{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 462,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004329004329004329,
      "grad_norm": 20.877743796637407,
      "learning_rate": 4.2553191489361704e-07,
      "loss": 1.7871,
      "step": 1
    },
    {
      "epoch": 0.021645021645021644,
      "grad_norm": 18.21795285874322,
      "learning_rate": 2.1276595744680853e-06,
      "loss": 1.7389,
      "step": 5
    },
    {
      "epoch": 0.04329004329004329,
      "grad_norm": 5.701059989509366,
      "learning_rate": 4.255319148936171e-06,
      "loss": 1.5421,
      "step": 10
    },
    {
      "epoch": 0.06493506493506493,
      "grad_norm": 2.789667646224892,
      "learning_rate": 6.382978723404256e-06,
      "loss": 1.3975,
      "step": 15
    },
    {
      "epoch": 0.08658008658008658,
      "grad_norm": 1.613528044644943,
      "learning_rate": 8.510638297872341e-06,
      "loss": 1.3146,
      "step": 20
    },
    {
      "epoch": 0.10822510822510822,
      "grad_norm": 1.222589469421322,
      "learning_rate": 1.0638297872340426e-05,
      "loss": 1.2876,
      "step": 25
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 1.3215528280582176,
      "learning_rate": 1.2765957446808513e-05,
      "loss": 1.2531,
      "step": 30
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 1.3282799697001735,
      "learning_rate": 1.4893617021276596e-05,
      "loss": 1.2096,
      "step": 35
    },
    {
      "epoch": 0.17316017316017315,
      "grad_norm": 1.1149401355405273,
      "learning_rate": 1.7021276595744682e-05,
      "loss": 1.2256,
      "step": 40
    },
    {
      "epoch": 0.19480519480519481,
      "grad_norm": 1.4141147361835624,
      "learning_rate": 1.914893617021277e-05,
      "loss": 1.1834,
      "step": 45
    },
    {
      "epoch": 0.21645021645021645,
      "grad_norm": 1.1822192980158253,
      "learning_rate": 1.9997421320309795e-05,
      "loss": 1.2118,
      "step": 50
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 1.1446997824008667,
      "learning_rate": 1.9981667538108588e-05,
      "loss": 1.201,
      "step": 55
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 1.1200026579741698,
      "learning_rate": 1.9951615113309076e-05,
      "loss": 1.1952,
      "step": 60
    },
    {
      "epoch": 0.2813852813852814,
      "grad_norm": 1.187192621847611,
      "learning_rate": 1.9907307095720304e-05,
      "loss": 1.2281,
      "step": 65
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 1.1254345317613856,
      "learning_rate": 1.984880695615066e-05,
      "loss": 1.1929,
      "step": 70
    },
    {
      "epoch": 0.3246753246753247,
      "grad_norm": 2.053142496804073,
      "learning_rate": 1.9776198495486566e-05,
      "loss": 1.2203,
      "step": 75
    },
    {
      "epoch": 0.3463203463203463,
      "grad_norm": 1.2029392175636573,
      "learning_rate": 1.9689585724648515e-05,
      "loss": 1.2179,
      "step": 80
    },
    {
      "epoch": 0.36796536796536794,
      "grad_norm": 1.1250217257278072,
      "learning_rate": 1.958909271559642e-05,
      "loss": 1.1996,
      "step": 85
    },
    {
      "epoch": 0.38961038961038963,
      "grad_norm": 1.1037575465342937,
      "learning_rate": 1.947486342359773e-05,
      "loss": 1.1843,
      "step": 90
    },
    {
      "epoch": 0.41125541125541126,
      "grad_norm": 1.6143939161369725,
      "learning_rate": 1.9347061481012894e-05,
      "loss": 1.1646,
      "step": 95
    },
    {
      "epoch": 0.4329004329004329,
      "grad_norm": 1.2124944707128797,
      "learning_rate": 1.9205869962893607e-05,
      "loss": 1.2082,
      "step": 100
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 1.366998499730903,
      "learning_rate": 1.9051491124729512e-05,
      "loss": 1.1927,
      "step": 105
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 1.120158585500849,
      "learning_rate": 1.8884146112719208e-05,
      "loss": 1.1637,
      "step": 110
    },
    {
      "epoch": 0.49783549783549785,
      "grad_norm": 1.169190437583552,
      "learning_rate": 1.8704074646980416e-05,
      "loss": 1.1739,
      "step": 115
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 1.5328426889406774,
      "learning_rate": 1.8511534678153243e-05,
      "loss": 1.1488,
      "step": 120
    },
    {
      "epoch": 0.5411255411255411,
      "grad_norm": 1.0366421774380163,
      "learning_rate": 1.830680201788836e-05,
      "loss": 1.1756,
      "step": 125
    },
    {
      "epoch": 0.5627705627705628,
      "grad_norm": 1.1075356705624422,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 1.1905,
      "step": 130
    },
    {
      "epoch": 0.5844155844155844,
      "grad_norm": 1.0847986023260712,
      "learning_rate": 1.7861948779096047e-05,
      "loss": 1.1665,
      "step": 135
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.0102263118741437,
      "learning_rate": 1.762246544854807e-05,
      "loss": 1.137,
      "step": 140
    },
    {
      "epoch": 0.6277056277056277,
      "grad_norm": 1.036983432238017,
      "learning_rate": 1.7372063009669685e-05,
      "loss": 1.1433,
      "step": 145
    },
    {
      "epoch": 0.6493506493506493,
      "grad_norm": 1.1129097876771734,
      "learning_rate": 1.7111100161542545e-05,
      "loss": 1.1756,
      "step": 150
    },
    {
      "epoch": 0.670995670995671,
      "grad_norm": 1.048990729813769,
      "learning_rate": 1.683995073093283e-05,
      "loss": 1.1225,
      "step": 155
    },
    {
      "epoch": 0.6926406926406926,
      "grad_norm": 1.1501277496328752,
      "learning_rate": 1.655900313678799e-05,
      "loss": 1.1335,
      "step": 160
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.1230467049226944,
      "learning_rate": 1.626865983383037e-05,
      "loss": 1.1359,
      "step": 165
    },
    {
      "epoch": 0.7359307359307359,
      "grad_norm": 1.0339043537639934,
      "learning_rate": 1.596933673604467e-05,
      "loss": 1.1525,
      "step": 170
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 1.3703136108639966,
      "learning_rate": 1.5661462620885198e-05,
      "loss": 1.1084,
      "step": 175
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 1.1235783405767077,
      "learning_rate": 1.534547851505627e-05,
      "loss": 1.1454,
      "step": 180
    },
    {
      "epoch": 0.8008658008658008,
      "grad_norm": 1.0145691819619813,
      "learning_rate": 1.5021837062745714e-05,
      "loss": 1.1314,
      "step": 185
    },
    {
      "epoch": 0.8225108225108225,
      "grad_norm": 1.0366379821859082,
      "learning_rate": 1.469100187721644e-05,
      "loss": 1.1347,
      "step": 190
    },
    {
      "epoch": 0.8441558441558441,
      "grad_norm": 0.9797343756954148,
      "learning_rate": 1.435344687668489e-05,
      "loss": 1.1267,
      "step": 195
    },
    {
      "epoch": 0.8658008658008658,
      "grad_norm": 1.0125169520271824,
      "learning_rate": 1.400965560543778e-05,
      "loss": 1.1432,
      "step": 200
    },
    {
      "epoch": 0.8874458874458875,
      "grad_norm": 1.0076883560029861,
      "learning_rate": 1.3660120541159536e-05,
      "loss": 1.1453,
      "step": 205
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.9594741075750862,
      "learning_rate": 1.3305342389462792e-05,
      "loss": 1.1235,
      "step": 210
    },
    {
      "epoch": 0.9307359307359307,
      "grad_norm": 1.0087650659111476,
      "learning_rate": 1.294582936663239e-05,
      "loss": 1.1333,
      "step": 215
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 1.021522349018145,
      "learning_rate": 1.2582096471610467e-05,
      "loss": 1.1104,
      "step": 220
    },
    {
      "epoch": 0.974025974025974,
      "grad_norm": 1.0148162711090376,
      "learning_rate": 1.221466474826543e-05,
      "loss": 1.1077,
      "step": 225
    },
    {
      "epoch": 0.9956709956709957,
      "grad_norm": 0.9665861752821213,
      "learning_rate": 1.1844060539001618e-05,
      "loss": 1.1016,
      "step": 230
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.1138663291931152,
      "eval_runtime": 4.3692,
      "eval_samples_per_second": 34.789,
      "eval_steps_per_second": 0.687,
      "step": 231
    },
    {
      "epoch": 1.0173160173160174,
      "grad_norm": 2.0527264159154432,
      "learning_rate": 1.1470814730778905e-05,
      "loss": 0.9102,
      "step": 235
    },
    {
      "epoch": 1.0389610389610389,
      "grad_norm": 1.455965475523599,
      "learning_rate": 1.109546199462221e-05,
      "loss": 0.8067,
      "step": 240
    },
    {
      "epoch": 1.0606060606060606,
      "grad_norm": 1.1731794708057288,
      "learning_rate": 1.0718540019710433e-05,
      "loss": 0.824,
      "step": 245
    },
    {
      "epoch": 1.0822510822510822,
      "grad_norm": 1.1851242426639188,
      "learning_rate": 1.0340588743141879e-05,
      "loss": 0.8115,
      "step": 250
    },
    {
      "epoch": 1.103896103896104,
      "grad_norm": 1.078251194842658,
      "learning_rate": 9.962149576479546e-06,
      "loss": 0.8114,
      "step": 255
    },
    {
      "epoch": 1.1255411255411256,
      "grad_norm": 1.0244399166247982,
      "learning_rate": 9.583764630184311e-06,
      "loss": 0.8198,
      "step": 260
    },
    {
      "epoch": 1.1471861471861473,
      "grad_norm": 1.0118125591636071,
      "learning_rate": 9.205975937046879e-06,
      "loss": 0.8043,
      "step": 265
    },
    {
      "epoch": 1.1688311688311688,
      "grad_norm": 1.0315115837254647,
      "learning_rate": 8.82932467573106e-06,
      "loss": 0.7932,
      "step": 270
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 1.0047518561511999,
      "learning_rate": 8.45435039554054e-06,
      "loss": 0.7865,
      "step": 275
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 1.0324907986018956,
      "learning_rate": 8.081590243519682e-06,
      "loss": 0.7959,
      "step": 280
    },
    {
      "epoch": 1.2337662337662338,
      "grad_norm": 0.9684538095728706,
      "learning_rate": 7.71157819499559e-06,
      "loss": 0.7692,
      "step": 285
    },
    {
      "epoch": 1.2554112554112553,
      "grad_norm": 1.026533916056025,
      "learning_rate": 7.344844288663571e-06,
      "loss": 0.8126,
      "step": 290
    },
    {
      "epoch": 1.277056277056277,
      "grad_norm": 0.9834883699233659,
      "learning_rate": 6.981913867311818e-06,
      "loss": 0.7872,
      "step": 295
    },
    {
      "epoch": 1.2987012987012987,
      "grad_norm": 1.1658729678515243,
      "learning_rate": 6.623306825272937e-06,
      "loss": 0.8035,
      "step": 300
    },
    {
      "epoch": 1.3203463203463204,
      "grad_norm": 0.9850249154792221,
      "learning_rate": 6.2695368636803075e-06,
      "loss": 0.8043,
      "step": 305
    },
    {
      "epoch": 1.341991341991342,
      "grad_norm": 0.9651304936317318,
      "learning_rate": 5.92111075459616e-06,
      "loss": 0.782,
      "step": 310
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.9621470633936673,
      "learning_rate": 5.5785276150654925e-06,
      "loss": 0.7969,
      "step": 315
    },
    {
      "epoch": 1.3852813852813852,
      "grad_norm": 0.9875120746768518,
      "learning_rate": 5.242278192135682e-06,
      "loss": 0.8255,
      "step": 320
    },
    {
      "epoch": 1.406926406926407,
      "grad_norm": 0.9703641243841216,
      "learning_rate": 4.912844159866113e-06,
      "loss": 0.8081,
      "step": 325
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 1.0333712850123837,
      "learning_rate": 4.59069742933468e-06,
      "loss": 0.8274,
      "step": 330
    },
    {
      "epoch": 1.4502164502164503,
      "grad_norm": 0.9681660489299534,
      "learning_rate": 4.276299472629735e-06,
      "loss": 0.7975,
      "step": 335
    },
    {
      "epoch": 1.4718614718614718,
      "grad_norm": 1.0012088021253578,
      "learning_rate": 3.970100661795766e-06,
      "loss": 0.7774,
      "step": 340
    },
    {
      "epoch": 1.4935064935064934,
      "grad_norm": 0.9522339979957177,
      "learning_rate": 3.6725396236797937e-06,
      "loss": 0.8325,
      "step": 345
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 0.9539695380134816,
      "learning_rate": 3.384042611602605e-06,
      "loss": 0.792,
      "step": 350
    },
    {
      "epoch": 1.5367965367965368,
      "grad_norm": 0.9876834897890561,
      "learning_rate": 3.105022894755003e-06,
      "loss": 0.8234,
      "step": 355
    },
    {
      "epoch": 1.5584415584415585,
      "grad_norm": 0.9521924923182135,
      "learning_rate": 2.835880166193683e-06,
      "loss": 0.7782,
      "step": 360
    },
    {
      "epoch": 1.5800865800865802,
      "grad_norm": 0.9556390207534557,
      "learning_rate": 2.576999970284735e-06,
      "loss": 0.8192,
      "step": 365
    },
    {
      "epoch": 1.601731601731602,
      "grad_norm": 0.9187916659434155,
      "learning_rate": 2.328753150415094e-06,
      "loss": 0.8044,
      "step": 370
    },
    {
      "epoch": 1.6233766233766234,
      "grad_norm": 0.9663741256129553,
      "learning_rate": 2.091495317762955e-06,
      "loss": 0.7728,
      "step": 375
    },
    {
      "epoch": 1.645021645021645,
      "grad_norm": 0.9519160746498837,
      "learning_rate": 1.8655663418881587e-06,
      "loss": 0.776,
      "step": 380
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.0062143070641176,
      "learning_rate": 1.6512898638723496e-06,
      "loss": 0.7845,
      "step": 385
    },
    {
      "epoch": 1.6883116883116882,
      "grad_norm": 0.9807077916152634,
      "learning_rate": 1.4489728327062325e-06,
      "loss": 0.7894,
      "step": 390
    },
    {
      "epoch": 1.70995670995671,
      "grad_norm": 0.9521910568116111,
      "learning_rate": 1.258905065588103e-06,
      "loss": 0.7711,
      "step": 395
    },
    {
      "epoch": 1.7316017316017316,
      "grad_norm": 0.9157886273812276,
      "learning_rate": 1.0813588327634961e-06,
      "loss": 0.7872,
      "step": 400
    },
    {
      "epoch": 1.7532467532467533,
      "grad_norm": 0.9518282733524287,
      "learning_rate": 9.165884675006931e-07,
      "loss": 0.7874,
      "step": 405
    },
    {
      "epoch": 1.774891774891775,
      "grad_norm": 0.9282109794972182,
      "learning_rate": 7.648300017607535e-07,
      "loss": 0.7737,
      "step": 410
    },
    {
      "epoch": 1.7965367965367967,
      "grad_norm": 1.0188698575765125,
      "learning_rate": 6.263008280840133e-07,
      "loss": 0.774,
      "step": 415
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.953904828798195,
      "learning_rate": 5.011993881773569e-07,
      "loss": 0.7737,
      "step": 420
    },
    {
      "epoch": 1.8398268398268398,
      "grad_norm": 0.9612309743009354,
      "learning_rate": 3.897048886483934e-07,
      "loss": 0.7734,
      "step": 425
    },
    {
      "epoch": 1.8614718614718615,
      "grad_norm": 0.9540258820581294,
      "learning_rate": 2.9197704429370976e-07,
      "loss": 0.7728,
      "step": 430
    },
    {
      "epoch": 1.883116883116883,
      "grad_norm": 0.9391259666010853,
      "learning_rate": 2.0815584930895972e-07,
      "loss": 0.7846,
      "step": 435
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.923039210320182,
      "learning_rate": 1.3836137674854254e-07,
      "loss": 0.7948,
      "step": 440
    },
    {
      "epoch": 1.9264069264069263,
      "grad_norm": 0.9661085243975593,
      "learning_rate": 8.269360652209291e-08,
      "loss": 0.775,
      "step": 445
    },
    {
      "epoch": 1.948051948051948,
      "grad_norm": 0.8801221387422419,
      "learning_rate": 4.1232282174229475e-08,
      "loss": 0.805,
      "step": 450
    },
    {
      "epoch": 1.9696969696969697,
      "grad_norm": 0.9540642633518202,
      "learning_rate": 1.403679665270108e-08,
      "loss": 0.7993,
      "step": 455
    },
    {
      "epoch": 1.9913419913419914,
      "grad_norm": 0.938537521673335,
      "learning_rate": 1.1461072285490205e-09,
      "loss": 0.8082,
      "step": 460
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.1257315874099731,
      "eval_runtime": 5.4011,
      "eval_samples_per_second": 28.142,
      "eval_steps_per_second": 0.555,
      "step": 462
    },
    {
      "epoch": 2.0,
      "step": 462,
      "total_flos": 96733400924160.0,
      "train_loss": 0.9972741247771623,
      "train_runtime": 3285.0208,
      "train_samples_per_second": 9.0,
      "train_steps_per_second": 0.141
    }
  ],
  "logging_steps": 5,
  "max_steps": 462,
  "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": 96733400924160.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}