Downloads · 30 days
7
2% of all-time downloads
DLL888/bert-base-uncased-squad
bert-base-uncased-squad is a question answering model from DLL888. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as apache-2.0.
probably proofread and complete it, then remove this comment. --
Downloads · 30 days
7
2% of all-time downloads
All-time downloads
337
Public
Repo size
875 MB
Likes
0
Public
Click a slice to open those files.
.h5436 MB · 99%
From the Hugging Face model README
This model is a fine-tuned version of bert-base-uncased on SQuAD dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
Trained in Google Colab Pro with the following specs:
Training took about 26 minutes for two epochs.
The following hyperparameters were used during training:
| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|---|---|---|---|---|---|---|
| 1.4348 | 0.6368 | 0.5974 | 1.0155 | 0.7193 | 0.6825 | 0 |
| 0.8072 | 0.7735 | 0.7320 | 0.9990 | 0.7302 | 0.6983 | 1 |