{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09950248756218906,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01990049751243781,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.01990049751243781,
      "eval_loss": NaN,
      "eval_runtime": 64.2705,
      "eval_samples_per_second": 1.323,
      "eval_steps_per_second": 0.669,
      "step": 1
    },
    {
      "epoch": 0.03980099502487562,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.03980099502487562,
      "eval_loss": NaN,
      "eval_runtime": 0.5744,
      "eval_samples_per_second": 147.983,
      "eval_steps_per_second": 74.862,
      "step": 2
    },
    {
      "epoch": 0.05970149253731343,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.07960199004975124,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.07960199004975124,
      "eval_loss": NaN,
      "eval_runtime": 0.5962,
      "eval_samples_per_second": 142.561,
      "eval_steps_per_second": 72.119,
      "step": 4
    },
    {
      "epoch": 0.09950248756218906,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 178076327608320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}