{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.04,
  "eval_steps": 3,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "eval_loss": 3.4730746746063232,
      "eval_runtime": 0.2196,
      "eval_samples_per_second": 27.325,
      "eval_steps_per_second": 13.662,
      "step": 1
    },
    {
      "epoch": 0.24,
      "eval_loss": 3.44526743888855,
      "eval_runtime": 0.2198,
      "eval_samples_per_second": 27.298,
      "eval_steps_per_second": 13.649,
      "step": 3
    },
    {
      "epoch": 0.4,
      "grad_norm": 7.564265251159668,
      "learning_rate": 5e-05,
      "loss": 3.0771,
      "step": 5
    },
    {
      "epoch": 0.48,
      "eval_loss": 2.8557474613189697,
      "eval_runtime": 0.219,
      "eval_samples_per_second": 27.395,
      "eval_steps_per_second": 13.698,
      "step": 6
    },
    {
      "epoch": 0.72,
      "eval_loss": 2.287968635559082,
      "eval_runtime": 0.2202,
      "eval_samples_per_second": 27.253,
      "eval_steps_per_second": 13.627,
      "step": 9
    },
    {
      "epoch": 0.8,
      "grad_norm": 6.7110748291015625,
      "learning_rate": 0.0001,
      "loss": 2.5188,
      "step": 10
    },
    {
      "epoch": 0.96,
      "eval_loss": 1.9543577432632446,
      "eval_runtime": 0.2194,
      "eval_samples_per_second": 27.35,
      "eval_steps_per_second": 13.675,
      "step": 12
    }
  ],
  "logging_steps": 5,
  "max_steps": 13,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 4,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 630202658979840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}