{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9793011350990429,
  "eval_steps": 500,
  "global_step": 1100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.9459,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.8148,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.7727,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.6465,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.6394,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.7525,
      "step": 60
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.7717,
      "step": 70
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.8348,
      "step": 80
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.7589,
      "step": 90
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.6171,
      "step": 100
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.6472,
      "step": 110
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.7311,
      "step": 120
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.6712,
      "step": 130
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.7498,
      "step": 140
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.6112,
      "step": 150
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.667,
      "step": 160
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.6859,
      "step": 170
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.7634,
      "step": 180
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.7686,
      "step": 190
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.6848,
      "step": 200
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.7015,
      "step": 210
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.6901,
      "step": 220
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.6531,
      "step": 230
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.695,
      "step": 240
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.688,
      "step": 250
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.7264,
      "step": 260
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.7083,
      "step": 270
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.6178,
      "step": 280
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.7223,
      "step": 290
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.7643,
      "step": 300
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.6173,
      "step": 310
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.6647,
      "step": 320
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.7311,
      "step": 330
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.6626,
      "step": 340
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.7771,
      "step": 350
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.6919,
      "step": 360
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.6217,
      "step": 370
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.648,
      "step": 380
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.6945,
      "step": 390
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.7347,
      "step": 400
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.6961,
      "step": 410
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.7091,
      "step": 420
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.5628,
      "step": 430
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.6739,
      "step": 440
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.6701,
      "step": 450
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.6715,
      "step": 460
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.6739,
      "step": 470
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.6685,
      "step": 480
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.7288,
      "step": 490
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.7114,
      "step": 500
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.6927,
      "step": 510
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.6844,
      "step": 520
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.6497,
      "step": 530
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.7394,
      "step": 540
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.7035,
      "step": 550
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.6428,
      "step": 560
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.7143,
      "step": 570
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.6237,
      "step": 580
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.6361,
      "step": 590
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.6747,
      "step": 600
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.6272,
      "step": 610
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.6346,
      "step": 620
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.632,
      "step": 630
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.6582,
      "step": 640
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 1.6531,
      "step": 650
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.6465,
      "step": 660
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.7293,
      "step": 670
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.7436,
      "step": 680
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.7764,
      "step": 690
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 1.6331,
      "step": 700
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.5793,
      "step": 710
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 1.6957,
      "step": 720
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.5345,
      "step": 730
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.7638,
      "step": 740
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.7163,
      "step": 750
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 1.6633,
      "step": 760
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.6238,
      "step": 770
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.7047,
      "step": 780
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 1.6102,
      "step": 790
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.6589,
      "step": 800
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.6977,
      "step": 810
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.6633,
      "step": 820
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 1.6099,
      "step": 830
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 1.715,
      "step": 840
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.7477,
      "step": 850
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.7016,
      "step": 860
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.6656,
      "step": 870
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.6918,
      "step": 880
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 1.6168,
      "step": 890
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.6975,
      "step": 900
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.6662,
      "step": 910
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.601,
      "step": 920
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 1.6268,
      "step": 930
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.6147,
      "step": 940
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.5797,
      "step": 950
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.5992,
      "step": 960
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 1.6529,
      "step": 970
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002,
      "loss": 1.6555,
      "step": 980
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 1.6069,
      "step": 990
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 1.5477,
      "step": 1000
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002,
      "loss": 1.5833,
      "step": 1010
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 1.6947,
      "step": 1020
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 1.6369,
      "step": 1030
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.7215,
      "step": 1040
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.6916,
      "step": 1050
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002,
      "loss": 1.6982,
      "step": 1060
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 1.6352,
      "step": 1070
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 1.6895,
      "step": 1080
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 1.644,
      "step": 1090
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002,
      "loss": 1.5663,
      "step": 1100
    }
  ],
  "logging_steps": 10,
  "max_steps": 1200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "total_flos": 7.309842903687168e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}