Downloads · 30 days
0
anliR3-bert-base-uncased-kd
asun17904/anliR3-bert-base-uncased-kd
anliR3-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
3.1 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
- 2ea27a50
Model card
From the Hugging Face model README
Knowledge Continuity Regularized Network
Dataset: ANLI Round: None
Trainer Hyperparameters:
lr= 5e-05per_device_batch_size= 32gradient_accumulation_steps= 1weight_decay= 0.0seed= 42
Regularization Hyperparameters
numerical stability denominator constant= 0.01lambda= 0.01alpha= 2.0beta= 1.0
Extended Logs:
| eval_loss | eval_accuracy | epoch |
|---|---|---|
| 35.436 | 0.413 | 1.0 |
| 35.895 | 0.412 | 2.0 |
| 34.939 | 0.440 | 3.0 |
| 34.845 | 0.451 | 4.0 |
| 35.466 | 0.432 | 5.0 |
| 34.967 | 0.444 | 6.0 |
| 34.487 | 0.463 | 7.0 |
| 35.464 | 0.429 | 8.0 |
| 34.825 | 0.458 | 9.0 |
| 35.149 | 0.442 | 10.0 |
| 35.293 | 0.442 | 11.0 |
| 34.976 | 0.453 | 12.0 |
| 35.004 | 0.450 | 13.0 |
| 35.351 | 0.441 | 14.0 |
| 35.385 | 0.438 | 15.0 |
| 35.321 | 0.441 | 16.0 |
| 35.273 | 0.441 | 17.0 |
| 34.948 | 0.455 | 18.0 |
| 35.225 | 0.443 | 19.0 |
Test Accuracy: 0.453
- Library
- pytorch
- License
- mit
- Languages
- en
- Created
- Jan 28, 2024
- Updated
- Jan 30, 2024