{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 303,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01652892561983471,
      "grad_norm": 1.4201081991195679,
      "learning_rate": 1.5789473684210526e-06,
      "loss": 1.3341,
      "step": 5
    },
    {
      "epoch": 0.03305785123966942,
      "grad_norm": 0.8825254440307617,
      "learning_rate": 3.5526315789473683e-06,
      "loss": 1.3559,
      "step": 10
    },
    {
      "epoch": 0.049586776859504134,
      "grad_norm": 0.6610410213470459,
      "learning_rate": 5.526315789473684e-06,
      "loss": 1.3433,
      "step": 15
    },
    {
      "epoch": 0.06611570247933884,
      "grad_norm": 0.6865679025650024,
      "learning_rate": 7.5e-06,
      "loss": 1.2905,
      "step": 20
    },
    {
      "epoch": 0.08264462809917356,
      "grad_norm": 0.5552710294723511,
      "learning_rate": 9.473684210526315e-06,
      "loss": 1.3332,
      "step": 25
    },
    {
      "epoch": 0.09917355371900827,
      "grad_norm": 0.5776343941688538,
      "learning_rate": 1.1447368421052632e-05,
      "loss": 1.2557,
      "step": 30
    },
    {
      "epoch": 0.11570247933884298,
      "grad_norm": 0.4994240701198578,
      "learning_rate": 1.3421052631578948e-05,
      "loss": 1.2805,
      "step": 35
    },
    {
      "epoch": 0.1322314049586777,
      "grad_norm": 0.5451419353485107,
      "learning_rate": 1.5394736842105264e-05,
      "loss": 1.2875,
      "step": 40
    },
    {
      "epoch": 0.1487603305785124,
      "grad_norm": 0.5521426200866699,
      "learning_rate": 1.736842105263158e-05,
      "loss": 1.2729,
      "step": 45
    },
    {
      "epoch": 0.1652892561983471,
      "grad_norm": 0.448354572057724,
      "learning_rate": 1.9342105263157896e-05,
      "loss": 1.2043,
      "step": 50
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.5871981978416443,
      "learning_rate": 2.1315789473684212e-05,
      "loss": 1.1982,
      "step": 55
    },
    {
      "epoch": 0.19834710743801653,
      "grad_norm": 0.5270593762397766,
      "learning_rate": 2.3289473684210525e-05,
      "loss": 1.2128,
      "step": 60
    },
    {
      "epoch": 0.21487603305785125,
      "grad_norm": 0.513990044593811,
      "learning_rate": 2.526315789473684e-05,
      "loss": 1.1809,
      "step": 65
    },
    {
      "epoch": 0.23140495867768596,
      "grad_norm": 0.5345117449760437,
      "learning_rate": 2.723684210526316e-05,
      "loss": 1.2193,
      "step": 70
    },
    {
      "epoch": 0.24793388429752067,
      "grad_norm": 0.4606321454048157,
      "learning_rate": 2.9210526315789474e-05,
      "loss": 1.1448,
      "step": 75
    },
    {
      "epoch": 0.2644628099173554,
      "grad_norm": 0.46585503220558167,
      "learning_rate": 2.9999678278282968e-05,
      "loss": 1.1272,
      "step": 80
    },
    {
      "epoch": 0.2809917355371901,
      "grad_norm": 0.5272030234336853,
      "learning_rate": 2.9997712251100747e-05,
      "loss": 1.1208,
      "step": 85
    },
    {
      "epoch": 0.2975206611570248,
      "grad_norm": 0.5860956311225891,
      "learning_rate": 2.9993959165002407e-05,
      "loss": 1.0957,
      "step": 90
    },
    {
      "epoch": 0.3140495867768595,
      "grad_norm": 0.7299471497535706,
      "learning_rate": 2.998841946718855e-05,
      "loss": 1.1043,
      "step": 95
    },
    {
      "epoch": 0.3305785123966942,
      "grad_norm": 0.5312178134918213,
      "learning_rate": 2.9981093817744277e-05,
      "loss": 1.1348,
      "step": 100
    },
    {
      "epoch": 0.34710743801652894,
      "grad_norm": 0.7180105447769165,
      "learning_rate": 2.997198308956052e-05,
      "loss": 1.0544,
      "step": 105
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.6310957670211792,
      "learning_rate": 2.9961088368230065e-05,
      "loss": 1.0619,
      "step": 110
    },
    {
      "epoch": 0.38016528925619836,
      "grad_norm": 0.586087703704834,
      "learning_rate": 2.9948410951918154e-05,
      "loss": 1.0515,
      "step": 115
    },
    {
      "epoch": 0.39669421487603307,
      "grad_norm": 0.6914042830467224,
      "learning_rate": 2.993395235120784e-05,
      "loss": 1.0209,
      "step": 120
    },
    {
      "epoch": 0.4132231404958678,
      "grad_norm": 0.6734358668327332,
      "learning_rate": 2.991771428891996e-05,
      "loss": 0.9988,
      "step": 125
    },
    {
      "epoch": 0.4297520661157025,
      "grad_norm": 0.68830806016922,
      "learning_rate": 2.989969869990789e-05,
      "loss": 1.0326,
      "step": 130
    },
    {
      "epoch": 0.4462809917355372,
      "grad_norm": 0.7114909291267395,
      "learning_rate": 2.9879907730826946e-05,
      "loss": 1.0411,
      "step": 135
    },
    {
      "epoch": 0.4628099173553719,
      "grad_norm": 0.6947762370109558,
      "learning_rate": 2.9858343739878657e-05,
      "loss": 0.945,
      "step": 140
    },
    {
      "epoch": 0.4793388429752066,
      "grad_norm": 0.7105550765991211,
      "learning_rate": 2.9835009296529717e-05,
      "loss": 0.9779,
      "step": 145
    },
    {
      "epoch": 0.49586776859504134,
      "grad_norm": 0.9549520015716553,
      "learning_rate": 2.980990718120587e-05,
      "loss": 0.9691,
      "step": 150
    },
    {
      "epoch": 0.512396694214876,
      "grad_norm": 0.7530831694602966,
      "learning_rate": 2.978304038496056e-05,
      "loss": 0.961,
      "step": 155
    },
    {
      "epoch": 0.5289256198347108,
      "grad_norm": 0.7150148153305054,
      "learning_rate": 2.975441210911856e-05,
      "loss": 0.9344,
      "step": 160
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.6854411959648132,
      "learning_rate": 2.9724025764894513e-05,
      "loss": 0.9801,
      "step": 165
    },
    {
      "epoch": 0.5619834710743802,
      "grad_norm": 0.8350316286087036,
      "learning_rate": 2.9691884972986458e-05,
      "loss": 0.898,
      "step": 170
    },
    {
      "epoch": 0.5785123966942148,
      "grad_norm": 0.8690942525863647,
      "learning_rate": 2.965799356314441e-05,
      "loss": 0.911,
      "step": 175
    },
    {
      "epoch": 0.5950413223140496,
      "grad_norm": 0.796727180480957,
      "learning_rate": 2.9622355573714036e-05,
      "loss": 0.8893,
      "step": 180
    },
    {
      "epoch": 0.6115702479338843,
      "grad_norm": 0.8369293212890625,
      "learning_rate": 2.9584975251155434e-05,
      "loss": 0.8583,
      "step": 185
    },
    {
      "epoch": 0.628099173553719,
      "grad_norm": 0.9035501480102539,
      "learning_rate": 2.954585704953717e-05,
      "loss": 0.9182,
      "step": 190
    },
    {
      "epoch": 0.6446280991735537,
      "grad_norm": 0.8341655135154724,
      "learning_rate": 2.950500563000555e-05,
      "loss": 0.8838,
      "step": 195
    },
    {
      "epoch": 0.6611570247933884,
      "grad_norm": 0.8167555332183838,
      "learning_rate": 2.946242586022921e-05,
      "loss": 0.8592,
      "step": 200
    },
    {
      "epoch": 0.6776859504132231,
      "grad_norm": 0.958501398563385,
      "learning_rate": 2.94181228138191e-05,
      "loss": 0.8798,
      "step": 205
    },
    {
      "epoch": 0.6942148760330579,
      "grad_norm": 0.8715956807136536,
      "learning_rate": 2.9372101769723958e-05,
      "loss": 0.8307,
      "step": 210
    },
    {
      "epoch": 0.7107438016528925,
      "grad_norm": 0.8931337594985962,
      "learning_rate": 2.9324368211601284e-05,
      "loss": 0.8488,
      "step": 215
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.9372528791427612,
      "learning_rate": 2.9274927827163913e-05,
      "loss": 0.8181,
      "step": 220
    },
    {
      "epoch": 0.743801652892562,
      "grad_norm": 0.9352923631668091,
      "learning_rate": 2.9223786507502333e-05,
      "loss": 0.7852,
      "step": 225
    },
    {
      "epoch": 0.7603305785123967,
      "grad_norm": 1.0228369235992432,
      "learning_rate": 2.917095034638269e-05,
      "loss": 0.7731,
      "step": 230
    },
    {
      "epoch": 0.7768595041322314,
      "grad_norm": 1.1870708465576172,
      "learning_rate": 2.9116425639520713e-05,
      "loss": 0.8079,
      "step": 235
    },
    {
      "epoch": 0.7933884297520661,
      "grad_norm": 0.933369517326355,
      "learning_rate": 2.9060218883831517e-05,
      "loss": 0.7646,
      "step": 240
    },
    {
      "epoch": 0.8099173553719008,
      "grad_norm": 1.1031955480575562,
      "learning_rate": 2.9002336776655494e-05,
      "loss": 0.7794,
      "step": 245
    },
    {
      "epoch": 0.8264462809917356,
      "grad_norm": 0.9256858229637146,
      "learning_rate": 2.894278621496025e-05,
      "loss": 0.7541,
      "step": 250
    },
    {
      "epoch": 0.8429752066115702,
      "grad_norm": 1.17303466796875,
      "learning_rate": 2.888157429451883e-05,
      "loss": 0.7456,
      "step": 255
    },
    {
      "epoch": 0.859504132231405,
      "grad_norm": 1.0275311470031738,
      "learning_rate": 2.88187083090642e-05,
      "loss": 0.7497,
      "step": 260
    },
    {
      "epoch": 0.8760330578512396,
      "grad_norm": 0.9848041534423828,
      "learning_rate": 2.8754195749420145e-05,
      "loss": 0.7138,
      "step": 265
    },
    {
      "epoch": 0.8925619834710744,
      "grad_norm": 1.0821123123168945,
      "learning_rate": 2.8688044302608735e-05,
      "loss": 0.7326,
      "step": 270
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.0524564981460571,
      "learning_rate": 2.8620261850934338e-05,
      "loss": 0.6945,
      "step": 275
    },
    {
      "epoch": 0.9256198347107438,
      "grad_norm": 1.1582773923873901,
      "learning_rate": 2.8550856471044415e-05,
      "loss": 0.7245,
      "step": 280
    },
    {
      "epoch": 0.9421487603305785,
      "grad_norm": 0.9988569617271423,
      "learning_rate": 2.847983643296715e-05,
      "loss": 0.7613,
      "step": 285
    },
    {
      "epoch": 0.9586776859504132,
      "grad_norm": 1.1030054092407227,
      "learning_rate": 2.840721019912602e-05,
      "loss": 0.6793,
      "step": 290
    },
    {
      "epoch": 0.9752066115702479,
      "grad_norm": 1.0013433694839478,
      "learning_rate": 2.833298642333146e-05,
      "loss": 0.7052,
      "step": 295
    },
    {
      "epoch": 0.9917355371900827,
      "grad_norm": 1.1024919748306274,
      "learning_rate": 2.8257173949749703e-05,
      "loss": 0.7322,
      "step": 300
    }
  ],
  "logging_steps": 5,
  "max_steps": 1515,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.2486090752537395e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}