long-t5-tglobal-base-finetuned-scisumm
This model is a fine-tuned version of google/long-t5-tglobal-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3892
- Rouge1: 0.1745
- Rouge2: 0.1583
- Rougel: 0.1721
- Rougelsum: 0.1726
- 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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- 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 |
---|---|---|---|---|---|---|---|---|
No log | 0.99 | 28 | 1.4853 | 0.1408 | 0.1085 | 0.1354 | 0.1355 | 19.0 |
No log | 1.97 | 56 | 1.4135 | 0.1637 | 0.1384 | 0.1573 | 0.1578 | 19.0 |
No log | 3.0 | 85 | 1.3955 | 0.1758 | 0.1583 | 0.1733 | 0.1738 | 19.0 |
No log | 3.95 | 112 | 1.3892 | 0.1745 | 0.1583 | 0.1721 | 0.1726 | 19.0 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 10