trainer_state.json

{
  "best_metric": 0.8450704225352113,
  "best_model_checkpoint": "/cm/archive/namlh35/code-comment-classification/results/selection_wo_valid/Verification/codebert-postpretrained-HSUM-4layers-datav2-class-comment/java_deprecation/checkpoint-250",
  "epoch": 3.0303030303030303,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.38,
      "eval_f1": 0.0,
      "eval_loss": 0.056170761585235596,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 15.1951,
      "eval_samples_per_second": 139.058,
      "eval_steps_per_second": 8.753,
      "step": 50
    },
    {
      "epoch": 0.76,
      "eval_f1": 0.8059701492537312,
      "eval_loss": 0.029947876930236816,
      "eval_precision": 0.9,
      "eval_recall": 0.7297297297297297,
      "eval_runtime": 8.6149,
      "eval_samples_per_second": 245.272,
      "eval_steps_per_second": 15.438,
      "step": 100
    },
    {
      "epoch": 1.14,
      "eval_f1": 0.8169014084507041,
      "eval_loss": 0.03486325964331627,
      "eval_precision": 0.8529411764705882,
      "eval_recall": 0.7837837837837838,
      "eval_runtime": 8.6487,
      "eval_samples_per_second": 244.315,
      "eval_steps_per_second": 15.378,
      "step": 150
    },
    {
      "epoch": 1.52,
      "eval_f1": 0.8169014084507041,
      "eval_loss": 0.030027925968170166,
      "eval_precision": 0.8529411764705882,
      "eval_recall": 0.7837837837837838,
      "eval_runtime": 8.7028,
      "eval_samples_per_second": 242.796,
      "eval_steps_per_second": 15.282,
      "step": 200
    },
    {
      "epoch": 1.89,
      "eval_f1": 0.8450704225352113,
      "eval_loss": 0.025771863758563995,
      "eval_precision": 0.8823529411764706,
      "eval_recall": 0.8108108108108109,
      "eval_runtime": 8.4673,
      "eval_samples_per_second": 249.547,
      "eval_steps_per_second": 15.707,
      "step": 250
    },
    {
      "epoch": 2.27,
      "eval_f1": 0.823529411764706,
      "eval_loss": 0.03130728378891945,
      "eval_precision": 0.9032258064516129,
      "eval_recall": 0.7567567567567568,
      "eval_runtime": 9.0162,
      "eval_samples_per_second": 234.356,
      "eval_steps_per_second": 14.751,
      "step": 300
    },
    {
      "epoch": 2.65,
      "eval_f1": 0.8219178082191781,
      "eval_loss": 0.028314711526036263,
      "eval_precision": 0.8333333333333334,
      "eval_recall": 0.8108108108108109,
      "eval_runtime": 9.6845,
      "eval_samples_per_second": 218.183,
      "eval_steps_per_second": 13.733,
      "step": 350
    },
    {
      "epoch": 3.03,
      "eval_f1": 0.8219178082191781,
      "eval_loss": 0.030898844823241234,
      "eval_precision": 0.8333333333333334,
      "eval_recall": 0.8108108108108109,
      "eval_runtime": 8.964,
      "eval_samples_per_second": 235.72,
      "eval_steps_per_second": 14.837,
      "step": 400
    }
  ],
  "logging_steps": 500,
  "max_steps": 1320,
  "num_train_epochs": 10,
  "save_steps": 50,
  "total_flos": 1119873879427584.0,
  "trial_name": null,
  "trial_params": null
}