{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.75,
      "grad_norm": 0.32135602831840515,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.6606,
      "step": 3
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.363742858171463,
      "learning_rate": 0.00018888888888888888,
      "loss": 1.6221,
      "step": 6
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.311320424079895,
      "learning_rate": 0.00017222222222222224,
      "loss": 1.45,
      "step": 9
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.33547547459602356,
      "learning_rate": 0.00015555555555555556,
      "loss": 1.325,
      "step": 12
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.6902549266815186,
      "learning_rate": 0.0001388888888888889,
      "loss": 1.2939,
      "step": 15
    },
    {
      "epoch": 4.5,
      "grad_norm": 0.3069547712802887,
      "learning_rate": 0.00012222222222222224,
      "loss": 1.2417,
      "step": 18
    },
    {
      "epoch": 5.25,
      "grad_norm": 0.3101882338523865,
      "learning_rate": 0.00010555555555555557,
      "loss": 1.1295,
      "step": 21
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.2894340455532074,
      "learning_rate": 8.888888888888889e-05,
      "loss": 1.1576,
      "step": 24
    },
    {
      "epoch": 6.75,
      "grad_norm": 0.27182096242904663,
      "learning_rate": 7.222222222222222e-05,
      "loss": 1.116,
      "step": 27
    },
    {
      "epoch": 7.5,
      "grad_norm": 0.297147661447525,
      "learning_rate": 5.555555555555556e-05,
      "loss": 1.1066,
      "step": 30
    },
    {
      "epoch": 8.25,
      "grad_norm": 0.2640742063522339,
      "learning_rate": 3.888888888888889e-05,
      "loss": 1.0402,
      "step": 33
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.29420170187950134,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 1.0585,
      "step": 36
    },
    {
      "epoch": 9.75,
      "grad_norm": 0.2858324646949768,
      "learning_rate": 5.555555555555556e-06,
      "loss": 1.0162,
      "step": 39
    }
  ],
  "logging_steps": 3,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 6503529405480960.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}