{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00019922154182531757,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.984430836506351e-05,
      "grad_norm": 32.60482406616211,
      "learning_rate": 1e-05,
      "loss": 113.5889,
      "step": 1
    },
    {
      "epoch": 3.984430836506351e-05,
      "eval_loss": 7.187979698181152,
      "eval_runtime": 3000.0578,
      "eval_samples_per_second": 14.09,
      "eval_steps_per_second": 7.045,
      "step": 1
    },
    {
      "epoch": 7.968861673012702e-05,
      "grad_norm": 29.80782127380371,
      "learning_rate": 2e-05,
      "loss": 109.9531,
      "step": 2
    },
    {
      "epoch": 7.968861673012702e-05,
      "eval_loss": 6.9893646240234375,
      "eval_runtime": 3188.0178,
      "eval_samples_per_second": 13.259,
      "eval_steps_per_second": 6.63,
      "step": 2
    },
    {
      "epoch": 0.00011953292509519055,
      "grad_norm": 33.624717712402344,
      "learning_rate": 3e-05,
      "loss": 118.2667,
      "step": 3
    },
    {
      "epoch": 0.00015937723346025405,
      "grad_norm": 32.48634338378906,
      "learning_rate": 4e-05,
      "loss": 112.53,
      "step": 4
    },
    {
      "epoch": 0.00015937723346025405,
      "eval_loss": 6.8872599601745605,
      "eval_runtime": 4829.6199,
      "eval_samples_per_second": 8.752,
      "eval_steps_per_second": 4.376,
      "step": 4
    },
    {
      "epoch": 0.00019922154182531757,
      "grad_norm": 36.08415985107422,
      "learning_rate": 5e-05,
      "loss": 114.6641,
      "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": 6332448610713600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}