{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01171929361957708,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002343858723915416,
      "grad_norm": 7.478665351867676,
      "learning_rate": 1.40625e-07,
      "loss": 0.6732528686523438,
      "step": 10
    },
    {
      "epoch": 0.0004687717447830832,
      "grad_norm": 7.584623336791992,
      "learning_rate": 2.96875e-07,
      "loss": 0.66597900390625,
      "step": 20
    },
    {
      "epoch": 0.0007031576171746248,
      "grad_norm": 6.306713581085205,
      "learning_rate": 4.53125e-07,
      "loss": 0.6197677612304687,
      "step": 30
    },
    {
      "epoch": 0.0009375434895661664,
      "grad_norm": 4.607383728027344,
      "learning_rate": 6.09375e-07,
      "loss": 0.5319419860839844,
      "step": 40
    },
    {
      "epoch": 0.001171929361957708,
      "grad_norm": 2.3062853813171387,
      "learning_rate": 7.656250000000001e-07,
      "loss": 0.42061538696289064,
      "step": 50
    },
    {
      "epoch": 0.0014063152343492496,
      "grad_norm": 1.4863656759262085,
      "learning_rate": 9.218750000000002e-07,
      "loss": 0.3130531311035156,
      "step": 60
    },
    {
      "epoch": 0.0016407011067407912,
      "grad_norm": 0.8237831592559814,
      "learning_rate": 1.0781250000000002e-06,
      "loss": 0.23311138153076172,
      "step": 70
    },
    {
      "epoch": 0.0018750869791323327,
      "grad_norm": 0.6643654704093933,
      "learning_rate": 1.2343750000000001e-06,
      "loss": 0.2020857810974121,
      "step": 80
    },
    {
      "epoch": 0.0021094728515238742,
      "grad_norm": 0.5149619579315186,
      "learning_rate": 1.3906250000000001e-06,
      "loss": 0.18220624923706055,
      "step": 90
    },
    {
      "epoch": 0.002343858723915416,
      "grad_norm": 0.5113442540168762,
      "learning_rate": 1.5468750000000001e-06,
      "loss": 0.16905088424682618,
      "step": 100
    },
    {
      "epoch": 0.0025782445963069577,
      "grad_norm": 0.5090538859367371,
      "learning_rate": 1.703125e-06,
      "loss": 0.16316838264465333,
      "step": 110
    },
    {
      "epoch": 0.0028126304686984993,
      "grad_norm": 0.4110700190067291,
      "learning_rate": 1.8593750000000003e-06,
      "loss": 0.1580258846282959,
      "step": 120
    },
    {
      "epoch": 0.003047016341090041,
      "grad_norm": 0.5005377531051636,
      "learning_rate": 2.0156250000000003e-06,
      "loss": 0.14841842651367188,
      "step": 130
    },
    {
      "epoch": 0.0032814022134815823,
      "grad_norm": 0.4914725124835968,
      "learning_rate": 2.1718750000000003e-06,
      "loss": 0.14541361331939698,
      "step": 140
    },
    {
      "epoch": 0.003515788085873124,
      "grad_norm": 0.5155150294303894,
      "learning_rate": 2.3281250000000003e-06,
      "loss": 0.14492216110229492,
      "step": 150
    },
    {
      "epoch": 0.0037501739582646654,
      "grad_norm": 0.4690794050693512,
      "learning_rate": 2.4843750000000002e-06,
      "loss": 0.14195268154144286,
      "step": 160
    },
    {
      "epoch": 0.003984559830656207,
      "grad_norm": 0.50107342004776,
      "learning_rate": 2.640625e-06,
      "loss": 0.1428708553314209,
      "step": 170
    },
    {
      "epoch": 0.0042189457030477485,
      "grad_norm": 0.48859548568725586,
      "learning_rate": 2.796875e-06,
      "loss": 0.14226298332214354,
      "step": 180
    },
    {
      "epoch": 0.0044533315754392904,
      "grad_norm": 0.5123774409294128,
      "learning_rate": 2.953125e-06,
      "loss": 0.1370567798614502,
      "step": 190
    },
    {
      "epoch": 0.004687717447830832,
      "grad_norm": 0.4833315312862396,
      "learning_rate": 3.109375e-06,
      "loss": 0.1390127420425415,
      "step": 200
    },
    {
      "epoch": 0.0049221033202223735,
      "grad_norm": 0.43915465474128723,
      "learning_rate": 3.265625e-06,
      "loss": 0.13475892543792725,
      "step": 210
    },
    {
      "epoch": 0.0051564891926139155,
      "grad_norm": 0.46104806661605835,
      "learning_rate": 3.421875e-06,
      "loss": 0.13139626979827881,
      "step": 220
    },
    {
      "epoch": 0.005390875065005457,
      "grad_norm": 0.5122255086898804,
      "learning_rate": 3.578125e-06,
      "loss": 0.13110661506652832,
      "step": 230
    },
    {
      "epoch": 0.0056252609373969985,
      "grad_norm": 0.48517927527427673,
      "learning_rate": 3.734375e-06,
      "loss": 0.12811717987060547,
      "step": 240
    },
    {
      "epoch": 0.00585964680978854,
      "grad_norm": 0.4835013449192047,
      "learning_rate": 3.890625e-06,
      "loss": 0.13097090721130372,
      "step": 250
    },
    {
      "epoch": 0.006094032682180082,
      "grad_norm": 0.4820455312728882,
      "learning_rate": 4.046875e-06,
      "loss": 0.12818758487701415,
      "step": 260
    },
    {
      "epoch": 0.006328418554571624,
      "grad_norm": 0.44813403487205505,
      "learning_rate": 4.2031250000000005e-06,
      "loss": 0.12801458835601806,
      "step": 270
    },
    {
      "epoch": 0.006562804426963165,
      "grad_norm": 0.5279086232185364,
      "learning_rate": 4.359375e-06,
      "loss": 0.12751049995422364,
      "step": 280
    },
    {
      "epoch": 0.006797190299354707,
      "grad_norm": 0.42281895875930786,
      "learning_rate": 4.5156250000000005e-06,
      "loss": 0.13442916870117189,
      "step": 290
    },
    {
      "epoch": 0.007031576171746248,
      "grad_norm": 0.4167884588241577,
      "learning_rate": 4.671875e-06,
      "loss": 0.12415478229522706,
      "step": 300
    },
    {
      "epoch": 0.00726596204413779,
      "grad_norm": 0.4328134059906006,
      "learning_rate": 4.8281250000000005e-06,
      "loss": 0.12891750335693358,
      "step": 310
    },
    {
      "epoch": 0.007500347916529331,
      "grad_norm": 0.45806413888931274,
      "learning_rate": 4.984375e-06,
      "loss": 0.12102985382080078,
      "step": 320
    },
    {
      "epoch": 0.007734733788920873,
      "grad_norm": 0.5078896880149841,
      "learning_rate": 5.1406250000000004e-06,
      "loss": 0.12243216037750244,
      "step": 330
    },
    {
      "epoch": 0.007969119661312415,
      "grad_norm": 0.527930498123169,
      "learning_rate": 5.296875e-06,
      "loss": 0.12513620853424073,
      "step": 340
    },
    {
      "epoch": 0.008203505533703956,
      "grad_norm": 0.431318461894989,
      "learning_rate": 5.453125e-06,
      "loss": 0.12151198387145996,
      "step": 350
    },
    {
      "epoch": 0.008437891406095497,
      "grad_norm": 0.4996262788772583,
      "learning_rate": 5.609375e-06,
      "loss": 0.11847388744354248,
      "step": 360
    },
    {
      "epoch": 0.00867227727848704,
      "grad_norm": 0.4818030893802643,
      "learning_rate": 5.765625e-06,
      "loss": 0.1227838158607483,
      "step": 370
    },
    {
      "epoch": 0.008906663150878581,
      "grad_norm": 0.4577305018901825,
      "learning_rate": 5.921875e-06,
      "loss": 0.1199771523475647,
      "step": 380
    },
    {
      "epoch": 0.009141049023270122,
      "grad_norm": 0.48360294103622437,
      "learning_rate": 6.078125e-06,
      "loss": 0.11903550624847412,
      "step": 390
    },
    {
      "epoch": 0.009375434895661665,
      "grad_norm": 0.47577178478240967,
      "learning_rate": 6.234375e-06,
      "loss": 0.12074012756347656,
      "step": 400
    },
    {
      "epoch": 0.009609820768053206,
      "grad_norm": 0.4833427369594574,
      "learning_rate": 6.390625e-06,
      "loss": 0.12326394319534302,
      "step": 410
    },
    {
      "epoch": 0.009844206640444747,
      "grad_norm": 0.43909400701522827,
      "learning_rate": 6.546875e-06,
      "loss": 0.11921967267990112,
      "step": 420
    },
    {
      "epoch": 0.010078592512836288,
      "grad_norm": 0.5028750896453857,
      "learning_rate": 6.703125e-06,
      "loss": 0.12188574075698852,
      "step": 430
    },
    {
      "epoch": 0.010312978385227831,
      "grad_norm": 0.47389668226242065,
      "learning_rate": 6.859375000000001e-06,
      "loss": 0.1192385196685791,
      "step": 440
    },
    {
      "epoch": 0.010547364257619372,
      "grad_norm": 0.5239953398704529,
      "learning_rate": 7.015625e-06,
      "loss": 0.11499193906784058,
      "step": 450
    },
    {
      "epoch": 0.010781750130010913,
      "grad_norm": 0.5061202645301819,
      "learning_rate": 7.171875000000001e-06,
      "loss": 0.11584588289260864,
      "step": 460
    },
    {
      "epoch": 0.011016136002402456,
      "grad_norm": 0.4635751247406006,
      "learning_rate": 7.328125e-06,
      "loss": 0.11434779167175294,
      "step": 470
    },
    {
      "epoch": 0.011250521874793997,
      "grad_norm": 0.4353443682193756,
      "learning_rate": 7.484375000000001e-06,
      "loss": 0.11755821704864503,
      "step": 480
    },
    {
      "epoch": 0.011484907747185538,
      "grad_norm": 0.41028693318367004,
      "learning_rate": 7.640625000000001e-06,
      "loss": 0.11704204082489014,
      "step": 490
    },
    {
      "epoch": 0.01171929361957708,
      "grad_norm": 0.4426499009132385,
      "learning_rate": 7.796875e-06,
      "loss": 0.11789888143539429,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 42665,
  "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": 2.1936814887618478e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}