<!-- 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-multiwoz2.1_400-ep10
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: 0.3731
- Accuracy: 38.5004
- Num: 7365
- Gen Len: 15.7255
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: 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 |
---|---|---|---|---|---|---|
1.19 | 1.16 | 200 | 0.5197 | 29.041 | 7365 | 13.9306 |
0.5494 | 2.33 | 400 | 0.4373 | 32.846 | 7365 | 15.4056 |
0.4725 | 3.49 | 600 | 0.4054 | 35.0281 | 7365 | 15.8865 |
0.4448 | 4.65 | 800 | 0.3899 | 36.8807 | 7365 | 16.027 |
0.4179 | 5.81 | 1000 | 0.3814 | 36.7527 | 7365 | 15.021 |
0.4048 | 6.98 | 1200 | 0.3766 | 37.2922 | 7365 | 15.6229 |
0.3902 | 8.14 | 1400 | 0.3731 | 38.5004 | 7365 | 15.7255 |
0.3851 | 9.3 | 1600 | 0.3720 | 38.4204 | 7365 | 15.7783 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1