<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
flan-t5-large-da-multiwoz2.0_800-ep20-nonstop
This model is a fine-tuned version of google/flan-t5-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3410
- Accuracy: 43.8809
- Num: 7358
- Gen Len: 15.5621
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: 16
- eval_batch_size: 64
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Num | Gen Len |
|---|---|---|---|---|---|---|
| 0.6162 | 2.98 | 1000 | 0.3647 | 37.6718 | 7358 | 14.561 |
| 0.3779 | 5.95 | 2000 | 0.3429 | 40.5537 | 7358 | 15.6453 |
| 0.3392 | 8.93 | 3000 | 0.3363 | 42.0162 | 7358 | 15.4191 |
| 0.3122 | 11.9 | 4000 | 0.3379 | 43.6228 | 7358 | 15.4768 |
| 0.2969 | 14.88 | 5000 | 0.3381 | 44.0703 | 7358 | 15.6844 |
| 0.2845 | 17.86 | 6000 | 0.3413 | 43.946 | 7358 | 15.5164 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1
