{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9918809201623815,
  "eval_steps": 500,
  "global_step": 368,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005412719891745603,
      "grad_norm": 23.5,
      "learning_rate": 5.405405405405406e-07,
      "loss": 2.2045,
      "step": 1
    },
    {
      "epoch": 0.02706359945872801,
      "grad_norm": 19.375,
      "learning_rate": 2.702702702702703e-06,
      "loss": 2.2384,
      "step": 5
    },
    {
      "epoch": 0.05412719891745602,
      "grad_norm": 6.6875,
      "learning_rate": 5.405405405405406e-06,
      "loss": 2.1809,
      "step": 10
    },
    {
      "epoch": 0.08119079837618404,
      "grad_norm": 3.921875,
      "learning_rate": 8.108108108108109e-06,
      "loss": 2.0942,
      "step": 15
    },
    {
      "epoch": 0.10825439783491204,
      "grad_norm": 2.765625,
      "learning_rate": 1.0810810810810812e-05,
      "loss": 2.0225,
      "step": 20
    },
    {
      "epoch": 0.13531799729364005,
      "grad_norm": 3.40625,
      "learning_rate": 1.3513513513513515e-05,
      "loss": 1.9498,
      "step": 25
    },
    {
      "epoch": 0.16238159675236807,
      "grad_norm": 2.703125,
      "learning_rate": 1.6216216216216218e-05,
      "loss": 1.8531,
      "step": 30
    },
    {
      "epoch": 0.18944519621109607,
      "grad_norm": 1.78125,
      "learning_rate": 1.891891891891892e-05,
      "loss": 1.7903,
      "step": 35
    },
    {
      "epoch": 0.2165087956698241,
      "grad_norm": 1.703125,
      "learning_rate": 1.9995946530314384e-05,
      "loss": 1.7538,
      "step": 40
    },
    {
      "epoch": 0.2435723951285521,
      "grad_norm": 1.5078125,
      "learning_rate": 1.9971187226043746e-05,
      "loss": 1.7264,
      "step": 45
    },
    {
      "epoch": 0.2706359945872801,
      "grad_norm": 1.3515625,
      "learning_rate": 1.9923976226947417e-05,
      "loss": 1.6995,
      "step": 50
    },
    {
      "epoch": 0.2976995940460081,
      "grad_norm": 1.28125,
      "learning_rate": 1.985441983600819e-05,
      "loss": 1.6901,
      "step": 55
    },
    {
      "epoch": 0.32476319350473615,
      "grad_norm": 1.34375,
      "learning_rate": 1.9762674670369757e-05,
      "loss": 1.6784,
      "step": 60
    },
    {
      "epoch": 0.35182679296346414,
      "grad_norm": 1.2890625,
      "learning_rate": 1.9648947308688594e-05,
      "loss": 1.6738,
      "step": 65
    },
    {
      "epoch": 0.37889039242219213,
      "grad_norm": 1.328125,
      "learning_rate": 1.9513493825989664e-05,
      "loss": 1.6719,
      "step": 70
    },
    {
      "epoch": 0.4059539918809202,
      "grad_norm": 1.2734375,
      "learning_rate": 1.9356619217073252e-05,
      "loss": 1.6617,
      "step": 75
    },
    {
      "epoch": 0.4330175913396482,
      "grad_norm": 1.2734375,
      "learning_rate": 1.917867670977126e-05,
      "loss": 1.6447,
      "step": 80
    },
    {
      "epoch": 0.46008119079837617,
      "grad_norm": 1.296875,
      "learning_rate": 1.8980066969599216e-05,
      "loss": 1.6337,
      "step": 85
    },
    {
      "epoch": 0.4871447902571042,
      "grad_norm": 1.25,
      "learning_rate": 1.8761237197594945e-05,
      "loss": 1.6549,
      "step": 90
    },
    {
      "epoch": 0.5142083897158322,
      "grad_norm": 1.25,
      "learning_rate": 1.852268012337514e-05,
      "loss": 1.6334,
      "step": 95
    },
    {
      "epoch": 0.5412719891745602,
      "grad_norm": 1.265625,
      "learning_rate": 1.8264932895677195e-05,
      "loss": 1.6276,
      "step": 100
    },
    {
      "epoch": 0.5683355886332883,
      "grad_norm": 1.2421875,
      "learning_rate": 1.798857587288445e-05,
      "loss": 1.6326,
      "step": 105
    },
    {
      "epoch": 0.5953991880920162,
      "grad_norm": 1.203125,
      "learning_rate": 1.769423131625808e-05,
      "loss": 1.6334,
      "step": 110
    },
    {
      "epoch": 0.6224627875507442,
      "grad_norm": 1.234375,
      "learning_rate": 1.738256198881809e-05,
      "loss": 1.6327,
      "step": 115
    },
    {
      "epoch": 0.6495263870094723,
      "grad_norm": 1.3125,
      "learning_rate": 1.7054269663028232e-05,
      "loss": 1.6271,
      "step": 120
    },
    {
      "epoch": 0.6765899864682002,
      "grad_norm": 1.25,
      "learning_rate": 1.6710093540645056e-05,
      "loss": 1.6247,
      "step": 125
    },
    {
      "epoch": 0.7036535859269283,
      "grad_norm": 1.296875,
      "learning_rate": 1.6350808588288964e-05,
      "loss": 1.6255,
      "step": 130
    },
    {
      "epoch": 0.7307171853856563,
      "grad_norm": 1.234375,
      "learning_rate": 1.597722379248512e-05,
      "loss": 1.6155,
      "step": 135
    },
    {
      "epoch": 0.7577807848443843,
      "grad_norm": 1.2421875,
      "learning_rate": 1.559018033810316e-05,
      "loss": 1.6162,
      "step": 140
    },
    {
      "epoch": 0.7848443843031123,
      "grad_norm": 1.21875,
      "learning_rate": 1.5190549714297303e-05,
      "loss": 1.6081,
      "step": 145
    },
    {
      "epoch": 0.8119079837618404,
      "grad_norm": 1.21875,
      "learning_rate": 1.4779231752211546e-05,
      "loss": 1.6031,
      "step": 150
    },
    {
      "epoch": 0.8389715832205683,
      "grad_norm": 1.28125,
      "learning_rate": 1.4357152598868478e-05,
      "loss": 1.6155,
      "step": 155
    },
    {
      "epoch": 0.8660351826792964,
      "grad_norm": 1.2109375,
      "learning_rate": 1.3925262631803722e-05,
      "loss": 1.6039,
      "step": 160
    },
    {
      "epoch": 0.8930987821380244,
      "grad_norm": 1.2265625,
      "learning_rate": 1.3484534319141592e-05,
      "loss": 1.608,
      "step": 165
    },
    {
      "epoch": 0.9201623815967523,
      "grad_norm": 1.1875,
      "learning_rate": 1.303596002993028e-05,
      "loss": 1.6036,
      "step": 170
    },
    {
      "epoch": 0.9472259810554804,
      "grad_norm": 1.2578125,
      "learning_rate": 1.2580549799667034e-05,
      "loss": 1.6157,
      "step": 175
    },
    {
      "epoch": 0.9742895805142084,
      "grad_norm": 1.2734375,
      "learning_rate": 1.2119329056044533e-05,
      "loss": 1.601,
      "step": 180
    },
    {
      "epoch": 0.9959404600811907,
      "eval_loss": 1.6971594095230103,
      "eval_runtime": 28.8094,
      "eval_samples_per_second": 15.099,
      "eval_steps_per_second": 1.909,
      "step": 184
    },
    {
      "epoch": 1.0013531799729365,
      "grad_norm": 1.21875,
      "learning_rate": 1.165333631003928e-05,
      "loss": 1.5923,
      "step": 185
    },
    {
      "epoch": 1.0284167794316643,
      "grad_norm": 1.2109375,
      "learning_rate": 1.1183620817540985e-05,
      "loss": 1.5652,
      "step": 190
    },
    {
      "epoch": 1.0554803788903924,
      "grad_norm": 1.2265625,
      "learning_rate": 1.0711240216788036e-05,
      "loss": 1.5483,
      "step": 195
    },
    {
      "epoch": 1.0825439783491204,
      "grad_norm": 1.2578125,
      "learning_rate": 1.0237258146928849e-05,
      "loss": 1.5504,
      "step": 200
    },
    {
      "epoch": 1.1096075778078485,
      "grad_norm": 1.21875,
      "learning_rate": 9.762741853071153e-06,
      "loss": 1.555,
      "step": 205
    },
    {
      "epoch": 1.1366711772665765,
      "grad_norm": 1.1796875,
      "learning_rate": 9.288759783211967e-06,
      "loss": 1.5659,
      "step": 210
    },
    {
      "epoch": 1.1637347767253043,
      "grad_norm": 1.2109375,
      "learning_rate": 8.81637918245902e-06,
      "loss": 1.5601,
      "step": 215
    },
    {
      "epoch": 1.1907983761840324,
      "grad_norm": 1.1640625,
      "learning_rate": 8.346663689960724e-06,
      "loss": 1.5516,
      "step": 220
    },
    {
      "epoch": 1.2178619756427604,
      "grad_norm": 1.171875,
      "learning_rate": 7.880670943955467e-06,
      "loss": 1.5542,
      "step": 225
    },
    {
      "epoch": 1.2449255751014885,
      "grad_norm": 1.203125,
      "learning_rate": 7.419450200332965e-06,
      "loss": 1.5491,
      "step": 230
    },
    {
      "epoch": 1.2719891745602165,
      "grad_norm": 1.1640625,
      "learning_rate": 6.964039970069722e-06,
      "loss": 1.5564,
      "step": 235
    },
    {
      "epoch": 1.2990527740189446,
      "grad_norm": 1.1796875,
      "learning_rate": 6.515465680858412e-06,
      "loss": 1.5584,
      "step": 240
    },
    {
      "epoch": 1.3261163734776726,
      "grad_norm": 1.21875,
      "learning_rate": 6.074737368196279e-06,
      "loss": 1.5534,
      "step": 245
    },
    {
      "epoch": 1.3531799729364005,
      "grad_norm": 1.2421875,
      "learning_rate": 5.642847401131526e-06,
      "loss": 1.5588,
      "step": 250
    },
    {
      "epoch": 1.3802435723951285,
      "grad_norm": 1.21875,
      "learning_rate": 5.220768247788458e-06,
      "loss": 1.552,
      "step": 255
    },
    {
      "epoch": 1.4073071718538566,
      "grad_norm": 1.1875,
      "learning_rate": 4.809450285702697e-06,
      "loss": 1.5462,
      "step": 260
    },
    {
      "epoch": 1.4343707713125846,
      "grad_norm": 1.203125,
      "learning_rate": 4.409819661896839e-06,
      "loss": 1.5623,
      "step": 265
    },
    {
      "epoch": 1.4614343707713127,
      "grad_norm": 1.2421875,
      "learning_rate": 4.022776207514885e-06,
      "loss": 1.5605,
      "step": 270
    },
    {
      "epoch": 1.4884979702300405,
      "grad_norm": 1.2265625,
      "learning_rate": 3.6491914117110405e-06,
      "loss": 1.5616,
      "step": 275
    },
    {
      "epoch": 1.5155615696887685,
      "grad_norm": 1.1875,
      "learning_rate": 3.2899064593549477e-06,
      "loss": 1.5578,
      "step": 280
    },
    {
      "epoch": 1.5426251691474966,
      "grad_norm": 1.1953125,
      "learning_rate": 2.945730336971767e-06,
      "loss": 1.5482,
      "step": 285
    },
    {
      "epoch": 1.5696887686062246,
      "grad_norm": 1.21875,
      "learning_rate": 2.6174380111819144e-06,
      "loss": 1.5559,
      "step": 290
    },
    {
      "epoch": 1.5967523680649527,
      "grad_norm": 1.21875,
      "learning_rate": 2.3057686837419246e-06,
      "loss": 1.5481,
      "step": 295
    },
    {
      "epoch": 1.6238159675236807,
      "grad_norm": 1.1640625,
      "learning_rate": 2.011424127115552e-06,
      "loss": 1.5412,
      "step": 300
    },
    {
      "epoch": 1.6508795669824088,
      "grad_norm": 1.234375,
      "learning_rate": 1.7350671043228072e-06,
      "loss": 1.5611,
      "step": 305
    },
    {
      "epoch": 1.6779431664411368,
      "grad_norm": 1.203125,
      "learning_rate": 1.4773198766248642e-06,
      "loss": 1.5669,
      "step": 310
    },
    {
      "epoch": 1.7050067658998647,
      "grad_norm": 1.2109375,
      "learning_rate": 1.2387628024050557e-06,
      "loss": 1.5515,
      "step": 315
    },
    {
      "epoch": 1.7320703653585927,
      "grad_norm": 1.2109375,
      "learning_rate": 1.0199330304007858e-06,
      "loss": 1.5633,
      "step": 320
    },
    {
      "epoch": 1.7591339648173205,
      "grad_norm": 1.234375,
      "learning_rate": 8.213232902287438e-07,
      "loss": 1.5542,
      "step": 325
    },
    {
      "epoch": 1.7861975642760486,
      "grad_norm": 1.2421875,
      "learning_rate": 6.433807829267491e-07,
      "loss": 1.5575,
      "step": 330
    },
    {
      "epoch": 1.8132611637347766,
      "grad_norm": 1.1953125,
      "learning_rate": 4.865061740103361e-07,
      "loss": 1.5532,
      "step": 335
    },
    {
      "epoch": 1.8403247631935047,
      "grad_norm": 1.21875,
      "learning_rate": 3.510526913114065e-07,
      "loss": 1.5686,
      "step": 340
    },
    {
      "epoch": 1.8673883626522327,
      "grad_norm": 1.1953125,
      "learning_rate": 2.3732532963024468e-07,
      "loss": 1.5484,
      "step": 345
    },
    {
      "epoch": 1.8944519621109608,
      "grad_norm": 1.1953125,
      "learning_rate": 1.4558016399181086e-07,
      "loss": 1.56,
      "step": 350
    },
    {
      "epoch": 1.9215155615696888,
      "grad_norm": 1.1953125,
      "learning_rate": 7.602377305258479e-08,
      "loss": 1.5479,
      "step": 355
    },
    {
      "epoch": 1.9485791610284169,
      "grad_norm": 1.1796875,
      "learning_rate": 2.8812773956256034e-08,
      "loss": 1.5456,
      "step": 360
    },
    {
      "epoch": 1.975642760487145,
      "grad_norm": 1.2265625,
      "learning_rate": 4.053469685617595e-09,
      "loss": 1.5526,
      "step": 365
    },
    {
      "epoch": 1.9918809201623815,
      "eval_loss": 1.697079062461853,
      "eval_runtime": 28.912,
      "eval_samples_per_second": 15.046,
      "eval_steps_per_second": 1.902,
      "step": 368
    },
    {
      "epoch": 1.9918809201623815,
      "step": 368,
      "total_flos": 1.4968483831454106e+17,
      "train_loss": 1.6339908747569374,
      "train_runtime": 3216.6871,
      "train_samples_per_second": 3.675,
      "train_steps_per_second": 0.114
    }
  ],
  "logging_steps": 5,
  "max_steps": 368,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4968483831454106e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}