{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7109471094710947,
  "eval_steps": 500,
  "global_step": 289,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012300123001230012,
      "grad_norm": 18.199485778808594,
      "learning_rate": 2.162496240601504e-06,
      "loss": 0.4246,
      "mean_token_accuracy": 0.8806516230106354,
      "num_tokens": 790501.0,
      "step": 5
    },
    {
      "epoch": 0.024600246002460024,
      "grad_norm": 2.4167041778564453,
      "learning_rate": 4.865616541353383e-06,
      "loss": 0.241,
      "mean_token_accuracy": 0.9394735991954803,
      "num_tokens": 1595623.0,
      "step": 10
    },
    {
      "epoch": 0.03690036900369004,
      "grad_norm": 1.149552822113037,
      "learning_rate": 7.568736842105265e-06,
      "loss": 0.1773,
      "mean_token_accuracy": 0.950838902592659,
      "num_tokens": 2398289.0,
      "step": 15
    },
    {
      "epoch": 0.04920049200492005,
      "grad_norm": 0.9481139779090881,
      "learning_rate": 1.0271857142857143e-05,
      "loss": 0.157,
      "mean_token_accuracy": 0.9564695209264755,
      "num_tokens": 3203705.0,
      "step": 20
    },
    {
      "epoch": 0.06150061500615006,
      "grad_norm": 0.8733962178230286,
      "learning_rate": 1.2974977443609024e-05,
      "loss": 0.131,
      "mean_token_accuracy": 0.9600439041852951,
      "num_tokens": 4015006.0,
      "step": 25
    },
    {
      "epoch": 0.07380073800738007,
      "grad_norm": 1.0072107315063477,
      "learning_rate": 1.5678097744360906e-05,
      "loss": 0.1537,
      "mean_token_accuracy": 0.9557969391345977,
      "num_tokens": 4820265.0,
      "step": 30
    },
    {
      "epoch": 0.08610086100861009,
      "grad_norm": 0.7826172709465027,
      "learning_rate": 1.8381218045112784e-05,
      "loss": 0.1268,
      "mean_token_accuracy": 0.9640105336904525,
      "num_tokens": 5616213.0,
      "step": 35
    },
    {
      "epoch": 0.0984009840098401,
      "grad_norm": 0.9519556164741516,
      "learning_rate": 1.8917772099043e-05,
      "loss": 0.1462,
      "mean_token_accuracy": 0.9602459371089935,
      "num_tokens": 6417677.0,
      "step": 40
    },
    {
      "epoch": 0.11070110701107011,
      "grad_norm": 0.9456686973571777,
      "learning_rate": 1.8901245700523577e-05,
      "loss": 0.1316,
      "mean_token_accuracy": 0.9606737971305848,
      "num_tokens": 7225911.0,
      "step": 45
    },
    {
      "epoch": 0.12300123001230012,
      "grad_norm": 1.011513113975525,
      "learning_rate": 1.887203813289407e-05,
      "loss": 0.1376,
      "mean_token_accuracy": 0.9603729248046875,
      "num_tokens": 8037098.0,
      "step": 50
    },
    {
      "epoch": 0.13530135301353013,
      "grad_norm": 0.6402825117111206,
      "learning_rate": 1.883020174684894e-05,
      "loss": 0.1159,
      "mean_token_accuracy": 0.9652995616197586,
      "num_tokens": 8823871.0,
      "step": 55
    },
    {
      "epoch": 0.14760147601476015,
      "grad_norm": 0.8527904152870178,
      "learning_rate": 1.877581152856611e-05,
      "loss": 0.1484,
      "mean_token_accuracy": 0.9576063752174377,
      "num_tokens": 9618779.0,
      "step": 60
    },
    {
      "epoch": 0.15990159901599016,
      "grad_norm": 0.8437458276748657,
      "learning_rate": 1.8708964965304196e-05,
      "loss": 0.1589,
      "mean_token_accuracy": 0.9575431704521179,
      "num_tokens": 10420794.0,
      "step": 65
    },
    {
      "epoch": 0.17220172201722017,
      "grad_norm": 0.7675455212593079,
      "learning_rate": 1.8629781870669497e-05,
      "loss": 0.1261,
      "mean_token_accuracy": 0.9612848222255707,
      "num_tokens": 11233552.0,
      "step": 70
    },
    {
      "epoch": 0.18450184501845018,
      "grad_norm": 0.7388719916343689,
      "learning_rate": 1.853840416986599e-05,
      "loss": 0.1119,
      "mean_token_accuracy": 0.965791004896164,
      "num_tokens": 12060611.0,
      "step": 75
    },
    {
      "epoch": 0.1968019680196802,
      "grad_norm": 1.247281789779663,
      "learning_rate": 1.8434995645313208e-05,
      "loss": 0.1297,
      "mean_token_accuracy": 0.9641236394643784,
      "num_tokens": 12869437.0,
      "step": 80
    },
    {
      "epoch": 0.2091020910209102,
      "grad_norm": 0.7254406809806824,
      "learning_rate": 1.831974164308797e-05,
      "loss": 0.1202,
      "mean_token_accuracy": 0.963805866241455,
      "num_tokens": 13677681.0,
      "step": 85
    },
    {
      "epoch": 0.22140221402214022,
      "grad_norm": 0.5883035659790039,
      "learning_rate": 1.819284874071608e-05,
      "loss": 0.1409,
      "mean_token_accuracy": 0.9604643911123276,
      "num_tokens": 14490475.0,
      "step": 90
    },
    {
      "epoch": 0.23370233702337023,
      "grad_norm": 0.8015240430831909,
      "learning_rate": 1.805454437690949e-05,
      "loss": 0.1745,
      "mean_token_accuracy": 0.9539424449205398,
      "num_tokens": 15295083.0,
      "step": 95
    },
    {
      "epoch": 0.24600246002460024,
      "grad_norm": 0.5748587250709534,
      "learning_rate": 1.7905076443912563e-05,
      "loss": 0.0991,
      "mean_token_accuracy": 0.9699145495891571,
      "num_tokens": 16095676.0,
      "step": 100
    },
    {
      "epoch": 0.25830258302583026,
      "grad_norm": 0.6817578077316284,
      "learning_rate": 1.7744712843188067e-05,
      "loss": 0.1105,
      "mean_token_accuracy": 0.9672652065753937,
      "num_tokens": 16912282.0,
      "step": 105
    },
    {
      "epoch": 0.27060270602706027,
      "grad_norm": 0.7608867883682251,
      "learning_rate": 1.7573741005239295e-05,
      "loss": 0.1362,
      "mean_token_accuracy": 0.9618319183588028,
      "num_tokens": 17719577.0,
      "step": 110
    },
    {
      "epoch": 0.2829028290282903,
      "grad_norm": 0.5761942863464355,
      "learning_rate": 1.7392467374429e-05,
      "loss": 0.1212,
      "mean_token_accuracy": 0.96499003469944,
      "num_tokens": 18514230.0,
      "step": 115
    },
    {
      "epoch": 0.2952029520295203,
      "grad_norm": 0.5040966868400574,
      "learning_rate": 1.7201216859718456e-05,
      "loss": 0.1063,
      "mean_token_accuracy": 0.9666215687990188,
      "num_tokens": 19318636.0,
      "step": 120
    },
    {
      "epoch": 0.3075030750307503,
      "grad_norm": 0.5919148921966553,
      "learning_rate": 1.7000332252311218e-05,
      "loss": 0.1177,
      "mean_token_accuracy": 0.9667188465595246,
      "num_tokens": 20111682.0,
      "step": 125
    },
    {
      "epoch": 0.3198031980319803,
      "grad_norm": 0.7549655437469482,
      "learning_rate": 1.6790173611245328e-05,
      "loss": 0.1281,
      "mean_token_accuracy": 0.9631649076938629,
      "num_tokens": 20922527.0,
      "step": 130
    },
    {
      "epoch": 0.33210332103321033,
      "grad_norm": 0.5316765904426575,
      "learning_rate": 1.657111761803517e-05,
      "loss": 0.1083,
      "mean_token_accuracy": 0.9673703461885452,
      "num_tokens": 21720061.0,
      "step": 135
    },
    {
      "epoch": 0.34440344403444034,
      "grad_norm": 0.4782826006412506,
      "learning_rate": 1.6343556901519795e-05,
      "loss": 0.1258,
      "mean_token_accuracy": 0.9614889621734619,
      "num_tokens": 22508178.0,
      "step": 140
    },
    {
      "epoch": 0.35670356703567035,
      "grad_norm": 0.6960135102272034,
      "learning_rate": 1.610789933412776e-05,
      "loss": 0.1099,
      "mean_token_accuracy": 0.9675571650266648,
      "num_tokens": 23316007.0,
      "step": 145
    },
    {
      "epoch": 0.36900369003690037,
      "grad_norm": 0.5626348257064819,
      "learning_rate": 1.5864567300819845e-05,
      "loss": 0.14,
      "mean_token_accuracy": 0.9606057971715927,
      "num_tokens": 24119453.0,
      "step": 150
    },
    {
      "epoch": 0.3813038130381304,
      "grad_norm": 0.5676774978637695,
      "learning_rate": 1.5613996942019973e-05,
      "loss": 0.1289,
      "mean_token_accuracy": 0.9622929930686951,
      "num_tokens": 24923962.0,
      "step": 155
    },
    {
      "epoch": 0.3936039360393604,
      "grad_norm": 0.5314252376556396,
      "learning_rate": 1.53566373718913e-05,
      "loss": 0.1128,
      "mean_token_accuracy": 0.9672234207391739,
      "num_tokens": 25738830.0,
      "step": 160
    },
    {
      "epoch": 0.4059040590405904,
      "grad_norm": 0.7133026719093323,
      "learning_rate": 1.5092949873358618e-05,
      "loss": 0.1119,
      "mean_token_accuracy": 0.9660748809576034,
      "num_tokens": 26556768.0,
      "step": 165
    },
    {
      "epoch": 0.4182041820418204,
      "grad_norm": 0.5564062595367432,
      "learning_rate": 1.4823407071319808e-05,
      "loss": 0.1237,
      "mean_token_accuracy": 0.9653019607067108,
      "num_tokens": 27362311.0,
      "step": 170
    },
    {
      "epoch": 0.43050430504305043,
      "grad_norm": 0.7625254392623901,
      "learning_rate": 1.4548492085528362e-05,
      "loss": 0.1299,
      "mean_token_accuracy": 0.9637782484292984,
      "num_tokens": 28165694.0,
      "step": 175
    },
    {
      "epoch": 0.44280442804428044,
      "grad_norm": 0.4590056836605072,
      "learning_rate": 1.426869766466523e-05,
      "loss": 0.1109,
      "mean_token_accuracy": 0.9668718069791794,
      "num_tokens": 28976977.0,
      "step": 180
    },
    {
      "epoch": 0.45510455104551045,
      "grad_norm": 0.7241837978363037,
      "learning_rate": 1.3984525303152131e-05,
      "loss": 0.1258,
      "mean_token_accuracy": 0.9663730651140213,
      "num_tokens": 29771869.0,
      "step": 185
    },
    {
      "epoch": 0.46740467404674046,
      "grad_norm": 0.6697683334350586,
      "learning_rate": 1.369648434228923e-05,
      "loss": 0.116,
      "mean_token_accuracy": 0.9648581147193909,
      "num_tokens": 30581064.0,
      "step": 190
    },
    {
      "epoch": 0.4797047970479705,
      "grad_norm": 0.5982561707496643,
      "learning_rate": 1.3405091057328378e-05,
      "loss": 0.1085,
      "mean_token_accuracy": 0.9676321506500244,
      "num_tokens": 31385481.0,
      "step": 195
    },
    {
      "epoch": 0.4920049200492005,
      "grad_norm": 0.5491945147514343,
      "learning_rate": 1.3110867732118128e-05,
      "loss": 0.1093,
      "mean_token_accuracy": 0.9679040789604187,
      "num_tokens": 32196564.0,
      "step": 200
    },
    {
      "epoch": 0.5043050430504306,
      "grad_norm": 0.6740017533302307,
      "learning_rate": 1.2814341722979149e-05,
      "loss": 0.1148,
      "mean_token_accuracy": 0.9662465512752533,
      "num_tokens": 32998790.0,
      "step": 205
    },
    {
      "epoch": 0.5166051660516605,
      "grad_norm": 0.4156472980976105,
      "learning_rate": 1.2516044513487905e-05,
      "loss": 0.0993,
      "mean_token_accuracy": 0.969659423828125,
      "num_tokens": 33798826.0,
      "step": 210
    },
    {
      "epoch": 0.5289052890528906,
      "grad_norm": 0.47106194496154785,
      "learning_rate": 1.2216510761862786e-05,
      "loss": 0.1143,
      "mean_token_accuracy": 0.9660373240709305,
      "num_tokens": 34616522.0,
      "step": 215
    },
    {
      "epoch": 0.5412054120541205,
      "grad_norm": 0.7737653255462646,
      "learning_rate": 1.1916277342660076e-05,
      "loss": 0.1216,
      "mean_token_accuracy": 0.9647817283868789,
      "num_tokens": 35421018.0,
      "step": 220
    },
    {
      "epoch": 0.5535055350553506,
      "grad_norm": 0.5622140169143677,
      "learning_rate": 1.1615882384497483e-05,
      "loss": 0.1058,
      "mean_token_accuracy": 0.9678978323936462,
      "num_tokens": 36219260.0,
      "step": 225
    },
    {
      "epoch": 0.5658056580565806,
      "grad_norm": 0.5420289039611816,
      "learning_rate": 1.13158643055299e-05,
      "loss": 0.1073,
      "mean_token_accuracy": 0.9682381182909012,
      "num_tokens": 37024541.0,
      "step": 230
    },
    {
      "epoch": 0.5781057810578106,
      "grad_norm": 0.3959532678127289,
      "learning_rate": 1.1016760848406193e-05,
      "loss": 0.1061,
      "mean_token_accuracy": 0.9690022796392441,
      "num_tokens": 37821992.0,
      "step": 235
    },
    {
      "epoch": 0.5904059040590406,
      "grad_norm": 0.5564428567886353,
      "learning_rate": 1.0719108116436785e-05,
      "loss": 0.1317,
      "mean_token_accuracy": 0.9625335454940795,
      "num_tokens": 38632377.0,
      "step": 240
    },
    {
      "epoch": 0.6027060270602707,
      "grad_norm": 0.5967829823493958,
      "learning_rate": 1.0423439612699506e-05,
      "loss": 0.1272,
      "mean_token_accuracy": 0.9644939124584198,
      "num_tokens": 39428153.0,
      "step": 245
    },
    {
      "epoch": 0.6150061500615006,
      "grad_norm": 0.4877125322818756,
      "learning_rate": 1.0130285283806023e-05,
      "loss": 0.1115,
      "mean_token_accuracy": 0.9662620961666107,
      "num_tokens": 40235823.0,
      "step": 250
    },
    {
      "epoch": 0.6273062730627307,
      "grad_norm": 0.6021067500114441,
      "learning_rate": 9.840170570042768e-06,
      "loss": 0.1323,
      "mean_token_accuracy": 0.9612789899110794,
      "num_tokens": 41035006.0,
      "step": 255
    },
    {
      "epoch": 0.6396063960639606,
      "grad_norm": 0.6831470131874084,
      "learning_rate": 9.553615463588857e-06,
      "loss": 0.1106,
      "mean_token_accuracy": 0.9651778280735016,
      "num_tokens": 41848462.0,
      "step": 260
    },
    {
      "epoch": 0.6519065190651907,
      "grad_norm": 0.46584978699684143,
      "learning_rate": 9.271133576499006e-06,
      "loss": 0.1332,
      "mean_token_accuracy": 0.9595334082841873,
      "num_tokens": 42663965.0,
      "step": 265
    },
    {
      "epoch": 0.6642066420664207,
      "grad_norm": 0.5613858699798584,
      "learning_rate": 8.99323122012201e-06,
      "loss": 0.0999,
      "mean_token_accuracy": 0.9682179361581802,
      "num_tokens": 43463969.0,
      "step": 270
    },
    {
      "epoch": 0.6765067650676507,
      "grad_norm": 0.500439465045929,
      "learning_rate": 8.720406497604714e-06,
      "loss": 0.1091,
      "mean_token_accuracy": 0.9677204370498658,
      "num_tokens": 44276241.0,
      "step": 275
    },
    {
      "epoch": 0.6888068880688807,
      "grad_norm": 0.37819114327430725,
      "learning_rate": 8.453148411108156e-06,
      "loss": 0.0981,
      "mean_token_accuracy": 0.9704595625400543,
      "num_tokens": 45074698.0,
      "step": 280
    },
    {
      "epoch": 0.7011070110701108,
      "grad_norm": 0.5192675590515137,
      "learning_rate": 8.191935985335976e-06,
      "loss": 0.1097,
      "mean_token_accuracy": 0.9680727243423461,
      "num_tokens": 45867063.0,
      "step": 285
    }
  ],
  "logging_steps": 5,
  "max_steps": 406,
  "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": 2.850692145088561e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}