{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 244,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 1.1114288568496704,
      "learning_rate": 4.610655737704918e-05,
      "loss": 1.1993,
      "step": 20
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.016808271408081,
      "learning_rate": 4.200819672131148e-05,
      "loss": 1.1065,
      "step": 40
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.9619632363319397,
      "learning_rate": 3.790983606557377e-05,
      "loss": 1.0583,
      "step": 60
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.0110981464385986,
      "learning_rate": 3.381147540983607e-05,
      "loss": 1.0567,
      "step": 80
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.9327293038368225,
      "learning_rate": 2.9713114754098366e-05,
      "loss": 1.0537,
      "step": 100
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.9638545513153076,
      "learning_rate": 2.5614754098360656e-05,
      "loss": 1.0132,
      "step": 120
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.9243238568305969,
      "learning_rate": 2.1516393442622952e-05,
      "loss": 1.0462,
      "step": 140
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.9260810613632202,
      "learning_rate": 1.7418032786885245e-05,
      "loss": 1.0283,
      "step": 160
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.8994088172912598,
      "learning_rate": 1.3319672131147543e-05,
      "loss": 0.986,
      "step": 180
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.9872317314147949,
      "learning_rate": 9.221311475409836e-06,
      "loss": 1.0229,
      "step": 200
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.8821935653686523,
      "learning_rate": 5.122950819672131e-06,
      "loss": 0.9887,
      "step": 220
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.9044594168663025,
      "learning_rate": 1.024590163934426e-06,
      "loss": 1.0017,
      "step": 240
    }
  ],
  "logging_steps": 20,
  "max_steps": 244,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 244,
  "total_flos": 3.947086554857472e+16,
  "train_batch_size": 24,
  "trial_name": null,
  "trial_params": null
}