{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9536423841059603,
  "eval_steps": 500,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.26490066225165565,
      "grad_norm": 4.038422107696533,
      "learning_rate": 4.1069690242163484e-05,
      "loss": 1.2805,
      "step": 5
    },
    {
      "epoch": 0.5298013245033113,
      "grad_norm": 4.315277576446533,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 0.8658,
      "step": 10
    },
    {
      "epoch": 0.7947019867549668,
      "grad_norm": 4.228354454040527,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.6177,
      "step": 15
    },
    {
      "epoch": 0.9536423841059603,
      "step": 18,
      "total_flos": 1.039869065822208e+16,
      "train_loss": 0.8629565901226468,
      "train_runtime": 640.3959,
      "train_samples_per_second": 3.771,
      "train_steps_per_second": 0.028
    }
  ],
  "logging_steps": 5,
  "max_steps": 18,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.039869065822208e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}