T5-tuned/t5_disfluency/bilingual/checkpoint-980/trainer_state.json

{
  "best_metric": 0.0001887563121272251,
  "best_model_checkpoint": "/work/07144/yw23374/ls6/disfluency_predict/produce_disfluency/model/T5-tuned/t5_disfluency/bilingual/checkpoint-980",
  "epoch": 5.0,
  "global_step": 980,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.014369768090546131,
      "eval_runtime": 11.164,
      "eval_samples_per_second": 26.783,
      "eval_steps_per_second": 8.957,
      "step": 196
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.0007745437906123698,
      "eval_runtime": 11.1109,
      "eval_samples_per_second": 26.91,
      "eval_steps_per_second": 9.0,
      "step": 392
    },
    {
      "epoch": 2.55,
      "learning_rate": 3.177842565597668e-05,
      "loss": 2.0974,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.00042322053923271596,
      "eval_runtime": 11.0688,
      "eval_samples_per_second": 27.013,
      "eval_steps_per_second": 9.034,
      "step": 588
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.0002689457614906132,
      "eval_runtime": 11.0824,
      "eval_samples_per_second": 26.98,
      "eval_steps_per_second": 9.023,
      "step": 784
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.0001887563121272251,
      "eval_runtime": 11.0527,
      "eval_samples_per_second": 27.052,
      "eval_steps_per_second": 9.048,
      "step": 980
    }
  ],
  "max_steps": 1372,
  "num_train_epochs": 7,
  "total_flos": 1003079655751680.0,
  "trial_name": null,
  "trial_params": null
}