<!-- 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-nlg-multiwoz2.0_400
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9323
- Rouge1: 36.3522
- Rouge2: 19.5982
- Rougel: 33.0495
- Rougelsum: 34.4791
- Gen Len: 17.7927
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: 8
- eval_batch_size: 24
- 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 | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.4929 | 0.58 | 200 | 1.1051 | 33.8407 | 17.022 | 30.6518 | 32.2374 | 17.7195 |
| 1.1546 | 1.17 | 400 | 1.0221 | 33.4159 | 17.73 | 30.4168 | 31.6796 | 17.8444 |
| 1.0597 | 1.75 | 600 | 0.9819 | 34.8735 | 18.3373 | 31.5435 | 33.0184 | 17.7802 |
| 0.9863 | 2.33 | 800 | 0.9672 | 34.7204 | 18.0945 | 31.5299 | 32.9849 | 17.6341 |
| 0.9689 | 2.92 | 1000 | 0.9509 | 35.7006 | 19.2988 | 32.4312 | 33.8706 | 17.8081 |
| 0.9279 | 3.5 | 1200 | 0.9432 | 35.5086 | 19.1375 | 32.3084 | 33.7471 | 17.9298 |
| 0.9187 | 4.08 | 1400 | 0.9414 | 35.591 | 19.3273 | 32.4831 | 33.914 | 17.7133 |
| 0.8865 | 4.66 | 1600 | 0.9323 | 36.3522 | 19.5982 | 33.0495 | 34.4791 | 17.7927 |
| 0.8735 | 5.25 | 1800 | 0.9311 | 35.7889 | 18.75 | 32.3179 | 33.9012 | 17.8027 |
| 0.8556 | 5.83 | 2000 | 0.9284 | 36.1266 | 19.5539 | 32.7835 | 34.263 | 17.7171 |
| 0.8479 | 6.41 | 2200 | 0.9277 | 36.21 | 19.5396 | 32.8933 | 34.3317 | 17.8339 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1
