{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005614192679092746,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011228385358185493,
      "eval_loss": NaN,
      "eval_runtime": 202.4022,
      "eval_samples_per_second": 18.527,
      "eval_steps_per_second": 9.264,
      "step": 1
    },
    {
      "epoch": 0.0011228385358185494,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.5905,
      "step": 10
    },
    {
      "epoch": 0.0014596900965641142,
      "eval_loss": NaN,
      "eval_runtime": 201.436,
      "eval_samples_per_second": 18.616,
      "eval_steps_per_second": 9.308,
      "step": 13
    },
    {
      "epoch": 0.0022456770716370988,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 4.0278,
      "step": 20
    },
    {
      "epoch": 0.0029193801931282283,
      "eval_loss": NaN,
      "eval_runtime": 201.4812,
      "eval_samples_per_second": 18.612,
      "eval_steps_per_second": 9.306,
      "step": 26
    },
    {
      "epoch": 0.0033685156074556477,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.004379070289692342,
      "eval_loss": NaN,
      "eval_runtime": 201.4479,
      "eval_samples_per_second": 18.615,
      "eval_steps_per_second": 9.308,
      "step": 39
    },
    {
      "epoch": 0.0044913541432741975,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 1.4014,
      "step": 40
    },
    {
      "epoch": 0.005614192679092746,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 1.7603,
      "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": 1.5106509172113408e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}