<!-- 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-base-da-multiwoz2.1_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: 0.4778
- Accuracy: 32.7769
- Num: 7365
- Gen Len: 16.4826
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 |
---|---|---|---|---|---|---|
1.3467 | 20.0 | 200 | 0.5529 | 27.029 | 7365 | 15.8964 |
0.563 | 40.0 | 400 | 0.4906 | 30.8271 | 7365 | 16.614 |
0.4667 | 60.0 | 600 | 0.4778 | 32.7769 | 7365 | 16.4826 |
0.4221 | 80.0 | 800 | 0.4793 | 33.2596 | 7365 | 16.4266 |
0.4012 | 100.0 | 1000 | 0.4780 | 33.7326 | 7365 | 16.4459 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1