Edit model card

flan-t5-base-da-multiwoz2.0_80-loss-ep100

This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4747
  • Accuracy: 33.008
  • Num: 7358
  • Gen Len: 16.5684

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 60
  • eval_batch_size: 400
  • seed: 1799
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss Accuracy Num Gen Len
1.3481 20.0 200 0.5537 26.9473 7358 15.6079
0.564 40.0 400 0.4902 31.3033 7358 16.6331
0.4647 60.0 600 0.4747 33.008 7358 16.5684
0.4171 80.0 800 0.4818 33.1704 7358 16.5529
0.4009 100.0 1000 0.4793 33.533 7358 16.4897

Framework versions

  • Transformers 4.18.0
  • Pytorch 1.10.0+cu111
  • Datasets 2.5.1
  • Tokenizers 0.12.1
Downloads last month
1
Inference API
This model can be loaded on Inference API (serverless).