Downloads · 30 days
0
anliR2-bert-base-uncased-kd
asun17904/anliR2-bert-base-uncased-kd
anliR2-bert-base-uncased-kd is a machine learning model from asun17904. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as mit.
Access
Public
Updated Jan 30, 2024
Repo size
10.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin438 MB · 100%
At a glance
- Library
- pytorch
- License
- mit
- Access
- Public
- Created
- Jan 28, 2024
- Updated
- Jan 30, 2024
- SHA
- 693a9ffa
Model card
From the Hugging Face model README
Knowledge Continuity Regularized Network
Dataset: ANLI Round: None
Trainer Hyperparameters:
lr= 1e-05per_device_batch_size= 64gradient_accumulation_steps= 1weight_decay= 0.0seed= 42
Regularization Hyperparameters
numerical stability denominator constant= 0.01lambda= 0.001alpha= 2.0beta= 2.0
Extended Logs:
| eval_loss | eval_accuracy | epoch |
|---|---|---|
| 35.369 | 0.413 | 1.0 |
| 36.104 | 0.391 | 2.0 |
| 36.027 | 0.398 | 3.0 |
| 36.128 | 0.400 | 4.0 |
| 36.149 | 0.395 | 5.0 |
| 36.231 | 0.392 | 6.0 |
| 35.865 | 0.411 | 7.0 |
| 35.711 | 0.422 | 8.0 |
| 35.913 | 0.415 | 9.0 |
| 35.810 | 0.412 | 10.0 |
| 35.908 | 0.411 | 11.0 |
| 35.887 | 0.413 | 12.0 |
| 35.980 | 0.407 | 13.0 |
| 35.761 | 0.416 | 14.0 |
Test Accuracy: 0.413
- Library
- pytorch
- License
- mit
- Languages
- en
- Created
- Jan 28, 2024
- Updated
- Jan 30, 2024