{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8705493166187864,
  "global_step": 20000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.00010077565027123787,
      "loss": 0.4732,
      "step": 500
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00010075885246660077,
      "loss": 0.4445,
      "step": 1000
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00010073086073069567,
      "loss": 0.4329,
      "step": 1500
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001006916819700645,
      "loss": 0.4256,
      "step": 2000
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001006414377109213,
      "loss": 0.421,
      "step": 2500
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00010057993897463803,
      "loss": 0.4167,
      "step": 3000
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00010050729045131372,
      "loss": 0.4132,
      "step": 3500
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00010042351006588448,
      "loss": 0.4107,
      "step": 4000
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00010032861848990674,
      "loss": 0.4091,
      "step": 4500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001002228621438404,
      "loss": 0.4067,
      "step": 5000
    },
    {
      "epoch": 0.44,
      "eval_loss": 0.3877949118614197,
      "eval_runtime": 108.0468,
      "eval_samples_per_second": 46.276,
      "eval_steps_per_second": 0.731,
      "step": 5000
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010010584325708389,
      "loss": 0.4038,
      "step": 5500
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.997779155931062e-05,
      "loss": 0.402,
      "step": 6000
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.983873864536092e-05,
      "loss": 0.401,
      "step": 6500
    },
    {
      "epoch": 0.61,
      "learning_rate": 9.968871882446063e-05,
      "loss": 0.4001,
      "step": 7000
    },
    {
      "epoch": 0.65,
      "learning_rate": 9.952776911175577e-05,
      "loss": 0.3987,
      "step": 7500
    },
    {
      "epoch": 0.7,
      "learning_rate": 9.935592921917959e-05,
      "loss": 0.3974,
      "step": 8000
    },
    {
      "epoch": 0.74,
      "learning_rate": 9.917361771757108e-05,
      "loss": 0.3954,
      "step": 8500
    },
    {
      "epoch": 0.78,
      "learning_rate": 9.898014889719868e-05,
      "loss": 0.3945,
      "step": 9000
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.877592501404869e-05,
      "loss": 0.394,
      "step": 9500
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.856099645730841e-05,
      "loss": 0.3926,
      "step": 10000
    },
    {
      "epoch": 0.87,
      "eval_loss": 0.37431180477142334,
      "eval_runtime": 106.4392,
      "eval_samples_per_second": 46.975,
      "eval_steps_per_second": 0.742,
      "step": 10000
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.833541625738316e-05,
      "loss": 0.3929,
      "step": 10500
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.809924007281187e-05,
      "loss": 0.3906,
      "step": 11000
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.78525261765341e-05,
      "loss": 0.3899,
      "step": 11500
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.759533544151208e-05,
      "loss": 0.3892,
      "step": 12000
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.732773132571125e-05,
      "loss": 0.3889,
      "step": 12500
    },
    {
      "epoch": 0.26,
      "learning_rate": 9.705034604088048e-05,
      "loss": 0.3865,
      "step": 13000
    },
    {
      "epoch": 0.3,
      "learning_rate": 9.676213628592508e-05,
      "loss": 0.3865,
      "step": 13500
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.64637187296151e-05,
      "loss": 0.3867,
      "step": 14000
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.615516700201724e-05,
      "loss": 0.3858,
      "step": 14500
    },
    {
      "epoch": 0.44,
      "learning_rate": 9.583720443927501e-05,
      "loss": 0.3853,
      "step": 15000
    },
    {
      "epoch": 0.44,
      "eval_loss": 0.36506548523902893,
      "eval_runtime": 96.1419,
      "eval_samples_per_second": 52.006,
      "eval_steps_per_second": 0.822,
      "step": 15000
    },
    {
      "epoch": 0.48,
      "learning_rate": 9.550863512110018e-05,
      "loss": 0.3844,
      "step": 15500
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.517016728422667e-05,
      "loss": 0.3834,
      "step": 16000
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.482188444052858e-05,
      "loss": 0.3826,
      "step": 16500
    },
    {
      "epoch": 0.61,
      "learning_rate": 9.446387252358614e-05,
      "loss": 0.3824,
      "step": 17000
    },
    {
      "epoch": 0.65,
      "learning_rate": 9.40962198674828e-05,
      "loss": 0.3825,
      "step": 17500
    },
    {
      "epoch": 0.7,
      "learning_rate": 9.371901718501017e-05,
      "loss": 0.3804,
      "step": 18000
    },
    {
      "epoch": 0.74,
      "learning_rate": 9.333314023958391e-05,
      "loss": 0.3803,
      "step": 18500
    },
    {
      "epoch": 0.78,
      "learning_rate": 9.293713767144707e-05,
      "loss": 0.381,
      "step": 19000
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.253187106312908e-05,
      "loss": 0.3793,
      "step": 19500
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.211744040810141e-05,
      "loss": 0.3793,
      "step": 20000
    },
    {
      "epoch": 0.87,
      "eval_loss": 0.35968872904777527,
      "eval_runtime": 95.0235,
      "eval_samples_per_second": 52.619,
      "eval_steps_per_second": 0.831,
      "step": 20000
    }
  ],
  "max_steps": 100000,
  "num_train_epochs": 9,
  "total_flos": 9.419722694590464e+20,
  "trial_name": null,
  "trial_params": null
}