{
  "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": 8.4873046875,
      "learning_rate": 4.957230266673969e-06,
      "loss": 0.7526,
      "step": 10
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 6.453182220458984,
      "learning_rate": 4.828686741593921e-06,
      "loss": 0.4679,
      "step": 20
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 3.154416799545288,
      "learning_rate": 4.618852307232078e-06,
      "loss": 0.2544,
      "step": 30
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 5.008462429046631,
      "learning_rate": 4.335051964269395e-06,
      "loss": 0.1482,
      "step": 40
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 3.7109785079956055,
      "learning_rate": 3.987192750660719e-06,
      "loss": 0.1171,
      "step": 50
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 2.6461384296417236,
      "learning_rate": 3.587417902020876e-06,
      "loss": 0.1406,
      "step": 60
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 2.4678690433502197,
      "learning_rate": 3.1496829497545268e-06,
      "loss": 0.0862,
      "step": 70
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 3.6291213035583496,
      "learning_rate": 2.6892685546987724e-06,
      "loss": 0.0944,
      "step": 80
    },
    {
      "epoch": 1.6,
      "grad_norm": 5.3926897048950195,
      "learning_rate": 2.2222470825144806e-06,
      "loss": 0.1177,
      "step": 90
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 1.8201929330825806,
      "learning_rate": 1.7649215418673847e-06,
      "loss": 0.0735,
      "step": 100
    },
    {
      "epoch": 1.9555555555555557,
      "grad_norm": 1.5708659887313843,
      "learning_rate": 1.3332564712129845e-06,
      "loss": 0.1145,
      "step": 110
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 2.2869913578033447,
      "learning_rate": 9.423206410612498e-07,
      "loss": 0.0876,
      "step": 120
    },
    {
      "epoch": 2.311111111111111,
      "grad_norm": 1.3838794231414795,
      "learning_rate": 6.057610261367044e-07,
      "loss": 0.0931,
      "step": 130
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 2.4476680755615234,
      "learning_rate": 3.3532641026504415e-07,
      "loss": 0.1052,
      "step": 140
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 2.1095035076141357,
      "learning_rate": 1.4045725421448332e-07,
      "loss": 0.0899,
      "step": 150
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 2.335554838180542,
      "learning_rate": 2.7956143581177874e-08,
      "loss": 0.0744,
      "step": 160
    },
    {
      "epoch": 2.986666666666667,
      "step": 168,
      "total_flos": 1.610915690299392e+16,
      "train_loss": 0.17055919482594445,
      "train_runtime": 689.6993,
      "train_samples_per_second": 3.915,
      "train_steps_per_second": 0.244
    }
  ],
  "logging_steps": 10,
  "max_steps": 168,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.610915690299392e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}