{
  "best_metric": 1.0107625722885132,
  "best_model_checkpoint": "/data/Andre/Ref-Finder-Mistral/checkpoint-3170",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 3170,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.031545741324921134,
      "grad_norm": 0.5029881000518799,
      "learning_rate": 5e-05,
      "loss": 1.7154,
      "step": 10
    },
    {
      "epoch": 0.06309148264984227,
      "grad_norm": 0.3064497709274292,
      "learning_rate": 5e-05,
      "loss": 1.5963,
      "step": 20
    },
    {
      "epoch": 0.0946372239747634,
      "grad_norm": 0.3118360638618469,
      "learning_rate": 5e-05,
      "loss": 1.5074,
      "step": 30
    },
    {
      "epoch": 0.12618296529968454,
      "grad_norm": 0.33069083094596863,
      "learning_rate": 5e-05,
      "loss": 1.4047,
      "step": 40
    },
    {
      "epoch": 0.15772870662460567,
      "grad_norm": 0.2797032296657562,
      "learning_rate": 5e-05,
      "loss": 1.4167,
      "step": 50
    },
    {
      "epoch": 0.1892744479495268,
      "grad_norm": 0.3190701901912689,
      "learning_rate": 5e-05,
      "loss": 1.3361,
      "step": 60
    },
    {
      "epoch": 0.22082018927444794,
      "grad_norm": 0.3070685863494873,
      "learning_rate": 5e-05,
      "loss": 1.2655,
      "step": 70
    },
    {
      "epoch": 0.25236593059936907,
      "grad_norm": 0.3203960359096527,
      "learning_rate": 5e-05,
      "loss": 1.2295,
      "step": 80
    },
    {
      "epoch": 0.28391167192429023,
      "grad_norm": 0.30132830142974854,
      "learning_rate": 5e-05,
      "loss": 1.2277,
      "step": 90
    },
    {
      "epoch": 0.31545741324921134,
      "grad_norm": 0.3356678783893585,
      "learning_rate": 5e-05,
      "loss": 1.1848,
      "step": 100
    },
    {
      "epoch": 0.3470031545741325,
      "grad_norm": 0.3275781273841858,
      "learning_rate": 5e-05,
      "loss": 1.183,
      "step": 110
    },
    {
      "epoch": 0.3785488958990536,
      "grad_norm": 0.30640777945518494,
      "learning_rate": 5e-05,
      "loss": 1.1488,
      "step": 120
    },
    {
      "epoch": 0.41009463722397477,
      "grad_norm": 0.5068441033363342,
      "learning_rate": 5e-05,
      "loss": 1.147,
      "step": 130
    },
    {
      "epoch": 0.4416403785488959,
      "grad_norm": 0.310285747051239,
      "learning_rate": 5e-05,
      "loss": 1.1908,
      "step": 140
    },
    {
      "epoch": 0.47318611987381703,
      "grad_norm": 0.38677722215652466,
      "learning_rate": 5e-05,
      "loss": 1.1319,
      "step": 150
    },
    {
      "epoch": 0.5047318611987381,
      "grad_norm": 0.3474641740322113,
      "learning_rate": 5e-05,
      "loss": 1.1215,
      "step": 160
    },
    {
      "epoch": 0.5362776025236593,
      "grad_norm": 0.37211593985557556,
      "learning_rate": 5e-05,
      "loss": 1.1503,
      "step": 170
    },
    {
      "epoch": 0.5678233438485805,
      "grad_norm": 0.3207016885280609,
      "learning_rate": 5e-05,
      "loss": 1.182,
      "step": 180
    },
    {
      "epoch": 0.5993690851735016,
      "grad_norm": 0.34209126234054565,
      "learning_rate": 5e-05,
      "loss": 1.1298,
      "step": 190
    },
    {
      "epoch": 0.6309148264984227,
      "grad_norm": 0.3956719934940338,
      "learning_rate": 5e-05,
      "loss": 1.1443,
      "step": 200
    },
    {
      "epoch": 0.6624605678233438,
      "grad_norm": 0.34193623065948486,
      "learning_rate": 5e-05,
      "loss": 1.1148,
      "step": 210
    },
    {
      "epoch": 0.694006309148265,
      "grad_norm": 0.3550577759742737,
      "learning_rate": 5e-05,
      "loss": 1.1091,
      "step": 220
    },
    {
      "epoch": 0.7255520504731862,
      "grad_norm": 0.34275463223457336,
      "learning_rate": 5e-05,
      "loss": 1.1185,
      "step": 230
    },
    {
      "epoch": 0.7570977917981072,
      "grad_norm": 0.36972326040267944,
      "learning_rate": 5e-05,
      "loss": 1.1388,
      "step": 240
    },
    {
      "epoch": 0.7886435331230284,
      "grad_norm": 0.36260902881622314,
      "learning_rate": 5e-05,
      "loss": 1.0982,
      "step": 250
    },
    {
      "epoch": 0.8201892744479495,
      "grad_norm": 0.35559672117233276,
      "learning_rate": 5e-05,
      "loss": 1.1032,
      "step": 260
    },
    {
      "epoch": 0.8517350157728707,
      "grad_norm": 0.3544253706932068,
      "learning_rate": 5e-05,
      "loss": 1.1239,
      "step": 270
    },
    {
      "epoch": 0.8832807570977917,
      "grad_norm": 0.3803843855857849,
      "learning_rate": 5e-05,
      "loss": 1.1006,
      "step": 280
    },
    {
      "epoch": 0.9148264984227129,
      "grad_norm": 0.3776736855506897,
      "learning_rate": 5e-05,
      "loss": 1.1001,
      "step": 290
    },
    {
      "epoch": 0.9463722397476341,
      "grad_norm": 0.4238007068634033,
      "learning_rate": 5e-05,
      "loss": 1.0968,
      "step": 300
    },
    {
      "epoch": 0.9779179810725552,
      "grad_norm": 0.4062643051147461,
      "learning_rate": 5e-05,
      "loss": 1.1188,
      "step": 310
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.1006102561950684,
      "eval_runtime": 66.4381,
      "eval_samples_per_second": 4.786,
      "eval_steps_per_second": 0.602,
      "step": 317
    },
    {
      "epoch": 1.0094637223974763,
      "grad_norm": 0.3485482633113861,
      "learning_rate": 5e-05,
      "loss": 1.0843,
      "step": 320
    },
    {
      "epoch": 1.0410094637223974,
      "grad_norm": 0.40558719635009766,
      "learning_rate": 5e-05,
      "loss": 1.097,
      "step": 330
    },
    {
      "epoch": 1.0725552050473186,
      "grad_norm": 0.4074763059616089,
      "learning_rate": 5e-05,
      "loss": 1.0697,
      "step": 340
    },
    {
      "epoch": 1.1041009463722398,
      "grad_norm": 0.40961453318595886,
      "learning_rate": 5e-05,
      "loss": 1.0635,
      "step": 350
    },
    {
      "epoch": 1.135646687697161,
      "grad_norm": 0.3752257227897644,
      "learning_rate": 5e-05,
      "loss": 1.0936,
      "step": 360
    },
    {
      "epoch": 1.167192429022082,
      "grad_norm": 0.3867760896682739,
      "learning_rate": 5e-05,
      "loss": 1.0782,
      "step": 370
    },
    {
      "epoch": 1.1987381703470033,
      "grad_norm": 0.4072268307209015,
      "learning_rate": 5e-05,
      "loss": 1.0574,
      "step": 380
    },
    {
      "epoch": 1.2302839116719242,
      "grad_norm": 0.3942580819129944,
      "learning_rate": 5e-05,
      "loss": 1.1081,
      "step": 390
    },
    {
      "epoch": 1.2618296529968454,
      "grad_norm": 0.4262318015098572,
      "learning_rate": 5e-05,
      "loss": 1.0821,
      "step": 400
    },
    {
      "epoch": 1.2933753943217665,
      "grad_norm": 0.39012083411216736,
      "learning_rate": 5e-05,
      "loss": 1.0712,
      "step": 410
    },
    {
      "epoch": 1.3249211356466877,
      "grad_norm": 0.4160712659358978,
      "learning_rate": 5e-05,
      "loss": 1.1106,
      "step": 420
    },
    {
      "epoch": 1.3564668769716088,
      "grad_norm": 0.3966641128063202,
      "learning_rate": 5e-05,
      "loss": 1.0411,
      "step": 430
    },
    {
      "epoch": 1.38801261829653,
      "grad_norm": 0.3720882833003998,
      "learning_rate": 5e-05,
      "loss": 1.0815,
      "step": 440
    },
    {
      "epoch": 1.4195583596214512,
      "grad_norm": 0.396207332611084,
      "learning_rate": 5e-05,
      "loss": 1.0462,
      "step": 450
    },
    {
      "epoch": 1.4511041009463723,
      "grad_norm": 0.38164132833480835,
      "learning_rate": 5e-05,
      "loss": 1.0891,
      "step": 460
    },
    {
      "epoch": 1.4826498422712935,
      "grad_norm": 0.38896164298057556,
      "learning_rate": 5e-05,
      "loss": 1.0905,
      "step": 470
    },
    {
      "epoch": 1.5141955835962144,
      "grad_norm": 0.4327830374240875,
      "learning_rate": 5e-05,
      "loss": 1.1205,
      "step": 480
    },
    {
      "epoch": 1.5457413249211358,
      "grad_norm": 0.423364520072937,
      "learning_rate": 5e-05,
      "loss": 1.0477,
      "step": 490
    },
    {
      "epoch": 1.5772870662460567,
      "grad_norm": 0.4212876558303833,
      "learning_rate": 5e-05,
      "loss": 1.12,
      "step": 500
    },
    {
      "epoch": 1.608832807570978,
      "grad_norm": 0.3814271092414856,
      "learning_rate": 5e-05,
      "loss": 1.0695,
      "step": 510
    },
    {
      "epoch": 1.640378548895899,
      "grad_norm": 0.3973582983016968,
      "learning_rate": 5e-05,
      "loss": 1.0832,
      "step": 520
    },
    {
      "epoch": 1.6719242902208202,
      "grad_norm": 0.4016555845737457,
      "learning_rate": 5e-05,
      "loss": 1.077,
      "step": 530
    },
    {
      "epoch": 1.7034700315457414,
      "grad_norm": 0.4084228575229645,
      "learning_rate": 5e-05,
      "loss": 1.0674,
      "step": 540
    },
    {
      "epoch": 1.7350157728706623,
      "grad_norm": 0.4218040406703949,
      "learning_rate": 5e-05,
      "loss": 1.0464,
      "step": 550
    },
    {
      "epoch": 1.7665615141955837,
      "grad_norm": 0.3857240080833435,
      "learning_rate": 5e-05,
      "loss": 1.0656,
      "step": 560
    },
    {
      "epoch": 1.7981072555205047,
      "grad_norm": 0.3926863968372345,
      "learning_rate": 5e-05,
      "loss": 1.056,
      "step": 570
    },
    {
      "epoch": 1.8296529968454258,
      "grad_norm": 0.4352160096168518,
      "learning_rate": 5e-05,
      "loss": 1.0443,
      "step": 580
    },
    {
      "epoch": 1.861198738170347,
      "grad_norm": 0.4079754650592804,
      "learning_rate": 5e-05,
      "loss": 1.0502,
      "step": 590
    },
    {
      "epoch": 1.8927444794952681,
      "grad_norm": 0.40210971236228943,
      "learning_rate": 5e-05,
      "loss": 1.0613,
      "step": 600
    },
    {
      "epoch": 1.9242902208201893,
      "grad_norm": 0.3993563950061798,
      "learning_rate": 5e-05,
      "loss": 1.0341,
      "step": 610
    },
    {
      "epoch": 1.9558359621451105,
      "grad_norm": 0.47853732109069824,
      "learning_rate": 5e-05,
      "loss": 1.0071,
      "step": 620
    },
    {
      "epoch": 1.9873817034700316,
      "grad_norm": 0.42926380038261414,
      "learning_rate": 5e-05,
      "loss": 1.0383,
      "step": 630
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.0646495819091797,
      "eval_runtime": 66.4837,
      "eval_samples_per_second": 4.783,
      "eval_steps_per_second": 0.602,
      "step": 634
    },
    {
      "epoch": 2.0189274447949526,
      "grad_norm": 0.3886430561542511,
      "learning_rate": 5e-05,
      "loss": 1.0667,
      "step": 640
    },
    {
      "epoch": 2.050473186119874,
      "grad_norm": 0.4253116846084595,
      "learning_rate": 5e-05,
      "loss": 1.0323,
      "step": 650
    },
    {
      "epoch": 2.082018927444795,
      "grad_norm": 0.40994375944137573,
      "learning_rate": 5e-05,
      "loss": 1.0027,
      "step": 660
    },
    {
      "epoch": 2.1135646687697163,
      "grad_norm": 0.3847936689853668,
      "learning_rate": 5e-05,
      "loss": 1.0022,
      "step": 670
    },
    {
      "epoch": 2.145110410094637,
      "grad_norm": 0.43215593695640564,
      "learning_rate": 5e-05,
      "loss": 1.0564,
      "step": 680
    },
    {
      "epoch": 2.176656151419558,
      "grad_norm": 0.4463648498058319,
      "learning_rate": 5e-05,
      "loss": 1.0277,
      "step": 690
    },
    {
      "epoch": 2.2082018927444795,
      "grad_norm": 0.42896410822868347,
      "learning_rate": 5e-05,
      "loss": 1.0466,
      "step": 700
    },
    {
      "epoch": 2.2397476340694005,
      "grad_norm": 0.4028797149658203,
      "learning_rate": 5e-05,
      "loss": 1.0588,
      "step": 710
    },
    {
      "epoch": 2.271293375394322,
      "grad_norm": 0.4177733361721039,
      "learning_rate": 5e-05,
      "loss": 1.0519,
      "step": 720
    },
    {
      "epoch": 2.302839116719243,
      "grad_norm": 0.42829203605651855,
      "learning_rate": 5e-05,
      "loss": 1.0202,
      "step": 730
    },
    {
      "epoch": 2.334384858044164,
      "grad_norm": 0.5054190158843994,
      "learning_rate": 5e-05,
      "loss": 0.9972,
      "step": 740
    },
    {
      "epoch": 2.365930599369085,
      "grad_norm": 0.4306070804595947,
      "learning_rate": 5e-05,
      "loss": 1.0412,
      "step": 750
    },
    {
      "epoch": 2.3974763406940065,
      "grad_norm": 0.443590372800827,
      "learning_rate": 5e-05,
      "loss": 1.0424,
      "step": 760
    },
    {
      "epoch": 2.4290220820189274,
      "grad_norm": 0.4287286400794983,
      "learning_rate": 5e-05,
      "loss": 1.0331,
      "step": 770
    },
    {
      "epoch": 2.4605678233438484,
      "grad_norm": 0.39775350689888,
      "learning_rate": 5e-05,
      "loss": 1.0454,
      "step": 780
    },
    {
      "epoch": 2.4921135646687698,
      "grad_norm": 0.4093973636627197,
      "learning_rate": 5e-05,
      "loss": 1.0442,
      "step": 790
    },
    {
      "epoch": 2.5236593059936907,
      "grad_norm": 0.45389777421951294,
      "learning_rate": 5e-05,
      "loss": 1.024,
      "step": 800
    },
    {
      "epoch": 2.555205047318612,
      "grad_norm": 0.428648442029953,
      "learning_rate": 5e-05,
      "loss": 1.0407,
      "step": 810
    },
    {
      "epoch": 2.586750788643533,
      "grad_norm": 0.41237714886665344,
      "learning_rate": 5e-05,
      "loss": 1.0159,
      "step": 820
    },
    {
      "epoch": 2.6182965299684544,
      "grad_norm": 0.42067545652389526,
      "learning_rate": 5e-05,
      "loss": 1.0347,
      "step": 830
    },
    {
      "epoch": 2.6498422712933754,
      "grad_norm": 0.4184909462928772,
      "learning_rate": 5e-05,
      "loss": 1.0337,
      "step": 840
    },
    {
      "epoch": 2.6813880126182967,
      "grad_norm": 0.414995014667511,
      "learning_rate": 5e-05,
      "loss": 1.092,
      "step": 850
    },
    {
      "epoch": 2.7129337539432177,
      "grad_norm": 0.4137355089187622,
      "learning_rate": 5e-05,
      "loss": 1.0514,
      "step": 860
    },
    {
      "epoch": 2.7444794952681386,
      "grad_norm": 0.45818576216697693,
      "learning_rate": 5e-05,
      "loss": 1.0225,
      "step": 870
    },
    {
      "epoch": 2.77602523659306,
      "grad_norm": 0.455785870552063,
      "learning_rate": 5e-05,
      "loss": 1.0483,
      "step": 880
    },
    {
      "epoch": 2.807570977917981,
      "grad_norm": 0.4084894061088562,
      "learning_rate": 5e-05,
      "loss": 0.9846,
      "step": 890
    },
    {
      "epoch": 2.8391167192429023,
      "grad_norm": 0.4103436768054962,
      "learning_rate": 5e-05,
      "loss": 1.0217,
      "step": 900
    },
    {
      "epoch": 2.8706624605678233,
      "grad_norm": 0.40420758724212646,
      "learning_rate": 5e-05,
      "loss": 1.0399,
      "step": 910
    },
    {
      "epoch": 2.9022082018927446,
      "grad_norm": 0.5487234592437744,
      "learning_rate": 5e-05,
      "loss": 1.0394,
      "step": 920
    },
    {
      "epoch": 2.9337539432176656,
      "grad_norm": 0.47695016860961914,
      "learning_rate": 5e-05,
      "loss": 1.0445,
      "step": 930
    },
    {
      "epoch": 2.965299684542587,
      "grad_norm": 0.41771531105041504,
      "learning_rate": 5e-05,
      "loss": 1.0377,
      "step": 940
    },
    {
      "epoch": 2.996845425867508,
      "grad_norm": 0.5724055767059326,
      "learning_rate": 5e-05,
      "loss": 1.0193,
      "step": 950
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.0459696054458618,
      "eval_runtime": 66.4844,
      "eval_samples_per_second": 4.783,
      "eval_steps_per_second": 0.602,
      "step": 951
    },
    {
      "epoch": 3.028391167192429,
      "grad_norm": 0.481629878282547,
      "learning_rate": 5e-05,
      "loss": 0.9837,
      "step": 960
    },
    {
      "epoch": 3.0599369085173502,
      "grad_norm": 0.42061686515808105,
      "learning_rate": 5e-05,
      "loss": 1.0083,
      "step": 970
    },
    {
      "epoch": 3.091482649842271,
      "grad_norm": 0.4234108030796051,
      "learning_rate": 5e-05,
      "loss": 1.0249,
      "step": 980
    },
    {
      "epoch": 3.1230283911671926,
      "grad_norm": 0.43123263120651245,
      "learning_rate": 5e-05,
      "loss": 1.0319,
      "step": 990
    },
    {
      "epoch": 3.1545741324921135,
      "grad_norm": 0.4268761873245239,
      "learning_rate": 5e-05,
      "loss": 1.0067,
      "step": 1000
    },
    {
      "epoch": 3.186119873817035,
      "grad_norm": 0.41744470596313477,
      "learning_rate": 5e-05,
      "loss": 1.0316,
      "step": 1010
    },
    {
      "epoch": 3.217665615141956,
      "grad_norm": 0.46088990569114685,
      "learning_rate": 5e-05,
      "loss": 0.9993,
      "step": 1020
    },
    {
      "epoch": 3.249211356466877,
      "grad_norm": 0.43155333399772644,
      "learning_rate": 5e-05,
      "loss": 1.0275,
      "step": 1030
    },
    {
      "epoch": 3.280757097791798,
      "grad_norm": 0.4405035972595215,
      "learning_rate": 5e-05,
      "loss": 1.0014,
      "step": 1040
    },
    {
      "epoch": 3.312302839116719,
      "grad_norm": 0.466680645942688,
      "learning_rate": 5e-05,
      "loss": 1.0066,
      "step": 1050
    },
    {
      "epoch": 3.3438485804416405,
      "grad_norm": 0.4462493360042572,
      "learning_rate": 5e-05,
      "loss": 1.0081,
      "step": 1060
    },
    {
      "epoch": 3.3753943217665614,
      "grad_norm": 0.4766935706138611,
      "learning_rate": 5e-05,
      "loss": 0.9957,
      "step": 1070
    },
    {
      "epoch": 3.406940063091483,
      "grad_norm": 0.4287005364894867,
      "learning_rate": 5e-05,
      "loss": 1.0022,
      "step": 1080
    },
    {
      "epoch": 3.4384858044164037,
      "grad_norm": 0.43795284628868103,
      "learning_rate": 5e-05,
      "loss": 1.0248,
      "step": 1090
    },
    {
      "epoch": 3.470031545741325,
      "grad_norm": 0.4681282937526703,
      "learning_rate": 5e-05,
      "loss": 1.0241,
      "step": 1100
    },
    {
      "epoch": 3.501577287066246,
      "grad_norm": 0.44735008478164673,
      "learning_rate": 5e-05,
      "loss": 1.0209,
      "step": 1110
    },
    {
      "epoch": 3.5331230283911674,
      "grad_norm": 0.4473140835762024,
      "learning_rate": 5e-05,
      "loss": 0.9824,
      "step": 1120
    },
    {
      "epoch": 3.5646687697160884,
      "grad_norm": 0.44602036476135254,
      "learning_rate": 5e-05,
      "loss": 1.0095,
      "step": 1130
    },
    {
      "epoch": 3.5962145110410093,
      "grad_norm": 0.455937922000885,
      "learning_rate": 5e-05,
      "loss": 1.0045,
      "step": 1140
    },
    {
      "epoch": 3.6277602523659307,
      "grad_norm": 0.416535347700119,
      "learning_rate": 5e-05,
      "loss": 1.0293,
      "step": 1150
    },
    {
      "epoch": 3.6593059936908516,
      "grad_norm": 0.454054057598114,
      "learning_rate": 5e-05,
      "loss": 0.9761,
      "step": 1160
    },
    {
      "epoch": 3.690851735015773,
      "grad_norm": 0.4191015958786011,
      "learning_rate": 5e-05,
      "loss": 1.0275,
      "step": 1170
    },
    {
      "epoch": 3.722397476340694,
      "grad_norm": 0.45472997426986694,
      "learning_rate": 5e-05,
      "loss": 0.975,
      "step": 1180
    },
    {
      "epoch": 3.753943217665615,
      "grad_norm": 0.429548442363739,
      "learning_rate": 5e-05,
      "loss": 0.9638,
      "step": 1190
    },
    {
      "epoch": 3.7854889589905363,
      "grad_norm": 0.4479614198207855,
      "learning_rate": 5e-05,
      "loss": 1.0034,
      "step": 1200
    },
    {
      "epoch": 3.8170347003154577,
      "grad_norm": 0.41878965497016907,
      "learning_rate": 5e-05,
      "loss": 1.0102,
      "step": 1210
    },
    {
      "epoch": 3.8485804416403786,
      "grad_norm": 0.42527589201927185,
      "learning_rate": 5e-05,
      "loss": 0.9746,
      "step": 1220
    },
    {
      "epoch": 3.8801261829652995,
      "grad_norm": 0.4646793007850647,
      "learning_rate": 5e-05,
      "loss": 1.0139,
      "step": 1230
    },
    {
      "epoch": 3.911671924290221,
      "grad_norm": 0.41096052527427673,
      "learning_rate": 5e-05,
      "loss": 1.0247,
      "step": 1240
    },
    {
      "epoch": 3.943217665615142,
      "grad_norm": 0.4595187306404114,
      "learning_rate": 5e-05,
      "loss": 1.0149,
      "step": 1250
    },
    {
      "epoch": 3.9747634069400632,
      "grad_norm": 0.4228056073188782,
      "learning_rate": 5e-05,
      "loss": 1.0199,
      "step": 1260
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.032894492149353,
      "eval_runtime": 66.5042,
      "eval_samples_per_second": 4.782,
      "eval_steps_per_second": 0.601,
      "step": 1268
    },
    {
      "epoch": 4.006309148264984,
      "grad_norm": 0.4469398558139801,
      "learning_rate": 5e-05,
      "loss": 0.9636,
      "step": 1270
    },
    {
      "epoch": 4.037854889589905,
      "grad_norm": 0.4484340250492096,
      "learning_rate": 5e-05,
      "loss": 0.9827,
      "step": 1280
    },
    {
      "epoch": 4.069400630914826,
      "grad_norm": 0.4563854932785034,
      "learning_rate": 5e-05,
      "loss": 0.9877,
      "step": 1290
    },
    {
      "epoch": 4.100946372239748,
      "grad_norm": 0.44243761897087097,
      "learning_rate": 5e-05,
      "loss": 0.9872,
      "step": 1300
    },
    {
      "epoch": 4.132492113564669,
      "grad_norm": 0.448011189699173,
      "learning_rate": 5e-05,
      "loss": 1.0118,
      "step": 1310
    },
    {
      "epoch": 4.16403785488959,
      "grad_norm": 0.4259743094444275,
      "learning_rate": 5e-05,
      "loss": 1.0109,
      "step": 1320
    },
    {
      "epoch": 4.195583596214511,
      "grad_norm": 0.456064909696579,
      "learning_rate": 5e-05,
      "loss": 0.9552,
      "step": 1330
    },
    {
      "epoch": 4.2271293375394325,
      "grad_norm": 0.49178850650787354,
      "learning_rate": 5e-05,
      "loss": 0.9976,
      "step": 1340
    },
    {
      "epoch": 4.2586750788643535,
      "grad_norm": 0.4512215852737427,
      "learning_rate": 5e-05,
      "loss": 0.9889,
      "step": 1350
    },
    {
      "epoch": 4.290220820189274,
      "grad_norm": 0.4504569172859192,
      "learning_rate": 5e-05,
      "loss": 0.9675,
      "step": 1360
    },
    {
      "epoch": 4.321766561514195,
      "grad_norm": 0.4347565472126007,
      "learning_rate": 5e-05,
      "loss": 0.9904,
      "step": 1370
    },
    {
      "epoch": 4.353312302839116,
      "grad_norm": 0.4649258852005005,
      "learning_rate": 5e-05,
      "loss": 0.9832,
      "step": 1380
    },
    {
      "epoch": 4.384858044164038,
      "grad_norm": 0.4316873252391815,
      "learning_rate": 5e-05,
      "loss": 0.9952,
      "step": 1390
    },
    {
      "epoch": 4.416403785488959,
      "grad_norm": 0.4411141872406006,
      "learning_rate": 5e-05,
      "loss": 0.9743,
      "step": 1400
    },
    {
      "epoch": 4.44794952681388,
      "grad_norm": 0.46868711709976196,
      "learning_rate": 5e-05,
      "loss": 0.9737,
      "step": 1410
    },
    {
      "epoch": 4.479495268138801,
      "grad_norm": 0.47713035345077515,
      "learning_rate": 5e-05,
      "loss": 0.9646,
      "step": 1420
    },
    {
      "epoch": 4.511041009463723,
      "grad_norm": 0.4720157980918884,
      "learning_rate": 5e-05,
      "loss": 0.9645,
      "step": 1430
    },
    {
      "epoch": 4.542586750788644,
      "grad_norm": 0.4508207440376282,
      "learning_rate": 5e-05,
      "loss": 0.9669,
      "step": 1440
    },
    {
      "epoch": 4.574132492113565,
      "grad_norm": 0.4645206928253174,
      "learning_rate": 5e-05,
      "loss": 0.9945,
      "step": 1450
    },
    {
      "epoch": 4.605678233438486,
      "grad_norm": 0.45657721161842346,
      "learning_rate": 5e-05,
      "loss": 1.0193,
      "step": 1460
    },
    {
      "epoch": 4.6372239747634065,
      "grad_norm": 0.48605337738990784,
      "learning_rate": 5e-05,
      "loss": 0.9796,
      "step": 1470
    },
    {
      "epoch": 4.668769716088328,
      "grad_norm": 0.4564870595932007,
      "learning_rate": 5e-05,
      "loss": 1.0164,
      "step": 1480
    },
    {
      "epoch": 4.700315457413249,
      "grad_norm": 0.46090081334114075,
      "learning_rate": 5e-05,
      "loss": 0.9854,
      "step": 1490
    },
    {
      "epoch": 4.73186119873817,
      "grad_norm": 0.4782868027687073,
      "learning_rate": 5e-05,
      "loss": 0.985,
      "step": 1500
    },
    {
      "epoch": 4.763406940063091,
      "grad_norm": 0.45532533526420593,
      "learning_rate": 5e-05,
      "loss": 0.9555,
      "step": 1510
    },
    {
      "epoch": 4.794952681388013,
      "grad_norm": 0.4831511676311493,
      "learning_rate": 5e-05,
      "loss": 0.9775,
      "step": 1520
    },
    {
      "epoch": 4.826498422712934,
      "grad_norm": 0.4660089612007141,
      "learning_rate": 5e-05,
      "loss": 0.9805,
      "step": 1530
    },
    {
      "epoch": 4.858044164037855,
      "grad_norm": 0.47603532671928406,
      "learning_rate": 5e-05,
      "loss": 1.0222,
      "step": 1540
    },
    {
      "epoch": 4.889589905362776,
      "grad_norm": 0.4162875711917877,
      "learning_rate": 5e-05,
      "loss": 0.9867,
      "step": 1550
    },
    {
      "epoch": 4.921135646687697,
      "grad_norm": 0.4378200173377991,
      "learning_rate": 5e-05,
      "loss": 0.9762,
      "step": 1560
    },
    {
      "epoch": 4.952681388012619,
      "grad_norm": 0.43556976318359375,
      "learning_rate": 5e-05,
      "loss": 0.9557,
      "step": 1570
    },
    {
      "epoch": 4.9842271293375395,
      "grad_norm": 0.4165530204772949,
      "learning_rate": 5e-05,
      "loss": 0.998,
      "step": 1580
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.02390456199646,
      "eval_runtime": 66.4974,
      "eval_samples_per_second": 4.782,
      "eval_steps_per_second": 0.602,
      "step": 1585
    },
    {
      "epoch": 5.0157728706624605,
      "grad_norm": 0.557310938835144,
      "learning_rate": 5e-05,
      "loss": 0.9705,
      "step": 1590
    },
    {
      "epoch": 5.047318611987381,
      "grad_norm": 0.47156888246536255,
      "learning_rate": 5e-05,
      "loss": 0.9629,
      "step": 1600
    },
    {
      "epoch": 5.078864353312303,
      "grad_norm": 0.51046222448349,
      "learning_rate": 5e-05,
      "loss": 0.9429,
      "step": 1610
    },
    {
      "epoch": 5.110410094637224,
      "grad_norm": 0.48319852352142334,
      "learning_rate": 5e-05,
      "loss": 0.9637,
      "step": 1620
    },
    {
      "epoch": 5.141955835962145,
      "grad_norm": 0.45673197507858276,
      "learning_rate": 5e-05,
      "loss": 0.9233,
      "step": 1630
    },
    {
      "epoch": 5.173501577287066,
      "grad_norm": 0.5032113194465637,
      "learning_rate": 5e-05,
      "loss": 0.9486,
      "step": 1640
    },
    {
      "epoch": 5.205047318611987,
      "grad_norm": 0.449439138174057,
      "learning_rate": 5e-05,
      "loss": 0.9107,
      "step": 1650
    },
    {
      "epoch": 5.236593059936909,
      "grad_norm": 0.4683469831943512,
      "learning_rate": 5e-05,
      "loss": 0.9608,
      "step": 1660
    },
    {
      "epoch": 5.26813880126183,
      "grad_norm": 0.48362118005752563,
      "learning_rate": 5e-05,
      "loss": 0.9246,
      "step": 1670
    },
    {
      "epoch": 5.299684542586751,
      "grad_norm": 0.4709579050540924,
      "learning_rate": 5e-05,
      "loss": 0.9958,
      "step": 1680
    },
    {
      "epoch": 5.331230283911672,
      "grad_norm": 0.4630713164806366,
      "learning_rate": 5e-05,
      "loss": 0.9837,
      "step": 1690
    },
    {
      "epoch": 5.3627760252365935,
      "grad_norm": 0.475508451461792,
      "learning_rate": 5e-05,
      "loss": 1.0084,
      "step": 1700
    },
    {
      "epoch": 5.394321766561514,
      "grad_norm": 0.5352875590324402,
      "learning_rate": 5e-05,
      "loss": 0.9595,
      "step": 1710
    },
    {
      "epoch": 5.425867507886435,
      "grad_norm": 0.5087634325027466,
      "learning_rate": 5e-05,
      "loss": 0.9697,
      "step": 1720
    },
    {
      "epoch": 5.457413249211356,
      "grad_norm": 0.4558835029602051,
      "learning_rate": 5e-05,
      "loss": 0.9609,
      "step": 1730
    },
    {
      "epoch": 5.488958990536277,
      "grad_norm": 0.5090092420578003,
      "learning_rate": 5e-05,
      "loss": 0.9732,
      "step": 1740
    },
    {
      "epoch": 5.520504731861199,
      "grad_norm": 0.48192793130874634,
      "learning_rate": 5e-05,
      "loss": 0.9917,
      "step": 1750
    },
    {
      "epoch": 5.55205047318612,
      "grad_norm": 0.4428229033946991,
      "learning_rate": 5e-05,
      "loss": 0.9607,
      "step": 1760
    },
    {
      "epoch": 5.583596214511041,
      "grad_norm": 0.4858005940914154,
      "learning_rate": 5e-05,
      "loss": 0.994,
      "step": 1770
    },
    {
      "epoch": 5.615141955835962,
      "grad_norm": 0.4797442555427551,
      "learning_rate": 5e-05,
      "loss": 0.9554,
      "step": 1780
    },
    {
      "epoch": 5.646687697160884,
      "grad_norm": 0.4797378480434418,
      "learning_rate": 5e-05,
      "loss": 0.9486,
      "step": 1790
    },
    {
      "epoch": 5.678233438485805,
      "grad_norm": 0.4509980082511902,
      "learning_rate": 5e-05,
      "loss": 0.9693,
      "step": 1800
    },
    {
      "epoch": 5.709779179810726,
      "grad_norm": 0.45232152938842773,
      "learning_rate": 5e-05,
      "loss": 0.9622,
      "step": 1810
    },
    {
      "epoch": 5.7413249211356465,
      "grad_norm": 0.49943023920059204,
      "learning_rate": 5e-05,
      "loss": 1.0051,
      "step": 1820
    },
    {
      "epoch": 5.7728706624605675,
      "grad_norm": 0.4827818274497986,
      "learning_rate": 5e-05,
      "loss": 0.9536,
      "step": 1830
    },
    {
      "epoch": 5.804416403785489,
      "grad_norm": 0.4689510464668274,
      "learning_rate": 5e-05,
      "loss": 0.9706,
      "step": 1840
    },
    {
      "epoch": 5.83596214511041,
      "grad_norm": 0.47188493609428406,
      "learning_rate": 5e-05,
      "loss": 0.9582,
      "step": 1850
    },
    {
      "epoch": 5.867507886435331,
      "grad_norm": 0.47195523977279663,
      "learning_rate": 5e-05,
      "loss": 0.9688,
      "step": 1860
    },
    {
      "epoch": 5.899053627760252,
      "grad_norm": 0.4700336158275604,
      "learning_rate": 5e-05,
      "loss": 0.9399,
      "step": 1870
    },
    {
      "epoch": 5.930599369085174,
      "grad_norm": 0.5036072731018066,
      "learning_rate": 5e-05,
      "loss": 0.9726,
      "step": 1880
    },
    {
      "epoch": 5.962145110410095,
      "grad_norm": 0.5032414197921753,
      "learning_rate": 5e-05,
      "loss": 0.9426,
      "step": 1890
    },
    {
      "epoch": 5.993690851735016,
      "grad_norm": 0.4505554139614105,
      "learning_rate": 5e-05,
      "loss": 0.9911,
      "step": 1900
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.0179320573806763,
      "eval_runtime": 66.4482,
      "eval_samples_per_second": 4.786,
      "eval_steps_per_second": 0.602,
      "step": 1902
    },
    {
      "epoch": 6.025236593059937,
      "grad_norm": 0.48737627267837524,
      "learning_rate": 5e-05,
      "loss": 0.9504,
      "step": 1910
    },
    {
      "epoch": 6.056782334384858,
      "grad_norm": 0.520263135433197,
      "learning_rate": 5e-05,
      "loss": 0.9411,
      "step": 1920
    },
    {
      "epoch": 6.0883280757097795,
      "grad_norm": 0.4799466133117676,
      "learning_rate": 5e-05,
      "loss": 0.9448,
      "step": 1930
    },
    {
      "epoch": 6.1198738170347005,
      "grad_norm": 0.49849933385849,
      "learning_rate": 5e-05,
      "loss": 0.9511,
      "step": 1940
    },
    {
      "epoch": 6.151419558359621,
      "grad_norm": 0.4995006322860718,
      "learning_rate": 5e-05,
      "loss": 0.9315,
      "step": 1950
    },
    {
      "epoch": 6.182965299684542,
      "grad_norm": 0.5434730648994446,
      "learning_rate": 5e-05,
      "loss": 0.9509,
      "step": 1960
    },
    {
      "epoch": 6.214511041009464,
      "grad_norm": 0.5055322647094727,
      "learning_rate": 5e-05,
      "loss": 0.9449,
      "step": 1970
    },
    {
      "epoch": 6.246056782334385,
      "grad_norm": 0.4768029749393463,
      "learning_rate": 5e-05,
      "loss": 0.9356,
      "step": 1980
    },
    {
      "epoch": 6.277602523659306,
      "grad_norm": 0.5039747357368469,
      "learning_rate": 5e-05,
      "loss": 0.9478,
      "step": 1990
    },
    {
      "epoch": 6.309148264984227,
      "grad_norm": 0.5042532086372375,
      "learning_rate": 5e-05,
      "loss": 0.8941,
      "step": 2000
    },
    {
      "epoch": 6.340694006309148,
      "grad_norm": 0.5117079615592957,
      "learning_rate": 5e-05,
      "loss": 0.9081,
      "step": 2010
    },
    {
      "epoch": 6.37223974763407,
      "grad_norm": 0.5625054836273193,
      "learning_rate": 5e-05,
      "loss": 0.9588,
      "step": 2020
    },
    {
      "epoch": 6.403785488958991,
      "grad_norm": 0.49397581815719604,
      "learning_rate": 5e-05,
      "loss": 0.9405,
      "step": 2030
    },
    {
      "epoch": 6.435331230283912,
      "grad_norm": 0.5129591226577759,
      "learning_rate": 5e-05,
      "loss": 0.9357,
      "step": 2040
    },
    {
      "epoch": 6.466876971608833,
      "grad_norm": 0.5299010276794434,
      "learning_rate": 5e-05,
      "loss": 0.9425,
      "step": 2050
    },
    {
      "epoch": 6.498422712933754,
      "grad_norm": 0.512342095375061,
      "learning_rate": 5e-05,
      "loss": 0.936,
      "step": 2060
    },
    {
      "epoch": 6.529968454258675,
      "grad_norm": 0.5136451721191406,
      "learning_rate": 5e-05,
      "loss": 0.9549,
      "step": 2070
    },
    {
      "epoch": 6.561514195583596,
      "grad_norm": 0.6025319695472717,
      "learning_rate": 5e-05,
      "loss": 0.9705,
      "step": 2080
    },
    {
      "epoch": 6.593059936908517,
      "grad_norm": 0.48766204714775085,
      "learning_rate": 5e-05,
      "loss": 0.96,
      "step": 2090
    },
    {
      "epoch": 6.624605678233438,
      "grad_norm": 0.4721720516681671,
      "learning_rate": 5e-05,
      "loss": 0.9457,
      "step": 2100
    },
    {
      "epoch": 6.65615141955836,
      "grad_norm": 0.48331397771835327,
      "learning_rate": 5e-05,
      "loss": 0.9105,
      "step": 2110
    },
    {
      "epoch": 6.687697160883281,
      "grad_norm": 0.4890565872192383,
      "learning_rate": 5e-05,
      "loss": 0.9859,
      "step": 2120
    },
    {
      "epoch": 6.719242902208202,
      "grad_norm": 0.5263992547988892,
      "learning_rate": 5e-05,
      "loss": 0.9659,
      "step": 2130
    },
    {
      "epoch": 6.750788643533123,
      "grad_norm": 0.45187363028526306,
      "learning_rate": 5e-05,
      "loss": 0.9319,
      "step": 2140
    },
    {
      "epoch": 6.782334384858045,
      "grad_norm": 0.4888645112514496,
      "learning_rate": 5e-05,
      "loss": 0.9623,
      "step": 2150
    },
    {
      "epoch": 6.813880126182966,
      "grad_norm": 0.48433786630630493,
      "learning_rate": 5e-05,
      "loss": 0.9601,
      "step": 2160
    },
    {
      "epoch": 6.8454258675078865,
      "grad_norm": 0.5414565205574036,
      "learning_rate": 5e-05,
      "loss": 0.9381,
      "step": 2170
    },
    {
      "epoch": 6.8769716088328074,
      "grad_norm": 0.47471919655799866,
      "learning_rate": 5e-05,
      "loss": 0.9443,
      "step": 2180
    },
    {
      "epoch": 6.908517350157728,
      "grad_norm": 0.4787106513977051,
      "learning_rate": 5e-05,
      "loss": 0.9331,
      "step": 2190
    },
    {
      "epoch": 6.94006309148265,
      "grad_norm": 0.4515725076198578,
      "learning_rate": 5e-05,
      "loss": 0.9461,
      "step": 2200
    },
    {
      "epoch": 6.971608832807571,
      "grad_norm": 0.4714019000530243,
      "learning_rate": 5e-05,
      "loss": 0.9587,
      "step": 2210
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.0130518674850464,
      "eval_runtime": 66.5051,
      "eval_samples_per_second": 4.782,
      "eval_steps_per_second": 0.601,
      "step": 2219
    },
    {
      "epoch": 7.003154574132492,
      "grad_norm": 0.44392409920692444,
      "learning_rate": 5e-05,
      "loss": 0.9691,
      "step": 2220
    },
    {
      "epoch": 7.034700315457413,
      "grad_norm": 0.538865864276886,
      "learning_rate": 5e-05,
      "loss": 0.9095,
      "step": 2230
    },
    {
      "epoch": 7.066246056782334,
      "grad_norm": 0.5173049569129944,
      "learning_rate": 5e-05,
      "loss": 0.9281,
      "step": 2240
    },
    {
      "epoch": 7.097791798107256,
      "grad_norm": 0.4751831293106079,
      "learning_rate": 5e-05,
      "loss": 0.9094,
      "step": 2250
    },
    {
      "epoch": 7.129337539432177,
      "grad_norm": 0.5221697092056274,
      "learning_rate": 5e-05,
      "loss": 0.9148,
      "step": 2260
    },
    {
      "epoch": 7.160883280757098,
      "grad_norm": 0.5088801383972168,
      "learning_rate": 5e-05,
      "loss": 0.9383,
      "step": 2270
    },
    {
      "epoch": 7.192429022082019,
      "grad_norm": 0.5191715359687805,
      "learning_rate": 5e-05,
      "loss": 0.9187,
      "step": 2280
    },
    {
      "epoch": 7.2239747634069404,
      "grad_norm": 0.5438238382339478,
      "learning_rate": 5e-05,
      "loss": 0.9192,
      "step": 2290
    },
    {
      "epoch": 7.255520504731861,
      "grad_norm": 0.5197346210479736,
      "learning_rate": 5e-05,
      "loss": 0.9226,
      "step": 2300
    },
    {
      "epoch": 7.287066246056782,
      "grad_norm": 0.5286086797714233,
      "learning_rate": 5e-05,
      "loss": 0.9009,
      "step": 2310
    },
    {
      "epoch": 7.318611987381703,
      "grad_norm": 0.4977555274963379,
      "learning_rate": 5e-05,
      "loss": 0.9524,
      "step": 2320
    },
    {
      "epoch": 7.350157728706624,
      "grad_norm": 0.5014932751655579,
      "learning_rate": 5e-05,
      "loss": 0.9356,
      "step": 2330
    },
    {
      "epoch": 7.381703470031546,
      "grad_norm": 0.5207954049110413,
      "learning_rate": 5e-05,
      "loss": 0.9095,
      "step": 2340
    },
    {
      "epoch": 7.413249211356467,
      "grad_norm": 0.512366771697998,
      "learning_rate": 5e-05,
      "loss": 0.9357,
      "step": 2350
    },
    {
      "epoch": 7.444794952681388,
      "grad_norm": 0.5742561221122742,
      "learning_rate": 5e-05,
      "loss": 0.9188,
      "step": 2360
    },
    {
      "epoch": 7.476340694006309,
      "grad_norm": 0.5032497644424438,
      "learning_rate": 5e-05,
      "loss": 0.9624,
      "step": 2370
    },
    {
      "epoch": 7.50788643533123,
      "grad_norm": 0.6190054416656494,
      "learning_rate": 5e-05,
      "loss": 0.8954,
      "step": 2380
    },
    {
      "epoch": 7.539432176656152,
      "grad_norm": 0.5226176977157593,
      "learning_rate": 5e-05,
      "loss": 0.9212,
      "step": 2390
    },
    {
      "epoch": 7.570977917981073,
      "grad_norm": 0.5045409202575684,
      "learning_rate": 5e-05,
      "loss": 0.9459,
      "step": 2400
    },
    {
      "epoch": 7.6025236593059935,
      "grad_norm": 0.48342952132225037,
      "learning_rate": 5e-05,
      "loss": 0.9306,
      "step": 2410
    },
    {
      "epoch": 7.634069400630915,
      "grad_norm": 0.48288047313690186,
      "learning_rate": 5e-05,
      "loss": 0.9217,
      "step": 2420
    },
    {
      "epoch": 7.665615141955836,
      "grad_norm": 0.5119076371192932,
      "learning_rate": 5e-05,
      "loss": 0.9594,
      "step": 2430
    },
    {
      "epoch": 7.697160883280757,
      "grad_norm": 0.5182865262031555,
      "learning_rate": 5e-05,
      "loss": 0.9158,
      "step": 2440
    },
    {
      "epoch": 7.728706624605678,
      "grad_norm": 0.5085521340370178,
      "learning_rate": 5e-05,
      "loss": 0.9249,
      "step": 2450
    },
    {
      "epoch": 7.760252365930599,
      "grad_norm": 0.49291595816612244,
      "learning_rate": 5e-05,
      "loss": 0.9128,
      "step": 2460
    },
    {
      "epoch": 7.79179810725552,
      "grad_norm": 0.5067439675331116,
      "learning_rate": 5e-05,
      "loss": 0.8993,
      "step": 2470
    },
    {
      "epoch": 7.823343848580442,
      "grad_norm": 0.49475356936454773,
      "learning_rate": 5e-05,
      "loss": 0.9313,
      "step": 2480
    },
    {
      "epoch": 7.854889589905363,
      "grad_norm": 0.5028258562088013,
      "learning_rate": 5e-05,
      "loss": 0.9459,
      "step": 2490
    },
    {
      "epoch": 7.886435331230284,
      "grad_norm": 0.482112854719162,
      "learning_rate": 5e-05,
      "loss": 0.9243,
      "step": 2500
    },
    {
      "epoch": 7.917981072555205,
      "grad_norm": 0.5285838842391968,
      "learning_rate": 5e-05,
      "loss": 0.9847,
      "step": 2510
    },
    {
      "epoch": 7.9495268138801265,
      "grad_norm": 0.5217479467391968,
      "learning_rate": 5e-05,
      "loss": 0.9172,
      "step": 2520
    },
    {
      "epoch": 7.981072555205047,
      "grad_norm": 0.47651416063308716,
      "learning_rate": 5e-05,
      "loss": 0.9003,
      "step": 2530
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.0111174583435059,
      "eval_runtime": 66.5497,
      "eval_samples_per_second": 4.778,
      "eval_steps_per_second": 0.601,
      "step": 2536
    },
    {
      "epoch": 8.012618296529968,
      "grad_norm": 0.5173642635345459,
      "learning_rate": 5e-05,
      "loss": 0.9408,
      "step": 2540
    },
    {
      "epoch": 8.04416403785489,
      "grad_norm": 0.5017074346542358,
      "learning_rate": 5e-05,
      "loss": 0.9028,
      "step": 2550
    },
    {
      "epoch": 8.07570977917981,
      "grad_norm": 0.5437857508659363,
      "learning_rate": 5e-05,
      "loss": 0.916,
      "step": 2560
    },
    {
      "epoch": 8.107255520504731,
      "grad_norm": 0.485762357711792,
      "learning_rate": 5e-05,
      "loss": 0.8698,
      "step": 2570
    },
    {
      "epoch": 8.138801261829652,
      "grad_norm": 0.5231262445449829,
      "learning_rate": 5e-05,
      "loss": 0.9004,
      "step": 2580
    },
    {
      "epoch": 8.170347003154575,
      "grad_norm": 0.49633580446243286,
      "learning_rate": 5e-05,
      "loss": 0.9159,
      "step": 2590
    },
    {
      "epoch": 8.201892744479496,
      "grad_norm": 0.5477921366691589,
      "learning_rate": 5e-05,
      "loss": 0.9015,
      "step": 2600
    },
    {
      "epoch": 8.233438485804417,
      "grad_norm": 0.5651286840438843,
      "learning_rate": 5e-05,
      "loss": 0.8925,
      "step": 2610
    },
    {
      "epoch": 8.264984227129338,
      "grad_norm": 0.5210168957710266,
      "learning_rate": 5e-05,
      "loss": 0.9172,
      "step": 2620
    },
    {
      "epoch": 8.296529968454259,
      "grad_norm": 0.5071650743484497,
      "learning_rate": 5e-05,
      "loss": 0.9172,
      "step": 2630
    },
    {
      "epoch": 8.32807570977918,
      "grad_norm": 0.5585223436355591,
      "learning_rate": 5e-05,
      "loss": 0.9234,
      "step": 2640
    },
    {
      "epoch": 8.3596214511041,
      "grad_norm": 0.5303429961204529,
      "learning_rate": 5e-05,
      "loss": 0.896,
      "step": 2650
    },
    {
      "epoch": 8.391167192429021,
      "grad_norm": 0.5033040046691895,
      "learning_rate": 5e-05,
      "loss": 0.9431,
      "step": 2660
    },
    {
      "epoch": 8.422712933753942,
      "grad_norm": 0.4882967472076416,
      "learning_rate": 5e-05,
      "loss": 0.9103,
      "step": 2670
    },
    {
      "epoch": 8.454258675078865,
      "grad_norm": 0.5938067436218262,
      "learning_rate": 5e-05,
      "loss": 0.9067,
      "step": 2680
    },
    {
      "epoch": 8.485804416403786,
      "grad_norm": 0.5606987476348877,
      "learning_rate": 5e-05,
      "loss": 0.9177,
      "step": 2690
    },
    {
      "epoch": 8.517350157728707,
      "grad_norm": 0.5056515336036682,
      "learning_rate": 5e-05,
      "loss": 0.8924,
      "step": 2700
    },
    {
      "epoch": 8.548895899053628,
      "grad_norm": 0.5208995938301086,
      "learning_rate": 5e-05,
      "loss": 0.917,
      "step": 2710
    },
    {
      "epoch": 8.580441640378549,
      "grad_norm": 0.575134813785553,
      "learning_rate": 5e-05,
      "loss": 0.9132,
      "step": 2720
    },
    {
      "epoch": 8.61198738170347,
      "grad_norm": 0.5263710021972656,
      "learning_rate": 5e-05,
      "loss": 0.9162,
      "step": 2730
    },
    {
      "epoch": 8.64353312302839,
      "grad_norm": 0.5916036367416382,
      "learning_rate": 5e-05,
      "loss": 0.9147,
      "step": 2740
    },
    {
      "epoch": 8.675078864353312,
      "grad_norm": 0.5610800981521606,
      "learning_rate": 5e-05,
      "loss": 0.9022,
      "step": 2750
    },
    {
      "epoch": 8.706624605678233,
      "grad_norm": 0.5309184193611145,
      "learning_rate": 5e-05,
      "loss": 0.8736,
      "step": 2760
    },
    {
      "epoch": 8.738170347003155,
      "grad_norm": 0.5035881996154785,
      "learning_rate": 5e-05,
      "loss": 0.898,
      "step": 2770
    },
    {
      "epoch": 8.769716088328076,
      "grad_norm": 0.5445141196250916,
      "learning_rate": 5e-05,
      "loss": 0.903,
      "step": 2780
    },
    {
      "epoch": 8.801261829652997,
      "grad_norm": 0.5459301471710205,
      "learning_rate": 5e-05,
      "loss": 0.9124,
      "step": 2790
    },
    {
      "epoch": 8.832807570977918,
      "grad_norm": 0.5099250078201294,
      "learning_rate": 5e-05,
      "loss": 0.9132,
      "step": 2800
    },
    {
      "epoch": 8.864353312302839,
      "grad_norm": 0.5143303275108337,
      "learning_rate": 5e-05,
      "loss": 0.9085,
      "step": 2810
    },
    {
      "epoch": 8.89589905362776,
      "grad_norm": 0.5371480584144592,
      "learning_rate": 5e-05,
      "loss": 0.9463,
      "step": 2820
    },
    {
      "epoch": 8.927444794952681,
      "grad_norm": 0.517353892326355,
      "learning_rate": 5e-05,
      "loss": 0.8911,
      "step": 2830
    },
    {
      "epoch": 8.958990536277602,
      "grad_norm": 0.5601980090141296,
      "learning_rate": 5e-05,
      "loss": 0.915,
      "step": 2840
    },
    {
      "epoch": 8.990536277602523,
      "grad_norm": 0.5473778247833252,
      "learning_rate": 5e-05,
      "loss": 0.9254,
      "step": 2850
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.0110243558883667,
      "eval_runtime": 66.5208,
      "eval_samples_per_second": 4.78,
      "eval_steps_per_second": 0.601,
      "step": 2853
    },
    {
      "epoch": 9.022082018927446,
      "grad_norm": 0.5774141550064087,
      "learning_rate": 5e-05,
      "loss": 0.8731,
      "step": 2860
    },
    {
      "epoch": 9.053627760252366,
      "grad_norm": 0.5381526350975037,
      "learning_rate": 5e-05,
      "loss": 0.9125,
      "step": 2870
    },
    {
      "epoch": 9.085173501577287,
      "grad_norm": 0.5414624810218811,
      "learning_rate": 5e-05,
      "loss": 0.8838,
      "step": 2880
    },
    {
      "epoch": 9.116719242902208,
      "grad_norm": 0.526127815246582,
      "learning_rate": 5e-05,
      "loss": 0.8709,
      "step": 2890
    },
    {
      "epoch": 9.14826498422713,
      "grad_norm": 0.5719351768493652,
      "learning_rate": 5e-05,
      "loss": 0.8976,
      "step": 2900
    },
    {
      "epoch": 9.17981072555205,
      "grad_norm": 0.6119252443313599,
      "learning_rate": 5e-05,
      "loss": 0.9006,
      "step": 2910
    },
    {
      "epoch": 9.211356466876971,
      "grad_norm": 0.5286473035812378,
      "learning_rate": 5e-05,
      "loss": 0.873,
      "step": 2920
    },
    {
      "epoch": 9.242902208201892,
      "grad_norm": 0.5602397918701172,
      "learning_rate": 5e-05,
      "loss": 0.9113,
      "step": 2930
    },
    {
      "epoch": 9.274447949526813,
      "grad_norm": 0.5757038593292236,
      "learning_rate": 5e-05,
      "loss": 0.8967,
      "step": 2940
    },
    {
      "epoch": 9.305993690851736,
      "grad_norm": 0.5797662138938904,
      "learning_rate": 5e-05,
      "loss": 0.921,
      "step": 2950
    },
    {
      "epoch": 9.337539432176657,
      "grad_norm": 0.5598446726799011,
      "learning_rate": 5e-05,
      "loss": 0.9121,
      "step": 2960
    },
    {
      "epoch": 9.369085173501578,
      "grad_norm": 0.5119657516479492,
      "learning_rate": 5e-05,
      "loss": 0.8748,
      "step": 2970
    },
    {
      "epoch": 9.400630914826499,
      "grad_norm": 0.5484170317649841,
      "learning_rate": 5e-05,
      "loss": 0.8971,
      "step": 2980
    },
    {
      "epoch": 9.43217665615142,
      "grad_norm": 0.5351391434669495,
      "learning_rate": 5e-05,
      "loss": 0.8466,
      "step": 2990
    },
    {
      "epoch": 9.46372239747634,
      "grad_norm": 0.5337589979171753,
      "learning_rate": 5e-05,
      "loss": 0.8986,
      "step": 3000
    },
    {
      "epoch": 9.495268138801261,
      "grad_norm": 0.5773183703422546,
      "learning_rate": 5e-05,
      "loss": 0.9001,
      "step": 3010
    },
    {
      "epoch": 9.526813880126182,
      "grad_norm": 0.6163984537124634,
      "learning_rate": 5e-05,
      "loss": 0.902,
      "step": 3020
    },
    {
      "epoch": 9.558359621451103,
      "grad_norm": 0.5879700183868408,
      "learning_rate": 5e-05,
      "loss": 0.8855,
      "step": 3030
    },
    {
      "epoch": 9.589905362776026,
      "grad_norm": 0.5596455335617065,
      "learning_rate": 5e-05,
      "loss": 0.9052,
      "step": 3040
    },
    {
      "epoch": 9.621451104100947,
      "grad_norm": 0.5862036943435669,
      "learning_rate": 5e-05,
      "loss": 0.9092,
      "step": 3050
    },
    {
      "epoch": 9.652996845425868,
      "grad_norm": 0.5491965413093567,
      "learning_rate": 5e-05,
      "loss": 0.8887,
      "step": 3060
    },
    {
      "epoch": 9.684542586750789,
      "grad_norm": 0.5651736259460449,
      "learning_rate": 5e-05,
      "loss": 0.8873,
      "step": 3070
    },
    {
      "epoch": 9.71608832807571,
      "grad_norm": 0.5439329147338867,
      "learning_rate": 5e-05,
      "loss": 0.8871,
      "step": 3080
    },
    {
      "epoch": 9.74763406940063,
      "grad_norm": 0.5257729887962341,
      "learning_rate": 5e-05,
      "loss": 0.8711,
      "step": 3090
    },
    {
      "epoch": 9.779179810725552,
      "grad_norm": 0.5310476422309875,
      "learning_rate": 5e-05,
      "loss": 0.9118,
      "step": 3100
    },
    {
      "epoch": 9.810725552050473,
      "grad_norm": 0.5593333840370178,
      "learning_rate": 5e-05,
      "loss": 0.8647,
      "step": 3110
    },
    {
      "epoch": 9.842271293375394,
      "grad_norm": 0.5591513514518738,
      "learning_rate": 5e-05,
      "loss": 0.8788,
      "step": 3120
    },
    {
      "epoch": 9.873817034700316,
      "grad_norm": 0.5862401723861694,
      "learning_rate": 5e-05,
      "loss": 0.9113,
      "step": 3130
    },
    {
      "epoch": 9.905362776025237,
      "grad_norm": 0.5847012996673584,
      "learning_rate": 5e-05,
      "loss": 0.9228,
      "step": 3140
    },
    {
      "epoch": 9.936908517350158,
      "grad_norm": 0.5507489442825317,
      "learning_rate": 5e-05,
      "loss": 0.9114,
      "step": 3150
    },
    {
      "epoch": 9.968454258675079,
      "grad_norm": 0.5988635420799255,
      "learning_rate": 5e-05,
      "loss": 0.8753,
      "step": 3160
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.6517265439033508,
      "learning_rate": 5e-05,
      "loss": 0.8532,
      "step": 3170
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.0107625722885132,
      "eval_runtime": 66.5594,
      "eval_samples_per_second": 4.778,
      "eval_steps_per_second": 0.601,
      "step": 3170
    }
  ],
  "logging_steps": 10,
  "max_steps": 6340,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1112958196396851e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}