{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.71563981042654,
  "eval_steps": 500,
  "global_step": 1040,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1895734597156398,
      "grad_norm": 0.597112774848938,
      "learning_rate": 2.9711538461538464e-05,
      "loss": 0.435,
      "step": 10
    },
    {
      "epoch": 0.3791469194312796,
      "grad_norm": 0.16265545785427094,
      "learning_rate": 2.9423076923076923e-05,
      "loss": 0.1842,
      "step": 20
    },
    {
      "epoch": 0.5687203791469194,
      "grad_norm": 0.13190606236457825,
      "learning_rate": 2.9134615384615386e-05,
      "loss": 0.1818,
      "step": 30
    },
    {
      "epoch": 0.7582938388625592,
      "grad_norm": 0.1712672859430313,
      "learning_rate": 2.884615384615385e-05,
      "loss": 0.1685,
      "step": 40
    },
    {
      "epoch": 0.9478672985781991,
      "grad_norm": 0.17000597715377808,
      "learning_rate": 2.855769230769231e-05,
      "loss": 0.1694,
      "step": 50
    },
    {
      "epoch": 1.1374407582938388,
      "grad_norm": 0.04239616543054581,
      "learning_rate": 2.8269230769230768e-05,
      "loss": 0.1564,
      "step": 60
    },
    {
      "epoch": 1.3270142180094786,
      "grad_norm": 0.055856816470623016,
      "learning_rate": 2.798076923076923e-05,
      "loss": 0.1675,
      "step": 70
    },
    {
      "epoch": 1.5165876777251186,
      "grad_norm": 0.05924641340970993,
      "learning_rate": 2.7692307692307694e-05,
      "loss": 0.1751,
      "step": 80
    },
    {
      "epoch": 1.7061611374407581,
      "grad_norm": 0.04663912579417229,
      "learning_rate": 2.7403846153846153e-05,
      "loss": 0.1598,
      "step": 90
    },
    {
      "epoch": 1.8957345971563981,
      "grad_norm": 0.07988695800304413,
      "learning_rate": 2.7115384615384616e-05,
      "loss": 0.1489,
      "step": 100
    },
    {
      "epoch": 2.085308056872038,
      "grad_norm": 0.1717785745859146,
      "learning_rate": 2.682692307692308e-05,
      "loss": 0.1668,
      "step": 110
    },
    {
      "epoch": 2.2748815165876777,
      "grad_norm": 0.15836206078529358,
      "learning_rate": 2.6538461538461538e-05,
      "loss": 0.1543,
      "step": 120
    },
    {
      "epoch": 2.4644549763033177,
      "grad_norm": 0.023397250100970268,
      "learning_rate": 2.625e-05,
      "loss": 0.1686,
      "step": 130
    },
    {
      "epoch": 2.654028436018957,
      "grad_norm": 0.2287532091140747,
      "learning_rate": 2.5961538461538464e-05,
      "loss": 0.1645,
      "step": 140
    },
    {
      "epoch": 2.843601895734597,
      "grad_norm": 0.3427872061729431,
      "learning_rate": 2.5673076923076923e-05,
      "loss": 0.133,
      "step": 150
    },
    {
      "epoch": 3.0331753554502368,
      "grad_norm": 0.307771772146225,
      "learning_rate": 2.5384615384615386e-05,
      "loss": 0.103,
      "step": 160
    },
    {
      "epoch": 3.2227488151658767,
      "grad_norm": 0.30710339546203613,
      "learning_rate": 2.509615384615385e-05,
      "loss": 0.0924,
      "step": 170
    },
    {
      "epoch": 3.4123222748815167,
      "grad_norm": 0.20707634091377258,
      "learning_rate": 2.4807692307692305e-05,
      "loss": 0.0749,
      "step": 180
    },
    {
      "epoch": 3.6018957345971563,
      "grad_norm": 0.2535831034183502,
      "learning_rate": 2.4519230769230768e-05,
      "loss": 0.0704,
      "step": 190
    },
    {
      "epoch": 3.7914691943127963,
      "grad_norm": 0.2260940968990326,
      "learning_rate": 2.423076923076923e-05,
      "loss": 0.0688,
      "step": 200
    },
    {
      "epoch": 3.9810426540284363,
      "grad_norm": 0.21390962600708008,
      "learning_rate": 2.3942307692307694e-05,
      "loss": 0.0585,
      "step": 210
    },
    {
      "epoch": 4.170616113744076,
      "grad_norm": 0.1833769828081131,
      "learning_rate": 2.3653846153846153e-05,
      "loss": 0.054,
      "step": 220
    },
    {
      "epoch": 4.360189573459715,
      "grad_norm": 0.2922685146331787,
      "learning_rate": 2.3365384615384616e-05,
      "loss": 0.0538,
      "step": 230
    },
    {
      "epoch": 4.549763033175355,
      "grad_norm": 0.2239004522562027,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.0543,
      "step": 240
    },
    {
      "epoch": 4.739336492890995,
      "grad_norm": 0.17778703570365906,
      "learning_rate": 2.278846153846154e-05,
      "loss": 0.0561,
      "step": 250
    },
    {
      "epoch": 4.928909952606635,
      "grad_norm": 0.3559529483318329,
      "learning_rate": 2.25e-05,
      "loss": 0.0493,
      "step": 260
    },
    {
      "epoch": 5.118483412322275,
      "grad_norm": 0.12670384347438812,
      "learning_rate": 2.2211538461538464e-05,
      "loss": 0.049,
      "step": 270
    },
    {
      "epoch": 5.308056872037914,
      "grad_norm": 0.19230520725250244,
      "learning_rate": 2.1923076923076924e-05,
      "loss": 0.0477,
      "step": 280
    },
    {
      "epoch": 5.497630331753554,
      "grad_norm": 0.17324426770210266,
      "learning_rate": 2.1634615384615383e-05,
      "loss": 0.0434,
      "step": 290
    },
    {
      "epoch": 5.687203791469194,
      "grad_norm": 0.310581237077713,
      "learning_rate": 2.1346153846153846e-05,
      "loss": 0.0437,
      "step": 300
    },
    {
      "epoch": 5.876777251184834,
      "grad_norm": 0.14988450706005096,
      "learning_rate": 2.1057692307692306e-05,
      "loss": 0.0401,
      "step": 310
    },
    {
      "epoch": 6.0663507109004735,
      "grad_norm": 0.1281799077987671,
      "learning_rate": 2.076923076923077e-05,
      "loss": 0.0397,
      "step": 320
    },
    {
      "epoch": 6.2559241706161135,
      "grad_norm": 0.1899699568748474,
      "learning_rate": 2.048076923076923e-05,
      "loss": 0.0399,
      "step": 330
    },
    {
      "epoch": 6.4454976303317535,
      "grad_norm": 0.14849646389484406,
      "learning_rate": 2.0192307692307694e-05,
      "loss": 0.0394,
      "step": 340
    },
    {
      "epoch": 6.6350710900473935,
      "grad_norm": 0.1111103966832161,
      "learning_rate": 1.9903846153846154e-05,
      "loss": 0.0361,
      "step": 350
    },
    {
      "epoch": 6.8246445497630335,
      "grad_norm": 0.1525595635175705,
      "learning_rate": 1.9615384615384617e-05,
      "loss": 0.039,
      "step": 360
    },
    {
      "epoch": 7.014218009478673,
      "grad_norm": 0.2204810231924057,
      "learning_rate": 1.932692307692308e-05,
      "loss": 0.0374,
      "step": 370
    },
    {
      "epoch": 7.203791469194313,
      "grad_norm": 0.1169096827507019,
      "learning_rate": 1.903846153846154e-05,
      "loss": 0.0339,
      "step": 380
    },
    {
      "epoch": 7.393364928909953,
      "grad_norm": 0.09804651141166687,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.0359,
      "step": 390
    },
    {
      "epoch": 7.5829383886255926,
      "grad_norm": 0.14222651720046997,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 0.0321,
      "step": 400
    },
    {
      "epoch": 7.7725118483412325,
      "grad_norm": 0.0966310054063797,
      "learning_rate": 1.817307692307692e-05,
      "loss": 0.0327,
      "step": 410
    },
    {
      "epoch": 7.9620853080568725,
      "grad_norm": 0.11295436322689056,
      "learning_rate": 1.7884615384615384e-05,
      "loss": 0.0359,
      "step": 420
    },
    {
      "epoch": 8.151658767772512,
      "grad_norm": 0.09200425446033478,
      "learning_rate": 1.7596153846153846e-05,
      "loss": 0.0333,
      "step": 430
    },
    {
      "epoch": 8.341232227488153,
      "grad_norm": 0.08960484713315964,
      "learning_rate": 1.7307692307692306e-05,
      "loss": 0.03,
      "step": 440
    },
    {
      "epoch": 8.530805687203792,
      "grad_norm": 0.1008763536810875,
      "learning_rate": 1.701923076923077e-05,
      "loss": 0.0328,
      "step": 450
    },
    {
      "epoch": 8.72037914691943,
      "grad_norm": 0.18892982602119446,
      "learning_rate": 1.673076923076923e-05,
      "loss": 0.0316,
      "step": 460
    },
    {
      "epoch": 8.909952606635072,
      "grad_norm": 0.16451339423656464,
      "learning_rate": 1.6442307692307695e-05,
      "loss": 0.0301,
      "step": 470
    },
    {
      "epoch": 9.09952606635071,
      "grad_norm": 0.14853718876838684,
      "learning_rate": 1.6153846153846154e-05,
      "loss": 0.0302,
      "step": 480
    },
    {
      "epoch": 9.289099526066352,
      "grad_norm": 0.0903206467628479,
      "learning_rate": 1.5865384615384617e-05,
      "loss": 0.0314,
      "step": 490
    },
    {
      "epoch": 9.47867298578199,
      "grad_norm": 0.16619105637073517,
      "learning_rate": 1.557692307692308e-05,
      "loss": 0.0278,
      "step": 500
    },
    {
      "epoch": 9.66824644549763,
      "grad_norm": 0.11136868596076965,
      "learning_rate": 1.528846153846154e-05,
      "loss": 0.0303,
      "step": 510
    },
    {
      "epoch": 9.85781990521327,
      "grad_norm": 0.09969611465930939,
      "learning_rate": 1.5e-05,
      "loss": 0.0299,
      "step": 520
    },
    {
      "epoch": 10.04739336492891,
      "grad_norm": 0.09576759487390518,
      "learning_rate": 1.4711538461538462e-05,
      "loss": 0.0278,
      "step": 530
    },
    {
      "epoch": 10.23696682464455,
      "grad_norm": 0.1151731088757515,
      "learning_rate": 1.4423076923076924e-05,
      "loss": 0.0269,
      "step": 540
    },
    {
      "epoch": 10.42654028436019,
      "grad_norm": 0.2266397476196289,
      "learning_rate": 1.4134615384615384e-05,
      "loss": 0.0289,
      "step": 550
    },
    {
      "epoch": 10.616113744075829,
      "grad_norm": 0.12434451282024384,
      "learning_rate": 1.3846153846153847e-05,
      "loss": 0.0261,
      "step": 560
    },
    {
      "epoch": 10.80568720379147,
      "grad_norm": 0.1091102734208107,
      "learning_rate": 1.3557692307692308e-05,
      "loss": 0.028,
      "step": 570
    },
    {
      "epoch": 10.995260663507109,
      "grad_norm": 0.08422732353210449,
      "learning_rate": 1.3269230769230769e-05,
      "loss": 0.0256,
      "step": 580
    },
    {
      "epoch": 11.184834123222748,
      "grad_norm": 0.16355375945568085,
      "learning_rate": 1.2980769230769232e-05,
      "loss": 0.0269,
      "step": 590
    },
    {
      "epoch": 11.374407582938389,
      "grad_norm": 0.26286429166793823,
      "learning_rate": 1.2692307692307693e-05,
      "loss": 0.0239,
      "step": 600
    },
    {
      "epoch": 11.563981042654028,
      "grad_norm": 0.0981736034154892,
      "learning_rate": 1.2403846153846153e-05,
      "loss": 0.0291,
      "step": 610
    },
    {
      "epoch": 11.753554502369669,
      "grad_norm": 0.11100564897060394,
      "learning_rate": 1.2115384615384615e-05,
      "loss": 0.0251,
      "step": 620
    },
    {
      "epoch": 11.943127962085308,
      "grad_norm": 0.07715968787670135,
      "learning_rate": 1.1826923076923077e-05,
      "loss": 0.0266,
      "step": 630
    },
    {
      "epoch": 12.132701421800947,
      "grad_norm": 0.12548160552978516,
      "learning_rate": 1.153846153846154e-05,
      "loss": 0.0232,
      "step": 640
    },
    {
      "epoch": 12.322274881516588,
      "grad_norm": 0.11867664009332657,
      "learning_rate": 1.125e-05,
      "loss": 0.0239,
      "step": 650
    },
    {
      "epoch": 12.511848341232227,
      "grad_norm": 0.124052494764328,
      "learning_rate": 1.0961538461538462e-05,
      "loss": 0.0258,
      "step": 660
    },
    {
      "epoch": 12.701421800947868,
      "grad_norm": 0.45495718717575073,
      "learning_rate": 1.0673076923076923e-05,
      "loss": 0.0242,
      "step": 670
    },
    {
      "epoch": 12.890995260663507,
      "grad_norm": 0.0678386464715004,
      "learning_rate": 1.0384615384615384e-05,
      "loss": 0.0242,
      "step": 680
    },
    {
      "epoch": 13.080568720379146,
      "grad_norm": 0.06402502954006195,
      "learning_rate": 1.0096153846153847e-05,
      "loss": 0.0253,
      "step": 690
    },
    {
      "epoch": 13.270142180094787,
      "grad_norm": 0.10899492353200912,
      "learning_rate": 9.807692307692308e-06,
      "loss": 0.0234,
      "step": 700
    },
    {
      "epoch": 13.459715639810426,
      "grad_norm": 0.09529020637273788,
      "learning_rate": 9.51923076923077e-06,
      "loss": 0.0227,
      "step": 710
    },
    {
      "epoch": 13.649289099526067,
      "grad_norm": 0.10726472735404968,
      "learning_rate": 9.230769230769232e-06,
      "loss": 0.0226,
      "step": 720
    },
    {
      "epoch": 13.838862559241706,
      "grad_norm": 0.05985069274902344,
      "learning_rate": 8.942307692307692e-06,
      "loss": 0.0211,
      "step": 730
    },
    {
      "epoch": 14.028436018957345,
      "grad_norm": 0.12114176154136658,
      "learning_rate": 8.653846153846153e-06,
      "loss": 0.0245,
      "step": 740
    },
    {
      "epoch": 14.218009478672986,
      "grad_norm": 0.11160324513912201,
      "learning_rate": 8.365384615384616e-06,
      "loss": 0.0196,
      "step": 750
    },
    {
      "epoch": 14.407582938388625,
      "grad_norm": 0.087327741086483,
      "learning_rate": 8.076923076923077e-06,
      "loss": 0.0193,
      "step": 760
    },
    {
      "epoch": 14.597156398104266,
      "grad_norm": 0.06679825484752655,
      "learning_rate": 7.78846153846154e-06,
      "loss": 0.0206,
      "step": 770
    },
    {
      "epoch": 14.786729857819905,
      "grad_norm": 0.14305196702480316,
      "learning_rate": 7.5e-06,
      "loss": 0.0194,
      "step": 780
    },
    {
      "epoch": 14.976303317535544,
      "grad_norm": 0.11618325114250183,
      "learning_rate": 7.211538461538462e-06,
      "loss": 0.0257,
      "step": 790
    },
    {
      "epoch": 15.165876777251185,
      "grad_norm": 0.06295182555913925,
      "learning_rate": 6.923076923076923e-06,
      "loss": 0.0184,
      "step": 800
    },
    {
      "epoch": 15.355450236966824,
      "grad_norm": 0.08175351470708847,
      "learning_rate": 6.6346153846153846e-06,
      "loss": 0.0209,
      "step": 810
    },
    {
      "epoch": 15.545023696682465,
      "grad_norm": 0.11890088021755219,
      "learning_rate": 6.3461538461538466e-06,
      "loss": 0.0215,
      "step": 820
    },
    {
      "epoch": 15.734597156398104,
      "grad_norm": 0.17722468078136444,
      "learning_rate": 6.057692307692308e-06,
      "loss": 0.0203,
      "step": 830
    },
    {
      "epoch": 15.924170616113743,
      "grad_norm": 0.11907941102981567,
      "learning_rate": 5.76923076923077e-06,
      "loss": 0.021,
      "step": 840
    },
    {
      "epoch": 16.113744075829384,
      "grad_norm": 0.1066436693072319,
      "learning_rate": 5.480769230769231e-06,
      "loss": 0.0218,
      "step": 850
    },
    {
      "epoch": 16.303317535545023,
      "grad_norm": 0.053932033479213715,
      "learning_rate": 5.192307692307692e-06,
      "loss": 0.0184,
      "step": 860
    },
    {
      "epoch": 16.492890995260662,
      "grad_norm": 0.09704640507698059,
      "learning_rate": 4.903846153846154e-06,
      "loss": 0.0191,
      "step": 870
    },
    {
      "epoch": 16.682464454976305,
      "grad_norm": 0.10457386821508408,
      "learning_rate": 4.615384615384616e-06,
      "loss": 0.0197,
      "step": 880
    },
    {
      "epoch": 16.872037914691944,
      "grad_norm": 0.08160708844661713,
      "learning_rate": 4.3269230769230765e-06,
      "loss": 0.0204,
      "step": 890
    },
    {
      "epoch": 17.061611374407583,
      "grad_norm": 0.1239229142665863,
      "learning_rate": 4.0384615384615385e-06,
      "loss": 0.0208,
      "step": 900
    },
    {
      "epoch": 17.251184834123222,
      "grad_norm": 0.0887596532702446,
      "learning_rate": 3.75e-06,
      "loss": 0.017,
      "step": 910
    },
    {
      "epoch": 17.44075829383886,
      "grad_norm": 0.09922682493925095,
      "learning_rate": 3.4615384615384617e-06,
      "loss": 0.0223,
      "step": 920
    },
    {
      "epoch": 17.6303317535545,
      "grad_norm": 0.0974949300289154,
      "learning_rate": 3.1730769230769233e-06,
      "loss": 0.0191,
      "step": 930
    },
    {
      "epoch": 17.819905213270143,
      "grad_norm": 0.10244361311197281,
      "learning_rate": 2.884615384615385e-06,
      "loss": 0.0198,
      "step": 940
    },
    {
      "epoch": 18.009478672985782,
      "grad_norm": 0.06859322637319565,
      "learning_rate": 2.596153846153846e-06,
      "loss": 0.0188,
      "step": 950
    },
    {
      "epoch": 18.19905213270142,
      "grad_norm": 0.09902096539735794,
      "learning_rate": 2.307692307692308e-06,
      "loss": 0.0196,
      "step": 960
    },
    {
      "epoch": 18.38862559241706,
      "grad_norm": 0.058132074773311615,
      "learning_rate": 2.0192307692307692e-06,
      "loss": 0.0174,
      "step": 970
    },
    {
      "epoch": 18.578199052132703,
      "grad_norm": 0.11522402614355087,
      "learning_rate": 1.7307692307692308e-06,
      "loss": 0.0186,
      "step": 980
    },
    {
      "epoch": 18.767772511848342,
      "grad_norm": 0.07329108566045761,
      "learning_rate": 1.4423076923076924e-06,
      "loss": 0.0203,
      "step": 990
    },
    {
      "epoch": 18.95734597156398,
      "grad_norm": 0.08888276666402817,
      "learning_rate": 1.153846153846154e-06,
      "loss": 0.0182,
      "step": 1000
    },
    {
      "epoch": 19.14691943127962,
      "grad_norm": 0.16812676191329956,
      "learning_rate": 8.653846153846154e-07,
      "loss": 0.0201,
      "step": 1010
    },
    {
      "epoch": 19.33649289099526,
      "grad_norm": 0.051739402115345,
      "learning_rate": 5.76923076923077e-07,
      "loss": 0.0175,
      "step": 1020
    },
    {
      "epoch": 19.5260663507109,
      "grad_norm": 0.15502548217773438,
      "learning_rate": 2.884615384615385e-07,
      "loss": 0.0211,
      "step": 1030
    },
    {
      "epoch": 19.71563981042654,
      "grad_norm": 0.10121985524892807,
      "learning_rate": 0.0,
      "loss": 0.0202,
      "step": 1040
    }
  ],
  "logging_steps": 10,
  "max_steps": 1040,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.39069062991872e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}