{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16666666666666666,
  "eval_steps": 250,
  "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": 8.4375,
      "learning_rate": 1.98e-05,
      "loss": 1.6341,
      "step": 10
    },
    {
      "epoch": 0.0,
      "grad_norm": 7.34375,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 1.8818,
      "step": 20
    },
    {
      "epoch": 0.01,
      "grad_norm": 9.4375,
      "learning_rate": 1.94e-05,
      "loss": 2.2104,
      "step": 30
    },
    {
      "epoch": 0.01,
      "grad_norm": 9.0625,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 2.0186,
      "step": 40
    },
    {
      "epoch": 0.01,
      "grad_norm": 10.0625,
      "learning_rate": 1.9e-05,
      "loss": 1.7541,
      "step": 50
    },
    {
      "epoch": 0.01,
      "grad_norm": 10.0,
      "learning_rate": 1.88e-05,
      "loss": 1.8193,
      "step": 60
    },
    {
      "epoch": 0.01,
      "grad_norm": 6.71875,
      "learning_rate": 1.86e-05,
      "loss": 1.9009,
      "step": 70
    },
    {
      "epoch": 0.01,
      "grad_norm": 11.625,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 1.666,
      "step": 80
    },
    {
      "epoch": 0.01,
      "grad_norm": 10.4375,
      "learning_rate": 1.8200000000000002e-05,
      "loss": 2.0143,
      "step": 90
    },
    {
      "epoch": 0.02,
      "grad_norm": 9.0625,
      "learning_rate": 1.8e-05,
      "loss": 1.4298,
      "step": 100
    },
    {
      "epoch": 0.02,
      "grad_norm": 6.03125,
      "learning_rate": 1.7800000000000002e-05,
      "loss": 1.995,
      "step": 110
    },
    {
      "epoch": 0.02,
      "grad_norm": 9.1875,
      "learning_rate": 1.76e-05,
      "loss": 1.9436,
      "step": 120
    },
    {
      "epoch": 0.02,
      "grad_norm": 8.125,
      "learning_rate": 1.7400000000000003e-05,
      "loss": 2.1217,
      "step": 130
    },
    {
      "epoch": 0.02,
      "grad_norm": 11.0625,
      "learning_rate": 1.72e-05,
      "loss": 1.6722,
      "step": 140
    },
    {
      "epoch": 0.03,
      "grad_norm": 8.4375,
      "learning_rate": 1.7e-05,
      "loss": 2.353,
      "step": 150
    },
    {
      "epoch": 0.03,
      "grad_norm": 18.75,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 1.5962,
      "step": 160
    },
    {
      "epoch": 0.03,
      "grad_norm": 8.875,
      "learning_rate": 1.66e-05,
      "loss": 1.8234,
      "step": 170
    },
    {
      "epoch": 0.03,
      "grad_norm": 13.375,
      "learning_rate": 1.64e-05,
      "loss": 2.0789,
      "step": 180
    },
    {
      "epoch": 0.03,
      "grad_norm": 7.875,
      "learning_rate": 1.62e-05,
      "loss": 2.0655,
      "step": 190
    },
    {
      "epoch": 0.03,
      "grad_norm": 7.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.6532,
      "step": 200
    },
    {
      "epoch": 0.04,
      "grad_norm": 11.5625,
      "learning_rate": 1.58e-05,
      "loss": 1.5957,
      "step": 210
    },
    {
      "epoch": 0.04,
      "grad_norm": 11.375,
      "learning_rate": 1.5600000000000003e-05,
      "loss": 1.907,
      "step": 220
    },
    {
      "epoch": 0.04,
      "grad_norm": 8.5625,
      "learning_rate": 1.54e-05,
      "loss": 2.0679,
      "step": 230
    },
    {
      "epoch": 0.04,
      "grad_norm": 6.53125,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 1.6835,
      "step": 240
    },
    {
      "epoch": 0.04,
      "grad_norm": 8.1875,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.7236,
      "step": 250
    },
    {
      "epoch": 0.04,
      "eval_loss": 1.8578436374664307,
      "eval_runtime": 30.0677,
      "eval_samples_per_second": 33.258,
      "eval_steps_per_second": 33.258,
      "step": 250
    },
    {
      "epoch": 0.04,
      "grad_norm": 10.375,
      "learning_rate": 1.48e-05,
      "loss": 2.0319,
      "step": 260
    },
    {
      "epoch": 0.04,
      "grad_norm": 8.75,
      "learning_rate": 1.46e-05,
      "loss": 1.5004,
      "step": 270
    },
    {
      "epoch": 0.05,
      "grad_norm": 8.5,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 1.481,
      "step": 280
    },
    {
      "epoch": 0.05,
      "grad_norm": 9.375,
      "learning_rate": 1.4200000000000001e-05,
      "loss": 1.7318,
      "step": 290
    },
    {
      "epoch": 0.05,
      "grad_norm": 7.15625,
      "learning_rate": 1.4e-05,
      "loss": 1.6412,
      "step": 300
    },
    {
      "epoch": 0.05,
      "grad_norm": 8.5,
      "learning_rate": 1.38e-05,
      "loss": 1.84,
      "step": 310
    },
    {
      "epoch": 0.05,
      "grad_norm": 6.71875,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 1.5797,
      "step": 320
    },
    {
      "epoch": 0.06,
      "grad_norm": 8.625,
      "learning_rate": 1.3400000000000002e-05,
      "loss": 1.6014,
      "step": 330
    },
    {
      "epoch": 0.06,
      "grad_norm": 9.1875,
      "learning_rate": 1.3200000000000002e-05,
      "loss": 1.9005,
      "step": 340
    },
    {
      "epoch": 0.06,
      "grad_norm": 8.125,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.6747,
      "step": 350
    },
    {
      "epoch": 0.06,
      "grad_norm": 12.625,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 1.8032,
      "step": 360
    },
    {
      "epoch": 0.06,
      "grad_norm": 11.375,
      "learning_rate": 1.2600000000000001e-05,
      "loss": 1.665,
      "step": 370
    },
    {
      "epoch": 0.06,
      "grad_norm": 6.0,
      "learning_rate": 1.2400000000000002e-05,
      "loss": 1.5209,
      "step": 380
    },
    {
      "epoch": 0.07,
      "grad_norm": 9.375,
      "learning_rate": 1.22e-05,
      "loss": 2.0018,
      "step": 390
    },
    {
      "epoch": 0.07,
      "grad_norm": 16.375,
      "learning_rate": 1.2e-05,
      "loss": 1.9263,
      "step": 400
    },
    {
      "epoch": 0.07,
      "grad_norm": 9.5,
      "learning_rate": 1.18e-05,
      "loss": 1.7349,
      "step": 410
    },
    {
      "epoch": 0.07,
      "grad_norm": 10.3125,
      "learning_rate": 1.16e-05,
      "loss": 1.9482,
      "step": 420
    },
    {
      "epoch": 0.07,
      "grad_norm": 8.1875,
      "learning_rate": 1.14e-05,
      "loss": 1.6666,
      "step": 430
    },
    {
      "epoch": 0.07,
      "grad_norm": 9.6875,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 1.5945,
      "step": 440
    },
    {
      "epoch": 0.07,
      "grad_norm": 13.125,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.5596,
      "step": 450
    },
    {
      "epoch": 0.08,
      "grad_norm": 14.0,
      "learning_rate": 1.0800000000000002e-05,
      "loss": 1.984,
      "step": 460
    },
    {
      "epoch": 0.08,
      "grad_norm": 13.8125,
      "learning_rate": 1.0600000000000002e-05,
      "loss": 1.831,
      "step": 470
    },
    {
      "epoch": 0.08,
      "grad_norm": 8.125,
      "learning_rate": 1.04e-05,
      "loss": 1.8916,
      "step": 480
    },
    {
      "epoch": 0.08,
      "grad_norm": 10.1875,
      "learning_rate": 1.02e-05,
      "loss": 1.9689,
      "step": 490
    },
    {
      "epoch": 0.08,
      "grad_norm": 10.3125,
      "learning_rate": 1e-05,
      "loss": 1.7186,
      "step": 500
    },
    {
      "epoch": 0.08,
      "eval_loss": 1.7672193050384521,
      "eval_runtime": 30.0143,
      "eval_samples_per_second": 33.317,
      "eval_steps_per_second": 33.317,
      "step": 500
    },
    {
      "epoch": 0.09,
      "grad_norm": 8.75,
      "learning_rate": 9.800000000000001e-06,
      "loss": 2.1063,
      "step": 510
    },
    {
      "epoch": 0.09,
      "grad_norm": 12.875,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.5813,
      "step": 520
    },
    {
      "epoch": 0.09,
      "grad_norm": 6.0,
      "learning_rate": 9.4e-06,
      "loss": 1.8224,
      "step": 530
    },
    {
      "epoch": 0.09,
      "grad_norm": 8.0625,
      "learning_rate": 9.200000000000002e-06,
      "loss": 1.8282,
      "step": 540
    },
    {
      "epoch": 0.09,
      "grad_norm": 8.375,
      "learning_rate": 9e-06,
      "loss": 1.9588,
      "step": 550
    },
    {
      "epoch": 0.09,
      "grad_norm": 7.125,
      "learning_rate": 8.8e-06,
      "loss": 1.9539,
      "step": 560
    },
    {
      "epoch": 0.1,
      "grad_norm": 9.375,
      "learning_rate": 8.6e-06,
      "loss": 2.3026,
      "step": 570
    },
    {
      "epoch": 0.1,
      "grad_norm": 10.875,
      "learning_rate": 8.400000000000001e-06,
      "loss": 1.7161,
      "step": 580
    },
    {
      "epoch": 0.1,
      "grad_norm": 9.9375,
      "learning_rate": 8.2e-06,
      "loss": 1.9426,
      "step": 590
    },
    {
      "epoch": 0.1,
      "grad_norm": 10.4375,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.52,
      "step": 600
    },
    {
      "epoch": 0.1,
      "grad_norm": 9.125,
      "learning_rate": 7.800000000000002e-06,
      "loss": 1.3651,
      "step": 610
    },
    {
      "epoch": 0.1,
      "grad_norm": 20.375,
      "learning_rate": 7.600000000000001e-06,
      "loss": 2.0648,
      "step": 620
    },
    {
      "epoch": 0.1,
      "grad_norm": 12.125,
      "learning_rate": 7.4e-06,
      "loss": 1.9258,
      "step": 630
    },
    {
      "epoch": 0.11,
      "grad_norm": 10.0,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 2.1298,
      "step": 640
    },
    {
      "epoch": 0.11,
      "grad_norm": 21.25,
      "learning_rate": 7e-06,
      "loss": 1.6867,
      "step": 650
    },
    {
      "epoch": 0.11,
      "grad_norm": 15.75,
      "learning_rate": 6.800000000000001e-06,
      "loss": 2.0713,
      "step": 660
    },
    {
      "epoch": 0.11,
      "grad_norm": 8.375,
      "learning_rate": 6.600000000000001e-06,
      "loss": 2.0162,
      "step": 670
    },
    {
      "epoch": 0.11,
      "grad_norm": 19.5,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 1.7879,
      "step": 680
    },
    {
      "epoch": 0.12,
      "grad_norm": 11.75,
      "learning_rate": 6.200000000000001e-06,
      "loss": 2.1711,
      "step": 690
    },
    {
      "epoch": 0.12,
      "grad_norm": 9.4375,
      "learning_rate": 6e-06,
      "loss": 1.7888,
      "step": 700
    },
    {
      "epoch": 0.12,
      "grad_norm": 9.5,
      "learning_rate": 5.8e-06,
      "loss": 1.99,
      "step": 710
    },
    {
      "epoch": 0.12,
      "grad_norm": 9.6875,
      "learning_rate": 5.600000000000001e-06,
      "loss": 2.0291,
      "step": 720
    },
    {
      "epoch": 0.12,
      "grad_norm": 9.25,
      "learning_rate": 5.400000000000001e-06,
      "loss": 1.5828,
      "step": 730
    },
    {
      "epoch": 0.12,
      "grad_norm": 9.75,
      "learning_rate": 5.2e-06,
      "loss": 1.8112,
      "step": 740
    },
    {
      "epoch": 0.12,
      "grad_norm": 7.5625,
      "learning_rate": 5e-06,
      "loss": 1.8888,
      "step": 750
    },
    {
      "epoch": 0.12,
      "eval_loss": 1.7764592170715332,
      "eval_runtime": 29.9989,
      "eval_samples_per_second": 33.335,
      "eval_steps_per_second": 33.335,
      "step": 750
    },
    {
      "epoch": 0.13,
      "grad_norm": 11.6875,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.3511,
      "step": 760
    },
    {
      "epoch": 0.13,
      "grad_norm": 11.1875,
      "learning_rate": 4.600000000000001e-06,
      "loss": 1.7889,
      "step": 770
    },
    {
      "epoch": 0.13,
      "grad_norm": 12.5,
      "learning_rate": 4.4e-06,
      "loss": 1.9403,
      "step": 780
    },
    {
      "epoch": 0.13,
      "grad_norm": 9.375,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 1.7881,
      "step": 790
    },
    {
      "epoch": 0.13,
      "grad_norm": 7.53125,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.8992,
      "step": 800
    },
    {
      "epoch": 0.14,
      "grad_norm": 9.5625,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 1.8407,
      "step": 810
    },
    {
      "epoch": 0.14,
      "grad_norm": 18.125,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 1.5022,
      "step": 820
    },
    {
      "epoch": 0.14,
      "grad_norm": 8.1875,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 1.8158,
      "step": 830
    },
    {
      "epoch": 0.14,
      "grad_norm": 12.6875,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 1.9418,
      "step": 840
    },
    {
      "epoch": 0.14,
      "grad_norm": 14.6875,
      "learning_rate": 3e-06,
      "loss": 1.7942,
      "step": 850
    },
    {
      "epoch": 0.14,
      "grad_norm": 5.75,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 1.3924,
      "step": 860
    },
    {
      "epoch": 0.14,
      "grad_norm": 10.375,
      "learning_rate": 2.6e-06,
      "loss": 1.8403,
      "step": 870
    },
    {
      "epoch": 0.15,
      "grad_norm": 8.875,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.7975,
      "step": 880
    },
    {
      "epoch": 0.15,
      "grad_norm": 10.625,
      "learning_rate": 2.2e-06,
      "loss": 1.792,
      "step": 890
    },
    {
      "epoch": 0.15,
      "grad_norm": 8.9375,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.98,
      "step": 900
    },
    {
      "epoch": 0.15,
      "grad_norm": 10.9375,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 1.6802,
      "step": 910
    },
    {
      "epoch": 0.15,
      "grad_norm": 12.4375,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 1.9608,
      "step": 920
    },
    {
      "epoch": 0.15,
      "grad_norm": 8.125,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 1.7228,
      "step": 930
    },
    {
      "epoch": 0.16,
      "grad_norm": 7.75,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.2766,
      "step": 940
    },
    {
      "epoch": 0.16,
      "grad_norm": 10.5625,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 2.0451,
      "step": 950
    },
    {
      "epoch": 0.16,
      "grad_norm": 8.3125,
      "learning_rate": 8.000000000000001e-07,
      "loss": 1.8266,
      "step": 960
    },
    {
      "epoch": 0.16,
      "grad_norm": 10.6875,
      "learning_rate": 6.000000000000001e-07,
      "loss": 1.7288,
      "step": 970
    },
    {
      "epoch": 0.16,
      "grad_norm": 10.875,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 1.9444,
      "step": 980
    },
    {
      "epoch": 0.17,
      "grad_norm": 9.1875,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.0397,
      "step": 990
    },
    {
      "epoch": 0.17,
      "grad_norm": 9.375,
      "learning_rate": 0.0,
      "loss": 1.84,
      "step": 1000
    },
    {
      "epoch": 0.17,
      "eval_loss": 1.800995111465454,
      "eval_runtime": 30.0231,
      "eval_samples_per_second": 33.308,
      "eval_steps_per_second": 33.308,
      "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
}