{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.19900497512437812,
  "eval_steps": 35,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028429282160625444,
      "grad_norm": 11.854507446289062,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.9685,
      "step": 5
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 2.9244329929351807,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.5325,
      "step": 10
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 2.8243346214294434,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.2362,
      "step": 15
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 1.644755244255066,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.2163,
      "step": 20
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 5.001497268676758,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.2204,
      "step": 25
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 1.6563094854354858,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.2098,
      "step": 30
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 1.911417841911316,
      "learning_rate": 0.0001,
      "loss": 0.1803,
      "step": 35
    },
    {
      "epoch": 0.19900497512437812,
      "eval_loss": 0.16817478835582733,
      "eval_runtime": 318.5306,
      "eval_samples_per_second": 7.849,
      "eval_steps_per_second": 7.849,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 350,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 35,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.667852949478441e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}