{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 278,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017985611510791366,
      "grad_norm": 24.75,
      "learning_rate": 8.888888888888888e-06,
      "loss": 2.950368309020996,
      "step": 5
    },
    {
      "epoch": 0.03597122302158273,
      "grad_norm": 8.4375,
      "learning_rate": 2e-05,
      "loss": 2.4953432083129883,
      "step": 10
    },
    {
      "epoch": 0.0539568345323741,
      "grad_norm": 3.875,
      "learning_rate": 1.9982955597229275e-05,
      "loss": 2.1284584045410155,
      "step": 15
    },
    {
      "epoch": 0.07194244604316546,
      "grad_norm": 2.875,
      "learning_rate": 1.9931880491250263e-05,
      "loss": 1.9327747344970703,
      "step": 20
    },
    {
      "epoch": 0.08992805755395683,
      "grad_norm": 2.28125,
      "learning_rate": 1.9846948790998532e-05,
      "loss": 1.813704490661621,
      "step": 25
    },
    {
      "epoch": 0.1079136690647482,
      "grad_norm": 2.484375,
      "learning_rate": 1.9728450018495506e-05,
      "loss": 1.739830207824707,
      "step": 30
    },
    {
      "epoch": 0.12589928057553956,
      "grad_norm": 2.1875,
      "learning_rate": 1.9576788121902457e-05,
      "loss": 1.7107593536376953,
      "step": 35
    },
    {
      "epoch": 0.14388489208633093,
      "grad_norm": 2.109375,
      "learning_rate": 1.9392480098509488e-05,
      "loss": 1.6636060714721679,
      "step": 40
    },
    {
      "epoch": 0.1618705035971223,
      "grad_norm": 1.9765625,
      "learning_rate": 1.9176154232353513e-05,
      "loss": 1.6550146102905274,
      "step": 45
    },
    {
      "epoch": 0.17985611510791366,
      "grad_norm": 2.15625,
      "learning_rate": 1.8928547952473037e-05,
      "loss": 1.620616340637207,
      "step": 50
    },
    {
      "epoch": 0.19784172661870503,
      "grad_norm": 2.109375,
      "learning_rate": 1.865050531910062e-05,
      "loss": 1.5874693870544434,
      "step": 55
    },
    {
      "epoch": 0.2158273381294964,
      "grad_norm": 1.828125,
      "learning_rate": 1.8342974146362397e-05,
      "loss": 1.5906153678894044,
      "step": 60
    },
    {
      "epoch": 0.23381294964028776,
      "grad_norm": 1.9921875,
      "learning_rate": 1.80070027712929e-05,
      "loss": 1.5618690490722655,
      "step": 65
    },
    {
      "epoch": 0.2517985611510791,
      "grad_norm": 2.046875,
      "learning_rate": 1.7643736480179353e-05,
      "loss": 1.560389232635498,
      "step": 70
    },
    {
      "epoch": 0.2697841726618705,
      "grad_norm": 2.015625,
      "learning_rate": 1.725441360441752e-05,
      "loss": 1.5437555313110352,
      "step": 75
    },
    {
      "epoch": 0.28776978417266186,
      "grad_norm": 2.1875,
      "learning_rate": 1.684036129918786e-05,
      "loss": 1.523001766204834,
      "step": 80
    },
    {
      "epoch": 0.3057553956834532,
      "grad_norm": 2.203125,
      "learning_rate": 1.6402991019342073e-05,
      "loss": 1.5343033790588378,
      "step": 85
    },
    {
      "epoch": 0.3237410071942446,
      "grad_norm": 2.203125,
      "learning_rate": 1.5943793707922086e-05,
      "loss": 1.5191097259521484,
      "step": 90
    },
    {
      "epoch": 0.34172661870503596,
      "grad_norm": 2.0625,
      "learning_rate": 1.5464334713713312e-05,
      "loss": 1.5029571533203125,
      "step": 95
    },
    {
      "epoch": 0.3597122302158273,
      "grad_norm": 1.9140625,
      "learning_rate": 1.4966248455157622e-05,
      "loss": 1.5281996726989746,
      "step": 100
    },
    {
      "epoch": 0.3776978417266187,
      "grad_norm": 1.9140625,
      "learning_rate": 1.445123284881609e-05,
      "loss": 1.5251441955566407,
      "step": 105
    },
    {
      "epoch": 0.39568345323741005,
      "grad_norm": 2.03125,
      "learning_rate": 1.392104352137426e-05,
      "loss": 1.5085590362548829,
      "step": 110
    },
    {
      "epoch": 0.4136690647482014,
      "grad_norm": 2.1875,
      "learning_rate": 1.3377487824920459e-05,
      "loss": 1.500697422027588,
      "step": 115
    },
    {
      "epoch": 0.4316546762589928,
      "grad_norm": 2.015625,
      "learning_rate": 1.2822418675898428e-05,
      "loss": 1.4779583930969238,
      "step": 120
    },
    {
      "epoch": 0.44964028776978415,
      "grad_norm": 2.125,
      "learning_rate": 1.2257728238736468e-05,
      "loss": 1.4670068740844726,
      "step": 125
    },
    {
      "epoch": 0.4676258992805755,
      "grad_norm": 1.9609375,
      "learning_rate": 1.1685341475684935e-05,
      "loss": 1.489361572265625,
      "step": 130
    },
    {
      "epoch": 0.4856115107913669,
      "grad_norm": 2.015625,
      "learning_rate": 1.1107209584849845e-05,
      "loss": 1.4737789154052734,
      "step": 135
    },
    {
      "epoch": 0.5035971223021583,
      "grad_norm": 2.015625,
      "learning_rate": 1.0525303348791599e-05,
      "loss": 1.4690287590026856,
      "step": 140
    },
    {
      "epoch": 0.5215827338129496,
      "grad_norm": 2.25,
      "learning_rate": 9.94160641636263e-06,
      "loss": 1.49021577835083,
      "step": 145
    },
    {
      "epoch": 0.539568345323741,
      "grad_norm": 2.109375,
      "learning_rate": 9.358108540685406e-06,
      "loss": 1.4638582229614259,
      "step": 150
    },
    {
      "epoch": 0.5575539568345323,
      "grad_norm": 2.046875,
      "learning_rate": 8.776798796321715e-06,
      "loss": 1.4586694717407227,
      "step": 155
    },
    {
      "epoch": 0.5755395683453237,
      "grad_norm": 1.9921875,
      "learning_rate": 8.199658798755048e-06,
      "loss": 1.479645347595215,
      "step": 160
    },
    {
      "epoch": 0.5935251798561151,
      "grad_norm": 1.96875,
      "learning_rate": 7.628655949300133e-06,
      "loss": 1.455679225921631,
      "step": 165
    },
    {
      "epoch": 0.6115107913669064,
      "grad_norm": 1.9921875,
      "learning_rate": 7.065736728466832e-06,
      "loss": 1.4653221130371095,
      "step": 170
    },
    {
      "epoch": 0.6294964028776978,
      "grad_norm": 2.0,
      "learning_rate": 6.512820060640608e-06,
      "loss": 1.4618860244750977,
      "step": 175
    },
    {
      "epoch": 0.6474820143884892,
      "grad_norm": 1.8671875,
      "learning_rate": 5.971790772698467e-06,
      "loss": 1.449009895324707,
      "step": 180
    },
    {
      "epoch": 0.6654676258992805,
      "grad_norm": 1.9609375,
      "learning_rate": 5.444493168859304e-06,
      "loss": 1.449843692779541,
      "step": 185
    },
    {
      "epoch": 0.6834532374100719,
      "grad_norm": 2.015625,
      "learning_rate": 4.932724743671089e-06,
      "loss": 1.459362506866455,
      "step": 190
    },
    {
      "epoch": 0.7014388489208633,
      "grad_norm": 1.96875,
      "learning_rate": 4.438230054566678e-06,
      "loss": 1.470369243621826,
      "step": 195
    },
    {
      "epoch": 0.7194244604316546,
      "grad_norm": 1.9140625,
      "learning_rate": 3.96269477487588e-06,
      "loss": 1.4958831787109375,
      "step": 200
    },
    {
      "epoch": 0.737410071942446,
      "grad_norm": 1.984375,
      "learning_rate": 3.5077399475664474e-06,
      "loss": 1.4567132949829102,
      "step": 205
    },
    {
      "epoch": 0.7553956834532374,
      "grad_norm": 1.953125,
      "learning_rate": 3.074916459302211e-06,
      "loss": 1.4700736045837401,
      "step": 210
    },
    {
      "epoch": 0.7733812949640287,
      "grad_norm": 2.21875,
      "learning_rate": 2.665699753655684e-06,
      "loss": 1.442730712890625,
      "step": 215
    },
    {
      "epoch": 0.7913669064748201,
      "grad_norm": 1.9609375,
      "learning_rate": 2.281484801497186e-06,
      "loss": 1.464546012878418,
      "step": 220
    },
    {
      "epoch": 0.8093525179856115,
      "grad_norm": 2.0,
      "learning_rate": 1.923581345705736e-06,
      "loss": 1.4540756225585938,
      "step": 225
    },
    {
      "epoch": 0.8273381294964028,
      "grad_norm": 2.1875,
      "learning_rate": 1.5932094364120453e-06,
      "loss": 1.4824945449829101,
      "step": 230
    },
    {
      "epoch": 0.8453237410071942,
      "grad_norm": 1.765625,
      "learning_rate": 1.291495271993337e-06,
      "loss": 1.4647997856140136,
      "step": 235
    },
    {
      "epoch": 0.8633093525179856,
      "grad_norm": 1.8046875,
      "learning_rate": 1.0194673599976134e-06,
      "loss": 1.4619410514831543,
      "step": 240
    },
    {
      "epoch": 0.8812949640287769,
      "grad_norm": 1.8984375,
      "learning_rate": 7.780530110842566e-07,
      "loss": 1.4849969863891601,
      "step": 245
    },
    {
      "epoch": 0.8992805755395683,
      "grad_norm": 1.953125,
      "learning_rate": 5.680751779327742e-07,
      "loss": 1.4814369201660156,
      "step": 250
    },
    {
      "epoch": 0.9172661870503597,
      "grad_norm": 2.046875,
      "learning_rate": 3.9024964989539227e-07,
      "loss": 1.4613136291503905,
      "step": 255
    },
    {
      "epoch": 0.935251798561151,
      "grad_norm": 2.046875,
      "learning_rate": 2.4518261295667255e-07,
      "loss": 1.4574945449829102,
      "step": 260
    },
    {
      "epoch": 0.9532374100719424,
      "grad_norm": 1.96875,
      "learning_rate": 1.3336858331787993e-07,
      "loss": 1.468781089782715,
      "step": 265
    },
    {
      "epoch": 0.9712230215827338,
      "grad_norm": 2.34375,
      "learning_rate": 5.518872165033329e-08,
      "loss": 1.470302200317383,
      "step": 270
    },
    {
      "epoch": 0.9892086330935251,
      "grad_norm": 1.8671875,
      "learning_rate": 1.0909533764194013e-08,
      "loss": 1.4709739685058594,
      "step": 275
    },
    {
      "epoch": 1.0,
      "step": 278,
      "total_flos": 1.335043548266926e+17,
      "train_loss": 1.5747115251829298,
      "train_runtime": 2170.5286,
      "train_samples_per_second": 0.512,
      "train_steps_per_second": 0.128
    }
  ],
  "logging_steps": 5,
  "max_steps": 278,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.335043548266926e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}