Downloads · 30 days
3
13% of all-time downloads
bert-base-multilingual-cased
AnshulRustogi/bert-base-multilingual-cased
bert-base-multilingual-cased is a question answering model from AnshulRustogi. Use it when the input is a question plus a passage. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
24
Public
Repo size
4.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin709 MB · 99%
At a glance
- Task
- Question Answering
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- May 3, 2023
- Updated
- May 3, 2023
- SHA
- 60dbb2d2
Try a prompt
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
bert-base-multilingual-cased1
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8440
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 214 | 4.0240 |
| No log | 2.0 | 428 | 2.6347 |
| 4.063 | 3.0 | 642 | 2.3167 |
| 4.063 | 4.0 | 856 | 2.1420 |
| 2.3039 | 5.0 | 1070 | 2.0258 |
| 2.3039 | 6.0 | 1284 | 1.9483 |
| 2.3039 | 7.0 | 1498 | 1.8992 |
| 1.9096 | 8.0 | 1712 | 1.8669 |
| 1.9096 | 9.0 | 1926 | 1.8460 |
| 1.7069 | 10.0 | 2140 | 1.8440 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Question Answering
- Library
- transformers
- Type
- bert
- Created
- May 3, 2023
- Updated
- May 3, 2023