{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 3310,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "learning_rate": 1.8126888217522657e-05,
      "loss": 4.8887,
      "step": 100
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.625377643504531e-05,
      "loss": 2.628,
      "step": 200
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.438066465256798e-05,
      "loss": 2.4334,
      "step": 300
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.8610271903323265e-05,
      "loss": 2.3714,
      "step": 400
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.6596173212487415e-05,
      "loss": 2.3122,
      "step": 500
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.458207452165156e-05,
      "loss": 2.2847,
      "step": 600
    },
    {
      "epoch": 1.06,
      "learning_rate": 5.2567975830815716e-05,
      "loss": 2.1634,
      "step": 700
    },
    {
      "epoch": 1.21,
      "learning_rate": 5.055387713997986e-05,
      "loss": 2.0794,
      "step": 800
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.853977844914401e-05,
      "loss": 2.0694,
      "step": 900
    },
    {
      "epoch": 1.51,
      "learning_rate": 4.6525679758308154e-05,
      "loss": 2.0765,
      "step": 1000
    },
    {
      "epoch": 1.66,
      "learning_rate": 4.4511581067472304e-05,
      "loss": 2.0553,
      "step": 1100
    },
    {
      "epoch": 1.81,
      "learning_rate": 4.249748237663646e-05,
      "loss": 2.0391,
      "step": 1200
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.0483383685800605e-05,
      "loss": 2.0316,
      "step": 1300
    },
    {
      "epoch": 2.11,
      "learning_rate": 3.8469284994964755e-05,
      "loss": 1.9079,
      "step": 1400
    },
    {
      "epoch": 2.27,
      "learning_rate": 3.64551863041289e-05,
      "loss": 1.8636,
      "step": 1500
    },
    {
      "epoch": 2.42,
      "learning_rate": 3.444108761329305e-05,
      "loss": 1.8512,
      "step": 1600
    },
    {
      "epoch": 2.57,
      "learning_rate": 3.2426988922457206e-05,
      "loss": 1.8648,
      "step": 1700
    },
    {
      "epoch": 2.72,
      "learning_rate": 3.041289023162135e-05,
      "loss": 1.8774,
      "step": 1800
    },
    {
      "epoch": 2.87,
      "learning_rate": 2.83987915407855e-05,
      "loss": 1.8621,
      "step": 1900
    },
    {
      "epoch": 3.02,
      "learning_rate": 2.6384692849949647e-05,
      "loss": 1.8285,
      "step": 2000
    },
    {
      "epoch": 3.17,
      "learning_rate": 2.4370594159113798e-05,
      "loss": 1.7082,
      "step": 2100
    },
    {
      "epoch": 3.32,
      "learning_rate": 2.2356495468277945e-05,
      "loss": 1.7146,
      "step": 2200
    },
    {
      "epoch": 3.47,
      "learning_rate": 2.0342396777442095e-05,
      "loss": 1.7272,
      "step": 2300
    },
    {
      "epoch": 3.63,
      "learning_rate": 1.8328298086606246e-05,
      "loss": 1.7292,
      "step": 2400
    },
    {
      "epoch": 3.78,
      "learning_rate": 1.6314199395770393e-05,
      "loss": 1.725,
      "step": 2500
    },
    {
      "epoch": 3.93,
      "learning_rate": 1.4300100704934543e-05,
      "loss": 1.7308,
      "step": 2600
    },
    {
      "epoch": 4.08,
      "learning_rate": 1.228600201409869e-05,
      "loss": 1.6751,
      "step": 2700
    },
    {
      "epoch": 4.23,
      "learning_rate": 1.027190332326284e-05,
      "loss": 1.6192,
      "step": 2800
    },
    {
      "epoch": 4.38,
      "learning_rate": 8.257804632426989e-06,
      "loss": 1.6241,
      "step": 2900
    },
    {
      "epoch": 4.53,
      "learning_rate": 6.243705941591138e-06,
      "loss": 1.6271,
      "step": 3000
    },
    {
      "epoch": 4.68,
      "learning_rate": 4.229607250755287e-06,
      "loss": 1.6343,
      "step": 3100
    },
    {
      "epoch": 4.83,
      "learning_rate": 2.215508559919436e-06,
      "loss": 1.6325,
      "step": 3200
    },
    {
      "epoch": 4.98,
      "learning_rate": 2.014098690835851e-07,
      "loss": 1.628,
      "step": 3300
    },
    {
      "epoch": 5.0,
      "step": 3310,
      "total_flos": 5.435050739908608e+16,
      "train_loss": 2.0068074770924547,
      "train_runtime": 3754.219,
      "train_samples_per_second": 56.426,
      "train_steps_per_second": 0.882
    }
  ],
  "max_steps": 3310,
  "num_train_epochs": 5,
  "total_flos": 5.435050739908608e+16,
  "trial_name": null,
  "trial_params": null
}