{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16666666666666666,
  "eval_steps": 1000,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 21.75,
      "learning_rate": 3.7125e-06,
      "loss": 1.6333,
      "step": 10
    },
    {
      "epoch": 0.0,
      "grad_norm": 11.75,
      "learning_rate": 3.675e-06,
      "loss": 1.8863,
      "step": 20
    },
    {
      "epoch": 0.01,
      "grad_norm": 30.25,
      "learning_rate": 3.6375e-06,
      "loss": 2.1646,
      "step": 30
    },
    {
      "epoch": 0.01,
      "grad_norm": 20.0,
      "learning_rate": 3.6e-06,
      "loss": 2.0098,
      "step": 40
    },
    {
      "epoch": 0.01,
      "grad_norm": 21.125,
      "learning_rate": 3.5624999999999998e-06,
      "loss": 1.7331,
      "step": 50
    },
    {
      "epoch": 0.01,
      "grad_norm": 18.125,
      "learning_rate": 3.5249999999999997e-06,
      "loss": 1.8913,
      "step": 60
    },
    {
      "epoch": 0.01,
      "grad_norm": 17.5,
      "learning_rate": 3.4875e-06,
      "loss": 1.8686,
      "step": 70
    },
    {
      "epoch": 0.01,
      "grad_norm": 37.0,
      "learning_rate": 3.4500000000000004e-06,
      "loss": 1.6756,
      "step": 80
    },
    {
      "epoch": 0.01,
      "grad_norm": 21.125,
      "learning_rate": 3.4125000000000004e-06,
      "loss": 2.0029,
      "step": 90
    },
    {
      "epoch": 0.02,
      "grad_norm": 14.0,
      "learning_rate": 3.3750000000000003e-06,
      "loss": 1.4412,
      "step": 100
    },
    {
      "epoch": 0.02,
      "grad_norm": 12.75,
      "learning_rate": 3.3375000000000002e-06,
      "loss": 2.0556,
      "step": 110
    },
    {
      "epoch": 0.02,
      "grad_norm": 31.625,
      "learning_rate": 3.3e-06,
      "loss": 1.9298,
      "step": 120
    },
    {
      "epoch": 0.02,
      "grad_norm": 15.0625,
      "learning_rate": 3.2625e-06,
      "loss": 2.0686,
      "step": 130
    },
    {
      "epoch": 0.02,
      "grad_norm": 15.75,
      "learning_rate": 3.225e-06,
      "loss": 1.6107,
      "step": 140
    },
    {
      "epoch": 0.03,
      "grad_norm": 28.5,
      "learning_rate": 3.1875e-06,
      "loss": 2.4047,
      "step": 150
    },
    {
      "epoch": 0.03,
      "grad_norm": 17.375,
      "learning_rate": 3.15e-06,
      "loss": 1.5916,
      "step": 160
    },
    {
      "epoch": 0.03,
      "grad_norm": 23.0,
      "learning_rate": 3.1125e-06,
      "loss": 1.9109,
      "step": 170
    },
    {
      "epoch": 0.03,
      "grad_norm": 27.5,
      "learning_rate": 3.0749999999999998e-06,
      "loss": 2.1359,
      "step": 180
    },
    {
      "epoch": 0.03,
      "grad_norm": 18.0,
      "learning_rate": 3.0375e-06,
      "loss": 2.1144,
      "step": 190
    },
    {
      "epoch": 0.03,
      "grad_norm": 14.4375,
      "learning_rate": 3e-06,
      "loss": 1.6672,
      "step": 200
    },
    {
      "epoch": 0.04,
      "grad_norm": 22.125,
      "learning_rate": 2.9625e-06,
      "loss": 1.6704,
      "step": 210
    },
    {
      "epoch": 0.04,
      "grad_norm": 28.5,
      "learning_rate": 2.9250000000000004e-06,
      "loss": 1.9675,
      "step": 220
    },
    {
      "epoch": 0.04,
      "grad_norm": 13.0,
      "learning_rate": 2.8875000000000003e-06,
      "loss": 1.9873,
      "step": 230
    },
    {
      "epoch": 0.04,
      "grad_norm": 13.8125,
      "learning_rate": 2.8500000000000002e-06,
      "loss": 1.7557,
      "step": 240
    },
    {
      "epoch": 0.04,
      "grad_norm": 19.125,
      "learning_rate": 2.8125e-06,
      "loss": 1.7556,
      "step": 250
    },
    {
      "epoch": 0.04,
      "grad_norm": 16.5,
      "learning_rate": 2.775e-06,
      "loss": 2.0693,
      "step": 260
    },
    {
      "epoch": 0.04,
      "grad_norm": 18.25,
      "learning_rate": 2.7375e-06,
      "loss": 1.6011,
      "step": 270
    },
    {
      "epoch": 0.05,
      "grad_norm": 21.875,
      "learning_rate": 2.7e-06,
      "loss": 1.6058,
      "step": 280
    },
    {
      "epoch": 0.05,
      "grad_norm": 18.0,
      "learning_rate": 2.6625e-06,
      "loss": 1.8085,
      "step": 290
    },
    {
      "epoch": 0.05,
      "grad_norm": 14.875,
      "learning_rate": 2.625e-06,
      "loss": 1.777,
      "step": 300
    },
    {
      "epoch": 0.05,
      "grad_norm": 20.75,
      "learning_rate": 2.5875e-06,
      "loss": 1.8708,
      "step": 310
    },
    {
      "epoch": 0.05,
      "grad_norm": 14.625,
      "learning_rate": 2.55e-06,
      "loss": 1.5629,
      "step": 320
    },
    {
      "epoch": 0.06,
      "grad_norm": 16.125,
      "learning_rate": 2.5125e-06,
      "loss": 1.7416,
      "step": 330
    },
    {
      "epoch": 0.06,
      "grad_norm": 19.5,
      "learning_rate": 2.475e-06,
      "loss": 1.9123,
      "step": 340
    },
    {
      "epoch": 0.06,
      "grad_norm": 17.375,
      "learning_rate": 2.4375e-06,
      "loss": 1.6956,
      "step": 350
    },
    {
      "epoch": 0.06,
      "grad_norm": 30.125,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.863,
      "step": 360
    },
    {
      "epoch": 0.06,
      "grad_norm": 24.25,
      "learning_rate": 2.3625000000000003e-06,
      "loss": 1.7432,
      "step": 370
    },
    {
      "epoch": 0.06,
      "grad_norm": 15.5625,
      "learning_rate": 2.325e-06,
      "loss": 1.6194,
      "step": 380
    },
    {
      "epoch": 0.07,
      "grad_norm": 20.75,
      "learning_rate": 2.2875e-06,
      "loss": 2.1294,
      "step": 390
    },
    {
      "epoch": 0.07,
      "grad_norm": 24.125,
      "learning_rate": 2.25e-06,
      "loss": 1.8663,
      "step": 400
    },
    {
      "epoch": 0.07,
      "grad_norm": 22.625,
      "learning_rate": 2.2125e-06,
      "loss": 1.8445,
      "step": 410
    },
    {
      "epoch": 0.07,
      "grad_norm": 23.375,
      "learning_rate": 2.175e-06,
      "loss": 2.1122,
      "step": 420
    },
    {
      "epoch": 0.07,
      "grad_norm": 20.875,
      "learning_rate": 2.1375e-06,
      "loss": 1.8364,
      "step": 430
    },
    {
      "epoch": 0.07,
      "grad_norm": 20.0,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 1.6375,
      "step": 440
    },
    {
      "epoch": 0.07,
      "grad_norm": 18.25,
      "learning_rate": 2.0625e-06,
      "loss": 1.5882,
      "step": 450
    },
    {
      "epoch": 0.08,
      "grad_norm": 34.25,
      "learning_rate": 2.025e-06,
      "loss": 2.0043,
      "step": 460
    },
    {
      "epoch": 0.08,
      "grad_norm": 28.75,
      "learning_rate": 1.9875e-06,
      "loss": 1.9231,
      "step": 470
    },
    {
      "epoch": 0.08,
      "grad_norm": 17.5,
      "learning_rate": 1.95e-06,
      "loss": 2.0631,
      "step": 480
    },
    {
      "epoch": 0.08,
      "grad_norm": 17.125,
      "learning_rate": 1.9125e-06,
      "loss": 2.0359,
      "step": 490
    },
    {
      "epoch": 0.08,
      "grad_norm": 21.0,
      "learning_rate": 1.875e-06,
      "loss": 1.8175,
      "step": 500
    },
    {
      "epoch": 0.09,
      "grad_norm": 17.5,
      "learning_rate": 1.8375e-06,
      "loss": 2.0844,
      "step": 510
    },
    {
      "epoch": 0.09,
      "grad_norm": 20.25,
      "learning_rate": 1.8e-06,
      "loss": 1.6329,
      "step": 520
    },
    {
      "epoch": 0.09,
      "grad_norm": 12.375,
      "learning_rate": 1.7624999999999999e-06,
      "loss": 1.9352,
      "step": 530
    },
    {
      "epoch": 0.09,
      "grad_norm": 21.375,
      "learning_rate": 1.7250000000000002e-06,
      "loss": 1.8842,
      "step": 540
    },
    {
      "epoch": 0.09,
      "grad_norm": 16.375,
      "learning_rate": 1.6875000000000001e-06,
      "loss": 2.1543,
      "step": 550
    },
    {
      "epoch": 0.09,
      "grad_norm": 15.625,
      "learning_rate": 1.65e-06,
      "loss": 2.0122,
      "step": 560
    },
    {
      "epoch": 0.1,
      "grad_norm": 16.0,
      "learning_rate": 1.6125e-06,
      "loss": 2.3606,
      "step": 570
    },
    {
      "epoch": 0.1,
      "grad_norm": 22.375,
      "learning_rate": 1.575e-06,
      "loss": 1.8354,
      "step": 580
    },
    {
      "epoch": 0.1,
      "grad_norm": 18.75,
      "learning_rate": 1.5374999999999999e-06,
      "loss": 1.962,
      "step": 590
    },
    {
      "epoch": 0.1,
      "grad_norm": 22.625,
      "learning_rate": 1.5e-06,
      "loss": 1.6487,
      "step": 600
    },
    {
      "epoch": 0.1,
      "grad_norm": 17.875,
      "learning_rate": 1.4625000000000002e-06,
      "loss": 1.5496,
      "step": 610
    },
    {
      "epoch": 0.1,
      "grad_norm": 20.25,
      "learning_rate": 1.4250000000000001e-06,
      "loss": 2.0923,
      "step": 620
    },
    {
      "epoch": 0.1,
      "grad_norm": 20.125,
      "learning_rate": 1.3875e-06,
      "loss": 2.0688,
      "step": 630
    },
    {
      "epoch": 0.11,
      "grad_norm": 14.875,
      "learning_rate": 1.35e-06,
      "loss": 2.1762,
      "step": 640
    },
    {
      "epoch": 0.11,
      "grad_norm": 51.0,
      "learning_rate": 1.3125e-06,
      "loss": 1.7076,
      "step": 650
    },
    {
      "epoch": 0.11,
      "grad_norm": 27.0,
      "learning_rate": 1.275e-06,
      "loss": 2.1918,
      "step": 660
    },
    {
      "epoch": 0.11,
      "grad_norm": 16.125,
      "learning_rate": 1.2375e-06,
      "loss": 2.0706,
      "step": 670
    },
    {
      "epoch": 0.11,
      "grad_norm": 21.0,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.8599,
      "step": 680
    },
    {
      "epoch": 0.12,
      "grad_norm": 19.375,
      "learning_rate": 1.1625e-06,
      "loss": 2.1312,
      "step": 690
    },
    {
      "epoch": 0.12,
      "grad_norm": 22.5,
      "learning_rate": 1.125e-06,
      "loss": 1.9219,
      "step": 700
    },
    {
      "epoch": 0.12,
      "grad_norm": 24.75,
      "learning_rate": 1.0875e-06,
      "loss": 2.0628,
      "step": 710
    },
    {
      "epoch": 0.12,
      "grad_norm": 16.875,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.999,
      "step": 720
    },
    {
      "epoch": 0.12,
      "grad_norm": 20.875,
      "learning_rate": 1.0125e-06,
      "loss": 1.6709,
      "step": 730
    },
    {
      "epoch": 0.12,
      "grad_norm": 20.125,
      "learning_rate": 9.75e-07,
      "loss": 1.9329,
      "step": 740
    },
    {
      "epoch": 0.12,
      "grad_norm": 15.125,
      "learning_rate": 9.375e-07,
      "loss": 1.8998,
      "step": 750
    },
    {
      "epoch": 0.13,
      "grad_norm": 20.0,
      "learning_rate": 9e-07,
      "loss": 1.4411,
      "step": 760
    },
    {
      "epoch": 0.13,
      "grad_norm": 18.125,
      "learning_rate": 8.625000000000001e-07,
      "loss": 1.758,
      "step": 770
    },
    {
      "epoch": 0.13,
      "grad_norm": 17.0,
      "learning_rate": 8.25e-07,
      "loss": 2.0136,
      "step": 780
    },
    {
      "epoch": 0.13,
      "grad_norm": 19.25,
      "learning_rate": 7.875e-07,
      "loss": 1.8072,
      "step": 790
    },
    {
      "epoch": 0.13,
      "grad_norm": 14.625,
      "learning_rate": 7.5e-07,
      "loss": 1.9614,
      "step": 800
    },
    {
      "epoch": 0.14,
      "grad_norm": 17.5,
      "learning_rate": 7.125000000000001e-07,
      "loss": 1.9077,
      "step": 810
    },
    {
      "epoch": 0.14,
      "grad_norm": 25.625,
      "learning_rate": 6.75e-07,
      "loss": 1.6237,
      "step": 820
    },
    {
      "epoch": 0.14,
      "grad_norm": 23.875,
      "learning_rate": 6.375e-07,
      "loss": 1.875,
      "step": 830
    },
    {
      "epoch": 0.14,
      "grad_norm": 29.5,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.0392,
      "step": 840
    },
    {
      "epoch": 0.14,
      "grad_norm": 15.6875,
      "learning_rate": 5.625e-07,
      "loss": 1.9254,
      "step": 850
    },
    {
      "epoch": 0.14,
      "grad_norm": 11.8125,
      "learning_rate": 5.250000000000001e-07,
      "loss": 1.4531,
      "step": 860
    },
    {
      "epoch": 0.14,
      "grad_norm": 17.875,
      "learning_rate": 4.875e-07,
      "loss": 1.8028,
      "step": 870
    },
    {
      "epoch": 0.15,
      "grad_norm": 15.875,
      "learning_rate": 4.5e-07,
      "loss": 1.7695,
      "step": 880
    },
    {
      "epoch": 0.15,
      "grad_norm": 20.375,
      "learning_rate": 4.125e-07,
      "loss": 1.8477,
      "step": 890
    },
    {
      "epoch": 0.15,
      "grad_norm": 16.25,
      "learning_rate": 3.75e-07,
      "loss": 2.0242,
      "step": 900
    },
    {
      "epoch": 0.15,
      "grad_norm": 30.5,
      "learning_rate": 3.375e-07,
      "loss": 1.79,
      "step": 910
    },
    {
      "epoch": 0.15,
      "grad_norm": 21.875,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.0096,
      "step": 920
    },
    {
      "epoch": 0.15,
      "grad_norm": 18.75,
      "learning_rate": 2.6250000000000003e-07,
      "loss": 1.8059,
      "step": 930
    },
    {
      "epoch": 0.16,
      "grad_norm": 15.9375,
      "learning_rate": 2.25e-07,
      "loss": 1.4159,
      "step": 940
    },
    {
      "epoch": 0.16,
      "grad_norm": 21.25,
      "learning_rate": 1.875e-07,
      "loss": 2.0914,
      "step": 950
    },
    {
      "epoch": 0.16,
      "grad_norm": 19.25,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 1.9735,
      "step": 960
    },
    {
      "epoch": 0.16,
      "grad_norm": 18.0,
      "learning_rate": 1.125e-07,
      "loss": 1.7791,
      "step": 970
    },
    {
      "epoch": 0.16,
      "grad_norm": 20.25,
      "learning_rate": 7.500000000000001e-08,
      "loss": 2.0176,
      "step": 980
    },
    {
      "epoch": 0.17,
      "grad_norm": 17.5,
      "learning_rate": 3.7500000000000005e-08,
      "loss": 2.1275,
      "step": 990
    },
    {
      "epoch": 0.17,
      "grad_norm": 15.875,
      "learning_rate": 0.0,
      "loss": 1.9038,
      "step": 1000
    },
    {
      "epoch": 0.17,
      "eval_loss": 1.9000076055526733,
      "eval_runtime": 30.02,
      "eval_samples_per_second": 33.311,
      "eval_steps_per_second": 33.311,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "total_flos": 8069610209280000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}