{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1169024571854058,
  "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": 4.98758997269794e-05,
      "loss": 1.8077,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.97517994539588e-05,
      "loss": 1.7919,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.96276991809382e-05,
      "loss": 1.7931,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.95035989079176e-05,
      "loss": 1.7427,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9379498634897e-05,
      "loss": 1.7361,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.92553983618764e-05,
      "loss": 1.7501,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.91312980888558e-05,
      "loss": 1.6787,
      "step": 70
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.90071978158352e-05,
      "loss": 1.7201,
      "step": 80
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.88830975428146e-05,
      "loss": 1.6944,
      "step": 90
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.875899726979399e-05,
      "loss": 1.6702,
      "step": 100
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.86348969967734e-05,
      "loss": 1.6788,
      "step": 110
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.8510796723752796e-05,
      "loss": 1.7192,
      "step": 120
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.8386696450732196e-05,
      "loss": 1.6632,
      "step": 130
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.8262596177711595e-05,
      "loss": 1.6643,
      "step": 140
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.8138495904690995e-05,
      "loss": 1.6802,
      "step": 150
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.8014395631670394e-05,
      "loss": 1.7225,
      "step": 160
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.789029535864979e-05,
      "loss": 1.6649,
      "step": 170
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.7766195085629186e-05,
      "loss": 1.6951,
      "step": 180
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.764209481260859e-05,
      "loss": 1.6736,
      "step": 190
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.751799453958799e-05,
      "loss": 1.6874,
      "step": 200
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.739389426656739e-05,
      "loss": 1.6894,
      "step": 210
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.726979399354679e-05,
      "loss": 1.682,
      "step": 220
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.7145693720526184e-05,
      "loss": 1.6885,
      "step": 230
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.702159344750558e-05,
      "loss": 1.7011,
      "step": 240
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.689749317448498e-05,
      "loss": 1.6548,
      "step": 250
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.677339290146439e-05,
      "loss": 1.7147,
      "step": 260
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.664929262844379e-05,
      "loss": 1.6414,
      "step": 270
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.652519235542319e-05,
      "loss": 1.6986,
      "step": 280
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.640109208240258e-05,
      "loss": 1.676,
      "step": 290
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.627699180938198e-05,
      "loss": 1.7008,
      "step": 300
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.615289153636138e-05,
      "loss": 1.697,
      "step": 310
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.602879126334078e-05,
      "loss": 1.6687,
      "step": 320
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.590469099032018e-05,
      "loss": 1.6386,
      "step": 330
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.5780590717299585e-05,
      "loss": 1.7363,
      "step": 340
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.5656490444278984e-05,
      "loss": 1.6989,
      "step": 350
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.553239017125838e-05,
      "loss": 1.6976,
      "step": 360
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.5408289898237776e-05,
      "loss": 1.6699,
      "step": 370
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.5284189625217176e-05,
      "loss": 1.6899,
      "step": 380
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.5160089352196575e-05,
      "loss": 1.6911,
      "step": 390
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.5035989079175975e-05,
      "loss": 1.6817,
      "step": 400
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.491188880615538e-05,
      "loss": 1.6754,
      "step": 410
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.4787788533134774e-05,
      "loss": 1.6631,
      "step": 420
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.466368826011417e-05,
      "loss": 1.67,
      "step": 430
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.453958798709357e-05,
      "loss": 1.6579,
      "step": 440
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.441548771407297e-05,
      "loss": 1.7106,
      "step": 450
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.429138744105237e-05,
      "loss": 1.6756,
      "step": 460
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.416728716803177e-05,
      "loss": 1.6315,
      "step": 470
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.404318689501117e-05,
      "loss": 1.6599,
      "step": 480
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.391908662199057e-05,
      "loss": 1.6958,
      "step": 490
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.379498634896997e-05,
      "loss": 1.6641,
      "step": 500
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.367088607594937e-05,
      "loss": 1.6882,
      "step": 510
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.354678580292877e-05,
      "loss": 1.674,
      "step": 520
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.342268552990817e-05,
      "loss": 1.6857,
      "step": 530
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.329858525688757e-05,
      "loss": 1.6924,
      "step": 540
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.317448498386697e-05,
      "loss": 1.6747,
      "step": 550
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.3050384710846366e-05,
      "loss": 1.6745,
      "step": 560
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.2926284437825766e-05,
      "loss": 1.6719,
      "step": 570
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.2802184164805165e-05,
      "loss": 1.6876,
      "step": 580
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.2678083891784565e-05,
      "loss": 1.6586,
      "step": 590
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.2553983618763964e-05,
      "loss": 1.6897,
      "step": 600
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.2429883345743364e-05,
      "loss": 1.6563,
      "step": 610
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.2305783072722757e-05,
      "loss": 1.6897,
      "step": 620
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.218168279970216e-05,
      "loss": 1.6692,
      "step": 630
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.205758252668156e-05,
      "loss": 1.6706,
      "step": 640
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.193348225366096e-05,
      "loss": 1.6651,
      "step": 650
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.180938198064036e-05,
      "loss": 1.6825,
      "step": 660
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.168528170761976e-05,
      "loss": 1.6498,
      "step": 670
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.1561181434599153e-05,
      "loss": 1.6936,
      "step": 680
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.143708116157855e-05,
      "loss": 1.7123,
      "step": 690
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.131298088855796e-05,
      "loss": 1.6691,
      "step": 700
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.118888061553736e-05,
      "loss": 1.7012,
      "step": 710
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.106478034251676e-05,
      "loss": 1.6674,
      "step": 720
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.094068006949616e-05,
      "loss": 1.6844,
      "step": 730
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.081657979647556e-05,
      "loss": 1.6373,
      "step": 740
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.069247952345495e-05,
      "loss": 1.6868,
      "step": 750
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.056837925043435e-05,
      "loss": 1.6604,
      "step": 760
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.044427897741375e-05,
      "loss": 1.6834,
      "step": 770
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.0320178704393155e-05,
      "loss": 1.6587,
      "step": 780
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.0196078431372555e-05,
      "loss": 1.7264,
      "step": 790
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.0071978158351954e-05,
      "loss": 1.6618,
      "step": 800
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.994787788533135e-05,
      "loss": 1.6448,
      "step": 810
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.9823777612310746e-05,
      "loss": 1.6918,
      "step": 820
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.9699677339290146e-05,
      "loss": 1.6985,
      "step": 830
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.9575577066269545e-05,
      "loss": 1.6774,
      "step": 840
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.945147679324895e-05,
      "loss": 1.6627,
      "step": 850
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.932737652022835e-05,
      "loss": 1.6789,
      "step": 860
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.9203276247207744e-05,
      "loss": 1.6428,
      "step": 870
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.907917597418714e-05,
      "loss": 1.6933,
      "step": 880
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.895507570116654e-05,
      "loss": 1.7061,
      "step": 890
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.883097542814594e-05,
      "loss": 1.6626,
      "step": 900
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.870687515512534e-05,
      "loss": 1.6478,
      "step": 910
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.858277488210474e-05,
      "loss": 1.6741,
      "step": 920
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.845867460908415e-05,
      "loss": 1.6474,
      "step": 930
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.833457433606354e-05,
      "loss": 1.6721,
      "step": 940
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.821047406304294e-05,
      "loss": 1.6692,
      "step": 950
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.808637379002234e-05,
      "loss": 1.6877,
      "step": 960
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.796227351700174e-05,
      "loss": 1.6902,
      "step": 970
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.783817324398114e-05,
      "loss": 1.67,
      "step": 980
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.771407297096054e-05,
      "loss": 1.6489,
      "step": 990
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.758997269793994e-05,
      "loss": 1.6152,
      "step": 1000
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.7465872424919336e-05,
      "loss": 1.6342,
      "step": 1010
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.7341772151898736e-05,
      "loss": 1.7007,
      "step": 1020
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.7217671878878135e-05,
      "loss": 1.6869,
      "step": 1030
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.7093571605857535e-05,
      "loss": 1.6739,
      "step": 1040
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.6969471332836934e-05,
      "loss": 1.6451,
      "step": 1050
    },
    {
      "epoch": 0.79,
      "learning_rate": 3.6845371059816334e-05,
      "loss": 1.7087,
      "step": 1060
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.672127078679573e-05,
      "loss": 1.6473,
      "step": 1070
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.659717051377513e-05,
      "loss": 1.6848,
      "step": 1080
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.647307024075453e-05,
      "loss": 1.7159,
      "step": 1090
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.634896996773393e-05,
      "loss": 1.6728,
      "step": 1100
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.622486969471333e-05,
      "loss": 1.6719,
      "step": 1110
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.610076942169273e-05,
      "loss": 1.6785,
      "step": 1120
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.597666914867212e-05,
      "loss": 1.6803,
      "step": 1130
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.585256887565153e-05,
      "loss": 1.6699,
      "step": 1140
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.572846860263093e-05,
      "loss": 1.7113,
      "step": 1150
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.560436832961033e-05,
      "loss": 1.6633,
      "step": 1160
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.548026805658973e-05,
      "loss": 1.682,
      "step": 1170
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.535616778356913e-05,
      "loss": 1.6666,
      "step": 1180
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.523206751054853e-05,
      "loss": 1.6731,
      "step": 1190
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.510796723752792e-05,
      "loss": 1.6593,
      "step": 1200
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.498386696450732e-05,
      "loss": 1.6447,
      "step": 1210
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.4859766691486725e-05,
      "loss": 1.5988,
      "step": 1220
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.4735666418466125e-05,
      "loss": 1.6807,
      "step": 1230
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.4611566145445524e-05,
      "loss": 1.713,
      "step": 1240
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.4487465872424924e-05,
      "loss": 1.6622,
      "step": 1250
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.4363365599404317e-05,
      "loss": 1.7027,
      "step": 1260
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.4239265326383716e-05,
      "loss": 1.6428,
      "step": 1270
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.4115165053363115e-05,
      "loss": 1.6927,
      "step": 1280
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.399106478034252e-05,
      "loss": 1.6833,
      "step": 1290
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.386696450732192e-05,
      "loss": 1.6675,
      "step": 1300
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.374286423430132e-05,
      "loss": 1.6862,
      "step": 1310
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.3618763961280713e-05,
      "loss": 1.6729,
      "step": 1320
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.349466368826011e-05,
      "loss": 1.6459,
      "step": 1330
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.337056341523951e-05,
      "loss": 1.7022,
      "step": 1340
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.324646314221891e-05,
      "loss": 1.6457,
      "step": 1350
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.312236286919831e-05,
      "loss": 1.6501,
      "step": 1360
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.299826259617772e-05,
      "loss": 1.6801,
      "step": 1370
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.287416232315712e-05,
      "loss": 1.6756,
      "step": 1380
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.275006205013651e-05,
      "loss": 1.6152,
      "step": 1390
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.262596177711591e-05,
      "loss": 1.6636,
      "step": 1400
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.250186150409531e-05,
      "loss": 1.6726,
      "step": 1410
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.237776123107471e-05,
      "loss": 1.617,
      "step": 1420
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.225366095805411e-05,
      "loss": 1.6792,
      "step": 1430
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.2129560685033514e-05,
      "loss": 1.6745,
      "step": 1440
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.200546041201291e-05,
      "loss": 1.6935,
      "step": 1450
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.1881360138992306e-05,
      "loss": 1.6966,
      "step": 1460
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.1757259865971706e-05,
      "loss": 1.6419,
      "step": 1470
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.1633159592951105e-05,
      "loss": 1.662,
      "step": 1480
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.1509059319930505e-05,
      "loss": 1.6341,
      "step": 1490
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.1384959046909904e-05,
      "loss": 1.6635,
      "step": 1500
    }
  ],
  "logging_steps": 10,
  "max_steps": 4029,
  "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
}