{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.5833333333333335,
  "eval_steps": 500,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 1.9537,
      "step": 4
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.8029,
      "step": 8
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001875,
      "loss": 1.7018,
      "step": 12
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.000175,
      "loss": 1.6036,
      "step": 16
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00016250000000000002,
      "loss": 1.4489,
      "step": 20
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.3606,
      "step": 24
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0001375,
      "loss": 1.4032,
      "step": 28
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.000125,
      "loss": 1.1902,
      "step": 32
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00011250000000000001,
      "loss": 1.194,
      "step": 36
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0001,
      "loss": 1.1474,
      "step": 40
    }
  ],
  "logging_steps": 4,
  "max_steps": 72,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2590275903805440.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}