Downloads · 30 days
42
0% of all-time downloads
TinyBERT_General_4L_312D-squad
haritzpuerto/TinyBERT_General_4L_312D-squad
TinyBERT_General_4L_312D-squad is a question answering model from haritzpuerto. 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
67K
Public
Repo size
570 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin57 MB · 98%
At a glance
- Task
- Question Answering
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jun 5, 2022
- Updated
- Jun 5, 2022
- SHA
- 9a2840bf
Try a prompt
Datasets
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. -->
TinyBERT_General_4L_312D-squad
This model is a fine-tuned version of huawei-noah/TinyBERT_General_4L_312D on the squad dataset. It achieves the following results on the evaluation set:
- exact_match: 33.301797540208135
- f1: 45.03886349847048
- Loss: 2.5477
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: 1e-05
- train_batch_size: 20
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.7498 | 1.0 | 4380 | 2.5477 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
- Task
- Question Answering
- Library
- transformers
- Type
- bert
- Created
- Jun 5, 2022
- Updated
- Jun 5, 2022