{
  "best_metric": 0.7021857923497268,
  "best_model_checkpoint": "./save_phi2_ft_lora/checkpoint-100",
  "epoch": 0.2857142857142857,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 3.5220046043395996,
      "learning_rate": 5e-06,
      "loss": 5.6671,
      "step": 10
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 4.667470932006836,
      "learning_rate": 1e-05,
      "loss": 5.323,
      "step": 20
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 6.609537124633789,
      "learning_rate": 1.5e-05,
      "loss": 4.5029,
      "step": 30
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 4.244329929351807,
      "learning_rate": 2e-05,
      "loss": 2.4999,
      "step": 40
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.4203755557537079,
      "learning_rate": 2.5e-05,
      "loss": 1.0732,
      "step": 50
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.26867735385894775,
      "learning_rate": 3e-05,
      "loss": 1.0087,
      "step": 60
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.2248707115650177,
      "learning_rate": 3.5e-05,
      "loss": 0.9067,
      "step": 70
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.25006091594696045,
      "learning_rate": 4e-05,
      "loss": 0.8853,
      "step": 80
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.21982619166374207,
      "learning_rate": 4.5e-05,
      "loss": 0.8736,
      "step": 90
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.25194063782691956,
      "learning_rate": 5e-05,
      "loss": 0.8369,
      "step": 100
    },
    {
      "epoch": 0.2857142857142857,
      "eval_accuracy": 0.7021857923497268,
      "step": 100
    },
    {
      "epoch": 0.2857142857142857,
      "eval_loss": 0.8057097792625427,
      "eval_runtime": 331.5052,
      "eval_samples_per_second": 1.104,
      "eval_steps_per_second": 1.104,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3147305934848e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}