{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "learning_rate": 1.5e-05,
      "loss": 2.2878,
      "step": 2
    },
    {
      "epoch": 0.31,
      "learning_rate": 3e-05,
      "loss": 1.9832,
      "step": 4
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.8285714285714287e-05,
      "loss": 2.0662,
      "step": 6
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.657142857142857e-05,
      "loss": 1.9176,
      "step": 8
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.485714285714286e-05,
      "loss": 1.8796,
      "step": 10
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.3142857142857145e-05,
      "loss": 1.845,
      "step": 12
    },
    {
      "epoch": 1.08,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 1.6627,
      "step": 14
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.9714285714285714e-05,
      "loss": 1.7721,
      "step": 16
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.8e-05,
      "loss": 1.7231,
      "step": 18
    },
    {
      "epoch": 1.54,
      "learning_rate": 1.6285714285714283e-05,
      "loss": 1.5892,
      "step": 20
    },
    {
      "epoch": 1.69,
      "learning_rate": 1.4571428571428571e-05,
      "loss": 1.6807,
      "step": 22
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.2857142857142857e-05,
      "loss": 1.5308,
      "step": 24
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.1142857142857143e-05,
      "loss": 1.4867,
      "step": 26
    },
    {
      "epoch": 2.15,
      "learning_rate": 9.428571428571428e-06,
      "loss": 1.7313,
      "step": 28
    },
    {
      "epoch": 2.31,
      "learning_rate": 7.714285714285714e-06,
      "loss": 1.4176,
      "step": 30
    },
    {
      "epoch": 2.46,
      "learning_rate": 6e-06,
      "loss": 1.4243,
      "step": 32
    },
    {
      "epoch": 2.62,
      "learning_rate": 4.2857142857142855e-06,
      "loss": 1.4269,
      "step": 34
    },
    {
      "epoch": 2.77,
      "learning_rate": 2.5714285714285716e-06,
      "loss": 1.5218,
      "step": 36
    },
    {
      "epoch": 2.92,
      "learning_rate": 8.571428571428571e-07,
      "loss": 1.3782,
      "step": 38
    }
  ],
  "logging_steps": 2,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 3170470585171968.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}