{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6231916314266637,
  "eval_steps": 500,
  "global_step": 700,
  "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": 1.802,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.6981,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.6637,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.5537,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.5362,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.6402,
      "step": 60
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.6503,
      "step": 70
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.7586,
      "step": 80
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.6728,
      "step": 90
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.5074,
      "step": 100
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.5421,
      "step": 110
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.6692,
      "step": 120
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.5746,
      "step": 130
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.6294,
      "step": 140
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.4801,
      "step": 150
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.5532,
      "step": 160
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.6031,
      "step": 170
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.6602,
      "step": 180
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.6828,
      "step": 190
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.6285,
      "step": 200
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.5942,
      "step": 210
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.5852,
      "step": 220
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.531,
      "step": 230
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.5815,
      "step": 240
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.6078,
      "step": 250
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.6053,
      "step": 260
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.5821,
      "step": 270
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.5391,
      "step": 280
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.6388,
      "step": 290
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.6811,
      "step": 300
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.5114,
      "step": 310
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.5799,
      "step": 320
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.6448,
      "step": 330
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.5496,
      "step": 340
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.6716,
      "step": 350
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.6299,
      "step": 360
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.488,
      "step": 370
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.5755,
      "step": 380
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002,
      "loss": 1.6198,
      "step": 390
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.6548,
      "step": 400
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.5679,
      "step": 410
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002,
      "loss": 1.6263,
      "step": 420
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 1.4815,
      "step": 430
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 1.5841,
      "step": 440
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.5809,
      "step": 450
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002,
      "loss": 1.5562,
      "step": 460
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 1.617,
      "step": 470
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.5334,
      "step": 480
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.6136,
      "step": 490
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.5988,
      "step": 500
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002,
      "loss": 1.5921,
      "step": 510
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 1.563,
      "step": 520
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002,
      "loss": 1.5547,
      "step": 530
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 1.619,
      "step": 540
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0002,
      "loss": 1.6302,
      "step": 550
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.5529,
      "step": 560
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002,
      "loss": 1.618,
      "step": 570
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 1.4892,
      "step": 580
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.5379,
      "step": 590
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.5652,
      "step": 600
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 1.5119,
      "step": 610
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002,
      "loss": 1.5472,
      "step": 620
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.5417,
      "step": 630
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.5748,
      "step": 640
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 1.5817,
      "step": 650
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 1.5433,
      "step": 660
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 1.6663,
      "step": 670
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.6535,
      "step": 680
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 1.6764,
      "step": 690
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 1.5163,
      "step": 700
    }
  ],
  "logging_steps": 10,
  "max_steps": 700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 8.391498926321664e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}