{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8199999999999998,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.2045,
      "step": 30
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00017777777777777779,
      "loss": 1.1169,
      "step": 60
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00015555555555555556,
      "loss": 1.0648,
      "step": 90
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.0731,
      "step": 120
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00011111111111111112,
      "loss": 1.0164,
      "step": 150
    },
    {
      "epoch": 1.02,
      "learning_rate": 8.888888888888889e-05,
      "loss": 1.0471,
      "step": 180
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.9535,
      "step": 210
    },
    {
      "epoch": 1.42,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.0056,
      "step": 240
    },
    {
      "epoch": 1.62,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.9549,
      "step": 270
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0,
      "loss": 0.9755,
      "step": 300
    }
  ],
  "logging_steps": 30,
  "max_steps": 300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 2.6237862936576e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}