LED_multi_lexsum_peft
This model is a fine-tuned version of pszemraj/led-large-book-summary on an allenai/multi_lexsum dataset. It achieves the following results on the evaluation set:
- Loss: 4.2303
- Rouge1: 0.3156
- Rouge2: 0.1258
- Rougel: 0.1548
- Rougelsum: 0.185
- Bert Precision: 0.8468
- Bert Recall: 0.887
- Bert F1: 0.8664
- Gen Len: 949.968
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bert Precision | Bert Recall | Bert F1 | Gen Len |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 6.2726 | 1.0 | 850 | 4.2979 | 0.3208 | 0.1202 | 0.1551 | 0.185 | 0.8724 | 0.8797 | 0.876 | 906.8 |
| 4.5041 | 2.0 | 1700 | 4.2303 | 0.3156 | 0.1258 | 0.1548 | 0.185 | 0.8468 | 0.887 | 0.8664 | 949.968 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 3
Model tree for Rud/LED_multi_lexsum_peft
Base model
pszemraj/led-large-book-summary