flan-t5-small-book_summarizer
This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1264
- Rouge1: 7.7091
- Rouge2: 1.308
- Rougel: 6.1382
- Rougelsum: 7.2391
- Gen Len: 19.0
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 125 | 3.1340 | 6.9387 | 1.0696 | 5.7064 | 6.5921 | 18.998 |
| No log | 2.0 | 250 | 3.1286 | 7.3927 | 1.1818 | 5.9991 | 6.9879 | 19.0 |
| No log | 3.0 | 375 | 3.1285 | 7.7059 | 1.2952 | 6.1643 | 7.2308 | 19.0 |
| 3.4857 | 4.0 | 500 | 3.1264 | 7.7091 | 1.308 | 6.1382 | 7.2391 | 19.0 |
| 3.4857 | 5.0 | 625 | 3.1269 | 7.7705 | 1.3087 | 6.1761 | 7.3256 | 19.0 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0