{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6326530612244898,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 5.09375,
      "learning_rate": 2.9968542393565676e-06,
      "loss": 1.9388,
      "step": 5
    },
    {
      "epoch": 0.41,
      "grad_norm": 4.4375,
      "learning_rate": 2.9616157869703894e-06,
      "loss": 1.8455,
      "step": 10
    },
    {
      "epoch": 0.61,
      "grad_norm": 3.59375,
      "learning_rate": 2.8881318444640566e-06,
      "loss": 1.7796,
      "step": 15
    },
    {
      "epoch": 0.82,
      "grad_norm": 3.796875,
      "learning_rate": 2.778325235483954e-06,
      "loss": 1.8091,
      "step": 20
    },
    {
      "epoch": 1.02,
      "grad_norm": 4.625,
      "learning_rate": 2.6350692237265428e-06,
      "loss": 1.7224,
      "step": 25
    },
    {
      "epoch": 1.22,
      "grad_norm": 3.953125,
      "learning_rate": 2.4621123294467098e-06,
      "loss": 1.7108,
      "step": 30
    },
    {
      "epoch": 1.43,
      "grad_norm": 4.125,
      "learning_rate": 2.2639802434931445e-06,
      "loss": 1.7299,
      "step": 35
    },
    {
      "epoch": 1.63,
      "grad_norm": 3.625,
      "learning_rate": 2.0458574054452316e-06,
      "loss": 1.7111,
      "step": 40
    }
  ],
  "logging_steps": 5,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 20,
  "total_flos": 3199050392518656.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}