trainer_state.json

{
  "best_metric": 0.0809762105345726,
  "best_model_checkpoint": "bert_large_finetune_bloom_question_classifier_enhanced\\checkpoint-390",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 520,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9486301369863014,
      "eval_loss": 0.18780267238616943,
      "eval_runtime": 14.9911,
      "eval_samples_per_second": 38.956,
      "eval_steps_per_second": 2.201,
      "step": 130
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.964041095890411,
      "eval_loss": 0.15712498128414154,
      "eval_runtime": 14.9873,
      "eval_samples_per_second": 38.966,
      "eval_steps_per_second": 2.202,
      "step": 260
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9811643835616438,
      "eval_loss": 0.0809762105345726,
      "eval_runtime": 14.9624,
      "eval_samples_per_second": 39.031,
      "eval_steps_per_second": 2.206,
      "step": 390
    },
    {
      "epoch": 3.85,
      "learning_rate": 7.692307692307694e-07,
      "loss": 0.2409,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9811643835616438,
      "eval_loss": 0.08374008536338806,
      "eval_runtime": 14.9759,
      "eval_samples_per_second": 38.996,
      "eval_steps_per_second": 2.204,
      "step": 520
    }
  ],
  "logging_steps": 500,
  "max_steps": 520,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 8496707809392000.0,
  "trial_name": null,
  "trial_params": null
}