Downloads · 30 days
4
11% of all-time downloads
mdeberta-v3-base_EW-TT-PE_U1_S0_DROP1_mdeberta_E2_DEV100.0
pgajo/mdeberta-v3-base_EW-TT-PE_U1_S0_DROP1_mdeberta_E2_DEV100.0
mdeberta-v3-base_EW-TT-PE_U1_S0_DROP1_mdeberta_E2_DEV100.0 is a question answering model from pgajo. Use it when the input is a question plus a passage. It is set up for transformers.
All-time downloads
38
Public
Parameters
278M
1.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 98%
At a glance
- Task
- Question Answering
- Library
- transformers
- Model type
- deberta-v2
- Access
- Public
- Created
- Feb 11, 2024
- Updated
- Feb 11, 2024
- SHA
- 3f703910
Try a prompt
Model card
From the Hugging Face model README
Model description:
Model: microsoft/mdeberta-v3-base
Dataset: TASTEset
Unshuffled ratio: ['1']
Shuffled ratio: ['0']
Best exact match epoch: 2
Best exact match: 99.72
Best epoch: 2
Drop duplicates: ['1']
Max epochs = 10
Optimizer lr = 3e-05
Optimizer eps = 1e-08
Batch size = 8
Dataset path = pgajo/EW-TT-PE_U1_S0_DROP1_mdeberta
Results
| epoch | train_loss | train_f1 | train_exact | dev_loss | dev_f1 | dev_exact | test_loss | test_f1 | test_exact |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 1.1 | 75.67 | 72.08 | 0.04 | 99.63 | 98.9 | 0 | 0 | 0 |
| 2 | 0.05 | 99.41 | 98.96 | 0.02 | 99.95 | 99.72 | 0 | 0 | 0 |
| 3 | 0.03 | 99.51 | 99.03 | 0.01 | 99.95 | 99.72 | 0 | 0 | 0 |
| 4 | 0.01 | 99.82 | 99.72 | 0.01 | 99.95 | 99.72 | 0 | 0 | 0 |
| 5 | 0.01 | 99.83 | 99.79 | 0.01 | 99.72 | 99.17 | 0 | 0 | 0 |
- Task
- Question Answering
- Library
- transformers
- Type
- deberta-v2
- Created
- Feb 11, 2024
- Updated
- Feb 11, 2024