{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.0,
  "eval_steps": 5,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.67,
      "learning_rate": 2.9999177540482684e-05,
      "loss": 2.6576,
      "step": 2
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.9996710252122685e-05,
      "loss": 2.1353,
      "step": 4
    },
    {
      "epoch": 2.0,
      "learning_rate": 2.9992598405485974e-05,
      "loss": 1.8307,
      "step": 6
    },
    {
      "epoch": 2.67,
      "learning_rate": 2.9986842451482876e-05,
      "loss": 1.5685,
      "step": 8
    },
    {
      "epoch": 3.33,
      "learning_rate": 2.9979443021318607e-05,
      "loss": 1.3489,
      "step": 10
    },
    {
      "epoch": 4.0,
      "learning_rate": 2.9970400926424075e-05,
      "loss": 1.1757,
      "step": 12
    },
    {
      "epoch": 4.67,
      "learning_rate": 2.995971715836687e-05,
      "loss": 1.0709,
      "step": 14
    },
    {
      "epoch": 5.33,
      "learning_rate": 2.9947392888742566e-05,
      "loss": 1.0194,
      "step": 16
    },
    {
      "epoch": 6.0,
      "learning_rate": 2.9933429469046202e-05,
      "loss": 0.9694,
      "step": 18
    },
    {
      "epoch": 6.67,
      "learning_rate": 2.99178284305241e-05,
      "loss": 0.9486,
      "step": 20
    },
    {
      "epoch": 7.33,
      "learning_rate": 2.9900591484005944e-05,
      "loss": 0.9138,
      "step": 22
    },
    {
      "epoch": 8.0,
      "learning_rate": 2.988172051971717e-05,
      "loss": 0.8702,
      "step": 24
    }
  ],
  "logging_steps": 2,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 200,
  "save_steps": 500,
  "total_flos": 1311636707082240.0,
  "train_batch_size": 52,
  "trial_name": null,
  "trial_params": null
}