<!-- 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-tigger
This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0135
- Rouge1: 18.0026
- Rouge2: 10.6544
- Rougel: 17.8917
- Rougelsum: 17.9016
- Gen Len: 16.8967
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.2643 | 1.0 | 1800 | 2.0944 | 18.9867 | 11.8419 | 18.9199 | 18.9118 | 15.0372 |
| 2.1069 | 2.0 | 3600 | 2.0400 | 17.7894 | 10.6008 | 17.6678 | 17.6848 | 16.3131 |
| 2.0446 | 3.0 | 5400 | 2.0172 | 18.4179 | 11.1483 | 18.2905 | 18.3525 | 16.8078 |
| 2.0053 | 4.0 | 7200 | 2.0135 | 18.0026 | 10.6544 | 17.8917 | 17.9016 | 16.8967 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.0
- Datasets 2.12.0
- Tokenizers 0.13.3
