{
  "best_metric": 3.1994659900665283,
  "best_model_checkpoint": "output/dababy/checkpoint-117",
  "epoch": 1.0,
  "global_step": 117,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.00013658268089626933,
      "loss": 4.0049,
      "step": 5
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00013474183387300238,
      "loss": 3.8643,
      "step": 10
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00013171058983499535,
      "loss": 3.7669,
      "step": 15
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00012754350402576807,
      "loss": 3.5611,
      "step": 20
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00012231557416184888,
      "loss": 3.6081,
      "step": 25
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00011612089065075853,
      "loss": 3.4961,
      "step": 30
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00010907094318558624,
      "loss": 3.5888,
      "step": 35
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00010129261419346172,
      "loss": 3.5294,
      "step": 40
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.292589525111794e-05,
      "loss": 3.4875,
      "step": 45
    },
    {
      "epoch": 0.43,
      "learning_rate": 8.412136756667896e-05,
      "loss": 3.5702,
      "step": 50
    },
    {
      "epoch": 0.47,
      "learning_rate": 7.50374918730581e-05,
      "loss": 3.2463,
      "step": 55
    },
    {
      "epoch": 0.51,
      "learning_rate": 6.583775650849414e-05,
      "loss": 3.4277,
      "step": 60
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.668773501204858e-05,
      "loss": 3.2294,
      "step": 65
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.775210619040667e-05,
      "loss": 3.2776,
      "step": 70
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.9191690287750474e-05,
      "loss": 3.3029,
      "step": 75
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.116055460065698e-05,
      "loss": 3.276,
      "step": 80
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.3803240630126077e-05,
      "loss": 3.4075,
      "step": 85
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.725216267546246e-05,
      "loss": 3.4417,
      "step": 90
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.1625224689186402e-05,
      "loss": 3.5386,
      "step": 95
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.0236982839636524e-06,
      "loss": 3.2045,
      "step": 100
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.53040008242582e-06,
      "loss": 3.3209,
      "step": 105
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.2082012132853971e-06,
      "loss": 3.4274,
      "step": 110
    },
    {
      "epoch": 0.98,
      "learning_rate": 9.889577929987515e-08,
      "loss": 3.24,
      "step": 115
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.1994659900665283,
      "eval_runtime": 6.6375,
      "eval_samples_per_second": 22.9,
      "eval_steps_per_second": 2.863,
      "step": 117
    }
  ],
  "max_steps": 117,
  "num_train_epochs": 1,
  "total_flos": 121631440896000.0,
  "trial_name": null,
  "trial_params": null
}