T5-tuned/t5_disfluency/checkpoint-60/trainer_state.json

{
  "best_metric": 0.27354106307029724,
  "best_model_checkpoint": "t5_disfluency/checkpoint-60",
  "epoch": 5.0,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 4.745517730712891,
      "eval_runtime": 0.3017,
      "eval_samples_per_second": 106.065,
      "eval_steps_per_second": 6.629,
      "step": 12
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.9129016399383545,
      "eval_runtime": 0.3004,
      "eval_samples_per_second": 106.529,
      "eval_steps_per_second": 6.658,
      "step": 24
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.9317156076431274,
      "eval_runtime": 0.2946,
      "eval_samples_per_second": 108.629,
      "eval_steps_per_second": 6.789,
      "step": 36
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.42531687021255493,
      "eval_runtime": 0.3011,
      "eval_samples_per_second": 106.271,
      "eval_steps_per_second": 6.642,
      "step": 48
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.27354106307029724,
      "eval_runtime": 0.3028,
      "eval_samples_per_second": 105.672,
      "eval_steps_per_second": 6.605,
      "step": 60
    }
  ],
  "max_steps": 84,
  "num_train_epochs": 7,
  "total_flos": 242232913428480.0,
  "trial_name": null,
  "trial_params": null
}