T5-tuned/t5_disfluency/checkpoint-2055/trainer_state.json

{
  "best_metric": 0.08729018270969391,
  "best_model_checkpoint": "/work/07144/yw23374/ls6/disfluency_predict/produce_disfluency/model/T5-tuned/t5_disfluency/checkpoint-2055",
  "epoch": 5.0,
  "global_step": 2055,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.14043059945106506,
      "eval_runtime": 9.8338,
      "eval_samples_per_second": 111.35,
      "eval_steps_per_second": 4.678,
      "step": 411
    },
    {
      "epoch": 1.22,
      "learning_rate": 8.262078554049358e-05,
      "loss": 0.8396,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.11000446230173111,
      "eval_runtime": 9.7828,
      "eval_samples_per_second": 111.931,
      "eval_steps_per_second": 4.702,
      "step": 822
    },
    {
      "epoch": 2.43,
      "learning_rate": 6.524157108098714e-05,
      "loss": 0.1315,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.10077913105487823,
      "eval_runtime": 9.7096,
      "eval_samples_per_second": 112.774,
      "eval_steps_per_second": 4.738,
      "step": 1233
    },
    {
      "epoch": 3.65,
      "learning_rate": 4.7862356621480715e-05,
      "loss": 0.3494,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.09076198935508728,
      "eval_runtime": 9.7542,
      "eval_samples_per_second": 112.259,
      "eval_steps_per_second": 4.716,
      "step": 1644
    },
    {
      "epoch": 4.87,
      "learning_rate": 3.0483142161974283e-05,
      "loss": 0.0961,
      "step": 2000
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.08729018270969391,
      "eval_runtime": 9.7878,
      "eval_samples_per_second": 111.874,
      "eval_steps_per_second": 4.7,
      "step": 2055
    }
  ],
  "max_steps": 2877,
  "num_train_epochs": 7,
  "total_flos": 8427651115253760.0,
  "trial_name": null,
  "trial_params": null
}