{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8546628088137103,
  "eval_steps": 500,
  "global_step": 960,
  "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": 1.727,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.7292,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.7416,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.0158,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.143,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.6469,
      "step": 60
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.6423,
      "step": 70
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.6669,
      "step": 80
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.919,
      "step": 90
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.1557,
      "step": 100
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.5989,
      "step": 110
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.6912,
      "step": 120
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.565,
      "step": 130
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.9146,
      "step": 140
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 2.089,
      "step": 150
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.5365,
      "step": 160
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.6268,
      "step": 170
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.6888,
      "step": 180
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.9569,
      "step": 190
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 2.1153,
      "step": 200
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.5511,
      "step": 210
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.6054,
      "step": 220
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.5985,
      "step": 230
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.8473,
      "step": 240
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.9949,
      "step": 250
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.5932,
      "step": 260
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.5968,
      "step": 270
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.5577,
      "step": 280
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.943,
      "step": 290
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 2.1429,
      "step": 300
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.5053,
      "step": 310
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.6697,
      "step": 320
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.567,
      "step": 330
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.8498,
      "step": 340
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 2.0758,
      "step": 350
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.5627,
      "step": 360
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.5358,
      "step": 370
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.7167,
      "step": 380
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.9932,
      "step": 390
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.0632,
      "step": 400
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.5227,
      "step": 410
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.6192,
      "step": 420
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.6087,
      "step": 430
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.9396,
      "step": 440
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 2.1026,
      "step": 450
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.625,
      "step": 460
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.5609,
      "step": 470
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.542,
      "step": 480
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.9439,
      "step": 490
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 2.0576,
      "step": 500
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.5826,
      "step": 510
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.6084,
      "step": 520
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.6451,
      "step": 530
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.8193,
      "step": 540
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 2.0495,
      "step": 550
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.6288,
      "step": 560
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.5786,
      "step": 570
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.6585,
      "step": 580
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.9045,
      "step": 590
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 2.0053,
      "step": 600
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.5491,
      "step": 610
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.6077,
      "step": 620
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.6346,
      "step": 630
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.9414,
      "step": 640
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.1672,
      "step": 650
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.5987,
      "step": 660
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.5833,
      "step": 670
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.5564,
      "step": 680
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.8669,
      "step": 690
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 2.1056,
      "step": 700
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002,
      "loss": 1.5699,
      "step": 710
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 1.6089,
      "step": 720
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002,
      "loss": 1.6524,
      "step": 730
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 1.821,
      "step": 740
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 2.0973,
      "step": 750
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 1.5607,
      "step": 760
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.5428,
      "step": 770
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002,
      "loss": 1.5836,
      "step": 780
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 1.9913,
      "step": 790
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.9762,
      "step": 800
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 1.5603,
      "step": 810
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0002,
      "loss": 1.591,
      "step": 820
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 1.486,
      "step": 830
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 1.8912,
      "step": 840
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 1.9843,
      "step": 850
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.6012,
      "step": 860
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002,
      "loss": 1.6078,
      "step": 870
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 1.587,
      "step": 880
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 1.9116,
      "step": 890
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 2.0363,
      "step": 900
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002,
      "loss": 1.5466,
      "step": 910
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 1.604,
      "step": 920
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002,
      "loss": 1.6372,
      "step": 930
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 1.9387,
      "step": 940
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.9897,
      "step": 950
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.5116,
      "step": 960
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 4.998476659212288e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}