{
  "best_metric": 0.08275757730007172,
  "best_model_checkpoint": "./SFT/mistralai/Mistral-7B-Instruct-v0.2/checkpoint-100",
  "epoch": 0.19002375296912113,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09501187648456057,
      "grad_norm": 2.1188740730285645,
      "learning_rate": 4.9941569945885383e-05,
      "loss": 0.3014,
      "mean_token_accuracy": 0.948142276108265,
      "step": 50
    },
    {
      "epoch": 0.09501187648456057,
      "eval_loss": 0.0929923802614212,
      "eval_mean_token_accuracy": 0.9722640901917288,
      "eval_runtime": 798.1706,
      "eval_samples_per_second": 2.632,
      "eval_steps_per_second": 0.33,
      "step": 50
    },
    {
      "epoch": 0.19002375296912113,
      "grad_norm": 0.8110750913619995,
      "learning_rate": 4.964406308826261e-05,
      "loss": 0.047,
      "mean_token_accuracy": 0.9850780682265758,
      "step": 100
    },
    {
      "epoch": 0.19002375296912113,
      "eval_loss": 0.08275757730007172,
      "eval_mean_token_accuracy": 0.9794650943560292,
      "eval_runtime": 817.9871,
      "eval_samples_per_second": 2.569,
      "eval_steps_per_second": 0.322,
      "step": 100
    }
  ],
  "logging_steps": 50,
  "max_steps": 1578,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.258179627610112e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}