Downloads · 30 days
7
18% of all-time downloads
Legal_GQA_BERT7
farid1088/Legal_GQA_BERT7
Legal_GQA_BERT7 is a question answering model from farid1088. 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
38
Public
Parameters
108M
434 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors434 MB · 100%
At a glance
- Task
- Question Answering
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Mar 3, 2024
- Updated
- Mar 4, 2024
- SHA
- f8d5e160
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. -->
Legal_GQA_BERT7
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.7785
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: 32
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 5 | 3.9923 |
| No log | 2.0 | 10 | 3.5716 |
| No log | 3.0 | 15 | 3.4393 |
| No log | 4.0 | 20 | 3.4841 |
| No log | 5.0 | 25 | 3.5053 |
| No log | 6.0 | 30 | 3.6398 |
| No log | 7.0 | 35 | 3.9208 |
| No log | 8.0 | 40 | 4.0914 |
| No log | 9.0 | 45 | 4.2757 |
| No log | 10.0 | 50 | 4.3265 |
| No log | 11.0 | 55 | 4.4341 |
| No log | 12.0 | 60 | 4.6095 |
| No log | 13.0 | 65 | 4.7127 |
| No log | 14.0 | 70 | 4.7583 |
| No log | 15.0 | 75 | 4.7729 |
| No log | 16.0 | 80 | 4.7785 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.7
- Tokenizers 0.15.0
- Task
- Question Answering
- Library
- transformers
- Type
- bert
- Created
- Mar 3, 2024
- Updated
- Mar 4, 2024