{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 3322,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 2e-05,
      "loss": 5.0874,
      "step": 100
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.995250208167269e-05,
      "loss": 3.8099,
      "step": 200
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9810459537139835e-05,
      "loss": 3.7186,
      "step": 300
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.9575221711437283e-05,
      "loss": 3.6782,
      "step": 400
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.924902326597158e-05,
      "loss": 3.6658,
      "step": 500
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.8834962950166965e-05,
      "loss": 3.6644,
      "step": 600
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.8336974164635978e-05,
      "loss": 3.6594,
      "step": 700
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.7759787595511233e-05,
      "loss": 3.6464,
      "step": 800
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.7108886274896706e-05,
      "loss": 3.6364,
      "step": 900
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.639045349434554e-05,
      "loss": 3.6319,
      "step": 1000
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.5611314066164592e-05,
      "loss": 3.6096,
      "step": 1100
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.4778869490538927e-05,
      "loss": 3.6131,
      "step": 1200
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.3901027644361556e-05,
      "loss": 3.6074,
      "step": 1300
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2986127659695292e-05,
      "loss": 3.6134,
      "step": 1400
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.2042860705489998e-05,
      "loss": 3.6074,
      "step": 1500
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.1080187425096018e-05,
      "loss": 3.6057,
      "step": 1600
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.010725281388296e-05,
      "loss": 3.4945,
      "step": 1700
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.133299345591059e-06,
      "loss": 3.3152,
      "step": 1800
    },
    {
      "epoch": 1.14,
      "learning_rate": 8.16757917267863e-06,
      "loss": 3.3171,
      "step": 1900
    },
    {
      "epoch": 1.2,
      "learning_rate": 7.219266234725672e-06,
      "loss": 3.322,
      "step": 2000
    },
    {
      "epoch": 1.26,
      "learning_rate": 6.2973691098273205e-06,
      "loss": 3.3089,
      "step": 2100
    },
    {
      "epoch": 1.32,
      "learning_rate": 5.410645436852491e-06,
      "loss": 3.3124,
      "step": 2200
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.567518721520754e-06,
      "loss": 3.3064,
      "step": 2300
    },
    {
      "epoch": 1.44,
      "learning_rate": 3.775998316604984e-06,
      "loss": 3.2992,
      "step": 2400
    },
    {
      "epoch": 1.51,
      "learning_rate": 3.0436033364146135e-06,
      "loss": 3.2997,
      "step": 2500
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.377291228340114e-06,
      "loss": 3.2948,
      "step": 2600
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.7833916799994533e-06,
      "loss": 3.2986,
      "step": 2700
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.2675464898409772e-06,
      "loss": 3.2966,
      "step": 2800
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.346559724070181e-07,
      "loss": 3.2939,
      "step": 2900
    },
    {
      "epoch": 1.81,
      "learning_rate": 4.888324073859274e-07,
      "loss": 3.2912,
      "step": 3000
    },
    {
      "epoch": 1.87,
      "learning_rate": 2.3336097466711283e-07,
      "loss": 3.2915,
      "step": 3100
    },
    {
      "epoch": 1.93,
      "learning_rate": 7.066854649982025e-08,
      "loss": 3.2873,
      "step": 3200
    },
    {
      "epoch": 1.99,
      "learning_rate": 2.3006332171626733e-09,
      "loss": 3.2845,
      "step": 3300
    },
    {
      "epoch": 2.0,
      "step": 3322,
      "total_flos": 345709784072192.0,
      "train_loss": 3.518749882412703,
      "train_runtime": 8860.4079,
      "train_samples_per_second": 47.988,
      "train_steps_per_second": 0.375
    }
  ],
  "max_steps": 3322,
  "num_train_epochs": 2,
  "total_flos": 345709784072192.0,
  "trial_name": null,
  "trial_params": null
}