trainer_state.json

{
  "best_metric": 0.0010390824172645807,
  "best_model_checkpoint": "./model_stereotype/checkpoint-544",
  "epoch": 2.0,
  "global_step": 544,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 1.866666666666667e-05,
      "loss": 0.0021,
      "step": 272
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7658022690437601,
      "eval_f1": 0.7756211180124224,
      "eval_loss": 0.0014655768172815442,
      "eval_precision": 0.7444113263785395,
      "eval_recall": 0.8095623987034035,
      "eval_runtime": 7.495,
      "eval_samples_per_second": 658.575,
      "eval_steps_per_second": 41.228,
      "step": 272
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.7333333333333336e-05,
      "loss": 0.0007,
      "step": 544
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7862641815235009,
      "eval_f1": 0.7903001391373485,
      "eval_loss": 0.0010390824172645807,
      "eval_precision": 0.7756535310183379,
      "eval_recall": 0.8055105348460292,
      "eval_runtime": 7.5689,
      "eval_samples_per_second": 652.141,
      "eval_steps_per_second": 40.825,
      "step": 544
    }
  ],
  "max_steps": 4080,
  "num_train_epochs": 15,
  "total_flos": 446877683088000.0,
  "trial_name": null,
  "trial_params": null
}