{
  "best_metric": 0.5226846644169478,
  "best_model_checkpoint": "citation_intent_classification_roberta_dapt/checkpoint-316",
  "epoch": 4.0,
  "global_step": 422,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.95,
      "learning_rate": 1.9250253292806485e-05,
      "loss": 1.4387,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6140350877192983,
      "eval_f1_macro": 0.24471943248844252,
      "eval_loss": 1.0765323638916016,
      "eval_runtime": 0.3327,
      "eval_samples_per_second": 342.624,
      "eval_steps_per_second": 24.044,
      "step": 105
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.7223910840932118e-05,
      "loss": 1.0272,
      "step": 200
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7192982456140351,
      "eval_f1_macro": 0.34632500717772036,
      "eval_loss": 0.881606936454773,
      "eval_runtime": 0.3227,
      "eval_samples_per_second": 353.261,
      "eval_steps_per_second": 24.79,
      "step": 211
    },
    {
      "epoch": 2.84,
      "learning_rate": 1.5197568389057753e-05,
      "loss": 0.815,
      "step": 300
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7719298245614035,
      "eval_f1_macro": 0.5226846644169478,
      "eval_loss": 0.807743489742279,
      "eval_runtime": 0.3233,
      "eval_samples_per_second": 352.616,
      "eval_steps_per_second": 24.745,
      "step": 316
    },
    {
      "epoch": 3.79,
      "learning_rate": 1.3171225937183386e-05,
      "loss": 0.5604,
      "step": 400
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7280701754385965,
      "eval_f1_macro": 0.4904761087856539,
      "eval_loss": 0.7902174592018127,
      "eval_runtime": 0.3265,
      "eval_samples_per_second": 349.161,
      "eval_steps_per_second": 24.502,
      "step": 422
    }
  ],
  "max_steps": 1050,
  "num_train_epochs": 10,
  "total_flos": 352832263206048.0,
  "trial_name": null,
  "trial_params": null
}