{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008,
      "grad_norm": 27.330623626708984,
      "learning_rate": 1e-05,
      "loss": 14.9828,
      "mean_token_accuracy": 0.43762992322444916,
      "step": 1
    },
    {
      "epoch": 0.016,
      "grad_norm": 25.78533935546875,
      "learning_rate": 2e-05,
      "loss": 14.48,
      "mean_token_accuracy": 0.45947156846523285,
      "step": 2
    },
    {
      "epoch": 0.024,
      "grad_norm": 23.762821197509766,
      "learning_rate": 3e-05,
      "loss": 14.3424,
      "mean_token_accuracy": 0.4559449180960655,
      "step": 3
    },
    {
      "epoch": 0.032,
      "grad_norm": 21.071897506713867,
      "learning_rate": 4e-05,
      "loss": 13.9143,
      "mean_token_accuracy": 0.46790433675050735,
      "step": 4
    },
    {
      "epoch": 0.04,
      "grad_norm": 19.133302688598633,
      "learning_rate": 5e-05,
      "loss": 12.2497,
      "mean_token_accuracy": 0.5162213444709778,
      "step": 5
    },
    {
      "epoch": 0.048,
      "grad_norm": 17.784639358520508,
      "learning_rate": 4.9473684210526315e-05,
      "loss": 11.9364,
      "mean_token_accuracy": 0.5214760452508926,
      "step": 6
    },
    {
      "epoch": 0.056,
      "grad_norm": 18.64559555053711,
      "learning_rate": 4.8947368421052635e-05,
      "loss": 10.9395,
      "mean_token_accuracy": 0.5401209890842438,
      "step": 7
    },
    {
      "epoch": 0.064,
      "grad_norm": 17.828125,
      "learning_rate": 4.842105263157895e-05,
      "loss": 10.1876,
      "mean_token_accuracy": 0.5798913389444351,
      "step": 8
    },
    {
      "epoch": 0.072,
      "grad_norm": 18.621353149414062,
      "learning_rate": 4.789473684210526e-05,
      "loss": 9.51,
      "mean_token_accuracy": 0.6059905588626862,
      "step": 9
    },
    {
      "epoch": 0.08,
      "grad_norm": 14.266256332397461,
      "learning_rate": 4.736842105263158e-05,
      "loss": 9.324,
      "mean_token_accuracy": 0.623360276222229,
      "step": 10
    },
    {
      "epoch": 0.088,
      "grad_norm": 13.611992835998535,
      "learning_rate": 4.68421052631579e-05,
      "loss": 8.9613,
      "mean_token_accuracy": 0.6348667591810226,
      "step": 11
    },
    {
      "epoch": 0.096,
      "grad_norm": 13.141629219055176,
      "learning_rate": 4.6315789473684214e-05,
      "loss": 8.1299,
      "mean_token_accuracy": 0.6677338033914566,
      "step": 12
    },
    {
      "epoch": 0.104,
      "grad_norm": 11.582746505737305,
      "learning_rate": 4.5789473684210527e-05,
      "loss": 8.1148,
      "mean_token_accuracy": 0.663286492228508,
      "step": 13
    },
    {
      "epoch": 0.112,
      "grad_norm": 10.934531211853027,
      "learning_rate": 4.5263157894736846e-05,
      "loss": 7.5403,
      "mean_token_accuracy": 0.673496663570404,
      "step": 14
    },
    {
      "epoch": 0.12,
      "grad_norm": 9.977241516113281,
      "learning_rate": 4.473684210526316e-05,
      "loss": 7.2111,
      "mean_token_accuracy": 0.688684269785881,
      "step": 15
    },
    {
      "epoch": 0.128,
      "grad_norm": 10.482184410095215,
      "learning_rate": 4.421052631578947e-05,
      "loss": 7.5258,
      "mean_token_accuracy": 0.671795666217804,
      "step": 16
    },
    {
      "epoch": 0.136,
      "grad_norm": 10.160177230834961,
      "learning_rate": 4.368421052631579e-05,
      "loss": 7.1163,
      "mean_token_accuracy": 0.6790599226951599,
      "step": 17
    },
    {
      "epoch": 0.144,
      "grad_norm": 10.689698219299316,
      "learning_rate": 4.3157894736842105e-05,
      "loss": 7.1231,
      "mean_token_accuracy": 0.6911827921867371,
      "step": 18
    },
    {
      "epoch": 0.152,
      "grad_norm": 9.446402549743652,
      "learning_rate": 4.2631578947368425e-05,
      "loss": 7.3457,
      "mean_token_accuracy": 0.689079686999321,
      "step": 19
    },
    {
      "epoch": 0.16,
      "grad_norm": 10.626145362854004,
      "learning_rate": 4.210526315789474e-05,
      "loss": 6.9955,
      "mean_token_accuracy": 0.6898764669895172,
      "step": 20
    },
    {
      "epoch": 0.168,
      "grad_norm": 10.320823669433594,
      "learning_rate": 4.157894736842106e-05,
      "loss": 6.9504,
      "mean_token_accuracy": 0.6948718279600143,
      "step": 21
    },
    {
      "epoch": 0.176,
      "grad_norm": 10.236137390136719,
      "learning_rate": 4.105263157894737e-05,
      "loss": 6.2089,
      "mean_token_accuracy": 0.7240265011787415,
      "step": 22
    },
    {
      "epoch": 0.184,
      "grad_norm": 9.453045845031738,
      "learning_rate": 4.0526315789473684e-05,
      "loss": 6.7502,
      "mean_token_accuracy": 0.7005183100700378,
      "step": 23
    },
    {
      "epoch": 0.192,
      "grad_norm": 9.327564239501953,
      "learning_rate": 4e-05,
      "loss": 6.4527,
      "mean_token_accuracy": 0.7164693623781204,
      "step": 24
    },
    {
      "epoch": 0.2,
      "grad_norm": 9.546314239501953,
      "learning_rate": 3.9473684210526316e-05,
      "loss": 5.8974,
      "mean_token_accuracy": 0.7328019142150879,
      "step": 25
    },
    {
      "epoch": 0.208,
      "grad_norm": 8.894572257995605,
      "learning_rate": 3.894736842105263e-05,
      "loss": 6.109,
      "mean_token_accuracy": 0.7263201028108597,
      "step": 26
    },
    {
      "epoch": 0.216,
      "grad_norm": 9.127656936645508,
      "learning_rate": 3.842105263157895e-05,
      "loss": 6.4875,
      "mean_token_accuracy": 0.7085271328687668,
      "step": 27
    },
    {
      "epoch": 0.224,
      "grad_norm": 9.237127304077148,
      "learning_rate": 3.789473684210527e-05,
      "loss": 6.159,
      "mean_token_accuracy": 0.7449014335870743,
      "step": 28
    },
    {
      "epoch": 0.232,
      "grad_norm": 9.572649002075195,
      "learning_rate": 3.736842105263158e-05,
      "loss": 6.247,
      "mean_token_accuracy": 0.739266037940979,
      "step": 29
    },
    {
      "epoch": 0.24,
      "grad_norm": 9.581724166870117,
      "learning_rate": 3.6842105263157895e-05,
      "loss": 6.4162,
      "mean_token_accuracy": 0.7320354580879211,
      "step": 30
    },
    {
      "epoch": 0.248,
      "grad_norm": 9.571109771728516,
      "learning_rate": 3.6315789473684214e-05,
      "loss": 6.3865,
      "mean_token_accuracy": 0.7435038238763809,
      "step": 31
    },
    {
      "epoch": 0.256,
      "grad_norm": 9.66092300415039,
      "learning_rate": 3.578947368421053e-05,
      "loss": 5.8215,
      "mean_token_accuracy": 0.7524790912866592,
      "step": 32
    },
    {
      "epoch": 0.264,
      "grad_norm": 8.532500267028809,
      "learning_rate": 3.526315789473684e-05,
      "loss": 5.8042,
      "mean_token_accuracy": 0.7616962492465973,
      "step": 33
    },
    {
      "epoch": 0.272,
      "grad_norm": 8.403843879699707,
      "learning_rate": 3.473684210526316e-05,
      "loss": 5.9317,
      "mean_token_accuracy": 0.7603590935468674,
      "step": 34
    },
    {
      "epoch": 0.28,
      "grad_norm": 8.805196762084961,
      "learning_rate": 3.421052631578947e-05,
      "loss": 6.1436,
      "mean_token_accuracy": 0.7516646534204483,
      "step": 35
    },
    {
      "epoch": 0.288,
      "grad_norm": 8.515336036682129,
      "learning_rate": 3.368421052631579e-05,
      "loss": 6.0511,
      "mean_token_accuracy": 0.7515160739421844,
      "step": 36
    },
    {
      "epoch": 0.296,
      "grad_norm": 7.560244560241699,
      "learning_rate": 3.3157894736842106e-05,
      "loss": 5.4362,
      "mean_token_accuracy": 0.772291824221611,
      "step": 37
    },
    {
      "epoch": 0.304,
      "grad_norm": 8.334061622619629,
      "learning_rate": 3.2631578947368426e-05,
      "loss": 5.5668,
      "mean_token_accuracy": 0.7626153230667114,
      "step": 38
    },
    {
      "epoch": 0.312,
      "grad_norm": 8.146302223205566,
      "learning_rate": 3.210526315789474e-05,
      "loss": 6.1313,
      "mean_token_accuracy": 0.7336651831865311,
      "step": 39
    },
    {
      "epoch": 0.32,
      "grad_norm": 7.829502582550049,
      "learning_rate": 3.157894736842105e-05,
      "loss": 6.0167,
      "mean_token_accuracy": 0.7388159483671188,
      "step": 40
    },
    {
      "epoch": 0.328,
      "grad_norm": 8.113974571228027,
      "learning_rate": 3.105263157894737e-05,
      "loss": 5.2954,
      "mean_token_accuracy": 0.776334211230278,
      "step": 41
    },
    {
      "epoch": 0.336,
      "grad_norm": 7.286009311676025,
      "learning_rate": 3.0526315789473684e-05,
      "loss": 5.6481,
      "mean_token_accuracy": 0.7564087808132172,
      "step": 42
    },
    {
      "epoch": 0.344,
      "grad_norm": 7.154447555541992,
      "learning_rate": 3e-05,
      "loss": 5.3633,
      "mean_token_accuracy": 0.7598460763692856,
      "step": 43
    },
    {
      "epoch": 0.352,
      "grad_norm": 8.190098762512207,
      "learning_rate": 2.9473684210526314e-05,
      "loss": 5.3728,
      "mean_token_accuracy": 0.7727002501487732,
      "step": 44
    },
    {
      "epoch": 0.36,
      "grad_norm": 7.3226542472839355,
      "learning_rate": 2.8947368421052634e-05,
      "loss": 5.4446,
      "mean_token_accuracy": 0.7465341240167618,
      "step": 45
    },
    {
      "epoch": 0.368,
      "grad_norm": 8.403494834899902,
      "learning_rate": 2.842105263157895e-05,
      "loss": 4.6045,
      "mean_token_accuracy": 0.7857130914926529,
      "step": 46
    },
    {
      "epoch": 0.376,
      "grad_norm": 8.063408851623535,
      "learning_rate": 2.7894736842105263e-05,
      "loss": 5.2821,
      "mean_token_accuracy": 0.762213259935379,
      "step": 47
    },
    {
      "epoch": 0.384,
      "grad_norm": 7.193646430969238,
      "learning_rate": 2.7368421052631583e-05,
      "loss": 5.7485,
      "mean_token_accuracy": 0.7417114228010178,
      "step": 48
    },
    {
      "epoch": 0.392,
      "grad_norm": 7.28355073928833,
      "learning_rate": 2.6842105263157896e-05,
      "loss": 5.5915,
      "mean_token_accuracy": 0.7473081052303314,
      "step": 49
    },
    {
      "epoch": 0.4,
      "grad_norm": 7.384160995483398,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 6.1476,
      "mean_token_accuracy": 0.7356720864772797,
      "step": 50
    },
    {
      "epoch": 0.408,
      "grad_norm": 7.840450763702393,
      "learning_rate": 2.578947368421053e-05,
      "loss": 5.2035,
      "mean_token_accuracy": 0.7573880255222321,
      "step": 51
    },
    {
      "epoch": 0.416,
      "grad_norm": 7.19984245300293,
      "learning_rate": 2.5263157894736845e-05,
      "loss": 4.6355,
      "mean_token_accuracy": 0.7865147292613983,
      "step": 52
    },
    {
      "epoch": 0.424,
      "grad_norm": 7.227206707000732,
      "learning_rate": 2.4736842105263158e-05,
      "loss": 5.7802,
      "mean_token_accuracy": 0.7442787438631058,
      "step": 53
    },
    {
      "epoch": 0.432,
      "grad_norm": 7.431645393371582,
      "learning_rate": 2.4210526315789474e-05,
      "loss": 5.5745,
      "mean_token_accuracy": 0.7558661848306656,
      "step": 54
    },
    {
      "epoch": 0.44,
      "grad_norm": 9.079876899719238,
      "learning_rate": 2.368421052631579e-05,
      "loss": 5.6616,
      "mean_token_accuracy": 0.7577391117811203,
      "step": 55
    },
    {
      "epoch": 0.448,
      "grad_norm": 7.336010456085205,
      "learning_rate": 2.3157894736842107e-05,
      "loss": 4.7,
      "mean_token_accuracy": 0.7845469415187836,
      "step": 56
    },
    {
      "epoch": 0.456,
      "grad_norm": 6.669713020324707,
      "learning_rate": 2.2631578947368423e-05,
      "loss": 5.5094,
      "mean_token_accuracy": 0.7579665780067444,
      "step": 57
    },
    {
      "epoch": 0.464,
      "grad_norm": 7.331737995147705,
      "learning_rate": 2.2105263157894736e-05,
      "loss": 4.6607,
      "mean_token_accuracy": 0.7783682346343994,
      "step": 58
    },
    {
      "epoch": 0.472,
      "grad_norm": 6.724721431732178,
      "learning_rate": 2.1578947368421053e-05,
      "loss": 5.0542,
      "mean_token_accuracy": 0.7743726819753647,
      "step": 59
    },
    {
      "epoch": 0.48,
      "grad_norm": 6.390171527862549,
      "learning_rate": 2.105263157894737e-05,
      "loss": 5.0009,
      "mean_token_accuracy": 0.780523419380188,
      "step": 60
    },
    {
      "epoch": 0.488,
      "grad_norm": 7.519730567932129,
      "learning_rate": 2.0526315789473685e-05,
      "loss": 5.4899,
      "mean_token_accuracy": 0.7700912803411484,
      "step": 61
    },
    {
      "epoch": 0.496,
      "grad_norm": 6.765895366668701,
      "learning_rate": 2e-05,
      "loss": 4.8741,
      "mean_token_accuracy": 0.7866266071796417,
      "step": 62
    },
    {
      "epoch": 0.504,
      "grad_norm": 6.651461601257324,
      "learning_rate": 1.9473684210526315e-05,
      "loss": 5.1589,
      "mean_token_accuracy": 0.769757404923439,
      "step": 63
    },
    {
      "epoch": 0.512,
      "grad_norm": 6.601439952850342,
      "learning_rate": 1.8947368421052634e-05,
      "loss": 5.1586,
      "mean_token_accuracy": 0.7651441991329193,
      "step": 64
    },
    {
      "epoch": 0.52,
      "grad_norm": 7.300909042358398,
      "learning_rate": 1.8421052631578947e-05,
      "loss": 5.1605,
      "mean_token_accuracy": 0.7735024839639664,
      "step": 65
    },
    {
      "epoch": 0.528,
      "grad_norm": 6.311753749847412,
      "learning_rate": 1.7894736842105264e-05,
      "loss": 5.0041,
      "mean_token_accuracy": 0.7669179141521454,
      "step": 66
    },
    {
      "epoch": 0.536,
      "grad_norm": 7.332730293273926,
      "learning_rate": 1.736842105263158e-05,
      "loss": 5.2616,
      "mean_token_accuracy": 0.7765114605426788,
      "step": 67
    },
    {
      "epoch": 0.544,
      "grad_norm": 6.422898292541504,
      "learning_rate": 1.6842105263157896e-05,
      "loss": 6.1462,
      "mean_token_accuracy": 0.728233814239502,
      "step": 68
    },
    {
      "epoch": 0.552,
      "grad_norm": 6.685412883758545,
      "learning_rate": 1.6315789473684213e-05,
      "loss": 5.7309,
      "mean_token_accuracy": 0.7524611800909042,
      "step": 69
    },
    {
      "epoch": 0.56,
      "grad_norm": 7.049284934997559,
      "learning_rate": 1.5789473684210526e-05,
      "loss": 5.0148,
      "mean_token_accuracy": 0.77178093791008,
      "step": 70
    },
    {
      "epoch": 0.568,
      "grad_norm": 7.036037445068359,
      "learning_rate": 1.5263157894736842e-05,
      "loss": 5.0748,
      "mean_token_accuracy": 0.7729067206382751,
      "step": 71
    },
    {
      "epoch": 0.576,
      "grad_norm": 7.007073402404785,
      "learning_rate": 1.4736842105263157e-05,
      "loss": 4.5864,
      "mean_token_accuracy": 0.7893485873937607,
      "step": 72
    },
    {
      "epoch": 0.584,
      "grad_norm": 6.996627330780029,
      "learning_rate": 1.4210526315789475e-05,
      "loss": 5.8196,
      "mean_token_accuracy": 0.7412619888782501,
      "step": 73
    },
    {
      "epoch": 0.592,
      "grad_norm": 6.522240161895752,
      "learning_rate": 1.3684210526315791e-05,
      "loss": 4.3882,
      "mean_token_accuracy": 0.8006375879049301,
      "step": 74
    },
    {
      "epoch": 0.6,
      "grad_norm": 7.209001541137695,
      "learning_rate": 1.3157894736842106e-05,
      "loss": 4.9107,
      "mean_token_accuracy": 0.7705955505371094,
      "step": 75
    },
    {
      "epoch": 0.608,
      "grad_norm": 6.461360454559326,
      "learning_rate": 1.2631578947368422e-05,
      "loss": 4.9865,
      "mean_token_accuracy": 0.7676331996917725,
      "step": 76
    },
    {
      "epoch": 0.616,
      "grad_norm": 6.816041469573975,
      "learning_rate": 1.2105263157894737e-05,
      "loss": 4.7486,
      "mean_token_accuracy": 0.8014501333236694,
      "step": 77
    },
    {
      "epoch": 0.624,
      "grad_norm": 6.4101433753967285,
      "learning_rate": 1.1578947368421053e-05,
      "loss": 4.7705,
      "mean_token_accuracy": 0.7754499018192291,
      "step": 78
    },
    {
      "epoch": 0.632,
      "grad_norm": 6.9798970222473145,
      "learning_rate": 1.1052631578947368e-05,
      "loss": 4.9164,
      "mean_token_accuracy": 0.7753257304430008,
      "step": 79
    },
    {
      "epoch": 0.64,
      "grad_norm": 6.403416633605957,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 4.7818,
      "mean_token_accuracy": 0.7874085158109665,
      "step": 80
    },
    {
      "epoch": 0.648,
      "grad_norm": 6.675773620605469,
      "learning_rate": 1e-05,
      "loss": 4.5508,
      "mean_token_accuracy": 0.795722022652626,
      "step": 81
    },
    {
      "epoch": 0.656,
      "grad_norm": 6.712479591369629,
      "learning_rate": 9.473684210526317e-06,
      "loss": 4.9168,
      "mean_token_accuracy": 0.7771104872226715,
      "step": 82
    },
    {
      "epoch": 0.664,
      "grad_norm": 5.9163665771484375,
      "learning_rate": 8.947368421052632e-06,
      "loss": 4.891,
      "mean_token_accuracy": 0.7830108255147934,
      "step": 83
    },
    {
      "epoch": 0.672,
      "grad_norm": 7.163206100463867,
      "learning_rate": 8.421052631578948e-06,
      "loss": 5.149,
      "mean_token_accuracy": 0.7670323401689529,
      "step": 84
    },
    {
      "epoch": 0.68,
      "grad_norm": 6.317421913146973,
      "learning_rate": 7.894736842105263e-06,
      "loss": 4.8002,
      "mean_token_accuracy": 0.7903847545385361,
      "step": 85
    },
    {
      "epoch": 0.688,
      "grad_norm": 6.364376544952393,
      "learning_rate": 7.3684210526315784e-06,
      "loss": 4.7666,
      "mean_token_accuracy": 0.7809462994337082,
      "step": 86
    },
    {
      "epoch": 0.696,
      "grad_norm": 6.32914924621582,
      "learning_rate": 6.842105263157896e-06,
      "loss": 5.2743,
      "mean_token_accuracy": 0.7658153772354126,
      "step": 87
    },
    {
      "epoch": 0.704,
      "grad_norm": 6.604763984680176,
      "learning_rate": 6.315789473684211e-06,
      "loss": 5.2035,
      "mean_token_accuracy": 0.776008740067482,
      "step": 88
    },
    {
      "epoch": 0.712,
      "grad_norm": 6.310863494873047,
      "learning_rate": 5.789473684210527e-06,
      "loss": 5.5161,
      "mean_token_accuracy": 0.7567505836486816,
      "step": 89
    },
    {
      "epoch": 0.72,
      "grad_norm": 6.1613945960998535,
      "learning_rate": 5.263157894736842e-06,
      "loss": 5.0648,
      "mean_token_accuracy": 0.7786727696657181,
      "step": 90
    },
    {
      "epoch": 0.728,
      "grad_norm": 6.521576404571533,
      "learning_rate": 4.736842105263159e-06,
      "loss": 4.433,
      "mean_token_accuracy": 0.7890913188457489,
      "step": 91
    },
    {
      "epoch": 0.736,
      "grad_norm": 6.6246466636657715,
      "learning_rate": 4.210526315789474e-06,
      "loss": 4.6914,
      "mean_token_accuracy": 0.7863939553499222,
      "step": 92
    },
    {
      "epoch": 0.744,
      "grad_norm": 7.000185489654541,
      "learning_rate": 3.6842105263157892e-06,
      "loss": 5.0143,
      "mean_token_accuracy": 0.7784310281276703,
      "step": 93
    },
    {
      "epoch": 0.752,
      "grad_norm": 6.975312232971191,
      "learning_rate": 3.1578947368421056e-06,
      "loss": 4.7931,
      "mean_token_accuracy": 0.7743921875953674,
      "step": 94
    },
    {
      "epoch": 0.76,
      "grad_norm": 6.039007663726807,
      "learning_rate": 2.631578947368421e-06,
      "loss": 4.7647,
      "mean_token_accuracy": 0.780229240655899,
      "step": 95
    },
    {
      "epoch": 0.768,
      "grad_norm": 6.673982620239258,
      "learning_rate": 2.105263157894737e-06,
      "loss": 4.7419,
      "mean_token_accuracy": 0.7849721014499664,
      "step": 96
    },
    {
      "epoch": 0.776,
      "grad_norm": 6.379744529724121,
      "learning_rate": 1.5789473684210528e-06,
      "loss": 4.7868,
      "mean_token_accuracy": 0.7784082293510437,
      "step": 97
    },
    {
      "epoch": 0.784,
      "grad_norm": 6.387270450592041,
      "learning_rate": 1.0526315789473685e-06,
      "loss": 4.6571,
      "mean_token_accuracy": 0.7906839102506638,
      "step": 98
    },
    {
      "epoch": 0.792,
      "grad_norm": 6.2963056564331055,
      "learning_rate": 5.263157894736843e-07,
      "loss": 5.1662,
      "mean_token_accuracy": 0.7627293914556503,
      "step": 99
    },
    {
      "epoch": 0.8,
      "grad_norm": 7.28849983215332,
      "learning_rate": 0.0,
      "loss": 5.0461,
      "mean_token_accuracy": 0.7743319720029831,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 522011226931200.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}