bart_summarisation
This model is a fine-tuned version of MeetK/bart_summarisation on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7168
- Rouge1: 0.3288
- Rouge2: 0.1335
- Rougel: 0.2493
- Rougelsum: 0.2495
- Gen Len: 61.398
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: 16
- 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 | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 313 | 1.6942 | 0.3296 | 0.1385 | 0.2507 | 0.2507 | 60.888 |
1.4988 | 2.0 | 626 | 1.7168 | 0.3288 | 0.1335 | 0.2493 | 0.2495 | 61.398 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cpu
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 6