{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013967230727907601,
  "eval_steps": 10,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005372011818426001,
      "eval_loss": 0.18501441180706024,
      "eval_runtime": 79.5189,
      "eval_samples_per_second": 9.859,
      "eval_steps_per_second": 4.93,
      "step": 1
    },
    {
      "epoch": 0.0026860059092130005,
      "grad_norm": 0.7118232250213623,
      "learning_rate": 5e-05,
      "loss": 0.6911,
      "step": 5
    },
    {
      "epoch": 0.005372011818426001,
      "grad_norm": 0.3719102740287781,
      "learning_rate": 0.0001,
      "loss": 0.6331,
      "step": 10
    },
    {
      "epoch": 0.005372011818426001,
      "eval_loss": 0.1662459820508957,
      "eval_runtime": 79.9488,
      "eval_samples_per_second": 9.806,
      "eval_steps_per_second": 4.903,
      "step": 10
    },
    {
      "epoch": 0.008058017727639,
      "grad_norm": 0.5022017955780029,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.6189,
      "step": 15
    },
    {
      "epoch": 0.010744023636852002,
      "grad_norm": 0.42121511697769165,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.4692,
      "step": 20
    },
    {
      "epoch": 0.010744023636852002,
      "eval_loss": 0.12234125286340714,
      "eval_runtime": 80.4411,
      "eval_samples_per_second": 9.746,
      "eval_steps_per_second": 4.873,
      "step": 20
    },
    {
      "epoch": 0.013430029546065002,
      "grad_norm": 0.5769535303115845,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.493,
      "step": 25
    }
  ],
  "logging_steps": 5,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4543869219766272.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}