{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03555620056599666,
  "eval_steps": 500,
  "global_step": 490,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007256367462448298,
      "grad_norm": 12.0,
      "learning_rate": 5e-05,
      "loss": 3.0993,
      "step": 10
    },
    {
      "epoch": 0.0014512734924896596,
      "grad_norm": 10.4375,
      "learning_rate": 0.0001,
      "loss": 2.208,
      "step": 20
    },
    {
      "epoch": 0.0021769102387344894,
      "grad_norm": 6.5625,
      "learning_rate": 0.00015,
      "loss": 1.3285,
      "step": 30
    },
    {
      "epoch": 0.0029025469849793192,
      "grad_norm": 6.21875,
      "learning_rate": 0.0002,
      "loss": 0.6895,
      "step": 40
    },
    {
      "epoch": 0.003628183731224149,
      "grad_norm": 4.15625,
      "learning_rate": 0.00025,
      "loss": 0.714,
      "step": 50
    },
    {
      "epoch": 0.004353820477468979,
      "grad_norm": 4.71875,
      "learning_rate": 0.0003,
      "loss": 0.4849,
      "step": 60
    },
    {
      "epoch": 0.005079457223713809,
      "grad_norm": 3.828125,
      "learning_rate": 0.00035,
      "loss": 0.3671,
      "step": 70
    },
    {
      "epoch": 0.0058050939699586385,
      "grad_norm": 4.03125,
      "learning_rate": 0.0004,
      "loss": 0.5693,
      "step": 80
    },
    {
      "epoch": 0.006530730716203468,
      "grad_norm": 3.296875,
      "learning_rate": 0.00045000000000000004,
      "loss": 0.4133,
      "step": 90
    },
    {
      "epoch": 0.007256367462448298,
      "grad_norm": 2.640625,
      "learning_rate": 0.0005,
      "loss": 0.2668,
      "step": 100
    },
    {
      "epoch": 0.007982004208693128,
      "grad_norm": 1.5859375,
      "learning_rate": 0.000499999340865746,
      "loss": 0.2922,
      "step": 110
    },
    {
      "epoch": 0.008707640954937958,
      "grad_norm": 3.8125,
      "learning_rate": 0.0004999973634664594,
      "loss": 0.3996,
      "step": 120
    },
    {
      "epoch": 0.009433277701182788,
      "grad_norm": 2.0625,
      "learning_rate": 0.0004999940678125673,
      "loss": 0.2841,
      "step": 130
    },
    {
      "epoch": 0.010158914447427617,
      "grad_norm": 3.390625,
      "learning_rate": 0.000499989453921448,
      "loss": 0.3003,
      "step": 140
    },
    {
      "epoch": 0.010884551193672447,
      "grad_norm": 1.65625,
      "learning_rate": 0.0004999835218174307,
      "loss": 0.2747,
      "step": 150
    },
    {
      "epoch": 0.011610187939917277,
      "grad_norm": 1.671875,
      "learning_rate": 0.000499976271531796,
      "loss": 0.37,
      "step": 160
    },
    {
      "epoch": 0.012335824686162107,
      "grad_norm": 1.0390625,
      "learning_rate": 0.000499967703102775,
      "loss": 0.2163,
      "step": 170
    },
    {
      "epoch": 0.013061461432406937,
      "grad_norm": 2.546875,
      "learning_rate": 0.00049995781657555,
      "loss": 0.3652,
      "step": 180
    },
    {
      "epoch": 0.013787098178651766,
      "grad_norm": 3.71875,
      "learning_rate": 0.000499946612002253,
      "loss": 0.3177,
      "step": 190
    },
    {
      "epoch": 0.014512734924896596,
      "grad_norm": 2.6875,
      "learning_rate": 0.0004999340894419668,
      "loss": 0.2043,
      "step": 200
    },
    {
      "epoch": 0.015238371671141426,
      "grad_norm": 0.5,
      "learning_rate": 0.0004999202489607236,
      "loss": 0.2865,
      "step": 210
    },
    {
      "epoch": 0.015964008417386256,
      "grad_norm": 3.015625,
      "learning_rate": 0.0004999050906315055,
      "loss": 0.2039,
      "step": 220
    },
    {
      "epoch": 0.016689645163631087,
      "grad_norm": 0.99609375,
      "learning_rate": 0.0004998886145342434,
      "loss": 0.3509,
      "step": 230
    },
    {
      "epoch": 0.017415281909875915,
      "grad_norm": 1.34375,
      "learning_rate": 0.0004998708207558168,
      "loss": 0.3208,
      "step": 240
    },
    {
      "epoch": 0.018140918656120747,
      "grad_norm": 2.015625,
      "learning_rate": 0.0004998517093900539,
      "loss": 0.2307,
      "step": 250
    },
    {
      "epoch": 0.018866555402365575,
      "grad_norm": 1.0703125,
      "learning_rate": 0.0004998312805377302,
      "loss": 0.2232,
      "step": 260
    },
    {
      "epoch": 0.019592192148610407,
      "grad_norm": 1.7265625,
      "learning_rate": 0.0004998095343065685,
      "loss": 0.2587,
      "step": 270
    },
    {
      "epoch": 0.020317828894855235,
      "grad_norm": 1.21875,
      "learning_rate": 0.0004997864708112384,
      "loss": 0.2175,
      "step": 280
    },
    {
      "epoch": 0.021043465641100066,
      "grad_norm": 2.234375,
      "learning_rate": 0.0004997620901733554,
      "loss": 0.2185,
      "step": 290
    },
    {
      "epoch": 0.021769102387344894,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0004997363925214804,
      "loss": 0.2409,
      "step": 300
    },
    {
      "epoch": 0.022494739133589726,
      "grad_norm": 1.7109375,
      "learning_rate": 0.000499709377991119,
      "loss": 0.1976,
      "step": 310
    },
    {
      "epoch": 0.023220375879834554,
      "grad_norm": 1.7890625,
      "learning_rate": 0.0004996810467247207,
      "loss": 0.2899,
      "step": 320
    },
    {
      "epoch": 0.023946012626079385,
      "grad_norm": 1.9296875,
      "learning_rate": 0.0004996513988716786,
      "loss": 0.2324,
      "step": 330
    },
    {
      "epoch": 0.024671649372324213,
      "grad_norm": 1.59375,
      "learning_rate": 0.0004996204345883278,
      "loss": 0.2376,
      "step": 340
    },
    {
      "epoch": 0.025397286118569045,
      "grad_norm": 1.734375,
      "learning_rate": 0.0004995881540379454,
      "loss": 0.2927,
      "step": 350
    },
    {
      "epoch": 0.026122922864813873,
      "grad_norm": 1.9375,
      "learning_rate": 0.0004995545573907492,
      "loss": 0.2738,
      "step": 360
    },
    {
      "epoch": 0.026848559611058705,
      "grad_norm": 2.421875,
      "learning_rate": 0.0004995196448238966,
      "loss": 0.2427,
      "step": 370
    },
    {
      "epoch": 0.027574196357303533,
      "grad_norm": 2.671875,
      "learning_rate": 0.0004994834165214843,
      "loss": 0.2032,
      "step": 380
    },
    {
      "epoch": 0.028299833103548364,
      "grad_norm": 3.328125,
      "learning_rate": 0.0004994458726745468,
      "loss": 0.2748,
      "step": 390
    },
    {
      "epoch": 0.029025469849793192,
      "grad_norm": 0.498046875,
      "learning_rate": 0.0004994070134810556,
      "loss": 0.2275,
      "step": 400
    },
    {
      "epoch": 0.029751106596038024,
      "grad_norm": 1.0703125,
      "learning_rate": 0.000499366839145918,
      "loss": 0.1725,
      "step": 410
    },
    {
      "epoch": 0.030476743342282852,
      "grad_norm": 3.46875,
      "learning_rate": 0.0004993253498809762,
      "loss": 0.2298,
      "step": 420
    },
    {
      "epoch": 0.031202380088527683,
      "grad_norm": 2.875,
      "learning_rate": 0.0004992825459050064,
      "loss": 0.2721,
      "step": 430
    },
    {
      "epoch": 0.03192801683477251,
      "grad_norm": 1.6640625,
      "learning_rate": 0.0004992384274437171,
      "loss": 0.248,
      "step": 440
    },
    {
      "epoch": 0.03265365358101734,
      "grad_norm": 1.8984375,
      "learning_rate": 0.000499192994729748,
      "loss": 0.1529,
      "step": 450
    },
    {
      "epoch": 0.033379290327262175,
      "grad_norm": 2.234375,
      "learning_rate": 0.0004991462480026693,
      "loss": 0.2584,
      "step": 460
    },
    {
      "epoch": 0.034104927073507,
      "grad_norm": 0.984375,
      "learning_rate": 0.0004990981875089799,
      "loss": 0.25,
      "step": 470
    },
    {
      "epoch": 0.03483056381975183,
      "grad_norm": 1.75,
      "learning_rate": 0.0004990488135021065,
      "loss": 0.199,
      "step": 480
    },
    {
      "epoch": 0.03555620056599666,
      "grad_norm": 0.7421875,
      "learning_rate": 0.0004989981262424017,
      "loss": 0.2546,
      "step": 490
    }
  ],
  "logging_steps": 10,
  "max_steps": 13781,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 0.0,
  "train_batch_size": 5,
  "trial_name": null,
  "trial_params": null
}