Downloads · 30 days
6
18% of all-time downloads
taiypeo/bart-large-gigaword-rouge-3-loss-differentiable-10-cnt-supervised
bart-large-gigaword-rouge-3-loss-differentiable-10-cnt-supervised is a machine learning model from taiypeo. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
6
18% of all-time downloads
All-time downloads
34
Public
Parameters
406M
22.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.6 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 4.0729 | 1.8 | 5 | 3.5930 | 0.2888 | 0.1038 | 0.2511 | 0.2511 |
| 2.4277 | 3.4 | 10 | 2.7423 | 0.3837 | 0.1746 | 0.3494 | 0.3491 |
| 2.3159 | 5.0 | 15 | 2.6618 | 0.3908 | 0.1809 | 0.3603 | 0.3602 |
| 1.3652 | 6.8 | 20 | 2.6958 | 0.3988 | 0.1838 | 0.3651 | 0.365 |
| 0.6817 | 8.4 | 25 | 2.7761 | 0.4034 | 0.1862 | 0.368 | 0.3682 |
| 0.6196 | 10.0 | 30 | 2.8482 | 0.4012 | 0.1831 | 0.3671 | 0.367 |
| 0.4153 | 11.8 | 35 | 2.8866 | 0.4015 | 0.1823 | 0.3686 | 0.3686 |
| 0.0946 | 13.4 | 40 | 2.9000 | 0.3987 | 0.1797 | 0.3653 | 0.3654 |
| 0.2684 | 15.0 | 45 | 2.9176 | 0.3977 | 0.1789 | 0.3635 | 0.3635 |
| 0.4239 | 16.8 | 50 | 2.9608 | 0.3994 | 0.18 | 0.3657 | 0.3661 |