{
  "best_metric": 1.6883338689804077,
  "best_model_checkpoint": "output/pharaoh/checkpoint-174",
  "epoch": 1.0,
  "global_step": 174,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.00013689676402972123,
      "loss": 1.6111,
      "step": 5
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001359897369367762,
      "loss": 1.6407,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00013448693747453513,
      "loss": 1.7296,
      "step": 15
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001324016514404635,
      "loss": 1.6351,
      "step": 20
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00012975231422038792,
      "loss": 1.6431,
      "step": 25
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001265623478068018,
      "loss": 1.5934,
      "step": 30
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00012285995373208355,
      "loss": 1.6383,
      "step": 35
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00011867786374724195,
      "loss": 1.688,
      "step": 40
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00011405305045036307,
      "loss": 1.7355,
      "step": 45
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00010902640042300463,
      "loss": 1.6672,
      "step": 50
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00010364235276424244,
      "loss": 1.6835,
      "step": 55
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.794850621797833e-05,
      "loss": 1.5821,
      "step": 60
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.199519836678021e-05,
      "loss": 1.701,
      "step": 65
    },
    {
      "epoch": 0.42,
      "learning_rate": 8.583506061247361e-05,
      "loss": 1.6752,
      "step": 70
    },
    {
      "epoch": 0.45,
      "learning_rate": 7.95225528777695e-05,
      "loss": 1.6845,
      "step": 75
    },
    {
      "epoch": 0.48,
      "learning_rate": 7.311348214248791e-05,
      "loss": 1.6935,
      "step": 80
    },
    {
      "epoch": 0.51,
      "learning_rate": 6.666450907085589e-05,
      "loss": 1.7025,
      "step": 85
    },
    {
      "epoch": 0.54,
      "learning_rate": 6.023264709163982e-05,
      "loss": 1.6483,
      "step": 90
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.387475835959079e-05,
      "loss": 1.5692,
      "step": 95
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.7647051054259744e-05,
      "loss": 1.6434,
      "step": 100
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.1604582460408433e-05,
      "loss": 1.661,
      "step": 105
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.580077222313727e-05,
      "loss": 1.6785,
      "step": 110
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.0286930080889863e-05,
      "loss": 1.6299,
      "step": 115
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.511180225150775e-05,
      "loss": 1.6296,
      "step": 120
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.0321140481598987e-05,
      "loss": 1.6131,
      "step": 125
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.595729756912515e-05,
      "loss": 1.6039,
      "step": 130
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.2058852935068877e-05,
      "loss": 1.696,
      "step": 135
    },
    {
      "epoch": 0.84,
      "learning_rate": 8.660271554391817e-06,
      "loss": 1.6846,
      "step": 140
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.791599261570497e-06,
      "loss": 1.6253,
      "step": 145
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.4781971244218827e-06,
      "loss": 1.5759,
      "step": 150
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.7405172345409156e-06,
      "loss": 1.628,
      "step": 155
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.939218965176846e-07,
      "loss": 1.6359,
      "step": 160
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.8547814429227996e-08,
      "loss": 1.614,
      "step": 165
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.7224986553192139,
      "eval_runtime": 22.2232,
      "eval_samples_per_second": 22.454,
      "eval_steps_per_second": 2.835,
      "step": 167
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.5909924568597513e-06,
      "loss": 1.4675,
      "step": 170
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6883338689804077,
      "eval_runtime": 18.8954,
      "eval_samples_per_second": 23.498,
      "eval_steps_per_second": 2.964,
      "step": 174
    }
  ],
  "max_steps": 348,
  "num_train_epochs": 2,
  "total_flos": 181597962240000.0,
  "trial_name": null,
  "trial_params": null
}