{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9972396871645453,
  "eval_steps": 200.0,
  "global_step": 814,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 9.996276622795847e-06,
      "loss": 0.1401,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.98511203659851e-06,
      "loss": 0.0684,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.966522869394282e-06,
      "loss": 0.051,
      "step": 30
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.940536806975732e-06,
      "loss": 0.0444,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.907192551707831e-06,
      "loss": 0.0436,
      "step": 50
    },
    {
      "epoch": 0.15,
      "learning_rate": 9.866539764886562e-06,
      "loss": 0.038,
      "step": 60
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.818638992775822e-06,
      "loss": 0.0421,
      "step": 70
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.763561576432781e-06,
      "loss": 0.0415,
      "step": 80
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.70138954545603e-06,
      "loss": 0.0402,
      "step": 90
    },
    {
      "epoch": 0.25,
      "learning_rate": 9.632215495814724e-06,
      "loss": 0.0375,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 9.55614245194068e-06,
      "loss": 0.0362,
      "step": 110
    },
    {
      "epoch": 0.29,
      "learning_rate": 9.473283713288862e-06,
      "loss": 0.0373,
      "step": 120
    },
    {
      "epoch": 0.32,
      "learning_rate": 9.383762685594736e-06,
      "loss": 0.0375,
      "step": 130
    },
    {
      "epoch": 0.34,
      "learning_rate": 9.287712697079827e-06,
      "loss": 0.0374,
      "step": 140
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.185276799879212e-06,
      "loss": 0.0358,
      "step": 150
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.076607556986699e-06,
      "loss": 0.0365,
      "step": 160
    },
    {
      "epoch": 0.42,
      "learning_rate": 8.961866815035e-06,
      "loss": 0.0378,
      "step": 170
    },
    {
      "epoch": 0.44,
      "learning_rate": 8.841225463249305e-06,
      "loss": 0.0367,
      "step": 180
    },
    {
      "epoch": 0.47,
      "learning_rate": 8.714863178933258e-06,
      "loss": 0.0359,
      "step": 190
    },
    {
      "epoch": 0.49,
      "learning_rate": 8.582968159866416e-06,
      "loss": 0.0346,
      "step": 200
    },
    {
      "epoch": 0.52,
      "learning_rate": 8.445736844011712e-06,
      "loss": 0.0361,
      "step": 210
    },
    {
      "epoch": 0.54,
      "learning_rate": 8.303373616950408e-06,
      "loss": 0.0352,
      "step": 220
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.156090507480242e-06,
      "loss": 0.0351,
      "step": 230
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.004106871830155e-06,
      "loss": 0.0345,
      "step": 240
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.847649066961905e-06,
      "loss": 0.0364,
      "step": 250
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.68695011344511e-06,
      "loss": 0.0313,
      "step": 260
    },
    {
      "epoch": 0.66,
      "learning_rate": 7.52224934840788e-06,
      "loss": 0.0322,
      "step": 270
    },
    {
      "epoch": 0.69,
      "learning_rate": 7.353792069079826e-06,
      "loss": 0.0348,
      "step": 280
    },
    {
      "epoch": 0.71,
      "learning_rate": 7.181829167458441e-06,
      "loss": 0.0374,
      "step": 290
    },
    {
      "epoch": 0.74,
      "learning_rate": 7.006616756642867e-06,
      "loss": 0.0348,
      "step": 300
    },
    {
      "epoch": 0.76,
      "learning_rate": 6.828415789391632e-06,
      "loss": 0.0318,
      "step": 310
    },
    {
      "epoch": 0.79,
      "learning_rate": 6.647491669472421e-06,
      "loss": 0.0345,
      "step": 320
    },
    {
      "epoch": 0.81,
      "learning_rate": 6.464113856382752e-06,
      "loss": 0.034,
      "step": 330
    },
    {
      "epoch": 0.83,
      "learning_rate": 6.278555464030228e-06,
      "loss": 0.0305,
      "step": 340
    },
    {
      "epoch": 0.86,
      "learning_rate": 6.091092853970098e-06,
      "loss": 0.0337,
      "step": 350
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.902005223805931e-06,
      "loss": 0.0326,
      "step": 360
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.711574191366427e-06,
      "loss": 0.0344,
      "step": 370
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.520083375277644e-06,
      "loss": 0.032,
      "step": 380
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.3278179725553525e-06,
      "loss": 0.0329,
      "step": 390
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.135064333846612e-06,
      "loss": 0.0337,
      "step": 400
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.942109536953177e-06,
      "loss": 0.033,
      "step": 410
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.749240959271918e-06,
      "loss": 0.0298,
      "step": 420
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.556745849789055e-06,
      "loss": 0.0338,
      "step": 430
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.364910901265607e-06,
      "loss": 0.0332,
      "step": 440
    },
    {
      "epoch": 1.1,
      "learning_rate": 4.174021823251294e-06,
      "loss": 0.0328,
      "step": 450
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.984362916562753e-06,
      "loss": 0.0329,
      "step": 460
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.7962166498598785e-06,
      "loss": 0.0315,
      "step": 470
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.6098632389508637e-06,
      "loss": 0.0299,
      "step": 480
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.4255802294525464e-06,
      "loss": 0.0319,
      "step": 490
    },
    {
      "epoch": 1.23,
      "learning_rate": 3.2436420834276013e-06,
      "loss": 0.0319,
      "step": 500
    },
    {
      "epoch": 1.25,
      "learning_rate": 3.0643197706142136e-06,
      "loss": 0.0333,
      "step": 510
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.8878803648570773e-06,
      "loss": 0.0306,
      "step": 520
    },
    {
      "epoch": 1.3,
      "learning_rate": 2.7145866463407163e-06,
      "loss": 0.0309,
      "step": 530
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.544696710217588e-06,
      "loss": 0.0325,
      "step": 540
    },
    {
      "epoch": 1.35,
      "learning_rate": 2.3784635822138424e-06,
      "loss": 0.032,
      "step": 550
    },
    {
      "epoch": 1.37,
      "learning_rate": 2.2161348417852346e-06,
      "loss": 0.034,
      "step": 560
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.05795225338444e-06,
      "loss": 0.0322,
      "step": 570
    },
    {
      "epoch": 1.42,
      "learning_rate": 1.9041514063889571e-06,
      "loss": 0.0328,
      "step": 580
    },
    {
      "epoch": 1.45,
      "learning_rate": 1.7549613642258573e-06,
      "loss": 0.0336,
      "step": 590
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.6106043232159745e-06,
      "loss": 0.0339,
      "step": 600
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.4712952816456095e-06,
      "loss": 0.0325,
      "step": 610
    },
    {
      "epoch": 1.52,
      "learning_rate": 1.337241719558648e-06,
      "loss": 0.0327,
      "step": 620
    },
    {
      "epoch": 1.55,
      "learning_rate": 1.2086432897459738e-06,
      "loss": 0.0304,
      "step": 630
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.0856915203924096e-06,
      "loss": 0.0329,
      "step": 640
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.685695298240432e-07,
      "loss": 0.0322,
      "step": 650
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.574517537807897e-07,
      "loss": 0.0343,
      "step": 660
    },
    {
      "epoch": 1.64,
      "learning_rate": 7.525036856203677e-07,
      "loss": 0.0328,
      "step": 670
    },
    {
      "epoch": 1.67,
      "learning_rate": 6.538816298406203e-07,
      "loss": 0.0334,
      "step": 680
    },
    {
      "epoch": 1.69,
      "learning_rate": 5.617324692872744e-07,
      "loss": 0.0334,
      "step": 690
    },
    {
      "epoch": 1.72,
      "learning_rate": 4.7619344639384447e-07,
      "loss": 0.0337,
      "step": 700
    },
    {
      "epoch": 1.74,
      "learning_rate": 3.9739195877949223e-07,
      "loss": 0.0306,
      "step": 710
    },
    {
      "epoch": 1.77,
      "learning_rate": 3.254453695092752e-07,
      "loss": 0.032,
      "step": 720
    },
    {
      "epoch": 1.79,
      "learning_rate": 2.604608322993518e-07,
      "loss": 0.0325,
      "step": 730
    },
    {
      "epoch": 1.82,
      "learning_rate": 2.0253513192751374e-07,
      "loss": 0.0351,
      "step": 740
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.5175454008667712e-07,
      "loss": 0.0309,
      "step": 750
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.0819468689607426e-07,
      "loss": 0.0305,
      "step": 760
    },
    {
      "epoch": 1.89,
      "learning_rate": 7.192044826145772e-08,
      "loss": 0.0284,
      "step": 770
    },
    {
      "epoch": 1.91,
      "learning_rate": 4.298584925212068e-08,
      "loss": 0.0305,
      "step": 780
    },
    {
      "epoch": 1.94,
      "learning_rate": 2.143398363860738e-08,
      "loss": 0.0303,
      "step": 790
    },
    {
      "epoch": 1.96,
      "learning_rate": 7.2969497109715016e-09,
      "loss": 0.0313,
      "step": 800
    },
    {
      "epoch": 1.99,
      "learning_rate": 5.958024731567147e-10,
      "loss": 0.0331,
      "step": 810
    },
    {
      "epoch": 2.0,
      "step": 814,
      "tflops": 490.2053045046936,
      "token/s": 1736.022262942593,
      "total_flos": 1.5851362853622645e+19,
      "train_loss": 0.035910474946516446,
      "train_runtime": 31598.4886,
      "train_samples_per_second": 6.603,
      "train_steps_per_second": 0.026
    }
  ],
  "log_save_evaluate_time": 2188.9126505851746,
  "logging_steps": 10,
  "max_steps": 814,
  "num_train_epochs": 2,
  "save_steps": 200,
  "total_flos": 1.5851362853622645e+19,
  "total_tokens": 51055680.0,
  "trial_name": null,
  "trial_params": null
}