{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.986666666666667,
  "eval_steps": 500,
  "global_step": 168,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 4.22963809967041,
      "learning_rate": 4.957230266673969e-06,
      "loss": 0.8422,
      "step": 10
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 3.0976099967956543,
      "learning_rate": 4.828686741593921e-06,
      "loss": 0.7171,
      "step": 20
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 3.412571430206299,
      "learning_rate": 4.618852307232078e-06,
      "loss": 0.5551,
      "step": 30
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 3.297762393951416,
      "learning_rate": 4.335051964269395e-06,
      "loss": 0.4059,
      "step": 40
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.6004385948181152,
      "learning_rate": 3.987192750660719e-06,
      "loss": 0.3053,
      "step": 50
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 1.9239391088485718,
      "learning_rate": 3.587417902020876e-06,
      "loss": 0.2825,
      "step": 60
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 1.2859814167022705,
      "learning_rate": 3.1496829497545268e-06,
      "loss": 0.2082,
      "step": 70
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 1.2387938499450684,
      "learning_rate": 2.6892685546987724e-06,
      "loss": 0.1955,
      "step": 80
    },
    {
      "epoch": 1.6,
      "grad_norm": 2.38809871673584,
      "learning_rate": 2.2222470825144806e-06,
      "loss": 0.2161,
      "step": 90
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 1.2159907817840576,
      "learning_rate": 1.7649215418673847e-06,
      "loss": 0.169,
      "step": 100
    },
    {
      "epoch": 1.9555555555555557,
      "grad_norm": 1.050315499305725,
      "learning_rate": 1.3332564712129845e-06,
      "loss": 0.2051,
      "step": 110
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 2.968810796737671,
      "learning_rate": 9.423206410612498e-07,
      "loss": 0.2007,
      "step": 120
    },
    {
      "epoch": 2.311111111111111,
      "grad_norm": 2.0824708938598633,
      "learning_rate": 6.057610261367044e-07,
      "loss": 0.1866,
      "step": 130
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 1.7900301218032837,
      "learning_rate": 3.3532641026504415e-07,
      "loss": 0.2212,
      "step": 140
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 1.0882800817489624,
      "learning_rate": 1.4045725421448332e-07,
      "loss": 0.1776,
      "step": 150
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 1.0603089332580566,
      "learning_rate": 2.7956143581177874e-08,
      "loss": 0.1686,
      "step": 160
    },
    {
      "epoch": 2.986666666666667,
      "step": 168,
      "total_flos": 1.3957687162699776e+16,
      "train_loss": 0.30872942223435357,
      "train_runtime": 264.2672,
      "train_samples_per_second": 10.217,
      "train_steps_per_second": 0.636
    }
  ],
  "logging_steps": 10,
  "max_steps": 168,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.3957687162699776e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}