{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.33789491468153404,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.9022,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.9475,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.8892,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 1.9937,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.2178,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.5613,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.5452,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.5586,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.677,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.937,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.4744,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.4896,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 1.5956,
      "step": 130
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.5633,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.7898,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002,
      "loss": 1.4845,
      "step": 160
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.4648,
      "step": 170
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.4772,
      "step": 180
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.5044,
      "step": 190
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.6671,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.4571,
      "step": 210
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.4437,
      "step": 220
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.4913,
      "step": 230
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.5988,
      "step": 240
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 1.7506,
      "step": 250
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.474,
      "step": 260
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.4722,
      "step": 270
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 1.4948,
      "step": 280
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.5451,
      "step": 290
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.6789,
      "step": 300
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.4969,
      "step": 310
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.4503,
      "step": 320
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.4787,
      "step": 330
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.5204,
      "step": 340
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.7502,
      "step": 350
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 1.4734,
      "step": 360
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.4445,
      "step": 370
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.446,
      "step": 380
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.5525,
      "step": 390
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.6735,
      "step": 400
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.4653,
      "step": 410
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.4478,
      "step": 420
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.4446,
      "step": 430
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.491,
      "step": 440
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.7378,
      "step": 450
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.4653,
      "step": 460
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.4435,
      "step": 470
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 1.4698,
      "step": 480
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.4905,
      "step": 490
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.6413,
      "step": 500
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 1.4424,
      "step": 510
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.4612,
      "step": 520
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.4572,
      "step": 530
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.5237,
      "step": 540
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.6122,
      "step": 550
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.4277,
      "step": 560
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002,
      "loss": 1.4708,
      "step": 570
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.4843,
      "step": 580
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.4576,
      "step": 590
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.7181,
      "step": 600
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.4435,
      "step": 610
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.4587,
      "step": 620
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 1.4885,
      "step": 630
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.4864,
      "step": 640
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.6319,
      "step": 650
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.459,
      "step": 660
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.4425,
      "step": 670
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.4465,
      "step": 680
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002,
      "loss": 1.5243,
      "step": 690
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.7044,
      "step": 700
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.4758,
      "step": 710
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 1.4324,
      "step": 720
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.4978,
      "step": 730
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.4768,
      "step": 740
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 1.6861,
      "step": 750
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.4224,
      "step": 760
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.4528,
      "step": 770
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 1.4434,
      "step": 780
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.5349,
      "step": 790
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.584,
      "step": 800
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.441,
      "step": 810
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.4197,
      "step": 820
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.4941,
      "step": 830
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.4482,
      "step": 840
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.6076,
      "step": 850
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.4251,
      "step": 860
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 1.4146,
      "step": 870
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.4785,
      "step": 880
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.4505,
      "step": 890
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 1.5821,
      "step": 900
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.4202,
      "step": 910
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.4074,
      "step": 920
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002,
      "loss": 1.4604,
      "step": 930
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.4819,
      "step": 940
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.6435,
      "step": 950
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 1.4448,
      "step": 960
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.3856,
      "step": 970
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.3814,
      "step": 980
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.4481,
      "step": 990
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 1.6502,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "total_flos": 6.845729080171008e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}