{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1202389843166543,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.98755290017426e-05,
      "loss": 1.789,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.975105800348519e-05,
      "loss": 1.7866,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.962658700522779e-05,
      "loss": 1.7867,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9502116006970375e-05,
      "loss": 1.7551,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.937764500871298e-05,
      "loss": 1.6772,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9253174010455565e-05,
      "loss": 1.7077,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.912870301219816e-05,
      "loss": 1.6952,
      "step": 70
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9004232013940755e-05,
      "loss": 1.7137,
      "step": 80
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.887976101568335e-05,
      "loss": 1.701,
      "step": 90
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.8755290017425944e-05,
      "loss": 1.725,
      "step": 100
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.863081901916854e-05,
      "loss": 1.7188,
      "step": 110
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.850634802091113e-05,
      "loss": 1.7205,
      "step": 120
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.838187702265373e-05,
      "loss": 1.735,
      "step": 130
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.825740602439632e-05,
      "loss": 1.7021,
      "step": 140
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.813293502613891e-05,
      "loss": 1.6658,
      "step": 150
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.800846402788151e-05,
      "loss": 1.6846,
      "step": 160
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.78839930296241e-05,
      "loss": 1.6744,
      "step": 170
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.7759522031366697e-05,
      "loss": 1.6882,
      "step": 180
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.763505103310929e-05,
      "loss": 1.657,
      "step": 190
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.751058003485188e-05,
      "loss": 1.7129,
      "step": 200
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.738610903659448e-05,
      "loss": 1.7095,
      "step": 210
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.726163803833707e-05,
      "loss": 1.7279,
      "step": 220
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.7137167040079664e-05,
      "loss": 1.7039,
      "step": 230
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.701269604182226e-05,
      "loss": 1.6917,
      "step": 240
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.6888225043564854e-05,
      "loss": 1.6822,
      "step": 250
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.676375404530744e-05,
      "loss": 1.7254,
      "step": 260
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.6639283047050044e-05,
      "loss": 1.6765,
      "step": 270
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.651481204879263e-05,
      "loss": 1.6797,
      "step": 280
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.6390341050535227e-05,
      "loss": 1.7302,
      "step": 290
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.626587005227782e-05,
      "loss": 1.7466,
      "step": 300
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.6141399054020416e-05,
      "loss": 1.6344,
      "step": 310
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.601692805576301e-05,
      "loss": 1.6759,
      "step": 320
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.5892457057505606e-05,
      "loss": 1.66,
      "step": 330
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.5767986059248194e-05,
      "loss": 1.6633,
      "step": 340
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.5643515060990796e-05,
      "loss": 1.6951,
      "step": 350
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.5519044062733384e-05,
      "loss": 1.6829,
      "step": 360
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.539457306447598e-05,
      "loss": 1.6572,
      "step": 370
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.5270102066218574e-05,
      "loss": 1.647,
      "step": 380
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.514563106796117e-05,
      "loss": 1.6855,
      "step": 390
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.502116006970376e-05,
      "loss": 1.6737,
      "step": 400
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.489668907144636e-05,
      "loss": 1.6939,
      "step": 410
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.4772218073188946e-05,
      "loss": 1.6714,
      "step": 420
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.464774707493155e-05,
      "loss": 1.6675,
      "step": 430
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.4523276076674136e-05,
      "loss": 1.6228,
      "step": 440
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.439880507841673e-05,
      "loss": 1.6592,
      "step": 450
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.4274334080159326e-05,
      "loss": 1.6844,
      "step": 460
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.414986308190192e-05,
      "loss": 1.6751,
      "step": 470
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.4025392083644516e-05,
      "loss": 1.675,
      "step": 480
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.390092108538711e-05,
      "loss": 1.6794,
      "step": 490
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.37764500871297e-05,
      "loss": 1.6954,
      "step": 500
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.36519790888723e-05,
      "loss": 1.689,
      "step": 510
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.352750809061489e-05,
      "loss": 1.6729,
      "step": 520
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.340303709235748e-05,
      "loss": 1.6964,
      "step": 530
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.327856609410008e-05,
      "loss": 1.6569,
      "step": 540
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.315409509584267e-05,
      "loss": 1.6775,
      "step": 550
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.302962409758526e-05,
      "loss": 1.7104,
      "step": 560
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.290515309932786e-05,
      "loss": 1.6943,
      "step": 570
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.278068210107045e-05,
      "loss": 1.6928,
      "step": 580
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.2656211102813046e-05,
      "loss": 1.6627,
      "step": 590
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.253174010455564e-05,
      "loss": 1.7122,
      "step": 600
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.2407269106298235e-05,
      "loss": 1.6774,
      "step": 610
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.228279810804083e-05,
      "loss": 1.6428,
      "step": 620
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.2158327109783425e-05,
      "loss": 1.6474,
      "step": 630
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.203385611152601e-05,
      "loss": 1.6819,
      "step": 640
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.1909385113268615e-05,
      "loss": 1.6824,
      "step": 650
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.17849141150112e-05,
      "loss": 1.6817,
      "step": 660
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.16604431167538e-05,
      "loss": 1.7324,
      "step": 670
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.153597211849639e-05,
      "loss": 1.7009,
      "step": 680
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.141150112023899e-05,
      "loss": 1.6554,
      "step": 690
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.128703012198158e-05,
      "loss": 1.6717,
      "step": 700
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.116255912372418e-05,
      "loss": 1.6409,
      "step": 710
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.1038088125466765e-05,
      "loss": 1.7089,
      "step": 720
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.091361712720937e-05,
      "loss": 1.726,
      "step": 730
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.0789146128951955e-05,
      "loss": 1.6654,
      "step": 740
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.066467513069455e-05,
      "loss": 1.7242,
      "step": 750
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.0540204132437145e-05,
      "loss": 1.6711,
      "step": 760
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.041573313417974e-05,
      "loss": 1.6638,
      "step": 770
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.029126213592233e-05,
      "loss": 1.6806,
      "step": 780
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.016679113766493e-05,
      "loss": 1.6868,
      "step": 790
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.004232013940752e-05,
      "loss": 1.6938,
      "step": 800
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.991784914115011e-05,
      "loss": 1.6803,
      "step": 810
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.979337814289271e-05,
      "loss": 1.6861,
      "step": 820
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.96689071446353e-05,
      "loss": 1.6643,
      "step": 830
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.95444361463779e-05,
      "loss": 1.6764,
      "step": 840
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.941996514812049e-05,
      "loss": 1.6823,
      "step": 850
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.929549414986308e-05,
      "loss": 1.668,
      "step": 860
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.917102315160568e-05,
      "loss": 1.6843,
      "step": 870
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.904655215334827e-05,
      "loss": 1.6081,
      "step": 880
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.8922081155090865e-05,
      "loss": 1.6623,
      "step": 890
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.879761015683346e-05,
      "loss": 1.6617,
      "step": 900
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.8673139158576054e-05,
      "loss": 1.7024,
      "step": 910
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.854866816031865e-05,
      "loss": 1.7299,
      "step": 920
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.8424197162061244e-05,
      "loss": 1.6906,
      "step": 930
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.829972616380383e-05,
      "loss": 1.7044,
      "step": 940
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.8175255165546434e-05,
      "loss": 1.6661,
      "step": 950
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.805078416728902e-05,
      "loss": 1.6981,
      "step": 960
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.792631316903162e-05,
      "loss": 1.6618,
      "step": 970
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.780184217077421e-05,
      "loss": 1.7071,
      "step": 980
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.7677371172516806e-05,
      "loss": 1.6487,
      "step": 990
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.7552900174259395e-05,
      "loss": 1.6709,
      "step": 1000
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.7428429176001996e-05,
      "loss": 1.7045,
      "step": 1010
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.7303958177744584e-05,
      "loss": 1.6839,
      "step": 1020
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.717948717948718e-05,
      "loss": 1.6677,
      "step": 1030
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.7055016181229774e-05,
      "loss": 1.6359,
      "step": 1040
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.693054518297237e-05,
      "loss": 1.6796,
      "step": 1050
    },
    {
      "epoch": 0.79,
      "learning_rate": 3.6806074184714964e-05,
      "loss": 1.6365,
      "step": 1060
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.668160318645756e-05,
      "loss": 1.6753,
      "step": 1070
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.655713218820015e-05,
      "loss": 1.7041,
      "step": 1080
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.643266118994275e-05,
      "loss": 1.7067,
      "step": 1090
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.6308190191685337e-05,
      "loss": 1.6563,
      "step": 1100
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.618371919342793e-05,
      "loss": 1.6443,
      "step": 1110
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.6059248195170526e-05,
      "loss": 1.691,
      "step": 1120
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.593477719691312e-05,
      "loss": 1.6743,
      "step": 1130
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.5810306198655716e-05,
      "loss": 1.6558,
      "step": 1140
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.568583520039831e-05,
      "loss": 1.648,
      "step": 1150
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.55613642021409e-05,
      "loss": 1.6417,
      "step": 1160
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.54368932038835e-05,
      "loss": 1.6886,
      "step": 1170
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.531242220562609e-05,
      "loss": 1.7159,
      "step": 1180
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.5187951207368684e-05,
      "loss": 1.6784,
      "step": 1190
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.506348020911128e-05,
      "loss": 1.7053,
      "step": 1200
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.493900921085387e-05,
      "loss": 1.6832,
      "step": 1210
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.481453821259646e-05,
      "loss": 1.7337,
      "step": 1220
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.469006721433906e-05,
      "loss": 1.6491,
      "step": 1230
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.456559621608165e-05,
      "loss": 1.7013,
      "step": 1240
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.4441125217824246e-05,
      "loss": 1.6503,
      "step": 1250
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.431665421956684e-05,
      "loss": 1.6618,
      "step": 1260
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.4192183221309436e-05,
      "loss": 1.7154,
      "step": 1270
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.406771222305203e-05,
      "loss": 1.6909,
      "step": 1280
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.3943241224794625e-05,
      "loss": 1.6602,
      "step": 1290
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.3818770226537214e-05,
      "loss": 1.6601,
      "step": 1300
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.3694299228279815e-05,
      "loss": 1.7051,
      "step": 1310
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.35698282300224e-05,
      "loss": 1.6677,
      "step": 1320
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.3445357231765e-05,
      "loss": 1.6714,
      "step": 1330
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.332088623350759e-05,
      "loss": 1.6601,
      "step": 1340
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.319641523525019e-05,
      "loss": 1.6521,
      "step": 1350
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.307194423699278e-05,
      "loss": 1.6621,
      "step": 1360
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.294747323873538e-05,
      "loss": 1.6651,
      "step": 1370
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.2823002240477966e-05,
      "loss": 1.6666,
      "step": 1380
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.269853124222057e-05,
      "loss": 1.6809,
      "step": 1390
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.2574060243963156e-05,
      "loss": 1.6632,
      "step": 1400
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.244958924570575e-05,
      "loss": 1.6526,
      "step": 1410
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.2325118247448345e-05,
      "loss": 1.694,
      "step": 1420
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.220064724919094e-05,
      "loss": 1.6931,
      "step": 1430
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.2076176250933535e-05,
      "loss": 1.6709,
      "step": 1440
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.195170525267613e-05,
      "loss": 1.6711,
      "step": 1450
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.182723425441872e-05,
      "loss": 1.6675,
      "step": 1460
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.170276325616132e-05,
      "loss": 1.7054,
      "step": 1470
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.157829225790391e-05,
      "loss": 1.7015,
      "step": 1480
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.14538212596465e-05,
      "loss": 1.6854,
      "step": 1490
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.13293502613891e-05,
      "loss": 1.6427,
      "step": 1500
    }
  ],
  "logging_steps": 10,
  "max_steps": 4017,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 9.4803723288576e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}