{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 15375,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 19.442411422729492,
      "learning_rate": 4.8373983739837406e-05,
      "loss": 6.7559,
      "step": 500
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 22.672739028930664,
      "learning_rate": 4.6747967479674795e-05,
      "loss": 6.6932,
      "step": 1000
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 21.795516967773438,
      "learning_rate": 4.51219512195122e-05,
      "loss": 6.6652,
      "step": 1500
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 19.84381866455078,
      "learning_rate": 4.3495934959349595e-05,
      "loss": 6.6335,
      "step": 2000
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 14.22912883758545,
      "learning_rate": 4.186991869918699e-05,
      "loss": 6.6248,
      "step": 2500
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 14.391462326049805,
      "learning_rate": 4.0243902439024395e-05,
      "loss": 6.5929,
      "step": 3000
    },
    {
      "epoch": 0.6829268292682927,
      "grad_norm": 19.81720733642578,
      "learning_rate": 3.861788617886179e-05,
      "loss": 6.5589,
      "step": 3500
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 15.33761978149414,
      "learning_rate": 3.699186991869919e-05,
      "loss": 6.5327,
      "step": 4000
    },
    {
      "epoch": 0.8780487804878049,
      "grad_norm": 14.190281867980957,
      "learning_rate": 3.5365853658536584e-05,
      "loss": 6.5175,
      "step": 4500
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 16.57828712463379,
      "learning_rate": 3.373983739837399e-05,
      "loss": 6.5137,
      "step": 5000
    },
    {
      "epoch": 1.0731707317073171,
      "grad_norm": 16.75761604309082,
      "learning_rate": 3.2113821138211384e-05,
      "loss": 6.495,
      "step": 5500
    },
    {
      "epoch": 1.170731707317073,
      "grad_norm": 18.840726852416992,
      "learning_rate": 3.048780487804878e-05,
      "loss": 6.4757,
      "step": 6000
    },
    {
      "epoch": 1.2682926829268293,
      "grad_norm": 17.630483627319336,
      "learning_rate": 2.886178861788618e-05,
      "loss": 6.4633,
      "step": 6500
    },
    {
      "epoch": 1.3658536585365852,
      "grad_norm": 16.721818923950195,
      "learning_rate": 2.7235772357723577e-05,
      "loss": 6.4462,
      "step": 7000
    },
    {
      "epoch": 1.4634146341463414,
      "grad_norm": 14.650636672973633,
      "learning_rate": 2.5609756097560977e-05,
      "loss": 6.4404,
      "step": 7500
    },
    {
      "epoch": 1.5609756097560976,
      "grad_norm": 13.825970649719238,
      "learning_rate": 2.3983739837398377e-05,
      "loss": 6.4326,
      "step": 8000
    },
    {
      "epoch": 1.6585365853658538,
      "grad_norm": 11.85326862335205,
      "learning_rate": 2.2357723577235773e-05,
      "loss": 6.4239,
      "step": 8500
    },
    {
      "epoch": 1.7560975609756098,
      "grad_norm": 13.92196273803711,
      "learning_rate": 2.073170731707317e-05,
      "loss": 6.4098,
      "step": 9000
    },
    {
      "epoch": 1.8536585365853657,
      "grad_norm": 12.077308654785156,
      "learning_rate": 1.9105691056910573e-05,
      "loss": 6.3987,
      "step": 9500
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 12.406614303588867,
      "learning_rate": 1.747967479674797e-05,
      "loss": 6.3957,
      "step": 10000
    },
    {
      "epoch": 2.048780487804878,
      "grad_norm": 14.001736640930176,
      "learning_rate": 1.5853658536585366e-05,
      "loss": 6.3752,
      "step": 10500
    },
    {
      "epoch": 2.1463414634146343,
      "grad_norm": 12.691810607910156,
      "learning_rate": 1.4227642276422764e-05,
      "loss": 6.3566,
      "step": 11000
    },
    {
      "epoch": 2.2439024390243905,
      "grad_norm": 10.062420845031738,
      "learning_rate": 1.2601626016260162e-05,
      "loss": 6.3492,
      "step": 11500
    },
    {
      "epoch": 2.341463414634146,
      "grad_norm": 11.78906536102295,
      "learning_rate": 1.0975609756097562e-05,
      "loss": 6.3447,
      "step": 12000
    },
    {
      "epoch": 2.4390243902439024,
      "grad_norm": 13.368131637573242,
      "learning_rate": 9.34959349593496e-06,
      "loss": 6.339,
      "step": 12500
    },
    {
      "epoch": 2.5365853658536586,
      "grad_norm": 12.125652313232422,
      "learning_rate": 7.723577235772358e-06,
      "loss": 6.3305,
      "step": 13000
    },
    {
      "epoch": 2.6341463414634148,
      "grad_norm": 13.748695373535156,
      "learning_rate": 6.0975609756097564e-06,
      "loss": 6.3205,
      "step": 13500
    },
    {
      "epoch": 2.7317073170731705,
      "grad_norm": 13.787367820739746,
      "learning_rate": 4.471544715447155e-06,
      "loss": 6.3196,
      "step": 14000
    },
    {
      "epoch": 2.8292682926829267,
      "grad_norm": 15.013029098510742,
      "learning_rate": 2.8455284552845528e-06,
      "loss": 6.3116,
      "step": 14500
    },
    {
      "epoch": 2.926829268292683,
      "grad_norm": 15.244904518127441,
      "learning_rate": 1.2195121951219514e-06,
      "loss": 6.3107,
      "step": 15000
    },
    {
      "epoch": 3.0,
      "step": 15375,
      "total_flos": 5764753863475200.0,
      "train_loss": 6.457221655868903,
      "train_runtime": 1165.3935,
      "train_samples_per_second": 105.536,
      "train_steps_per_second": 13.193
    }
  ],
  "logging_steps": 500,
  "max_steps": 15375,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 5764753863475200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}