{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9975121565079723,
  "eval_steps": 500,
  "global_step": 276,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03618681442949225,
      "grad_norm": 0.017299316823482513,
      "learning_rate": 0.00011111111111111112,
      "loss": 0.2656,
      "step": 5
    },
    {
      "epoch": 0.0723736288589845,
      "grad_norm": 0.007974148727953434,
      "learning_rate": 0.0001999930778307066,
      "loss": 0.0503,
      "step": 10
    },
    {
      "epoch": 0.10856044328847676,
      "grad_norm": 0.0037575585301965475,
      "learning_rate": 0.00019975090251507638,
      "loss": 0.0278,
      "step": 15
    },
    {
      "epoch": 0.144747257717969,
      "grad_norm": 0.002968734595924616,
      "learning_rate": 0.00019916357646713006,
      "loss": 0.0176,
      "step": 20
    },
    {
      "epoch": 0.18093407214746127,
      "grad_norm": 0.004215618595480919,
      "learning_rate": 0.00019823313190923795,
      "loss": 0.0166,
      "step": 25
    },
    {
      "epoch": 0.21712088657695353,
      "grad_norm": 0.0023846502881497145,
      "learning_rate": 0.00019696278829718883,
      "loss": 0.0119,
      "step": 30
    },
    {
      "epoch": 0.2533077010064458,
      "grad_norm": 0.005997045431286097,
      "learning_rate": 0.00019535694118046583,
      "loss": 0.011,
      "step": 35
    },
    {
      "epoch": 0.289494515435938,
      "grad_norm": 0.001673985505476594,
      "learning_rate": 0.0001934211469930896,
      "loss": 0.0106,
      "step": 40
    },
    {
      "epoch": 0.3256813298654303,
      "grad_norm": 0.002548367250710726,
      "learning_rate": 0.0001911621038276542,
      "loss": 0.0131,
      "step": 45
    },
    {
      "epoch": 0.36186814429492253,
      "grad_norm": 0.0018577200826257467,
      "learning_rate": 0.00018858762825907998,
      "loss": 0.0117,
      "step": 50
    },
    {
      "epoch": 0.39805495872441476,
      "grad_norm": 0.0021968537475913763,
      "learning_rate": 0.0001857066282982763,
      "loss": 0.0095,
      "step": 55
    },
    {
      "epoch": 0.43424177315390705,
      "grad_norm": 0.0027511760126799345,
      "learning_rate": 0.00018252907256929775,
      "loss": 0.0137,
      "step": 60
    },
    {
      "epoch": 0.4704285875833993,
      "grad_norm": 0.0011977142421528697,
      "learning_rate": 0.00017906595581664462,
      "loss": 0.011,
      "step": 65
    },
    {
      "epoch": 0.5066154020128916,
      "grad_norm": 0.0016937833279371262,
      "learning_rate": 0.00017532926086205727,
      "loss": 0.0103,
      "step": 70
    },
    {
      "epoch": 0.5428022164423838,
      "grad_norm": 0.0024764479603618383,
      "learning_rate": 0.00017133191714243805,
      "loss": 0.0091,
      "step": 75
    },
    {
      "epoch": 0.578989030871876,
      "grad_norm": 0.0016686960589140654,
      "learning_rate": 0.00016708775597236506,
      "loss": 0.0104,
      "step": 80
    },
    {
      "epoch": 0.6151758453013683,
      "grad_norm": 0.001507140463218093,
      "learning_rate": 0.00016261146268599564,
      "loss": 0.0082,
      "step": 85
    },
    {
      "epoch": 0.6513626597308606,
      "grad_norm": 0.0012602421920746565,
      "learning_rate": 0.00015791852582395334,
      "loss": 0.009,
      "step": 90
    },
    {
      "epoch": 0.6875494741603528,
      "grad_norm": 0.0012762637343257666,
      "learning_rate": 0.0001530251835410199,
      "loss": 0.01,
      "step": 95
    },
    {
      "epoch": 0.7237362885898451,
      "grad_norm": 0.0010322288144379854,
      "learning_rate": 0.00014794836742006666,
      "loss": 0.0067,
      "step": 100
    },
    {
      "epoch": 0.7599231030193373,
      "grad_norm": 0.0019885932561010122,
      "learning_rate": 0.0001427056438866376,
      "loss": 0.0082,
      "step": 105
    },
    {
      "epoch": 0.7961099174488295,
      "grad_norm": 0.001030433108098805,
      "learning_rate": 0.00013731515342689654,
      "loss": 0.0087,
      "step": 110
    },
    {
      "epoch": 0.8322967318783219,
      "grad_norm": 0.0009500011801719666,
      "learning_rate": 0.0001317955478192515,
      "loss": 0.007,
      "step": 115
    },
    {
      "epoch": 0.8684835463078141,
      "grad_norm": 0.0011772976722568274,
      "learning_rate": 0.0001261659255968441,
      "loss": 0.0104,
      "step": 120
    },
    {
      "epoch": 0.9046703607373063,
      "grad_norm": 0.0012133896816521883,
      "learning_rate": 0.00012044576596421002,
      "loss": 0.0097,
      "step": 125
    },
    {
      "epoch": 0.9408571751667986,
      "grad_norm": 0.001016512862406671,
      "learning_rate": 0.00011465486139676955,
      "loss": 0.0093,
      "step": 130
    },
    {
      "epoch": 0.9770439895962908,
      "grad_norm": 0.0013122924137860537,
      "learning_rate": 0.00010881324915636019,
      "loss": 0.0081,
      "step": 135
    },
    {
      "epoch": 1.0132308040257831,
      "grad_norm": 0.0009057120769284666,
      "learning_rate": 0.00010294114195977795,
      "loss": 0.0094,
      "step": 140
    },
    {
      "epoch": 1.0494176184552753,
      "grad_norm": 0.0010994576150551438,
      "learning_rate": 9.705885804022206e-05,
      "loss": 0.0071,
      "step": 145
    },
    {
      "epoch": 1.0856044328847676,
      "grad_norm": 0.0009362389100715518,
      "learning_rate": 9.118675084363986e-05,
      "loss": 0.0061,
      "step": 150
    },
    {
      "epoch": 1.12179124731426,
      "grad_norm": 0.001235711737535894,
      "learning_rate": 8.534513860323046e-05,
      "loss": 0.0067,
      "step": 155
    },
    {
      "epoch": 1.157978061743752,
      "grad_norm": 0.0010548752034083009,
      "learning_rate": 7.955423403578998e-05,
      "loss": 0.0065,
      "step": 160
    },
    {
      "epoch": 1.1941648761732444,
      "grad_norm": 0.0010509549174457788,
      "learning_rate": 7.383407440315596e-05,
      "loss": 0.006,
      "step": 165
    },
    {
      "epoch": 1.2303516906027365,
      "grad_norm": 0.0009265425032936037,
      "learning_rate": 6.820445218074849e-05,
      "loss": 0.005,
      "step": 170
    },
    {
      "epoch": 1.2665385050322289,
      "grad_norm": 0.0009228007984347641,
      "learning_rate": 6.26848465731035e-05,
      "loss": 0.0054,
      "step": 175
    },
    {
      "epoch": 1.3027253194617212,
      "grad_norm": 0.0008026002906262875,
      "learning_rate": 5.729435611336239e-05,
      "loss": 0.0077,
      "step": 180
    },
    {
      "epoch": 1.3389121338912133,
      "grad_norm": 0.0006433480884879827,
      "learning_rate": 5.205163257993341e-05,
      "loss": 0.0051,
      "step": 185
    },
    {
      "epoch": 1.3750989483207057,
      "grad_norm": 0.0009176199091598392,
      "learning_rate": 4.697481645898012e-05,
      "loss": 0.0068,
      "step": 190
    },
    {
      "epoch": 1.411285762750198,
      "grad_norm": 0.0009827411267906427,
      "learning_rate": 4.2081474176046646e-05,
      "loss": 0.0072,
      "step": 195
    },
    {
      "epoch": 1.4474725771796901,
      "grad_norm": 0.001098952954635024,
      "learning_rate": 3.738853731400439e-05,
      "loss": 0.0066,
      "step": 200
    },
    {
      "epoch": 1.4836593916091825,
      "grad_norm": 0.001120549044571817,
      "learning_rate": 3.291224402763495e-05,
      "loss": 0.0069,
      "step": 205
    },
    {
      "epoch": 1.5198462060386748,
      "grad_norm": 0.0010113946627825499,
      "learning_rate": 2.8668082857562005e-05,
      "loss": 0.0058,
      "step": 210
    },
    {
      "epoch": 1.556033020468167,
      "grad_norm": 0.0006556404987350106,
      "learning_rate": 2.467073913794272e-05,
      "loss": 0.0065,
      "step": 215
    },
    {
      "epoch": 1.592219834897659,
      "grad_norm": 0.0013271564384922385,
      "learning_rate": 2.0934044183355383e-05,
      "loss": 0.0055,
      "step": 220
    },
    {
      "epoch": 1.6284066493271514,
      "grad_norm": 0.0009260373772121966,
      "learning_rate": 1.7470927430702277e-05,
      "loss": 0.0065,
      "step": 225
    },
    {
      "epoch": 1.6645934637566437,
      "grad_norm": 0.0008944201981648803,
      "learning_rate": 1.4293371701723702e-05,
      "loss": 0.0049,
      "step": 230
    },
    {
      "epoch": 1.7007802781861359,
      "grad_norm": 0.0013539205538108945,
      "learning_rate": 1.1412371740920036e-05,
      "loss": 0.0057,
      "step": 235
    },
    {
      "epoch": 1.7369670926156282,
      "grad_norm": 0.0013567405985668302,
      "learning_rate": 8.837896172345827e-06,
      "loss": 0.007,
      "step": 240
    },
    {
      "epoch": 1.7731539070451205,
      "grad_norm": 0.0009066512575373054,
      "learning_rate": 6.578853006910402e-06,
      "loss": 0.0059,
      "step": 245
    },
    {
      "epoch": 1.8093407214746127,
      "grad_norm": 0.0008445039275102317,
      "learning_rate": 4.643058819534185e-06,
      "loss": 0.006,
      "step": 250
    },
    {
      "epoch": 1.8455275359041048,
      "grad_norm": 0.001150821102783084,
      "learning_rate": 3.0372117028111825e-06,
      "loss": 0.0067,
      "step": 255
    },
    {
      "epoch": 1.8817143503335974,
      "grad_norm": 0.0007717085536569357,
      "learning_rate": 1.766868090762075e-06,
      "loss": 0.0054,
      "step": 260
    },
    {
      "epoch": 1.9179011647630895,
      "grad_norm": 0.0008303712238557637,
      "learning_rate": 8.364235328699566e-07,
      "loss": 0.0056,
      "step": 265
    },
    {
      "epoch": 1.9540879791925816,
      "grad_norm": 0.0007604911224916577,
      "learning_rate": 2.490974849236216e-07,
      "loss": 0.0048,
      "step": 270
    },
    {
      "epoch": 1.990274793622074,
      "grad_norm": 0.0010599087690934539,
      "learning_rate": 6.922169293421821e-09,
      "loss": 0.0065,
      "step": 275
    },
    {
      "epoch": 1.9975121565079723,
      "step": 276,
      "total_flos": 3.6366798218312076e+20,
      "train_loss": 0.014006755621833861,
      "train_runtime": 58629.8958,
      "train_samples_per_second": 0.302,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 5,
  "max_steps": 276,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.6366798218312076e+20,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}