{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02365464222353637,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004730928444707274,
      "eval_loss": NaN,
      "eval_runtime": 50.7302,
      "eval_samples_per_second": 17.544,
      "eval_steps_per_second": 8.772,
      "step": 1
    },
    {
      "epoch": 0.004730928444707274,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 92.2177,
      "step": 10
    },
    {
      "epoch": 0.006150206978119456,
      "eval_loss": NaN,
      "eval_runtime": 49.6462,
      "eval_samples_per_second": 17.927,
      "eval_steps_per_second": 8.963,
      "step": 13
    },
    {
      "epoch": 0.009461856889414548,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.012300413956238912,
      "eval_loss": NaN,
      "eval_runtime": 49.6409,
      "eval_samples_per_second": 17.929,
      "eval_steps_per_second": 8.964,
      "step": 26
    },
    {
      "epoch": 0.014192785334121822,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0429,
      "step": 30
    },
    {
      "epoch": 0.01845062093435837,
      "eval_loss": NaN,
      "eval_runtime": 49.6406,
      "eval_samples_per_second": 17.929,
      "eval_steps_per_second": 8.964,
      "step": 39
    },
    {
      "epoch": 0.018923713778829097,
      "grad_norm": NaN,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 1.165,
      "step": 40
    },
    {
      "epoch": 0.02365464222353637,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 2.0446,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.561006971027456e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}