T5-tuned/t5_disfluency/monolingual/checkpoint-954/trainer_state.json

{
  "best_metric": 0.0007711458601988852,
  "best_model_checkpoint": "/work/07144/yw23374/ls6/disfluency_predict/produce_disfluency/model/T5-tuned/t5_disfluency/monolingual/checkpoint-954",
  "epoch": 6.0,
  "global_step": 954,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.05837405100464821,
      "eval_runtime": 236.4036,
      "eval_samples_per_second": 0.66,
      "eval_steps_per_second": 0.66,
      "step": 159
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.010237111710011959,
      "eval_runtime": 234.8187,
      "eval_samples_per_second": 0.664,
      "eval_steps_per_second": 0.664,
      "step": 318
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.0026975590735673904,
      "eval_runtime": 234.2566,
      "eval_samples_per_second": 0.666,
      "eval_steps_per_second": 0.666,
      "step": 477
    },
    {
      "epoch": 3.14,
      "learning_rate": 2.75381850853549e-05,
      "loss": 2.6202,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.0009143440402112901,
      "eval_runtime": 235.0238,
      "eval_samples_per_second": 0.664,
      "eval_steps_per_second": 0.664,
      "step": 636
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.0008895916980691254,
      "eval_runtime": 233.4383,
      "eval_samples_per_second": 0.668,
      "eval_steps_per_second": 0.668,
      "step": 795
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.0007711458601988852,
      "eval_runtime": 234.5132,
      "eval_samples_per_second": 0.665,
      "eval_steps_per_second": 0.665,
      "step": 954
    }
  ],
  "max_steps": 1113,
  "num_train_epochs": 7,
  "total_flos": 326599997128704.0,
  "trial_name": null,
  "trial_params": null
}