metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: t5-base-da-multiwoz2.1_500
results: []
t5-base-da-multiwoz2.1_500
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4253
- Accuracy: 22.6359
- Num: 3689
- Gen Len: 15.4806
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: 24
- eval_batch_size: 48
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Num | Gen Len |
|---|---|---|---|---|---|---|
| 0.5137 | 2.78 | 400 | 0.4454 | 21.1276 | 3689 | 15.569 |
| 0.4673 | 5.56 | 800 | 0.4329 | 21.7406 | 3689 | 15.4573 |
| 0.4591 | 8.33 | 1200 | 0.4253 | 22.6359 | 3689 | 15.4806 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1