Downloads · 30 days
10
29% of all-time downloads
mbert-idkmrc-webis
intanm/mbert-idkmrc-webis
mbert-idkmrc-webis is a question answering model from intanm. 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
35
Public
Repo size
3.5 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
- Oct 29, 2023
- Updated
- Oct 29, 2023
- SHA
- d0143a90
Try a prompt
Base models
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. -->
mbert-idkmrc-webis
This model is a fine-tuned version of rifkiaputri/mbert-base-id-finetune-idk-mrc on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.1790
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-05
- 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 | 200 | 3.0307 |
| No log | 2.0 | 400 | 2.9397 |
| 2.8458 | 3.0 | 600 | 3.1800 |
| 2.8458 | 4.0 | 800 | 3.5039 |
| 1.3208 | 5.0 | 1000 | 3.9778 |
| 1.3208 | 6.0 | 1200 | 4.4905 |
| 1.3208 | 7.0 | 1400 | 4.7502 |
| 0.5372 | 8.0 | 1600 | 4.8481 |
| 0.5372 | 9.0 | 1800 | 5.1920 |
| 0.2723 | 10.0 | 2000 | 5.1790 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Task
- Question Answering
- Library
- transformers
- Type
- bert
- Created
- Oct 29, 2023
- Updated
- Oct 29, 2023