Downloads · 30 days
5
2% of all-time downloads
intanm/20230429-002-baseline-xlmr-no-qa-ft-clickbait-spoiling
20230429-002-baseline-xlmr-no-qa-ft-clickbait-spoiling is a question answering model from intanm. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
5
2% of all-time downloads
All-time downloads
290
Public
Repo size
5.6 GB
Likes
0
Public
Click a slice to open those files.
.bin1.1 GB · 98%
From the Hugging Face model README
This model is a fine-tuned version of xlm-roberta-base on the None 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 |
|---|---|---|---|
| No log | 1.0 | 200 | 3.1638 |
| No log | 2.0 | 400 | 3.0033 |
| 2.1763 | 3.0 | 600 | 3.3458 |
| 2.1763 | 4.0 | 800 | 3.5899 |
| 1.3037 | 5.0 | 1000 | 3.7460 |
| 1.3037 | 6.0 | 1200 | 4.1879 |
| 1.3037 | 7.0 | 1400 | 4.4619 |
| 0.6515 | 8.0 | 1600 | 4.5780 |
| 0.6515 | 9.0 | 1800 | 4.8045 |
| 0.3926 | 10.0 | 2000 | 4.8065 |