Downloads · 30 days
4
5% of all-time downloads
mhdafifan/xlm-roberta-squad-id-LR-2e-05-BS-8-ML-512
xlm-roberta-squad-id-LR-2e-05-BS-8-ML-512 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
4
5% of all-time downloads
All-time downloads
76
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 FacebookAI/xlm-roberta-base on the squad_v2_id 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 |
|---|---|---|---|---|---|
| 1.3549 | 1.0 | 16325 | 1.2145 | 63.4634 | 59.3868 |
| 1.1768 | 2.0 | 32650 | 1.1055 | 66.9538 | 62.0315 |
| 0.9496 | 3.0 | 48975 | 1.1979 | 67.1915 | 61.7704 |
| 0.7631 | 4.0 | 65300 | 1.2978 | 67.0689 | 61.8378 |
| 0.5868 | 5.0 | 81625 | 1.4163 | 67.3285 | 62.2758 |