{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.175,
  "eval_steps": 500,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025,
      "grad_norm": 28.533191680908203,
      "learning_rate": 0.00019950000000000002,
      "loss": 10.2028,
      "step": 10
    },
    {
      "epoch": 0.005,
      "grad_norm": 1.5962224006652832,
      "learning_rate": 0.000199,
      "loss": 1.8731,
      "step": 20
    },
    {
      "epoch": 0.0075,
      "grad_norm": 0.8784465193748474,
      "learning_rate": 0.00019850000000000003,
      "loss": 0.5834,
      "step": 30
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.6551746726036072,
      "learning_rate": 0.00019800000000000002,
      "loss": 0.4274,
      "step": 40
    },
    {
      "epoch": 0.0125,
      "grad_norm": 0.7458402514457703,
      "learning_rate": 0.00019750000000000003,
      "loss": 0.2921,
      "step": 50
    },
    {
      "epoch": 0.015,
      "grad_norm": 0.6910417675971985,
      "learning_rate": 0.00019700000000000002,
      "loss": 0.1889,
      "step": 60
    },
    {
      "epoch": 0.0175,
      "grad_norm": 0.575136125087738,
      "learning_rate": 0.0001965,
      "loss": 0.1379,
      "step": 70
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.2535680532455444,
      "learning_rate": 0.000196,
      "loss": 0.1053,
      "step": 80
    },
    {
      "epoch": 0.0225,
      "grad_norm": 0.9697864651679993,
      "learning_rate": 0.0001955,
      "loss": 0.0756,
      "step": 90
    },
    {
      "epoch": 0.025,
      "grad_norm": 0.508269727230072,
      "learning_rate": 0.000195,
      "loss": 0.055,
      "step": 100
    },
    {
      "epoch": 0.0275,
      "grad_norm": 0.6621774435043335,
      "learning_rate": 0.0001945,
      "loss": 0.0487,
      "step": 110
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.5406679511070251,
      "learning_rate": 0.000194,
      "loss": 0.0406,
      "step": 120
    },
    {
      "epoch": 0.0325,
      "grad_norm": 0.35967350006103516,
      "learning_rate": 0.00019350000000000001,
      "loss": 0.0347,
      "step": 130
    },
    {
      "epoch": 0.035,
      "grad_norm": 0.6122244000434875,
      "learning_rate": 0.000193,
      "loss": 0.0334,
      "step": 140
    },
    {
      "epoch": 0.0375,
      "grad_norm": 0.4679579734802246,
      "learning_rate": 0.00019250000000000002,
      "loss": 0.0342,
      "step": 150
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.6229879856109619,
      "learning_rate": 0.000192,
      "loss": 0.0328,
      "step": 160
    },
    {
      "epoch": 0.0425,
      "grad_norm": 0.4741787314414978,
      "learning_rate": 0.00019150000000000002,
      "loss": 0.0328,
      "step": 170
    },
    {
      "epoch": 0.045,
      "grad_norm": 0.3581089377403259,
      "learning_rate": 0.000191,
      "loss": 0.0329,
      "step": 180
    },
    {
      "epoch": 0.0475,
      "grad_norm": 0.2805705964565277,
      "learning_rate": 0.00019050000000000002,
      "loss": 0.0316,
      "step": 190
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.36797094345092773,
      "learning_rate": 0.00019,
      "loss": 0.0314,
      "step": 200
    },
    {
      "epoch": 0.0525,
      "grad_norm": 0.22872206568717957,
      "learning_rate": 0.0001895,
      "loss": 0.0304,
      "step": 210
    },
    {
      "epoch": 0.055,
      "grad_norm": 0.3525296151638031,
      "learning_rate": 0.00018899999999999999,
      "loss": 0.0315,
      "step": 220
    },
    {
      "epoch": 0.0575,
      "grad_norm": 0.21026159822940826,
      "learning_rate": 0.0001885,
      "loss": 0.0302,
      "step": 230
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.1741417497396469,
      "learning_rate": 0.000188,
      "loss": 0.0307,
      "step": 240
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.35116010904312134,
      "learning_rate": 0.0001875,
      "loss": 0.0305,
      "step": 250
    },
    {
      "epoch": 0.065,
      "grad_norm": 0.2572971284389496,
      "learning_rate": 0.00018700000000000002,
      "loss": 0.0313,
      "step": 260
    },
    {
      "epoch": 0.0675,
      "grad_norm": 0.2466694414615631,
      "learning_rate": 0.0001865,
      "loss": 0.0299,
      "step": 270
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.19943873584270477,
      "learning_rate": 0.00018600000000000002,
      "loss": 0.0304,
      "step": 280
    },
    {
      "epoch": 0.0725,
      "grad_norm": 0.3378709852695465,
      "learning_rate": 0.0001855,
      "loss": 0.0299,
      "step": 290
    },
    {
      "epoch": 0.075,
      "grad_norm": 0.23438668251037598,
      "learning_rate": 0.00018500000000000002,
      "loss": 0.0301,
      "step": 300
    },
    {
      "epoch": 0.0775,
      "grad_norm": 0.3201534152030945,
      "learning_rate": 0.0001845,
      "loss": 0.0307,
      "step": 310
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.19868455827236176,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.0294,
      "step": 320
    },
    {
      "epoch": 0.0825,
      "grad_norm": 0.20487827062606812,
      "learning_rate": 0.00018350000000000002,
      "loss": 0.0309,
      "step": 330
    },
    {
      "epoch": 0.085,
      "grad_norm": 0.3057793378829956,
      "learning_rate": 0.000183,
      "loss": 0.0307,
      "step": 340
    },
    {
      "epoch": 0.0875,
      "grad_norm": 0.12229125201702118,
      "learning_rate": 0.0001825,
      "loss": 0.0303,
      "step": 350
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.18177232146263123,
      "learning_rate": 0.000182,
      "loss": 0.0302,
      "step": 360
    },
    {
      "epoch": 0.0925,
      "grad_norm": 0.28575578331947327,
      "learning_rate": 0.0001815,
      "loss": 0.0304,
      "step": 370
    },
    {
      "epoch": 0.095,
      "grad_norm": 0.19034205377101898,
      "learning_rate": 0.000181,
      "loss": 0.03,
      "step": 380
    },
    {
      "epoch": 0.0975,
      "grad_norm": 0.23103861510753632,
      "learning_rate": 0.0001805,
      "loss": 0.0305,
      "step": 390
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.15927983820438385,
      "learning_rate": 0.00018,
      "loss": 0.0292,
      "step": 400
    },
    {
      "epoch": 0.1025,
      "grad_norm": 0.19252969324588776,
      "learning_rate": 0.0001795,
      "loss": 0.0314,
      "step": 410
    },
    {
      "epoch": 0.105,
      "grad_norm": 0.20013266801834106,
      "learning_rate": 0.00017900000000000001,
      "loss": 0.0299,
      "step": 420
    },
    {
      "epoch": 0.1075,
      "grad_norm": 0.14499768614768982,
      "learning_rate": 0.0001785,
      "loss": 0.0304,
      "step": 430
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.16168737411499023,
      "learning_rate": 0.00017800000000000002,
      "loss": 0.0312,
      "step": 440
    },
    {
      "epoch": 0.1125,
      "grad_norm": 0.22811977565288544,
      "learning_rate": 0.0001775,
      "loss": 0.0297,
      "step": 450
    },
    {
      "epoch": 0.115,
      "grad_norm": 0.13746319711208344,
      "learning_rate": 0.00017700000000000002,
      "loss": 0.0299,
      "step": 460
    },
    {
      "epoch": 0.1175,
      "grad_norm": 0.24217799305915833,
      "learning_rate": 0.0001765,
      "loss": 0.0298,
      "step": 470
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.20098623633384705,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.031,
      "step": 480
    },
    {
      "epoch": 0.1225,
      "grad_norm": 0.16132541000843048,
      "learning_rate": 0.0001755,
      "loss": 0.0298,
      "step": 490
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.1743323802947998,
      "learning_rate": 0.000175,
      "loss": 0.0311,
      "step": 500
    },
    {
      "epoch": 0.1275,
      "grad_norm": 0.25642746686935425,
      "learning_rate": 0.0001745,
      "loss": 0.0293,
      "step": 510
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.14132989943027496,
      "learning_rate": 0.000174,
      "loss": 0.0298,
      "step": 520
    },
    {
      "epoch": 0.1325,
      "grad_norm": 0.15414279699325562,
      "learning_rate": 0.00017350000000000002,
      "loss": 0.0306,
      "step": 530
    },
    {
      "epoch": 0.135,
      "grad_norm": 0.1769929677248001,
      "learning_rate": 0.000173,
      "loss": 0.0308,
      "step": 540
    },
    {
      "epoch": 0.1375,
      "grad_norm": 0.23861835896968842,
      "learning_rate": 0.00017250000000000002,
      "loss": 0.03,
      "step": 550
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.14238761365413666,
      "learning_rate": 0.000172,
      "loss": 0.0302,
      "step": 560
    },
    {
      "epoch": 0.1425,
      "grad_norm": 0.12197570502758026,
      "learning_rate": 0.00017150000000000002,
      "loss": 0.0291,
      "step": 570
    },
    {
      "epoch": 0.145,
      "grad_norm": 0.16140304505825043,
      "learning_rate": 0.000171,
      "loss": 0.0308,
      "step": 580
    },
    {
      "epoch": 0.1475,
      "grad_norm": 0.1349712610244751,
      "learning_rate": 0.00017050000000000002,
      "loss": 0.0296,
      "step": 590
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.15457607805728912,
      "learning_rate": 0.00017,
      "loss": 0.0294,
      "step": 600
    },
    {
      "epoch": 0.1525,
      "grad_norm": 0.24771223962306976,
      "learning_rate": 0.00016950000000000003,
      "loss": 0.0295,
      "step": 610
    },
    {
      "epoch": 0.155,
      "grad_norm": 0.1785576194524765,
      "learning_rate": 0.00016900000000000002,
      "loss": 0.0294,
      "step": 620
    },
    {
      "epoch": 0.1575,
      "grad_norm": 0.208939328789711,
      "learning_rate": 0.0001685,
      "loss": 0.0287,
      "step": 630
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.15111897885799408,
      "learning_rate": 0.000168,
      "loss": 0.0297,
      "step": 640
    },
    {
      "epoch": 0.1625,
      "grad_norm": 0.16397146880626678,
      "learning_rate": 0.0001675,
      "loss": 0.0306,
      "step": 650
    },
    {
      "epoch": 0.165,
      "grad_norm": 0.1457725465297699,
      "learning_rate": 0.000167,
      "loss": 0.029,
      "step": 660
    },
    {
      "epoch": 0.1675,
      "grad_norm": 0.1790078729391098,
      "learning_rate": 0.0001665,
      "loss": 0.0293,
      "step": 670
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.13654978573322296,
      "learning_rate": 0.000166,
      "loss": 0.0292,
      "step": 680
    },
    {
      "epoch": 0.1725,
      "grad_norm": 0.14379267394542694,
      "learning_rate": 0.0001655,
      "loss": 0.0295,
      "step": 690
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.21510595083236694,
      "learning_rate": 0.000165,
      "loss": 0.0306,
      "step": 700
    }
  ],
  "logging_steps": 10,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 770786761113600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}