{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3373534620899047,
  "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": 5e-05,
      "loss": 0.7081,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 0.6774,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 0.6781,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 0.6772,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-05,
      "loss": 0.6802,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-05,
      "loss": 0.6749,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-05,
      "loss": 0.6745,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 0.6729,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 0.6586,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 0.636,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 5e-05,
      "loss": 0.6237,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 5e-05,
      "loss": 0.6098,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 5e-05,
      "loss": 0.5978,
      "step": 130
    },
    {
      "epoch": 0.05,
      "learning_rate": 5e-05,
      "loss": 0.602,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 5e-05,
      "loss": 0.5959,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 5e-05,
      "loss": 0.5906,
      "step": 160
    },
    {
      "epoch": 0.06,
      "learning_rate": 5e-05,
      "loss": 0.5778,
      "step": 170
    },
    {
      "epoch": 0.06,
      "learning_rate": 5e-05,
      "loss": 0.5795,
      "step": 180
    },
    {
      "epoch": 0.06,
      "learning_rate": 5e-05,
      "loss": 0.5883,
      "step": 190
    },
    {
      "epoch": 0.07,
      "learning_rate": 5e-05,
      "loss": 0.604,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 5e-05,
      "loss": 0.5882,
      "step": 210
    },
    {
      "epoch": 0.07,
      "learning_rate": 5e-05,
      "loss": 0.5747,
      "step": 220
    },
    {
      "epoch": 0.08,
      "learning_rate": 5e-05,
      "loss": 0.5745,
      "step": 230
    },
    {
      "epoch": 0.08,
      "learning_rate": 5e-05,
      "loss": 0.5846,
      "step": 240
    },
    {
      "epoch": 0.08,
      "learning_rate": 5e-05,
      "loss": 0.5823,
      "step": 250
    },
    {
      "epoch": 0.09,
      "learning_rate": 5e-05,
      "loss": 0.5722,
      "step": 260
    },
    {
      "epoch": 0.09,
      "learning_rate": 5e-05,
      "loss": 0.5599,
      "step": 270
    },
    {
      "epoch": 0.09,
      "learning_rate": 5e-05,
      "loss": 0.5716,
      "step": 280
    },
    {
      "epoch": 0.1,
      "learning_rate": 5e-05,
      "loss": 0.5832,
      "step": 290
    },
    {
      "epoch": 0.1,
      "learning_rate": 5e-05,
      "loss": 0.5745,
      "step": 300
    },
    {
      "epoch": 0.1,
      "learning_rate": 5e-05,
      "loss": 0.5691,
      "step": 310
    },
    {
      "epoch": 0.11,
      "learning_rate": 5e-05,
      "loss": 0.5711,
      "step": 320
    },
    {
      "epoch": 0.11,
      "learning_rate": 5e-05,
      "loss": 0.5821,
      "step": 330
    },
    {
      "epoch": 0.11,
      "learning_rate": 5e-05,
      "loss": 0.5557,
      "step": 340
    },
    {
      "epoch": 0.12,
      "learning_rate": 5e-05,
      "loss": 0.5581,
      "step": 350
    },
    {
      "epoch": 0.12,
      "learning_rate": 5e-05,
      "loss": 0.5761,
      "step": 360
    },
    {
      "epoch": 0.12,
      "learning_rate": 5e-05,
      "loss": 0.5643,
      "step": 370
    },
    {
      "epoch": 0.13,
      "learning_rate": 5e-05,
      "loss": 0.5745,
      "step": 380
    },
    {
      "epoch": 0.13,
      "learning_rate": 5e-05,
      "loss": 0.5702,
      "step": 390
    },
    {
      "epoch": 0.13,
      "learning_rate": 5e-05,
      "loss": 0.5648,
      "step": 400
    },
    {
      "epoch": 0.14,
      "learning_rate": 5e-05,
      "loss": 0.5691,
      "step": 410
    },
    {
      "epoch": 0.14,
      "learning_rate": 5e-05,
      "loss": 0.556,
      "step": 420
    },
    {
      "epoch": 0.15,
      "learning_rate": 5e-05,
      "loss": 0.5578,
      "step": 430
    },
    {
      "epoch": 0.15,
      "learning_rate": 5e-05,
      "loss": 0.564,
      "step": 440
    },
    {
      "epoch": 0.15,
      "learning_rate": 5e-05,
      "loss": 0.5562,
      "step": 450
    },
    {
      "epoch": 0.16,
      "learning_rate": 5e-05,
      "loss": 0.559,
      "step": 460
    },
    {
      "epoch": 0.16,
      "learning_rate": 5e-05,
      "loss": 0.565,
      "step": 470
    },
    {
      "epoch": 0.16,
      "learning_rate": 5e-05,
      "loss": 0.5508,
      "step": 480
    },
    {
      "epoch": 0.17,
      "learning_rate": 5e-05,
      "loss": 0.5588,
      "step": 490
    },
    {
      "epoch": 0.17,
      "learning_rate": 5e-05,
      "loss": 0.5584,
      "step": 500
    },
    {
      "epoch": 0.17,
      "learning_rate": 5e-05,
      "loss": 0.5555,
      "step": 510
    },
    {
      "epoch": 0.18,
      "learning_rate": 5e-05,
      "loss": 0.5597,
      "step": 520
    },
    {
      "epoch": 0.18,
      "learning_rate": 5e-05,
      "loss": 0.5483,
      "step": 530
    },
    {
      "epoch": 0.18,
      "learning_rate": 5e-05,
      "loss": 0.5621,
      "step": 540
    },
    {
      "epoch": 0.19,
      "learning_rate": 5e-05,
      "loss": 0.5568,
      "step": 550
    },
    {
      "epoch": 0.19,
      "learning_rate": 5e-05,
      "loss": 0.5527,
      "step": 560
    },
    {
      "epoch": 0.19,
      "learning_rate": 5e-05,
      "loss": 0.5524,
      "step": 570
    },
    {
      "epoch": 0.2,
      "learning_rate": 5e-05,
      "loss": 0.5458,
      "step": 580
    },
    {
      "epoch": 0.2,
      "learning_rate": 5e-05,
      "loss": 0.5426,
      "step": 590
    },
    {
      "epoch": 0.2,
      "learning_rate": 5e-05,
      "loss": 0.5524,
      "step": 600
    },
    {
      "epoch": 0.21,
      "learning_rate": 5e-05,
      "loss": 0.5553,
      "step": 610
    },
    {
      "epoch": 0.21,
      "learning_rate": 5e-05,
      "loss": 0.5582,
      "step": 620
    },
    {
      "epoch": 0.21,
      "learning_rate": 5e-05,
      "loss": 0.5518,
      "step": 630
    },
    {
      "epoch": 0.22,
      "learning_rate": 5e-05,
      "loss": 0.5485,
      "step": 640
    },
    {
      "epoch": 0.22,
      "learning_rate": 5e-05,
      "loss": 0.5511,
      "step": 650
    },
    {
      "epoch": 0.22,
      "learning_rate": 5e-05,
      "loss": 0.5444,
      "step": 660
    },
    {
      "epoch": 0.23,
      "learning_rate": 5e-05,
      "loss": 0.5522,
      "step": 670
    },
    {
      "epoch": 0.23,
      "learning_rate": 5e-05,
      "loss": 0.5417,
      "step": 680
    },
    {
      "epoch": 0.23,
      "learning_rate": 5e-05,
      "loss": 0.5543,
      "step": 690
    },
    {
      "epoch": 0.24,
      "learning_rate": 5e-05,
      "loss": 0.56,
      "step": 700
    },
    {
      "epoch": 0.24,
      "learning_rate": 5e-05,
      "loss": 0.5394,
      "step": 710
    },
    {
      "epoch": 0.24,
      "learning_rate": 5e-05,
      "loss": 0.5475,
      "step": 720
    },
    {
      "epoch": 0.25,
      "learning_rate": 5e-05,
      "loss": 0.5437,
      "step": 730
    },
    {
      "epoch": 0.25,
      "learning_rate": 5e-05,
      "loss": 0.5438,
      "step": 740
    },
    {
      "epoch": 0.25,
      "learning_rate": 5e-05,
      "loss": 0.5454,
      "step": 750
    },
    {
      "epoch": 0.26,
      "learning_rate": 5e-05,
      "loss": 0.5481,
      "step": 760
    },
    {
      "epoch": 0.26,
      "learning_rate": 5e-05,
      "loss": 0.5434,
      "step": 770
    },
    {
      "epoch": 0.26,
      "learning_rate": 5e-05,
      "loss": 0.5422,
      "step": 780
    },
    {
      "epoch": 0.27,
      "learning_rate": 5e-05,
      "loss": 0.5465,
      "step": 790
    },
    {
      "epoch": 0.27,
      "learning_rate": 5e-05,
      "loss": 0.5447,
      "step": 800
    },
    {
      "epoch": 0.27,
      "learning_rate": 5e-05,
      "loss": 0.5396,
      "step": 810
    },
    {
      "epoch": 0.28,
      "learning_rate": 5e-05,
      "loss": 0.543,
      "step": 820
    },
    {
      "epoch": 0.28,
      "learning_rate": 5e-05,
      "loss": 0.5461,
      "step": 830
    },
    {
      "epoch": 0.28,
      "learning_rate": 5e-05,
      "loss": 0.5482,
      "step": 840
    },
    {
      "epoch": 0.29,
      "learning_rate": 5e-05,
      "loss": 0.5426,
      "step": 850
    },
    {
      "epoch": 0.29,
      "learning_rate": 5e-05,
      "loss": 0.5453,
      "step": 860
    },
    {
      "epoch": 0.29,
      "learning_rate": 5e-05,
      "loss": 0.5493,
      "step": 870
    },
    {
      "epoch": 0.3,
      "learning_rate": 5e-05,
      "loss": 0.5477,
      "step": 880
    },
    {
      "epoch": 0.3,
      "learning_rate": 5e-05,
      "loss": 0.542,
      "step": 890
    },
    {
      "epoch": 0.3,
      "learning_rate": 5e-05,
      "loss": 0.5393,
      "step": 900
    },
    {
      "epoch": 0.31,
      "learning_rate": 5e-05,
      "loss": 0.5365,
      "step": 910
    },
    {
      "epoch": 0.31,
      "learning_rate": 5e-05,
      "loss": 0.5433,
      "step": 920
    },
    {
      "epoch": 0.31,
      "learning_rate": 5e-05,
      "loss": 0.542,
      "step": 930
    },
    {
      "epoch": 0.32,
      "learning_rate": 5e-05,
      "loss": 0.5368,
      "step": 940
    },
    {
      "epoch": 0.32,
      "learning_rate": 5e-05,
      "loss": 0.542,
      "step": 950
    },
    {
      "epoch": 0.32,
      "learning_rate": 5e-05,
      "loss": 0.5467,
      "step": 960
    },
    {
      "epoch": 0.33,
      "learning_rate": 5e-05,
      "loss": 0.5382,
      "step": 970
    },
    {
      "epoch": 0.33,
      "learning_rate": 5e-05,
      "loss": 0.5366,
      "step": 980
    },
    {
      "epoch": 0.33,
      "learning_rate": 5e-05,
      "loss": 0.5354,
      "step": 990
    },
    {
      "epoch": 0.34,
      "learning_rate": 5e-05,
      "loss": 0.5322,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 8892,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}