Downloads · 30 days
16
19% of all-time downloads
mhdafifan/xlm-roberta-squad-qasina-LR-5e-06-BS-8-ML-384
xlm-roberta-squad-qasina-LR-5e-06-BS-8-ML-384 is a question answering model from mhdafifan. 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
16
19% of all-time downloads
All-time downloads
84
Public
Parameters
277M
1.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.1 GB · 98%
From the Hugging Face model README
This model is a fine-tuned version of mhdafifan/xlm-roberta-squad-id-LR-2e-05-BS-16-ML-384 on the QASiNa 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 | F1 | Exact Match |
|---|---|---|---|---|---|
| 1.1836 | 1.0 | 77 | 1.1817 | 79.0581 | 64.1509 |
| 0.9345 | 2.0 | 154 | 1.1492 | 75.8319 | 60.3774 |
| 0.3746 | 3.0 | 231 | 1.2317 | 77.4529 | 62.2642 |
| 0.3547 | 4.0 | 308 | 1.3021 | 77.8021 | 62.2642 |