{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 492,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0040650406504065045,
      "grad_norm": 16.96013186396094,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 1.5409,
      "step": 1
    },
    {
      "epoch": 0.02032520325203252,
      "grad_norm": 16.916170957900782,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.5345,
      "step": 5
    },
    {
      "epoch": 0.04065040650406504,
      "grad_norm": 4.992436085095587,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.3026,
      "step": 10
    },
    {
      "epoch": 0.06097560975609756,
      "grad_norm": 2.654639415277273,
      "learning_rate": 6e-06,
      "loss": 1.2217,
      "step": 15
    },
    {
      "epoch": 0.08130081300813008,
      "grad_norm": 2.2317048430147577,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.162,
      "step": 20
    },
    {
      "epoch": 0.1016260162601626,
      "grad_norm": 1.3761478430076108,
      "learning_rate": 1e-05,
      "loss": 1.124,
      "step": 25
    },
    {
      "epoch": 0.12195121951219512,
      "grad_norm": 1.1540940483296693,
      "learning_rate": 1.2e-05,
      "loss": 1.1148,
      "step": 30
    },
    {
      "epoch": 0.14227642276422764,
      "grad_norm": 1.1928473894163938,
      "learning_rate": 1.4e-05,
      "loss": 1.1046,
      "step": 35
    },
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 1.185131002730624,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.1034,
      "step": 40
    },
    {
      "epoch": 0.18292682926829268,
      "grad_norm": 1.3370638997381883,
      "learning_rate": 1.8e-05,
      "loss": 1.0685,
      "step": 45
    },
    {
      "epoch": 0.2032520325203252,
      "grad_norm": 1.4250484136195543,
      "learning_rate": 2e-05,
      "loss": 1.0857,
      "step": 50
    },
    {
      "epoch": 0.22357723577235772,
      "grad_norm": 1.3017876025421216,
      "learning_rate": 1.9993685782892184e-05,
      "loss": 1.0214,
      "step": 55
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 1.486201507551871,
      "learning_rate": 1.9974751105436266e-05,
      "loss": 1.0418,
      "step": 60
    },
    {
      "epoch": 0.26422764227642276,
      "grad_norm": 1.2014188024997923,
      "learning_rate": 1.9943219879165113e-05,
      "loss": 1.0753,
      "step": 65
    },
    {
      "epoch": 0.2845528455284553,
      "grad_norm": 1.3819404641565476,
      "learning_rate": 1.98991319230804e-05,
      "loss": 1.0214,
      "step": 70
    },
    {
      "epoch": 0.3048780487804878,
      "grad_norm": 1.1959378462736852,
      "learning_rate": 1.984254291336743e-05,
      "loss": 1.0168,
      "step": 75
    },
    {
      "epoch": 0.3252032520325203,
      "grad_norm": 1.183753776787632,
      "learning_rate": 1.9773524313084857e-05,
      "loss": 1.0293,
      "step": 80
    },
    {
      "epoch": 0.34552845528455284,
      "grad_norm": 1.2267547234529148,
      "learning_rate": 1.9692163281918016e-05,
      "loss": 1.0394,
      "step": 85
    },
    {
      "epoch": 0.36585365853658536,
      "grad_norm": 1.1369844018691624,
      "learning_rate": 1.959856256610988e-05,
      "loss": 1.0491,
      "step": 90
    },
    {
      "epoch": 0.3861788617886179,
      "grad_norm": 1.1999534529754976,
      "learning_rate": 1.9492840368708668e-05,
      "loss": 1.0136,
      "step": 95
    },
    {
      "epoch": 0.4065040650406504,
      "grad_norm": 1.1735600472638217,
      "learning_rate": 1.937513020029588e-05,
      "loss": 1.0361,
      "step": 100
    },
    {
      "epoch": 0.4268292682926829,
      "grad_norm": 1.250115647846771,
      "learning_rate": 1.9245580710383344e-05,
      "loss": 1.0283,
      "step": 105
    },
    {
      "epoch": 0.44715447154471544,
      "grad_norm": 1.1840318671469985,
      "learning_rate": 1.9104355499692166e-05,
      "loss": 1.0483,
      "step": 110
    },
    {
      "epoch": 0.46747967479674796,
      "grad_norm": 1.1355456855985984,
      "learning_rate": 1.8951632913550625e-05,
      "loss": 1.0076,
      "step": 115
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 1.176376978993297,
      "learning_rate": 1.8787605816671956e-05,
      "loss": 1.0451,
      "step": 120
    },
    {
      "epoch": 0.508130081300813,
      "grad_norm": 1.2157595019570657,
      "learning_rate": 1.8612481349596406e-05,
      "loss": 0.9807,
      "step": 125
    },
    {
      "epoch": 0.5284552845528455,
      "grad_norm": 1.617382778432822,
      "learning_rate": 1.8426480667105178e-05,
      "loss": 1.0273,
      "step": 130
    },
    {
      "epoch": 0.5487804878048781,
      "grad_norm": 1.072969358036799,
      "learning_rate": 1.8229838658936566e-05,
      "loss": 1.0239,
      "step": 135
    },
    {
      "epoch": 0.5691056910569106,
      "grad_norm": 1.1349667239072485,
      "learning_rate": 1.8022803653156983e-05,
      "loss": 1.0191,
      "step": 140
    },
    {
      "epoch": 0.5894308943089431,
      "grad_norm": 1.061992535593682,
      "learning_rate": 1.7805637102561516e-05,
      "loss": 1.004,
      "step": 145
    },
    {
      "epoch": 0.6097560975609756,
      "grad_norm": 1.1127139653197202,
      "learning_rate": 1.757861325449997e-05,
      "loss": 0.9924,
      "step": 150
    },
    {
      "epoch": 0.6300813008130082,
      "grad_norm": 1.1022251104365055,
      "learning_rate": 1.73420188045454e-05,
      "loss": 0.9971,
      "step": 155
    },
    {
      "epoch": 0.6504065040650406,
      "grad_norm": 1.273269943630818,
      "learning_rate": 1.7096152534442515e-05,
      "loss": 1.0056,
      "step": 160
    },
    {
      "epoch": 0.6707317073170732,
      "grad_norm": 1.0563584964584172,
      "learning_rate": 1.6841324934793096e-05,
      "loss": 0.9856,
      "step": 165
    },
    {
      "epoch": 0.6910569105691057,
      "grad_norm": 1.145292649525439,
      "learning_rate": 1.6577857812954994e-05,
      "loss": 1.0083,
      "step": 170
    },
    {
      "epoch": 0.7113821138211383,
      "grad_norm": 1.0928885418057457,
      "learning_rate": 1.6306083886649823e-05,
      "loss": 0.9936,
      "step": 175
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 1.13829615874657,
      "learning_rate": 1.6026346363792565e-05,
      "loss": 0.9874,
      "step": 180
    },
    {
      "epoch": 0.7520325203252033,
      "grad_norm": 1.0862202261960012,
      "learning_rate": 1.573899850907373e-05,
      "loss": 0.9856,
      "step": 185
    },
    {
      "epoch": 0.7723577235772358,
      "grad_norm": 1.0544760585534974,
      "learning_rate": 1.5444403197841345e-05,
      "loss": 1.0079,
      "step": 190
    },
    {
      "epoch": 0.7926829268292683,
      "grad_norm": 1.1972116619581246,
      "learning_rate": 1.514293245784623e-05,
      "loss": 0.9818,
      "step": 195
    },
    {
      "epoch": 0.8130081300813008,
      "grad_norm": 1.0551988260235088,
      "learning_rate": 1.4834966999429179e-05,
      "loss": 0.9762,
      "step": 200
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 1.0937895071472443,
      "learning_rate": 1.4520895734743419e-05,
      "loss": 0.9967,
      "step": 205
    },
    {
      "epoch": 0.8536585365853658,
      "grad_norm": 2.1677819071037283,
      "learning_rate": 1.4201115286619464e-05,
      "loss": 0.9642,
      "step": 210
    },
    {
      "epoch": 0.8739837398373984,
      "grad_norm": 1.0198723964107377,
      "learning_rate": 1.387602948769257e-05,
      "loss": 0.9717,
      "step": 215
    },
    {
      "epoch": 0.8943089430894309,
      "grad_norm": 1.0362342965679063,
      "learning_rate": 1.3546048870425356e-05,
      "loss": 0.9714,
      "step": 220
    },
    {
      "epoch": 0.9146341463414634,
      "grad_norm": 0.997164008308899,
      "learning_rate": 1.3211590148669586e-05,
      "loss": 0.9713,
      "step": 225
    },
    {
      "epoch": 0.9349593495934959,
      "grad_norm": 1.1623269423245046,
      "learning_rate": 1.2873075691421808e-05,
      "loss": 0.9454,
      "step": 230
    },
    {
      "epoch": 0.9552845528455285,
      "grad_norm": 1.0749975590040124,
      "learning_rate": 1.2530932989437463e-05,
      "loss": 0.9845,
      "step": 235
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.988624506908827,
      "learning_rate": 1.2185594115376991e-05,
      "loss": 0.9547,
      "step": 240
    },
    {
      "epoch": 0.9959349593495935,
      "grad_norm": 1.0165003436015188,
      "learning_rate": 1.1837495178165706e-05,
      "loss": 0.9962,
      "step": 245
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.968990683555603,
      "eval_runtime": 4.2249,
      "eval_samples_per_second": 37.397,
      "eval_steps_per_second": 0.71,
      "step": 246
    },
    {
      "epoch": 1.016260162601626,
      "grad_norm": 2.2206925031006675,
      "learning_rate": 1.1487075772256517e-05,
      "loss": 0.7411,
      "step": 250
    },
    {
      "epoch": 1.0365853658536586,
      "grad_norm": 1.5057083208667505,
      "learning_rate": 1.1134778422490971e-05,
      "loss": 0.6718,
      "step": 255
    },
    {
      "epoch": 1.056910569105691,
      "grad_norm": 1.1997738500067352,
      "learning_rate": 1.0781048025259648e-05,
      "loss": 0.6885,
      "step": 260
    },
    {
      "epoch": 1.0772357723577235,
      "grad_norm": 1.129770949868323,
      "learning_rate": 1.0426331286667701e-05,
      "loss": 0.6459,
      "step": 265
    },
    {
      "epoch": 1.0975609756097562,
      "grad_norm": 1.0821575635964367,
      "learning_rate": 1.0071076158414977e-05,
      "loss": 0.6578,
      "step": 270
    },
    {
      "epoch": 1.1178861788617886,
      "grad_norm": 0.9858678711249164,
      "learning_rate": 9.715731272103172e-06,
      "loss": 0.6665,
      "step": 275
    },
    {
      "epoch": 1.1382113821138211,
      "grad_norm": 1.0404542015906177,
      "learning_rate": 9.360745372684346e-06,
      "loss": 0.6682,
      "step": 280
    },
    {
      "epoch": 1.1585365853658536,
      "grad_norm": 1.0009568415817596,
      "learning_rate": 9.00656675176633e-06,
      "loss": 0.6557,
      "step": 285
    },
    {
      "epoch": 1.1788617886178863,
      "grad_norm": 1.0425691363766654,
      "learning_rate": 8.653642681490608e-06,
      "loss": 0.6632,
      "step": 290
    },
    {
      "epoch": 1.1991869918699187,
      "grad_norm": 0.9980360375332701,
      "learning_rate": 8.30241884969764e-06,
      "loss": 0.6557,
      "step": 295
    },
    {
      "epoch": 1.2195121951219512,
      "grad_norm": 1.1151520476299475,
      "learning_rate": 7.953338797092902e-06,
      "loss": 0.676,
      "step": 300
    },
    {
      "epoch": 1.2398373983739837,
      "grad_norm": 1.1095243103350756,
      "learning_rate": 7.606843357124426e-06,
      "loss": 0.6514,
      "step": 305
    },
    {
      "epoch": 1.2601626016260163,
      "grad_norm": 1.0773726823725258,
      "learning_rate": 7.263370099279173e-06,
      "loss": 0.6592,
      "step": 310
    },
    {
      "epoch": 1.2804878048780488,
      "grad_norm": 1.0415539344975482,
      "learning_rate": 6.923352776501302e-06,
      "loss": 0.663,
      "step": 315
    },
    {
      "epoch": 1.3008130081300813,
      "grad_norm": 0.9921263103830474,
      "learning_rate": 6.587220777430097e-06,
      "loss": 0.6554,
      "step": 320
    },
    {
      "epoch": 1.321138211382114,
      "grad_norm": 1.0067612241699029,
      "learning_rate": 6.255398584149366e-06,
      "loss": 0.6592,
      "step": 325
    },
    {
      "epoch": 1.3414634146341464,
      "grad_norm": 0.9539630263562321,
      "learning_rate": 5.928305236133016e-06,
      "loss": 0.638,
      "step": 330
    },
    {
      "epoch": 1.3617886178861789,
      "grad_norm": 0.9724353060112348,
      "learning_rate": 5.60635380106383e-06,
      "loss": 0.6664,
      "step": 335
    },
    {
      "epoch": 1.3821138211382114,
      "grad_norm": 0.9667751887299418,
      "learning_rate": 5.2899508531936526e-06,
      "loss": 0.6582,
      "step": 340
    },
    {
      "epoch": 1.4024390243902438,
      "grad_norm": 1.0179726164365328,
      "learning_rate": 4.979495959903759e-06,
      "loss": 0.658,
      "step": 345
    },
    {
      "epoch": 1.4227642276422765,
      "grad_norm": 0.9892639534813169,
      "learning_rate": 4.675381177113837e-06,
      "loss": 0.6588,
      "step": 350
    },
    {
      "epoch": 1.443089430894309,
      "grad_norm": 0.9663435093514263,
      "learning_rate": 4.377990554176729e-06,
      "loss": 0.6295,
      "step": 355
    },
    {
      "epoch": 1.4634146341463414,
      "grad_norm": 0.9475872699295589,
      "learning_rate": 4.087699648884248e-06,
      "loss": 0.6309,
      "step": 360
    },
    {
      "epoch": 1.4837398373983741,
      "grad_norm": 1.0174077533995098,
      "learning_rate": 3.804875053196477e-06,
      "loss": 0.6548,
      "step": 365
    },
    {
      "epoch": 1.5040650406504064,
      "grad_norm": 0.9473261301601033,
      "learning_rate": 3.529873930293546e-06,
      "loss": 0.6585,
      "step": 370
    },
    {
      "epoch": 1.524390243902439,
      "grad_norm": 0.9724565020578093,
      "learning_rate": 3.2630435635344283e-06,
      "loss": 0.6579,
      "step": 375
    },
    {
      "epoch": 1.5447154471544715,
      "grad_norm": 0.9377507057850171,
      "learning_rate": 3.004720917892464e-06,
      "loss": 0.6325,
      "step": 380
    },
    {
      "epoch": 1.565040650406504,
      "grad_norm": 1.220689589737471,
      "learning_rate": 2.7552322144213405e-06,
      "loss": 0.6656,
      "step": 385
    },
    {
      "epoch": 1.5853658536585367,
      "grad_norm": 0.9445474318613094,
      "learning_rate": 2.514892518288988e-06,
      "loss": 0.6484,
      "step": 390
    },
    {
      "epoch": 1.6056910569105691,
      "grad_norm": 0.915729013522606,
      "learning_rate": 2.2840053408996154e-06,
      "loss": 0.6611,
      "step": 395
    },
    {
      "epoch": 1.6260162601626016,
      "grad_norm": 0.9261545603143331,
      "learning_rate": 2.0628622566063063e-06,
      "loss": 0.6366,
      "step": 400
    },
    {
      "epoch": 1.6463414634146343,
      "grad_norm": 0.9879532897121964,
      "learning_rate": 1.8517425344982831e-06,
      "loss": 0.6349,
      "step": 405
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.9360662238523524,
      "learning_rate": 1.6509127857277784e-06,
      "loss": 0.654,
      "step": 410
    },
    {
      "epoch": 1.6869918699186992,
      "grad_norm": 0.9548880407020373,
      "learning_rate": 1.4606266268218783e-06,
      "loss": 0.6625,
      "step": 415
    },
    {
      "epoch": 1.7073170731707317,
      "grad_norm": 0.9497166098139703,
      "learning_rate": 1.2811243594045697e-06,
      "loss": 0.6593,
      "step": 420
    },
    {
      "epoch": 1.7276422764227641,
      "grad_norm": 0.937994818106022,
      "learning_rate": 1.1126326667334196e-06,
      "loss": 0.657,
      "step": 425
    },
    {
      "epoch": 1.7479674796747968,
      "grad_norm": 0.9426215224621286,
      "learning_rate": 9.55364327434105e-07,
      "loss": 0.6572,
      "step": 430
    },
    {
      "epoch": 1.7682926829268293,
      "grad_norm": 0.956528393469926,
      "learning_rate": 8.095179467943293e-07,
      "loss": 0.6538,
      "step": 435
    },
    {
      "epoch": 1.7886178861788617,
      "grad_norm": 0.9816007976764832,
      "learning_rate": 6.752777059564431e-07,
      "loss": 0.6683,
      "step": 440
    },
    {
      "epoch": 1.8089430894308944,
      "grad_norm": 0.9327650063702297,
      "learning_rate": 5.528131293254957e-07,
      "loss": 0.6204,
      "step": 445
    },
    {
      "epoch": 1.8292682926829267,
      "grad_norm": 0.9411103321287626,
      "learning_rate": 4.4227887048646335e-07,
      "loss": 0.6595,
      "step": 450
    },
    {
      "epoch": 1.8495934959349594,
      "grad_norm": 0.9788741395392418,
      "learning_rate": 3.4381451690097653e-07,
      "loss": 0.6425,
      "step": 455
    },
    {
      "epoch": 1.8699186991869918,
      "grad_norm": 0.9336996330937468,
      "learning_rate": 2.5754441363021854e-07,
      "loss": 0.6345,
      "step": 460
    },
    {
      "epoch": 1.8902439024390243,
      "grad_norm": 0.9453351615169212,
      "learning_rate": 1.8357750630658367e-07,
      "loss": 0.6489,
      "step": 465
    },
    {
      "epoch": 1.910569105691057,
      "grad_norm": 0.9708668647842268,
      "learning_rate": 1.2200720355239893e-07,
      "loss": 0.6509,
      "step": 470
    },
    {
      "epoch": 1.9308943089430894,
      "grad_norm": 0.984113893821567,
      "learning_rate": 7.291125901946027e-08,
      "loss": 0.6546,
      "step": 475
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 0.9685414915217074,
      "learning_rate": 3.635167319834709e-08,
      "loss": 0.6384,
      "step": 480
    },
    {
      "epoch": 1.9715447154471546,
      "grad_norm": 0.9169491016884999,
      "learning_rate": 1.2374615121508726e-08,
      "loss": 0.6367,
      "step": 485
    },
    {
      "epoch": 1.9918699186991868,
      "grad_norm": 0.9084443808404363,
      "learning_rate": 1.0103640590064524e-09,
      "loss": 0.6291,
      "step": 490
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.9818947911262512,
      "eval_runtime": 6.2779,
      "eval_samples_per_second": 25.167,
      "eval_steps_per_second": 0.478,
      "step": 492
    },
    {
      "epoch": 2.0,
      "step": 492,
      "total_flos": 103014790594560.0,
      "train_loss": 0.8469056426509609,
      "train_runtime": 3499.6534,
      "train_samples_per_second": 8.98,
      "train_steps_per_second": 0.141
    }
  ],
  "logging_steps": 5,
  "max_steps": 492,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 103014790594560.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}