trainer_state.json

{
  "best_metric": 0.7093373493975904,
  "best_model_checkpoint": "./microsoft-codebert-base-finetuned-defect-detection/checkpoint-2991",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 2991,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.6157,
      "step": 997
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6882530120481928,
      "eval_loss": 0.5484088659286499,
      "eval_runtime": 16.7612,
      "eval_samples_per_second": 237.692,
      "eval_steps_per_second": 29.711,
      "step": 997
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.5023,
      "step": 1994
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.706074297188755,
      "eval_loss": 0.5381159782409668,
      "eval_runtime": 16.7179,
      "eval_samples_per_second": 238.308,
      "eval_steps_per_second": 29.788,
      "step": 1994
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.4403,
      "step": 2991
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7093373493975904,
      "eval_loss": 0.5346359610557556,
      "eval_runtime": 16.7593,
      "eval_samples_per_second": 237.719,
      "eval_steps_per_second": 29.715,
      "step": 2991
    },
    {
      "epoch": 3.0,
      "step": 2991,
      "total_flos": 2.516552000096256e+16,
      "train_loss": 0.5194375239977745,
      "train_runtime": 1111.5213,
      "train_samples_per_second": 86.05,
      "train_steps_per_second": 2.691
    }
  ],
  "logging_steps": 500,
  "max_steps": 2991,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2.516552000096256e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}