<!-- 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-loss-ep50
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: 0.3367
- Accuracy: 42.2298
- Num: 7358
- Gen Len: 15.2759
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: 192
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Num | Gen Len |
|---|---|---|---|---|---|---|
| 1.1324 | 0.89 | 200 | 0.4829 | 29.9104 | 7358 | 13.9689 |
| 0.5151 | 1.79 | 400 | 0.4123 | 33.4043 | 7358 | 14.642 |
| 0.4551 | 2.68 | 600 | 0.3829 | 35.7701 | 7358 | 15.1242 |
| 0.4219 | 3.57 | 800 | 0.3643 | 36.7057 | 7358 | 15.3396 |
| 0.3957 | 4.46 | 1000 | 0.3564 | 38.4778 | 7358 | 14.7546 |
| 0.3794 | 5.36 | 1200 | 0.3535 | 39.5482 | 7358 | 15.7898 |
| 0.3691 | 6.25 | 1400 | 0.3462 | 40.9266 | 7358 | 15.1525 |
| 0.3572 | 7.14 | 1600 | 0.3433 | 41.2441 | 7358 | 15.5348 |
| 0.3458 | 8.04 | 1800 | 0.3423 | 41.3965 | 7358 | 15.9547 |
| 0.3383 | 8.93 | 2000 | 0.3367 | 42.2298 | 7358 | 15.2759 |
| 0.3298 | 9.82 | 2200 | 0.3369 | 42.0268 | 7358 | 15.1411 |
| 0.3193 | 10.71 | 2400 | 0.3377 | 42.2034 | 7358 | 15.6401 |
| 0.3126 | 11.61 | 2600 | 0.3403 | 43.2389 | 7358 | 15.657 |
| 0.3049 | 12.5 | 2800 | 0.3380 | 43.1584 | 7358 | 14.8736 |
| 0.3014 | 13.39 | 3000 | 0.3394 | 43.1853 | 7358 | 15.4948 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1
