{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2672623883021934,
  "eval_steps": 500,
  "global_step": 780,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2e-05,
      "loss": 1.6459,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 2e-05,
      "loss": 1.6104,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 2e-05,
      "loss": 1.7463,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 2e-05,
      "loss": 1.9997,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 2e-05,
      "loss": 2.6636,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 2e-05,
      "loss": 1.6339,
      "step": 60
    },
    {
      "epoch": 0.11,
      "learning_rate": 2e-05,
      "loss": 1.5789,
      "step": 70
    },
    {
      "epoch": 0.13,
      "learning_rate": 2e-05,
      "loss": 1.7218,
      "step": 80
    },
    {
      "epoch": 0.15,
      "learning_rate": 2e-05,
      "loss": 1.9388,
      "step": 90
    },
    {
      "epoch": 0.16,
      "learning_rate": 2e-05,
      "loss": 2.504,
      "step": 100
    },
    {
      "epoch": 0.18,
      "learning_rate": 2e-05,
      "loss": 1.544,
      "step": 110
    },
    {
      "epoch": 0.19,
      "learning_rate": 2e-05,
      "loss": 1.647,
      "step": 120
    },
    {
      "epoch": 0.21,
      "learning_rate": 2e-05,
      "loss": 1.7066,
      "step": 130
    },
    {
      "epoch": 0.23,
      "learning_rate": 2e-05,
      "loss": 1.9831,
      "step": 140
    },
    {
      "epoch": 0.24,
      "learning_rate": 2e-05,
      "loss": 2.2824,
      "step": 150
    },
    {
      "epoch": 0.26,
      "learning_rate": 2e-05,
      "loss": 1.6211,
      "step": 160
    },
    {
      "epoch": 0.28,
      "learning_rate": 2e-05,
      "loss": 1.5657,
      "step": 170
    },
    {
      "epoch": 0.29,
      "learning_rate": 2e-05,
      "loss": 1.6386,
      "step": 180
    },
    {
      "epoch": 0.31,
      "learning_rate": 2e-05,
      "loss": 1.9473,
      "step": 190
    },
    {
      "epoch": 0.32,
      "learning_rate": 2e-05,
      "loss": 2.2312,
      "step": 200
    },
    {
      "epoch": 0.34,
      "learning_rate": 2e-05,
      "loss": 1.4949,
      "step": 210
    },
    {
      "epoch": 0.36,
      "learning_rate": 2e-05,
      "loss": 1.5492,
      "step": 220
    },
    {
      "epoch": 0.37,
      "learning_rate": 2e-05,
      "loss": 1.6168,
      "step": 230
    },
    {
      "epoch": 0.39,
      "learning_rate": 2e-05,
      "loss": 1.9018,
      "step": 240
    },
    {
      "epoch": 0.41,
      "learning_rate": 2e-05,
      "loss": 2.2353,
      "step": 250
    },
    {
      "epoch": 0.42,
      "learning_rate": 2e-05,
      "loss": 1.482,
      "step": 260
    },
    {
      "epoch": 0.44,
      "learning_rate": 2e-05,
      "loss": 1.5858,
      "step": 270
    },
    {
      "epoch": 0.45,
      "learning_rate": 2e-05,
      "loss": 1.5966,
      "step": 280
    },
    {
      "epoch": 0.47,
      "learning_rate": 2e-05,
      "loss": 1.8736,
      "step": 290
    },
    {
      "epoch": 0.49,
      "learning_rate": 2e-05,
      "loss": 2.2563,
      "step": 300
    },
    {
      "epoch": 0.5,
      "learning_rate": 2e-05,
      "loss": 1.5332,
      "step": 310
    },
    {
      "epoch": 0.52,
      "learning_rate": 2e-05,
      "loss": 1.5242,
      "step": 320
    },
    {
      "epoch": 0.54,
      "learning_rate": 2e-05,
      "loss": 1.6715,
      "step": 330
    },
    {
      "epoch": 0.55,
      "learning_rate": 2e-05,
      "loss": 1.8371,
      "step": 340
    },
    {
      "epoch": 0.57,
      "learning_rate": 2e-05,
      "loss": 2.1844,
      "step": 350
    },
    {
      "epoch": 0.58,
      "learning_rate": 2e-05,
      "loss": 1.4603,
      "step": 360
    },
    {
      "epoch": 0.6,
      "learning_rate": 2e-05,
      "loss": 1.5206,
      "step": 370
    },
    {
      "epoch": 0.62,
      "learning_rate": 2e-05,
      "loss": 1.6291,
      "step": 380
    },
    {
      "epoch": 0.63,
      "learning_rate": 2e-05,
      "loss": 1.8907,
      "step": 390
    },
    {
      "epoch": 0.65,
      "learning_rate": 2e-05,
      "loss": 2.2713,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 2e-05,
      "loss": 1.5068,
      "step": 410
    },
    {
      "epoch": 0.68,
      "learning_rate": 2e-05,
      "loss": 1.5231,
      "step": 420
    },
    {
      "epoch": 0.7,
      "learning_rate": 2e-05,
      "loss": 1.5882,
      "step": 430
    },
    {
      "epoch": 0.71,
      "learning_rate": 2e-05,
      "loss": 1.9227,
      "step": 440
    },
    {
      "epoch": 0.73,
      "learning_rate": 2e-05,
      "loss": 2.1373,
      "step": 450
    },
    {
      "epoch": 0.75,
      "learning_rate": 2e-05,
      "loss": 1.5057,
      "step": 460
    },
    {
      "epoch": 0.76,
      "learning_rate": 2e-05,
      "loss": 1.5388,
      "step": 470
    },
    {
      "epoch": 0.78,
      "learning_rate": 2e-05,
      "loss": 1.6031,
      "step": 480
    },
    {
      "epoch": 0.8,
      "learning_rate": 2e-05,
      "loss": 1.766,
      "step": 490
    },
    {
      "epoch": 0.81,
      "learning_rate": 2e-05,
      "loss": 2.14,
      "step": 500
    },
    {
      "epoch": 0.83,
      "learning_rate": 2e-05,
      "loss": 1.5671,
      "step": 510
    },
    {
      "epoch": 0.84,
      "learning_rate": 2e-05,
      "loss": 1.4776,
      "step": 520
    },
    {
      "epoch": 0.86,
      "learning_rate": 2e-05,
      "loss": 1.659,
      "step": 530
    },
    {
      "epoch": 0.88,
      "learning_rate": 2e-05,
      "loss": 1.8881,
      "step": 540
    },
    {
      "epoch": 0.89,
      "learning_rate": 2e-05,
      "loss": 2.2121,
      "step": 550
    },
    {
      "epoch": 0.91,
      "learning_rate": 2e-05,
      "loss": 1.5339,
      "step": 560
    },
    {
      "epoch": 0.93,
      "learning_rate": 2e-05,
      "loss": 1.4865,
      "step": 570
    },
    {
      "epoch": 0.94,
      "learning_rate": 2e-05,
      "loss": 1.6755,
      "step": 580
    },
    {
      "epoch": 0.96,
      "learning_rate": 2e-05,
      "loss": 1.8526,
      "step": 590
    },
    {
      "epoch": 0.97,
      "learning_rate": 2e-05,
      "loss": 2.2115,
      "step": 600
    },
    {
      "epoch": 0.99,
      "learning_rate": 2e-05,
      "loss": 1.5663,
      "step": 610
    },
    {
      "epoch": 1.01,
      "learning_rate": 2e-05,
      "loss": 1.8172,
      "step": 620
    },
    {
      "epoch": 1.02,
      "learning_rate": 2e-05,
      "loss": 1.4821,
      "step": 630
    },
    {
      "epoch": 1.04,
      "learning_rate": 2e-05,
      "loss": 1.5518,
      "step": 640
    },
    {
      "epoch": 1.06,
      "learning_rate": 2e-05,
      "loss": 1.72,
      "step": 650
    },
    {
      "epoch": 1.07,
      "learning_rate": 2e-05,
      "loss": 2.0557,
      "step": 660
    },
    {
      "epoch": 1.09,
      "learning_rate": 2e-05,
      "loss": 1.8439,
      "step": 670
    },
    {
      "epoch": 1.1,
      "learning_rate": 2e-05,
      "loss": 1.5142,
      "step": 680
    },
    {
      "epoch": 1.12,
      "learning_rate": 2e-05,
      "loss": 1.5318,
      "step": 690
    },
    {
      "epoch": 1.14,
      "learning_rate": 2e-05,
      "loss": 1.6139,
      "step": 700
    },
    {
      "epoch": 1.15,
      "learning_rate": 2e-05,
      "loss": 2.0384,
      "step": 710
    },
    {
      "epoch": 1.17,
      "learning_rate": 2e-05,
      "loss": 1.8661,
      "step": 720
    },
    {
      "epoch": 1.19,
      "learning_rate": 2e-05,
      "loss": 1.485,
      "step": 730
    },
    {
      "epoch": 1.2,
      "learning_rate": 2e-05,
      "loss": 1.5184,
      "step": 740
    },
    {
      "epoch": 1.22,
      "learning_rate": 2e-05,
      "loss": 1.6338,
      "step": 750
    },
    {
      "epoch": 1.23,
      "learning_rate": 2e-05,
      "loss": 1.8811,
      "step": 760
    },
    {
      "epoch": 1.25,
      "learning_rate": 2e-05,
      "loss": 1.879,
      "step": 770
    },
    {
      "epoch": 1.27,
      "learning_rate": 2e-05,
      "loss": 1.4522,
      "step": 780
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "total_flos": 7.233525496756224e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}