{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8044243338360986,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01608848667672197,
      "grad_norm": 6.964079856872559,
      "learning_rate": 4e-05,
      "loss": 2.7497,
      "step": 20
    },
    {
      "epoch": 0.03217697335344394,
      "grad_norm": 2.735353946685791,
      "learning_rate": 8e-05,
      "loss": 1.4988,
      "step": 40
    },
    {
      "epoch": 0.048265460030165915,
      "grad_norm": 2.258044481277466,
      "learning_rate": 0.00012,
      "loss": 1.3571,
      "step": 60
    },
    {
      "epoch": 0.06435394670688788,
      "grad_norm": 2.981090784072876,
      "learning_rate": 0.00016,
      "loss": 1.3767,
      "step": 80
    },
    {
      "epoch": 0.08044243338360986,
      "grad_norm": 2.452106475830078,
      "learning_rate": 0.0002,
      "loss": 1.309,
      "step": 100
    },
    {
      "epoch": 0.09653092006033183,
      "grad_norm": 2.4377968311309814,
      "learning_rate": 0.00019650043744531934,
      "loss": 1.3168,
      "step": 120
    },
    {
      "epoch": 0.1126194067370538,
      "grad_norm": 2.38288950920105,
      "learning_rate": 0.00019300087489063867,
      "loss": 1.3587,
      "step": 140
    },
    {
      "epoch": 0.12870789341377575,
      "grad_norm": 2.5989363193511963,
      "learning_rate": 0.000189501312335958,
      "loss": 1.325,
      "step": 160
    },
    {
      "epoch": 0.14479638009049775,
      "grad_norm": 2.084688901901245,
      "learning_rate": 0.00018600174978127736,
      "loss": 1.3187,
      "step": 180
    },
    {
      "epoch": 0.16088486676721972,
      "grad_norm": 2.4337613582611084,
      "learning_rate": 0.0001825021872265967,
      "loss": 1.2917,
      "step": 200
    },
    {
      "epoch": 0.1769733534439417,
      "grad_norm": 2.2334115505218506,
      "learning_rate": 0.00017900262467191602,
      "loss": 1.279,
      "step": 220
    },
    {
      "epoch": 0.19306184012066366,
      "grad_norm": 2.3266961574554443,
      "learning_rate": 0.00017550306211723535,
      "loss": 1.2932,
      "step": 240
    },
    {
      "epoch": 0.20915032679738563,
      "grad_norm": 2.333585500717163,
      "learning_rate": 0.00017200349956255468,
      "loss": 1.2868,
      "step": 260
    },
    {
      "epoch": 0.2252388134741076,
      "grad_norm": 2.11601185798645,
      "learning_rate": 0.000168503937007874,
      "loss": 1.2997,
      "step": 280
    },
    {
      "epoch": 0.24132730015082957,
      "grad_norm": 2.2596933841705322,
      "learning_rate": 0.00016500437445319337,
      "loss": 1.2587,
      "step": 300
    },
    {
      "epoch": 0.2574157868275515,
      "grad_norm": 2.280146598815918,
      "learning_rate": 0.0001615048118985127,
      "loss": 1.2571,
      "step": 320
    },
    {
      "epoch": 0.27350427350427353,
      "grad_norm": 2.0850765705108643,
      "learning_rate": 0.00015800524934383203,
      "loss": 1.2706,
      "step": 340
    },
    {
      "epoch": 0.2895927601809955,
      "grad_norm": 1.557936668395996,
      "learning_rate": 0.00015450568678915136,
      "loss": 1.2334,
      "step": 360
    },
    {
      "epoch": 0.30568124685771747,
      "grad_norm": 1.4320595264434814,
      "learning_rate": 0.0001510061242344707,
      "loss": 1.2243,
      "step": 380
    },
    {
      "epoch": 0.32176973353443944,
      "grad_norm": 2.060842514038086,
      "learning_rate": 0.00014750656167979002,
      "loss": 1.2652,
      "step": 400
    },
    {
      "epoch": 0.3378582202111614,
      "grad_norm": 1.5861530303955078,
      "learning_rate": 0.00014400699912510938,
      "loss": 1.1902,
      "step": 420
    },
    {
      "epoch": 0.3539467068878834,
      "grad_norm": 2.1270854473114014,
      "learning_rate": 0.0001405074365704287,
      "loss": 1.2269,
      "step": 440
    },
    {
      "epoch": 0.37003519356460535,
      "grad_norm": 1.6317099332809448,
      "learning_rate": 0.00013700787401574804,
      "loss": 1.1482,
      "step": 460
    },
    {
      "epoch": 0.3861236802413273,
      "grad_norm": 1.7842175960540771,
      "learning_rate": 0.00013350831146106737,
      "loss": 1.2013,
      "step": 480
    },
    {
      "epoch": 0.4022121669180493,
      "grad_norm": 2.0094027519226074,
      "learning_rate": 0.0001300087489063867,
      "loss": 1.1789,
      "step": 500
    },
    {
      "epoch": 0.41830065359477125,
      "grad_norm": 1.899143934249878,
      "learning_rate": 0.00012650918635170603,
      "loss": 1.1602,
      "step": 520
    },
    {
      "epoch": 0.4343891402714932,
      "grad_norm": 2.16550350189209,
      "learning_rate": 0.0001230096237970254,
      "loss": 1.1804,
      "step": 540
    },
    {
      "epoch": 0.4504776269482152,
      "grad_norm": 1.6540337800979614,
      "learning_rate": 0.00011951006124234472,
      "loss": 1.202,
      "step": 560
    },
    {
      "epoch": 0.46656611362493716,
      "grad_norm": 2.159453868865967,
      "learning_rate": 0.00011601049868766405,
      "loss": 1.1415,
      "step": 580
    },
    {
      "epoch": 0.48265460030165913,
      "grad_norm": 1.7094770669937134,
      "learning_rate": 0.00011251093613298338,
      "loss": 1.177,
      "step": 600
    },
    {
      "epoch": 0.4987430869783811,
      "grad_norm": 1.721779227256775,
      "learning_rate": 0.00010901137357830271,
      "loss": 1.1343,
      "step": 620
    },
    {
      "epoch": 0.514831573655103,
      "grad_norm": 1.6354072093963623,
      "learning_rate": 0.00010551181102362204,
      "loss": 1.1501,
      "step": 640
    },
    {
      "epoch": 0.530920060331825,
      "grad_norm": 1.8426846265792847,
      "learning_rate": 0.0001020122484689414,
      "loss": 1.095,
      "step": 660
    },
    {
      "epoch": 0.5470085470085471,
      "grad_norm": 1.441419005393982,
      "learning_rate": 9.851268591426073e-05,
      "loss": 1.1536,
      "step": 680
    },
    {
      "epoch": 0.563097033685269,
      "grad_norm": 2.076209545135498,
      "learning_rate": 9.501312335958006e-05,
      "loss": 1.0939,
      "step": 700
    },
    {
      "epoch": 0.579185520361991,
      "grad_norm": 1.6805191040039062,
      "learning_rate": 9.151356080489939e-05,
      "loss": 1.1148,
      "step": 720
    },
    {
      "epoch": 0.5952740070387129,
      "grad_norm": 1.650302767753601,
      "learning_rate": 8.801399825021873e-05,
      "loss": 1.1416,
      "step": 740
    },
    {
      "epoch": 0.6113624937154349,
      "grad_norm": 1.9106342792510986,
      "learning_rate": 8.451443569553806e-05,
      "loss": 1.1169,
      "step": 760
    },
    {
      "epoch": 0.6274509803921569,
      "grad_norm": 1.8341450691223145,
      "learning_rate": 8.10148731408574e-05,
      "loss": 1.0639,
      "step": 780
    },
    {
      "epoch": 0.6435394670688789,
      "grad_norm": 1.4700909852981567,
      "learning_rate": 7.751531058617674e-05,
      "loss": 1.0996,
      "step": 800
    },
    {
      "epoch": 0.6596279537456008,
      "grad_norm": 1.8903424739837646,
      "learning_rate": 7.401574803149607e-05,
      "loss": 1.1005,
      "step": 820
    },
    {
      "epoch": 0.6757164404223228,
      "grad_norm": 2.014308214187622,
      "learning_rate": 7.05161854768154e-05,
      "loss": 1.0935,
      "step": 840
    },
    {
      "epoch": 0.6918049270990447,
      "grad_norm": 1.742974877357483,
      "learning_rate": 6.701662292213474e-05,
      "loss": 1.089,
      "step": 860
    },
    {
      "epoch": 0.7078934137757668,
      "grad_norm": 1.8661373853683472,
      "learning_rate": 6.351706036745407e-05,
      "loss": 1.1048,
      "step": 880
    },
    {
      "epoch": 0.7239819004524887,
      "grad_norm": 1.6748634576797485,
      "learning_rate": 6.00174978127734e-05,
      "loss": 1.0903,
      "step": 900
    },
    {
      "epoch": 0.7400703871292107,
      "grad_norm": 1.7615855932235718,
      "learning_rate": 5.6517935258092734e-05,
      "loss": 1.0356,
      "step": 920
    },
    {
      "epoch": 0.7561588738059326,
      "grad_norm": 1.7509955167770386,
      "learning_rate": 5.301837270341208e-05,
      "loss": 1.0446,
      "step": 940
    },
    {
      "epoch": 0.7722473604826546,
      "grad_norm": 1.871839165687561,
      "learning_rate": 4.951881014873141e-05,
      "loss": 1.0521,
      "step": 960
    },
    {
      "epoch": 0.7883358471593765,
      "grad_norm": 1.7496371269226074,
      "learning_rate": 4.6019247594050745e-05,
      "loss": 1.0813,
      "step": 980
    },
    {
      "epoch": 0.8044243338360986,
      "grad_norm": 1.7232415676116943,
      "learning_rate": 4.251968503937008e-05,
      "loss": 1.0358,
      "step": 1000
    }
  ],
  "logging_steps": 20,
  "max_steps": 1243,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.363282340552499e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}