{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1365,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.18978102189781e-06,
      "loss": 13.9701,
      "step": 1
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.1897810218978098e-05,
      "loss": 9.8829,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.3795620437956196e-05,
      "loss": 7.6246,
      "step": 20
    },
    {
      "epoch": 0.11,
      "learning_rate": 6.56934306569343e-05,
      "loss": 7.2381,
      "step": 30
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.759124087591239e-05,
      "loss": 7.2,
      "step": 40
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00010948905109489051,
      "loss": 7.1787,
      "step": 50
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001313868613138686,
      "loss": 7.1182,
      "step": 60
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00015328467153284672,
      "loss": 7.1756,
      "step": 70
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017518248175182478,
      "loss": 6.9204,
      "step": 80
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001970802919708029,
      "loss": 6.739,
      "step": 90
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00021897810218978101,
      "loss": 6.6124,
      "step": 100
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002408759124087591,
      "loss": 6.5668,
      "step": 110
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002627737226277372,
      "loss": 6.4359,
      "step": 120
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002846715328467153,
      "loss": 6.5331,
      "step": 130
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00029999558221422155,
      "loss": 6.4523,
      "step": 140
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00029991705103933765,
      "loss": 6.2601,
      "step": 150
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00029974040600590614,
      "loss": 6.1484,
      "step": 160
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002994657627200285,
      "loss": 6.0018,
      "step": 170
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002990933009231839,
      "loss": 5.8596,
      "step": 180
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002986232643745964,
      "loss": 5.7249,
      "step": 190
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000298055960691706,
      "loss": 5.5685,
      "step": 200
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002973917611488469,
      "loss": 5.4467,
      "step": 210
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002966311004342651,
      "loss": 5.3091,
      "step": 220
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002957744763656356,
      "loss": 5.1977,
      "step": 230
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00029482244956426253,
      "loss": 5.0377,
      "step": 240
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002937756430881789,
      "loss": 4.9283,
      "step": 250
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002926347420243833,
      "loss": 5.091,
      "step": 260
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002914004930404816,
      "loss": 4.8342,
      "step": 270
    },
    {
      "epoch": 1.0,
      "eval_loss": 4.737916946411133,
      "eval_runtime": 30.7851,
      "eval_samples_per_second": 501.248,
      "eval_steps_per_second": 1.981,
      "step": 273
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00029007370389602736,
      "loss": 4.7528,
      "step": 280
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00028865524291388006,
      "loss": 4.6222,
      "step": 290
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002871460384119274,
      "loss": 4.4689,
      "step": 300
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00028554707809554385,
      "loss": 4.3523,
      "step": 310
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002838594084111824,
      "loss": 4.3172,
      "step": 320
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00028208413386152326,
      "loss": 4.1787,
      "step": 330
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00028022241628262735,
      "loss": 4.1082,
      "step": 340
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00027827547408356773,
      "loss": 3.9914,
      "step": 350
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00027624458144903663,
      "loss": 4.0363,
      "step": 360
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002741310675054493,
      "loss": 5.2644,
      "step": 370
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002719363154510924,
      "loss": 4.8735,
      "step": 380
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.000269661761650883,
      "loss": 4.4014,
      "step": 390
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00026730889469633406,
      "loss": 4.1602,
      "step": 400
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002648792544313389,
      "loss": 4.0027,
      "step": 410
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002623744309444141,
      "loss": 3.9095,
      "step": 420
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0002597960635280588,
      "loss": 3.8225,
      "step": 430
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00025714583960591324,
      "loss": 3.7638,
      "step": 440
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002544254936284164,
      "loss": 3.7038,
      "step": 450
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002516368059376883,
      "loss": 3.6738,
      "step": 460
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00024878160160237653,
      "loss": 3.6142,
      "step": 470
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00024586174922323293,
      "loss": 3.5565,
      "step": 480
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002428791597101996,
      "loss": 3.5071,
      "step": 490
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00023983578503180541,
      "loss": 3.4761,
      "step": 500
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00023673361693769216,
      "loss": 3.4575,
      "step": 510
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00023357468565510535,
      "loss": 3.4062,
      "step": 520
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00023036105856020315,
      "loss": 3.3653,
      "step": 530
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00022709483882505315,
      "loss": 3.3301,
      "step": 540
    },
    {
      "epoch": 2.0,
      "eval_loss": 3.2846388816833496,
      "eval_runtime": 30.5512,
      "eval_samples_per_second": 505.086,
      "eval_steps_per_second": 1.997,
      "step": 546
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00022377816404120263,
      "loss": 3.2758,
      "step": 550
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00022041320482072218,
      "loss": 3.2522,
      "step": 560
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00021700216337563975,
      "loss": 3.1993,
      "step": 570
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00021354727207669315,
      "loss": 3.147,
      "step": 580
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00021005079199234558,
      "loss": 3.1192,
      "step": 590
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00020651501140901961,
      "loss": 3.0901,
      "step": 600
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0002029422443335184,
      "loss": 3.0812,
      "step": 610
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00019933482897861385,
      "loss": 3.0369,
      "step": 620
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00019569512623279333,
      "loss": 2.9916,
      "step": 630
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00019202551811516592,
      "loss": 2.9367,
      "step": 640
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00018832840621653993,
      "loss": 2.9235,
      "step": 650
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00018460621012769126,
      "loss": 3.0402,
      "step": 660
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0001808613658558521,
      "loss": 2.9328,
      "step": 670
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00017709632423045527,
      "loss": 2.8384,
      "step": 680
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0001733135492991784,
      "loss": 2.7372,
      "step": 690
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00016951551671533753,
      "loss": 2.7189,
      "step": 700
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.00016570471211768486,
      "loss": 2.6697,
      "step": 710
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.00016188362950367204,
      "loss": 2.6319,
      "step": 720
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.00015805476959724273,
      "loss": 2.5963,
      "step": 730
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.00015422063821222292,
      "loss": 2.5732,
      "step": 740
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.00015038374461238062,
      "loss": 2.5426,
      "step": 750
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.00014654659986922697,
      "loss": 2.5217,
      "step": 760
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.00014271171521863514,
      "loss": 2.4971,
      "step": 770
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.00013888160041735086,
      "loss": 2.4917,
      "step": 780
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0001350587621004716,
      "loss": 2.4795,
      "step": 790
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.00013124570214096816,
      "loss": 2.4464,
      "step": 800
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.00012744491601232355,
      "loss": 2.4158,
      "step": 810
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.413381576538086,
      "eval_runtime": 30.6479,
      "eval_samples_per_second": 503.492,
      "eval_steps_per_second": 1.99,
      "step": 819
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00012365889115535916,
      "loss": 2.402,
      "step": 820
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.00011989010535031889,
      "loss": 2.3491,
      "step": 830
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.00011614102509527481,
      "loss": 2.3247,
      "step": 840
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.00011241410399191728,
      "loss": 2.3179,
      "step": 850
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.00010871178113978432,
      "loss": 2.3006,
      "step": 860
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.00010503647953998295,
      "loss": 2.305,
      "step": 870
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.00010139060450944528,
      "loss": 2.2922,
      "step": 880
    },
    {
      "epoch": 3.26,
      "learning_rate": 9.777654210675867e-05,
      "loss": 2.2766,
      "step": 890
    },
    {
      "epoch": 3.3,
      "learning_rate": 9.419665757059952e-05,
      "loss": 2.2732,
      "step": 900
    },
    {
      "epoch": 3.33,
      "learning_rate": 9.065329377179248e-05,
      "loss": 2.2591,
      "step": 910
    },
    {
      "epoch": 3.37,
      "learning_rate": 8.714876968000853e-05,
      "loss": 2.2477,
      "step": 920
    },
    {
      "epoch": 3.41,
      "learning_rate": 8.368537884610555e-05,
      "loss": 2.243,
      "step": 930
    },
    {
      "epoch": 3.44,
      "learning_rate": 8.026538790110405e-05,
      "loss": 2.2341,
      "step": 940
    },
    {
      "epoch": 3.48,
      "learning_rate": 7.689103507278047e-05,
      "loss": 2.2249,
      "step": 950
    },
    {
      "epoch": 3.52,
      "learning_rate": 7.356452872084971e-05,
      "loss": 2.236,
      "step": 960
    },
    {
      "epoch": 3.55,
      "learning_rate": 7.028804589169443e-05,
      "loss": 2.2097,
      "step": 970
    },
    {
      "epoch": 3.59,
      "learning_rate": 6.706373089358791e-05,
      "loss": 2.1968,
      "step": 980
    },
    {
      "epoch": 3.63,
      "learning_rate": 6.389369389334193e-05,
      "loss": 2.187,
      "step": 990
    },
    {
      "epoch": 3.66,
      "learning_rate": 6.0780009535299393e-05,
      "loss": 2.1865,
      "step": 1000
    },
    {
      "epoch": 3.7,
      "learning_rate": 5.772471558357407e-05,
      "loss": 2.1732,
      "step": 1010
    },
    {
      "epoch": 3.74,
      "learning_rate": 5.4729811588427536e-05,
      "loss": 2.1648,
      "step": 1020
    },
    {
      "epoch": 3.77,
      "learning_rate": 5.179725757765449e-05,
      "loss": 2.1696,
      "step": 1030
    },
    {
      "epoch": 3.81,
      "learning_rate": 4.892897277383434e-05,
      "loss": 2.1591,
      "step": 1040
    },
    {
      "epoch": 3.85,
      "learning_rate": 4.6126834338287713e-05,
      "loss": 2.1536,
      "step": 1050
    },
    {
      "epoch": 3.88,
      "learning_rate": 4.339267614256027e-05,
      "loss": 2.1536,
      "step": 1060
    },
    {
      "epoch": 3.92,
      "learning_rate": 4.07282875682373e-05,
      "loss": 2.1404,
      "step": 1070
    },
    {
      "epoch": 3.96,
      "learning_rate": 3.813541233587552e-05,
      "loss": 2.1403,
      "step": 1080
    },
    {
      "epoch": 3.99,
      "learning_rate": 3.561574736381752e-05,
      "loss": 2.1322,
      "step": 1090
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.1637322902679443,
      "eval_runtime": 30.5067,
      "eval_samples_per_second": 505.824,
      "eval_steps_per_second": 2.0,
      "step": 1092
    },
    {
      "epoch": 4.03,
      "learning_rate": 3.317094165763639e-05,
      "loss": 2.0822,
      "step": 1100
    },
    {
      "epoch": 4.07,
      "learning_rate": 3.080259523093675e-05,
      "loss": 2.0771,
      "step": 1110
    },
    {
      "epoch": 4.1,
      "learning_rate": 2.8512258058219112e-05,
      "loss": 2.0782,
      "step": 1120
    },
    {
      "epoch": 4.14,
      "learning_rate": 2.6301429060492306e-05,
      "loss": 2.0688,
      "step": 1130
    },
    {
      "epoch": 4.18,
      "learning_rate": 2.417155512429832e-05,
      "loss": 2.0603,
      "step": 1140
    },
    {
      "epoch": 4.21,
      "learning_rate": 2.2124030154791035e-05,
      "loss": 2.0602,
      "step": 1150
    },
    {
      "epoch": 4.25,
      "learning_rate": 2.0160194163489062e-05,
      "loss": 2.0603,
      "step": 1160
    },
    {
      "epoch": 4.29,
      "learning_rate": 1.828133239129944e-05,
      "loss": 2.0617,
      "step": 1170
    },
    {
      "epoch": 4.32,
      "learning_rate": 1.6488674467386278e-05,
      "loss": 2.065,
      "step": 1180
    },
    {
      "epoch": 4.36,
      "learning_rate": 1.47833936044345e-05,
      "loss": 2.0479,
      "step": 1190
    },
    {
      "epoch": 4.4,
      "learning_rate": 1.3166605830835903e-05,
      "loss": 2.0553,
      "step": 1200
    },
    {
      "epoch": 4.43,
      "learning_rate": 1.1639369260299463e-05,
      "loss": 2.044,
      "step": 1210
    },
    {
      "epoch": 4.47,
      "learning_rate": 1.0202683399364469e-05,
      "loss": 2.0539,
      "step": 1220
    },
    {
      "epoch": 4.51,
      "learning_rate": 8.857488493268839e-06,
      "loss": 2.0471,
      "step": 1230
    },
    {
      "epoch": 4.54,
      "learning_rate": 7.604664910601915e-06,
      "loss": 2.0548,
      "step": 1240
    },
    {
      "epoch": 4.58,
      "learning_rate": 6.445032567143238e-06,
      "loss": 2.0447,
      "step": 1250
    },
    {
      "epoch": 4.62,
      "learning_rate": 5.379350389265319e-06,
      "loss": 2.0379,
      "step": 1260
    },
    {
      "epoch": 4.65,
      "learning_rate": 4.408315817250818e-06,
      "loss": 2.0351,
      "step": 1270
    },
    {
      "epoch": 4.69,
      "learning_rate": 3.5325643488498757e-06,
      "loss": 2.0463,
      "step": 1280
    },
    {
      "epoch": 4.73,
      "learning_rate": 2.7526691233758334e-06,
      "loss": 2.0436,
      "step": 1290
    },
    {
      "epoch": 4.76,
      "learning_rate": 2.0691405466118307e-06,
      "loss": 2.0491,
      "step": 1300
    },
    {
      "epoch": 4.8,
      "learning_rate": 1.4824259567733698e-06,
      "loss": 2.0461,
      "step": 1310
    },
    {
      "epoch": 4.84,
      "learning_rate": 9.929093317461057e-07,
      "loss": 2.041,
      "step": 1320
    },
    {
      "epoch": 4.87,
      "learning_rate": 6.009110377897086e-07,
      "loss": 2.04,
      "step": 1330
    },
    {
      "epoch": 4.91,
      "learning_rate": 3.066876198728474e-07,
      "loss": 2.0415,
      "step": 1340
    },
    {
      "epoch": 4.95,
      "learning_rate": 1.1043163377627562e-07,
      "loss": 2.0418,
      "step": 1350
    },
    {
      "epoch": 4.98,
      "learning_rate": 1.2271520073786623e-08,
      "loss": 2.0369,
      "step": 1360
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.118281126022339,
      "eval_runtime": 30.6172,
      "eval_samples_per_second": 503.999,
      "eval_steps_per_second": 1.992,
      "step": 1365
    },
    {
      "epoch": 5.0,
      "step": 1365,
      "total_flos": 457285168005120.0,
      "train_loss": 3.477488596011431,
      "train_runtime": 5141.5129,
      "train_samples_per_second": 135.588,
      "train_steps_per_second": 0.265
    }
  ],
  "logging_steps": 10,
  "max_steps": 1365,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 457285168005120.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}