758861899375916,
"learning_rate": 2e-05,
"loss": 0.6184,
"step": 10030
},
{
"epoch": 0.8403783376579894,
"grad_norm": 0.3510086238384247,
"learning_rate": 2e-05,
"loss": 0.6091,
"step": 10040
},
{
"epoch": 0.8412153678747802,
"grad_norm": 0.35117197036743164,
"learning_rate": 2e-05,
"loss": 0.6467,
"step": 10050
},
{
"epoch": 0.8420523980915711,
"grad_norm": 0.3920142948627472,
"learning_rate": 2e-05,
"loss": 0.6129,
"step": 10060
},
{
"epoch": 0.8428894283083619,
"grad_norm": 0.37400299310684204,
"learning_rate": 2e-05,
"loss": 0.6199,
"step": 10070
},
{
"epoch": 0.8437264585251527,
"grad_norm": 0.3962348401546478,
"learning_rate": 2e-05,
"loss": 0.626,
"step": 10080
},
{
"epoch": 0.8445634887419435,
"grad_norm": 0.3788360059261322,
"learning_rate": 2e-05,
"loss": 0.6385,
"step": 10090
},
{
"epoch": 0.8454005189587344,
"grad_norm": 0.3845363259315491,
"learning_rate": 2e-05,
"loss": 0.6087,
"step": 10100
},
{
"epoch": 0.8462375491755252,
"grad_norm": 0.35839444398880005,
"learning_rate": 2e-05,
"loss": 0.6439,
"step": 10110
},
{
"epoch": 0.847074579392316,
"grad_norm": 0.3566266894340515,
"learning_rate": 2e-05,
"loss": 0.6194,
"step": 10120
},
{
"epoch": 0.8479116096091069,
"grad_norm": 0.41644003987312317,
"learning_rate": 2e-05,
"loss": 0.6275,
"step": 10130
},
{
"epoch": 0.8487486398258978,
"grad_norm": 0.690693199634552,
"learning_rate": 2e-05,
"loss": 0.6116,
"step": 10140
},
{
"epoch": 0.8495856700426886,
"grad_norm": 0.36446458101272583,
"learning_rate": 2e-05,
"loss": 0.611,
"step": 10150
},
{
"epoch": 0.8504227002594794,
"grad_norm": 0.3604367673397064,
"learning_rate": 2e-05,
"loss": 0.5857,
"step": 10160
},
{
"epoch": 0.8512597304762702,
"grad_norm": 0.4150809943675995,
"learning_rate": 2e-05,
"loss": 0.6254,
"step": 10170
},
{
"epoch": 0.8520967606930611,
"grad_norm": 0.7485426664352417,
"learning_rate": 1.999957358086795e-05,
"loss": 0.5828,
"step": 10180
},
{
"epoch": 0.8529337909098519,
"grad_norm": 0.40085193514823914,
"learning_rate": 1.9991993813020483e-05,
"loss": 0.6095,
"step": 10190
},
{
"epoch": 0.8537708211266427,
"grad_norm": 0.3835459053516388,
"learning_rate": 1.9974946373028628e-05,
"loss": 0.6153,
"step": 10200
},
{
"epoch": 0.8546078513434335,
"grad_norm": 0.4353942573070526,
"learning_rate": 1.994844749501764e-05,
"loss": 0.6221,
"step": 10210
},
{
"epoch": 0.8554448815602244,
"grad_norm": 0.3906109929084778,
"learning_rate": 1.9912522413632988e-05,
"loss": 0.6086,
"step": 10220
},
{
"epoch": 0.8562819117770152,
"grad_norm": 0.38756048679351807,
"learning_rate": 1.9867205340009656e-05,
"loss": 0.611,
"step": 10230
},
{
"epoch": 0.857118941993806,
"grad_norm": 0.3337929844856262,
"learning_rate": 1.9812539429193164e-05,
"loss": 0.5898,
"step": 10240
},
{
"epoch": 0.8579559722105968,
"grad_norm": 0.35246601700782776,
"learning_rate": 1.9748576739043423e-05,
"loss": 0.6305,
"step": 10250
},
{
"epoch": 0.8587930024273877,
"grad_norm": 0.35268184542655945,
"learning_rate": 1.967537818066047e-05,
"loss": 0.6252,
"step": 10260
},
{
"epoch": 0.8596300326441785,
"grad_norm": 0.37320220470428467,
"learning_rate": 1.959301346037941e-05,
"loss": 0.6127,
"step": 10270
},
{
"epoch": 0.8604670628609693,
"grad_norm": 0.4707813560962677,
"learning_rate": 1.9501561013389646e-05,
"loss": 0.6008,
"step": 10280
},
{
"epoch": 0.8613040930777601,
"grad_norm": 0.3598954677581787,
"learning_rate": 1.9401107929041795e-05,
"loss": 0.6294,
"step": 10290
},
{
"epoch": 0.862141123294551,
"grad_norm": 0.3455922305583954,
"learning_rate": 1.9291749867913225e-05,
"loss": 0.6056,
"step": 10300
},
{
"epoch": 0.8629781535113418,
"grad_norm": 0.35194408893585205,
"learning_rate": 1.91735909707114e-05,
"loss": 0.6066,
"step": 10310
},
{
"epoch": 0.8638151837281326,
"grad_norm": 0.3290748596191406,
"learning_rate": 1.9046743759101545e-05,
"loss": 0.5989,
"step": 10320
},
{
"epoch": 0.8646522139449234,
"grad_norm": 0.36974453926086426,
"learning_rate": 1.8911329028553324e-05,
"loss": 0.6415,
"step": 10330
},
{
"epoch": 0.8654892441617142,
"grad_norm": 0.3532561957836151,
"learning_rate": 1.876747573330835e-05,
"loss": 0.6381,
"step": 10340
},
{
"epoch": 0.8663262743785051,
"grad_norm": 0.3644556403160095,
"learning_rate": 1.8615320863578244e-05,
"loss": 0.6182,
"step": 10350
},
{
"epoch": 0.8671633045952959,
"grad_norm": 0.34960946440696716,
"learning_rate": 1.8455009315090036e-05,
"loss": 0.6138,
"step": 10360
},
{
"epoch": 0.8680003348120867,
"grad_norm": 0.39046117663383484,
"learning_rate": 1.8286693751103294e-05,
"loss": 0.6369,
"step": 10370
},
{
"epoch": 0.8688373650288775,
"grad_norm": 0.6220808625221252,
"learning_rate": 1.811053445703024e-05,
"loss": 0.5812,
"step": 10380
},
{
"epoch": 0.8696743952456684,
"grad_norm": 0.42720869183540344,
"learning_rate": 1.7926699187797375e-05,
"loss": 0.6012,
"step": 10390
},
{
"epoch": 0.8705114254624592,
"grad_norm": 0.364810049533844,
"learning_rate": 1.7735363008093995e-05,
"loss": 0.6154,
"step": 10400
},
{
"epoch": 0.87134845567925,
"grad_norm": 0.4052015244960785,
"learning_rate": 1.7536708125659577e-05,
"loss": 0.6595,
"step": 10410
},
{
"epoch": 0.8721854858960408,
"grad_norm": 0.3937699496746063,
"learning_rate": 1.733092371776905e-05,
"loss": 0.6393,
"step": 10420
},
{
"epoch": 0.8730225161128317,
"grad_norm": 0.3622001111507416,
"learning_rate": 1.7118205751080915e-05,
"loss": 0.609,
"step": 10430
},
{
"epoch": 0.8738595463296225,
"grad_norm": 0.3573143780231476,
"learning_rate": 1.6898756795019935e-05,
"loss": 0.6142,
"step": 10440
},
{
"epoch": 0.8746965765464133,
"grad_norm": 0.3644012212753296,
"learning_rate": 1.667278582887211e-05,
"loss": 0.5902,
"step": 10450
},
{
"epoch": 0.8755336067632041,
"grad_norm": 0.37499353289604187,
"learning_rate": 1.6440508042775545e-05,
"loss": 0.634,
"step": 10460
},
{
"epoch": 0.876370636979995,
"grad_norm": 0.39060723781585693,
"learning_rate": 1.6202144632796796e-05,
"loss": 0.6097,
"step": 10470
},
{
"epoch": 0.8772076671967858,
"grad_norm": 0.367694616317749,
"learning_rate": 1.595792259028783e-05,
"loss": 0.608,
"step": 10480
},
{
"epoch": 0.8780446974135766,
"grad_norm": 0.3774787187576294,
"learning_rate": 1.570807448572419e-05,
"loss": 0.6294,
"step": 10490
},
{
"epoch": 0.8788817276303674,
"grad_norm": 0.43220317363739014,
"learning_rate": 1.5452838247230197e-05,
"loss": 0.6224,
"step": 10500
},
{
"epoch": 0.8797187578471583,
"grad_norm": 0.3842547833919525,
"learning_rate": 1.5192456934002106e-05,
"loss": 0.5915,
"step": 10510
},
{
"epoch": 0.8805557880639491,
"grad_norm": 0.47000840306282043,
"learning_rate": 1.492717850484502e-05,
"loss": 0.6131,
"step": 10520
},
{
"epoch": 0.8813928182807399,
"grad_norm": 0.3147537410259247,
"learning_rate": 1.4657255582043904e-05,
"loss": 0.6242,
"step": 10530
},
{
"epoch": 0.8822298484975307,
"grad_norm": 0.39530083537101746,
"learning_rate": 1.4382945210793663e-05,
"loss": 0.6279,
"step": 10540
},
{
"epoch": 0.8830668787143215,
"grad_norm": 0.35616403818130493,
"learning_rate": 1.4104508614417267e-05,
"loss": 0.6086,
"step": 10550
},
{
"epoch": 0.8839039089311124,
"grad_norm": 0.4383719563484192,
"learning_rate": 1.382221094560512e-05,
"loss": 0.6205,
"step": 10560
},
{
"epoch": 0.8847409391479032,
"grad_norm": 0.33425262570381165,
"learning_rate": 1.3536321033912506e-05,
"loss": 0.6442,
"step": 10570
},
{
"epoch": 0.885577969364694,
"grad_norm": 0.36328378319740295,
"learning_rate": 1.3247111129755609e-05,
"loss": 0.5914,
"step": 10580
},
{
"epoch": 0.8864149995814848,
"grad_norm": 0.3541567027568817,
"learning_rate": 1.2954856645149868e-05,
"loss": 0.6201,
"step": 10590
},
{
"epoch": 0.8872520297982757,
"grad_norm": 0.39288944005966187,
"learning_rate": 1.2659835891437553e-05,
"loss": 0.6264,
"step": 10600
},
{
"epoch": 0.8880890600150665,
"grad_norm": 0.3486575782299042,
"learning_rate": 1.236232981425436e-05,
"loss": 0.5637,
"step": 10610
},
{
"epoch": 0.8889260902318574,
"grad_norm": 0.3532477915287018,
"learning_rate": 1.2062621725987402e-05,
"loss": 0.592,
"step": 10620
},
{
"epoch": 0.8897631204486482,
"grad_norm": 0.36439892649650574,
"learning_rate": 1.1760997035979318e-05,
"loss": 0.6297,
"step": 10630
},
{
"epoch": 0.8906001506654391,
"grad_norm": 0.37439948320388794,
"learning_rate": 1.1457742978735514e-05,
"loss": 0.6192,
"step": 10640
},
{
"epoch": 0.8914371808822299,
"grad_norm": 0.41263723373413086,
"learning_rate": 1.1153148340393298e-05,
"loss": 0.5706,
"step": 10650
},
{
"epoch": 0.8922742110990207,
"grad_norm": 0.353598952293396,
"learning_rate": 1.0847503183713424e-05,
"loss": 0.6118,
"step": 10660
},
{
"epoch": 0.8931112413158115,
"grad_norm": 0.39881426095962524,
"learning_rate": 1.0541098571855896e-05,
"loss": 0.5964,
"step": 10670
},
{
"epoch": 0.8939482715326024,
"grad_norm": 0.3593898117542267,
"learning_rate": 1.0234226291203123e-05,
"loss": 0.5827,
"step": 10680
},
{
"epoch": 0.8947853017493932,
"grad_norm": 0.3899114727973938,
"learning_rate": 9.927178573494333e-06,
"loss": 0.6307,
"step": 10690
},
{
"epoch": 0.895622331966184,
"grad_norm": 0.3991129398345947,
"learning_rate": 9.620247817535902e-06,
"loss": 0.608,
"step": 10700
},
{
"epoch": 0.8964593621829748,
"grad_norm": 0.32787102460861206,
"learning_rate": 9.313726310752581e-06,
"loss": 0.6169,
"step": 10710
},
{
"epoch": 0.8972963923997657,
"grad_norm": 0.37895214557647705,
"learning_rate": 9.00790595084477e-06,
"loss": 0.603,
"step": 10720
},
{
"epoch": 0.8981334226165565,
"grad_norm": 0.37545907497406006,
"learning_rate": 8.703077967816944e-06,
"loss": 0.5913,
"step": 10730
},
{
"epoch": 0.8989704528333473,
"grad_norm": 0.41248559951782227,
"learning_rate": 8.39953264664192e-06,
"loss": 0.5932,
"step": 10740
},
{
"epoch": 0.8998074830501381,
"grad_norm": 0.37453097105026245,
"learning_rate": 8.097559050825058e-06,
"loss": 0.5913,
"step": 10750
},
{
"epoch": 0.900644513266929,
"grad_norm": 0.334861159324646,
"learning_rate": 7.79744474713166e-06,
"loss": 0.5874,
"step": 10760
},
{
"epoch": 0.9014815434837198,
"grad_norm": 0.5139070749282837,
"learning_rate": 7.499475531739696e-06,
"loss": 0.6148,
"step": 10770
},
{
"epoch": 0.9023185737005106,
"grad_norm": 0.405596524477005,
"learning_rate": 7.203935158078662e-06,
"loss": 0.6082,
"step": 10780
},
{
"epoch": 0.9031556039173014,
"grad_norm": 0.35360997915267944,
"learning_rate": 6.911105066613709e-06,
"loss": 0.6039,
"step": 10790
},
{
"epoch": 0.9039926341340923,
"grad_norm": 0.3629005551338196,
"learning_rate": 6.621264116832394e-06,
"loss": 0.6,
"step": 10800
},
{
"epoch": 0.9048296643508831,
"grad_norm": 0.3518105149269104,
"learning_rate": 6.334688321689274e-06,
"loss": 0.6136,
"step": 10810
},
{
"epoch": 0.9056666945676739,
"grad_norm": 0.3385161757469177,
"learning_rate": 6.051650584761237e-06,
"loss": 0.5971,
"step": 10820
},
{
"epoch": 0.9065037247844647,
"grad_norm": 0.4495178163051605,
"learning_rate": 5.772420440363841e-06,
"loss": 0.6179,
"step": 10830
},
{
"epoch": 0.9073407550012556,
"grad_norm": 0.33703598380088806,
"learning_rate": 5.497263796876207e-06,
"loss": 0.5645,
"step": 10840
},
{
"epoch": 0.9081777852180464,
"grad_norm": 0.36705470085144043,
"learning_rate": 5.226442683518813e-06,
"loss": 0.6092,
"step": 10850
},
{
"epoch": 0.9090148154348372,
"grad_norm": 0.37629008293151855,
"learning_rate": 4.960215000825432e-06,
"loss": 0.6008,
"step": 10860
},
{
"epoch": 0.909851845651628,
"grad_norm": 0.3484477996826172,
"learning_rate": 4.698834275046711e-06,
"loss": 0.6254,
"step": 10870
},
{
"epoch": 0.9106888758684188,
"grad_norm": 0.32401078939437866,
"learning_rate": 4.442549416719423e-06,
"loss": 0.6048,
"step": 10880
},
{
"epoch": 0.9115259060852097,
"grad_norm": 0.3878401219844818,
"learning_rate": 4.1916044836311565e-06,
"loss": 0.6195,
"step": 10890
},
{
"epoch": 0.9123629363020005,
"grad_norm": 0.3420516550540924,
"learning_rate": 3.94623844840626e-06,
"loss": 0.563,
"step": 10900
},
{
"epoch": 0.9131999665187913,
"grad_norm": 0.36567628383636475,
"learning_rate": 3.7066849709343467e-06,
"loss": 0.5984,
"step": 10910
},
{
"epoch": 0.9140369967355821,
"grad_norm": 0.394072949886322,
"learning_rate": 3.473172175858059e-06,
"loss": 0.5985,
"step": 10920
},
{
"epoch": 0.914874026952373,
"grad_norm": 0.40274447202682495,
"learning_rate": 3.2459224353320046e-06,
"loss": 0.6132,
"step": 10930
},
{
"epoch": 0.9157110571691638,
"grad_norm": 0.37817761301994324,
"learning_rate": 3.025152157259735e-06,
"loss": 0.6138,
"step": 10940
},
{
"epoch": 0.9165480873859546,
"grad_norm": 0.3820495903491974,
"learning_rate": 2.811071579210425e-06,
"loss": 0.5878,
"step": 10950
},
{
"epoch": 0.9173851176027454,
"grad_norm": 0.38701289892196655,
"learning_rate": 2.603884568211513e-06,
"loss": 0.5899,
"step": 10960
},
{
"epoch": 0.9182221478195363,
"grad_norm": 0.3448856770992279,
"learning_rate": 2.4037884266079434e-06,
"loss": 0.6166,
"step": 10970
},
{
"epoch": 0.9190591780363271,
"grad_norm": 0.34730589389801025,
"learning_rate": 2.2109737041728955e-06,
"loss": 0.5803,
"step": 10980
},
{
"epoch": 0.9198962082531179,
"grad_norm": 0.3200985789299011,
"learning_rate": 2.0256240166489454e-06,
"loss": 0.5816,
"step": 10990
},
{
"epoch": 0.9207332384699087,
"grad_norm": 0.48213061690330505,
"learning_rate": 1.847915870892413e-06,
"loss": 0.6243,
"step": 11000
},
{
"epoch": 0.9215702686866996,
"grad_norm": 0.3733295500278473,
"learning_rate": 1.6780184967874715e-06,
"loss": 0.6135,
"step": 11010
},
{
"epoch": 0.9224072989034904,
"grad_norm": 0.3837072253227234,
"learning_rate": 1.5160936860900294e-06,
"loss": 0.6305,
"step": 11020
},
{
"epoch": 0.9232443291202812,
"grad_norm": 0.33880406618118286,
"learning_rate": 1.3622956383548762e-06,
"loss": 0.6266,
"step": 11030
},
{
"epoch": 0.924081359337072,
"grad_norm": 0.3343767523765564,
"learning_rate": 1.216770814092834e-06,
"loss": 0.6163,
"step": 11040
},
{
"epoch": 0.9249183895538629,
"grad_norm": 0.3547482490539551,
"learning_rate": 1.0796577952977013e-06,
"loss": 0.5669,
"step": 11050
},
{
"epoch": 0.9257554197706537,
"grad_norm": 0.3457980453968048,
"learning_rate": 9.510871534758705e-07,
"loss": 0.6015,
"step": 11060
},
{
"epoch": 0.9265924499874445,
"grad_norm": 0.32496410608291626,
"learning_rate": 8.311813253042334e-07,
"loss": 0.5854,
"step": 11070
},
{
"epoch": 0.9274294802042353,
"grad_norm": 0.3630751967430115,
"learning_rate": 7.200544960348308e-07,
"loss": 0.5813,
"step": 11080
},
{
"epoch": 0.9282665104210261,
"grad_norm": 0.3603667914867401,
"learning_rate": 6.178124907572545e-07,
"loss": 0.6052,
"step": 11090
},
{
"epoch": 0.929103540637817,
"grad_norm": 0.36034899950027466,
"learning_rate": 5.245526736223528e-07,
"loss": 0.5952,
"step": 11100
},
{
"epoch": 0.9299405708546079,
"grad_norm": 0.3739122748374939,
"learning_rate": 4.403638551232205e-07,
"loss": 0.5812,
"step": 11110
},
{
"epoch": 0.9307776010713987,
"grad_norm": 0.35268348455429077,
"learning_rate": 3.6532620752175616e-07,
"loss": 0.5956,
"step": 11120
},
{
"epoch": 0.9316146312881896,
"grad_norm": 0.375112384557724,
"learning_rate": 2.9951118850133247e-07,
"loss": 0.6201,
"step": 11130
},
{
"epoch": 0.9324516615049804,
"grad_norm": 0.3165109157562256,
"learning_rate": 2.429814731182774e-07,
"loss": 0.5721,
"step": 11140
},
{
"epoch": 0.9332886917217712,
"grad_norm": 0.4722680449485779,
"learning_rate": 1.957908941169813e-07,
"loss": 0.6219,
"step": 11150
},
{
"epoch": 0.934125721938562,
"grad_norm": 0.3671278655529022,
"learning_rate": 1.5798439066545254e-07,
"loss": 0.5932,
"step": 11160
},
{
"epoch": 0.9349627521553528,
"grad_norm": 0.36083364486694336,
"learning_rate": 1.2959796556014471e-07,
"loss": 0.589,
"step": 11170
},
{
"epoch": 0.9357997823721437,
"grad_norm": 0.3682437539100647,
"learning_rate": 1.1065865094081884e-07,
"loss": 0.6063,
"step": 11180
},
{
"epoch": 0.9366368125889345,
"grad_norm": 0.3515765070915222,
"learning_rate": 1.011844825480734e-07,
"loss": 0.5984,
"step": 11190
},
{
"epoch": 0.9369716246756508,
"step": 11194,
"total_flos": 4.547514943786923e+19,
"train_loss": 0.003452657950399432,
"train_runtime": 609.5586,
"train_samples_per_second": 220.369,
"train_steps_per_second": 18.364
}
],
"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
}