{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8571428571428571,
  "eval_steps": 5,
  "global_step": 21,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04081632653061224,
      "eval_loss": 11.885836601257324,
      "eval_runtime": 2.4584,
      "eval_samples_per_second": 67.116,
      "eval_steps_per_second": 8.542,
      "step": 1
    },
    {
      "epoch": 0.20408163265306123,
      "eval_loss": 11.879362106323242,
      "eval_runtime": 1.6783,
      "eval_samples_per_second": 98.315,
      "eval_steps_per_second": 12.513,
      "step": 5
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 0.5947085618972778,
      "learning_rate": 7.300325188655761e-05,
      "loss": 11.8803,
      "step": 10
    },
    {
      "epoch": 0.40816326530612246,
      "eval_loss": 11.870901107788086,
      "eval_runtime": 1.6553,
      "eval_samples_per_second": 99.68,
      "eval_steps_per_second": 12.687,
      "step": 10
    },
    {
      "epoch": 0.6122448979591837,
      "eval_loss": 11.865002632141113,
      "eval_runtime": 1.6738,
      "eval_samples_per_second": 98.576,
      "eval_steps_per_second": 12.546,
      "step": 15
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 0.5802960395812988,
      "learning_rate": 1.1214435464779006e-05,
      "loss": 11.8687,
      "step": 20
    },
    {
      "epoch": 0.8163265306122449,
      "eval_loss": 11.86227035522461,
      "eval_runtime": 1.6443,
      "eval_samples_per_second": 100.347,
      "eval_steps_per_second": 12.771,
      "step": 20
    }
  ],
  "logging_steps": 10,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 7,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 83103540314112.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}