{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.594059405940594,
  "eval_steps": 42,
  "global_step": 210,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002828854314002829,
      "eval_loss": 11.916790962219238,
      "eval_runtime": 6.6784,
      "eval_samples_per_second": 89.243,
      "eval_steps_per_second": 11.23,
      "step": 1
    },
    {
      "epoch": 0.008486562942008486,
      "grad_norm": 0.5188692212104797,
      "learning_rate": 3e-05,
      "loss": 11.92,
      "step": 3
    },
    {
      "epoch": 0.016973125884016973,
      "grad_norm": 0.48136115074157715,
      "learning_rate": 6e-05,
      "loss": 11.9198,
      "step": 6
    },
    {
      "epoch": 0.02545968882602546,
      "grad_norm": 0.5018041729927063,
      "learning_rate": 9e-05,
      "loss": 11.9077,
      "step": 9
    },
    {
      "epoch": 0.033946251768033946,
      "grad_norm": 0.6158789992332458,
      "learning_rate": 9.999588943391597e-05,
      "loss": 11.9074,
      "step": 12
    },
    {
      "epoch": 0.042432814710042434,
      "grad_norm": 0.6823853850364685,
      "learning_rate": 9.99743108100344e-05,
      "loss": 11.9042,
      "step": 15
    },
    {
      "epoch": 0.05091937765205092,
      "grad_norm": 0.8695465922355652,
      "learning_rate": 9.993424445916923e-05,
      "loss": 11.8991,
      "step": 18
    },
    {
      "epoch": 0.0594059405940594,
      "grad_norm": 0.9028195142745972,
      "learning_rate": 9.987570520365104e-05,
      "loss": 11.8853,
      "step": 21
    },
    {
      "epoch": 0.06789250353606789,
      "grad_norm": 0.9360626935958862,
      "learning_rate": 9.979871469976196e-05,
      "loss": 11.8781,
      "step": 24
    },
    {
      "epoch": 0.07637906647807638,
      "grad_norm": 0.8196120858192444,
      "learning_rate": 9.970330142972401e-05,
      "loss": 11.8677,
      "step": 27
    },
    {
      "epoch": 0.08486562942008487,
      "grad_norm": 0.7162870168685913,
      "learning_rate": 9.95895006911623e-05,
      "loss": 11.8614,
      "step": 30
    },
    {
      "epoch": 0.09335219236209336,
      "grad_norm": 0.5132609605789185,
      "learning_rate": 9.945735458404681e-05,
      "loss": 11.8498,
      "step": 33
    },
    {
      "epoch": 0.10183875530410184,
      "grad_norm": 0.4584226608276367,
      "learning_rate": 9.930691199511775e-05,
      "loss": 11.8467,
      "step": 36
    },
    {
      "epoch": 0.11032531824611033,
      "grad_norm": 0.29786884784698486,
      "learning_rate": 9.91382285798002e-05,
      "loss": 11.8511,
      "step": 39
    },
    {
      "epoch": 0.1188118811881188,
      "grad_norm": 0.2889010012149811,
      "learning_rate": 9.895136674161465e-05,
      "loss": 11.8408,
      "step": 42
    },
    {
      "epoch": 0.1188118811881188,
      "eval_loss": 11.839421272277832,
      "eval_runtime": 6.332,
      "eval_samples_per_second": 94.125,
      "eval_steps_per_second": 11.845,
      "step": 42
    },
    {
      "epoch": 0.1272984441301273,
      "grad_norm": 0.20692946016788483,
      "learning_rate": 9.874639560909117e-05,
      "loss": 11.8396,
      "step": 45
    },
    {
      "epoch": 0.13578500707213578,
      "grad_norm": 0.23685254156589508,
      "learning_rate": 9.852339101019574e-05,
      "loss": 11.8316,
      "step": 48
    },
    {
      "epoch": 0.14427157001414428,
      "grad_norm": 0.2432631552219391,
      "learning_rate": 9.828243544427796e-05,
      "loss": 11.8341,
      "step": 51
    },
    {
      "epoch": 0.15275813295615276,
      "grad_norm": 0.11745542287826538,
      "learning_rate": 9.802361805155097e-05,
      "loss": 11.8301,
      "step": 54
    },
    {
      "epoch": 0.16124469589816123,
      "grad_norm": 0.134097158908844,
      "learning_rate": 9.774703458011453e-05,
      "loss": 11.8359,
      "step": 57
    },
    {
      "epoch": 0.16973125884016974,
      "grad_norm": 0.19680051505565643,
      "learning_rate": 9.745278735053343e-05,
      "loss": 11.8378,
      "step": 60
    },
    {
      "epoch": 0.1782178217821782,
      "grad_norm": 0.10566498339176178,
      "learning_rate": 9.714098521798465e-05,
      "loss": 11.832,
      "step": 63
    },
    {
      "epoch": 0.1867043847241867,
      "grad_norm": 0.1530551165342331,
      "learning_rate": 9.681174353198687e-05,
      "loss": 11.8363,
      "step": 66
    },
    {
      "epoch": 0.19519094766619519,
      "grad_norm": 0.1929464042186737,
      "learning_rate": 9.64651840937276e-05,
      "loss": 11.8284,
      "step": 69
    },
    {
      "epoch": 0.2036775106082037,
      "grad_norm": 0.17411480844020844,
      "learning_rate": 9.610143511100354e-05,
      "loss": 11.8314,
      "step": 72
    },
    {
      "epoch": 0.21216407355021216,
      "grad_norm": 0.14971987903118134,
      "learning_rate": 9.572063115079063e-05,
      "loss": 11.832,
      "step": 75
    },
    {
      "epoch": 0.22065063649222066,
      "grad_norm": 0.18370923399925232,
      "learning_rate": 9.53229130894619e-05,
      "loss": 11.8275,
      "step": 78
    },
    {
      "epoch": 0.22913719943422914,
      "grad_norm": 0.26103201508522034,
      "learning_rate": 9.490842806067095e-05,
      "loss": 11.8278,
      "step": 81
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 0.21483545005321503,
      "learning_rate": 9.44773294009206e-05,
      "loss": 11.825,
      "step": 84
    },
    {
      "epoch": 0.2376237623762376,
      "eval_loss": 11.825268745422363,
      "eval_runtime": 6.402,
      "eval_samples_per_second": 93.097,
      "eval_steps_per_second": 11.715,
      "step": 84
    },
    {
      "epoch": 0.24611032531824611,
      "grad_norm": 0.28861185908317566,
      "learning_rate": 9.40297765928369e-05,
      "loss": 11.8219,
      "step": 87
    },
    {
      "epoch": 0.2545968882602546,
      "grad_norm": 0.13039568066596985,
      "learning_rate": 9.356593520616948e-05,
      "loss": 11.8245,
      "step": 90
    },
    {
      "epoch": 0.26308345120226306,
      "grad_norm": 0.1711033284664154,
      "learning_rate": 9.308597683653975e-05,
      "loss": 11.8246,
      "step": 93
    },
    {
      "epoch": 0.27157001414427157,
      "grad_norm": 0.2108013778924942,
      "learning_rate": 9.259007904196023e-05,
      "loss": 11.8228,
      "step": 96
    },
    {
      "epoch": 0.28005657708628007,
      "grad_norm": 0.1204076036810875,
      "learning_rate": 9.207842527714767e-05,
      "loss": 11.82,
      "step": 99
    },
    {
      "epoch": 0.28854314002828857,
      "grad_norm": 0.1477670669555664,
      "learning_rate": 9.155120482565521e-05,
      "loss": 11.8189,
      "step": 102
    },
    {
      "epoch": 0.297029702970297,
      "grad_norm": 0.10705884546041489,
      "learning_rate": 9.10086127298478e-05,
      "loss": 11.8169,
      "step": 105
    },
    {
      "epoch": 0.3055162659123055,
      "grad_norm": 0.29956066608428955,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.8205,
      "step": 108
    },
    {
      "epoch": 0.314002828854314,
      "grad_norm": 0.13027921319007874,
      "learning_rate": 8.987812213377424e-05,
      "loss": 11.8168,
      "step": 111
    },
    {
      "epoch": 0.32248939179632247,
      "grad_norm": 0.13590934872627258,
      "learning_rate": 8.929064185241213e-05,
      "loss": 11.819,
      "step": 114
    },
    {
      "epoch": 0.33097595473833097,
      "grad_norm": 0.09333682060241699,
      "learning_rate": 8.868862620982534e-05,
      "loss": 11.8267,
      "step": 117
    },
    {
      "epoch": 0.33946251768033947,
      "grad_norm": 0.12400602549314499,
      "learning_rate": 8.807229791845673e-05,
      "loss": 11.818,
      "step": 120
    },
    {
      "epoch": 0.347949080622348,
      "grad_norm": 0.12071343511343002,
      "learning_rate": 8.744188498563641e-05,
      "loss": 11.8166,
      "step": 123
    },
    {
      "epoch": 0.3564356435643564,
      "grad_norm": 0.1693616658449173,
      "learning_rate": 8.679762062923175e-05,
      "loss": 11.8183,
      "step": 126
    },
    {
      "epoch": 0.3564356435643564,
      "eval_loss": 11.819117546081543,
      "eval_runtime": 6.7651,
      "eval_samples_per_second": 88.1,
      "eval_steps_per_second": 11.086,
      "step": 126
    },
    {
      "epoch": 0.3649222065063649,
      "grad_norm": 0.17696824669837952,
      "learning_rate": 8.613974319136958e-05,
      "loss": 11.8171,
      "step": 129
    },
    {
      "epoch": 0.3734087694483734,
      "grad_norm": 0.11144156008958817,
      "learning_rate": 8.54684960502629e-05,
      "loss": 11.815,
      "step": 132
    },
    {
      "epoch": 0.38189533239038187,
      "grad_norm": 0.16119325160980225,
      "learning_rate": 8.478412753017433e-05,
      "loss": 11.8134,
      "step": 135
    },
    {
      "epoch": 0.39038189533239037,
      "grad_norm": 0.10234789550304413,
      "learning_rate": 8.408689080954998e-05,
      "loss": 11.8138,
      "step": 138
    },
    {
      "epoch": 0.3988684582743989,
      "grad_norm": 0.12111084908246994,
      "learning_rate": 8.33770438273574e-05,
      "loss": 11.8152,
      "step": 141
    },
    {
      "epoch": 0.4073550212164074,
      "grad_norm": 0.07516127824783325,
      "learning_rate": 8.265484918766243e-05,
      "loss": 11.8128,
      "step": 144
    },
    {
      "epoch": 0.4158415841584158,
      "grad_norm": 0.23707596957683563,
      "learning_rate": 8.192057406248028e-05,
      "loss": 11.8202,
      "step": 147
    },
    {
      "epoch": 0.4243281471004243,
      "grad_norm": 0.1228451356291771,
      "learning_rate": 8.117449009293668e-05,
      "loss": 11.8201,
      "step": 150
    },
    {
      "epoch": 0.4328147100424328,
      "grad_norm": 0.16358840465545654,
      "learning_rate": 8.041687328877567e-05,
      "loss": 11.8141,
      "step": 153
    },
    {
      "epoch": 0.44130127298444133,
      "grad_norm": 0.10192089527845383,
      "learning_rate": 7.964800392625129e-05,
      "loss": 11.8128,
      "step": 156
    },
    {
      "epoch": 0.4497878359264498,
      "grad_norm": 0.07679455727338791,
      "learning_rate": 7.886816644444098e-05,
      "loss": 11.8124,
      "step": 159
    },
    {
      "epoch": 0.4582743988684583,
      "grad_norm": 0.10075189918279648,
      "learning_rate": 7.807764934001874e-05,
      "loss": 11.8119,
      "step": 162
    },
    {
      "epoch": 0.4667609618104668,
      "grad_norm": 0.1872919499874115,
      "learning_rate": 7.727674506052743e-05,
      "loss": 11.8203,
      "step": 165
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 0.12166598439216614,
      "learning_rate": 7.646574989618938e-05,
      "loss": 11.8202,
      "step": 168
    },
    {
      "epoch": 0.4752475247524752,
      "eval_loss": 11.818514823913574,
      "eval_runtime": 6.4158,
      "eval_samples_per_second": 92.895,
      "eval_steps_per_second": 11.69,
      "step": 168
    },
    {
      "epoch": 0.4837340876944837,
      "grad_norm": 0.13749000430107117,
      "learning_rate": 7.564496387029532e-05,
      "loss": 11.8156,
      "step": 171
    },
    {
      "epoch": 0.49222065063649223,
      "grad_norm": 0.07802052795886993,
      "learning_rate": 7.481469062821252e-05,
      "loss": 11.8182,
      "step": 174
    },
    {
      "epoch": 0.5007072135785007,
      "grad_norm": 0.150814950466156,
      "learning_rate": 7.39752373250527e-05,
      "loss": 11.8179,
      "step": 177
    },
    {
      "epoch": 0.5091937765205092,
      "grad_norm": 0.1514790952205658,
      "learning_rate": 7.312691451204178e-05,
      "loss": 11.8099,
      "step": 180
    },
    {
      "epoch": 0.5176803394625177,
      "grad_norm": 0.13362684845924377,
      "learning_rate": 7.227003602163295e-05,
      "loss": 11.8172,
      "step": 183
    },
    {
      "epoch": 0.5261669024045261,
      "grad_norm": 0.09337490051984787,
      "learning_rate": 7.14049188514063e-05,
      "loss": 11.8184,
      "step": 186
    },
    {
      "epoch": 0.5346534653465347,
      "grad_norm": 0.08015663921833038,
      "learning_rate": 7.05318830467969e-05,
      "loss": 11.8158,
      "step": 189
    },
    {
      "epoch": 0.5431400282885431,
      "grad_norm": 0.16405069828033447,
      "learning_rate": 6.965125158269619e-05,
      "loss": 11.816,
      "step": 192
    },
    {
      "epoch": 0.5516265912305516,
      "grad_norm": 0.14057497680187225,
      "learning_rate": 6.876335024396872e-05,
      "loss": 11.8147,
      "step": 195
    },
    {
      "epoch": 0.5601131541725601,
      "grad_norm": 0.1409187614917755,
      "learning_rate": 6.786850750493006e-05,
      "loss": 11.8157,
      "step": 198
    },
    {
      "epoch": 0.5685997171145686,
      "grad_norm": 0.1987845003604889,
      "learning_rate": 6.696705440782938e-05,
      "loss": 11.8185,
      "step": 201
    },
    {
      "epoch": 0.5770862800565771,
      "grad_norm": 0.10339465737342834,
      "learning_rate": 6.605932444038229e-05,
      "loss": 11.815,
      "step": 204
    },
    {
      "epoch": 0.5855728429985856,
      "grad_norm": 0.12926329672336578,
      "learning_rate": 6.514565341239861e-05,
      "loss": 11.818,
      "step": 207
    },
    {
      "epoch": 0.594059405940594,
      "grad_norm": 0.07949727028608322,
      "learning_rate": 6.422637933155162e-05,
      "loss": 11.8151,
      "step": 210
    },
    {
      "epoch": 0.594059405940594,
      "eval_loss": 11.818094253540039,
      "eval_runtime": 6.6444,
      "eval_samples_per_second": 89.7,
      "eval_steps_per_second": 11.288,
      "step": 210
    }
  ],
  "logging_steps": 3,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 42,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1284750704640.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}