Downloads · 30 days
0
anliR2-gpt2-kd
asun17904/anliR2-gpt2-kd
anliR2-gpt2-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
15.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin498 MB · 100%
At a glance
- Library
- pytorch
- License
- mit
- Access
- Public
- Created
- Jan 28, 2024
- Updated
- Jan 30, 2024
- SHA
- e1a86482
Model card
From the Hugging Face model README
Knowledge Continuity Regularized Network
Dataset: ANLI Round: None
Trainer Hyperparameters:
lr= 5e-05per_device_batch_size= 8gradient_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 |
|---|---|---|
| 36.424 | 0.388 | 1.0 |
| 36.257 | 0.398 | 2.0 |
| 36.011 | 0.413 | 3.0 |
| 36.333 | 0.394 | 4.0 |
| 36.104 | 0.406 | 5.0 |
| 35.441 | 0.432 | 6.0 |
| 35.057 | 0.443 | 7.0 |
| 35.235 | 0.434 | 8.0 |
| 34.987 | 0.448 | 9.0 |
| 34.987 | 0.447 | 10.0 |
| 34.540 | 0.464 | 11.0 |
| 34.358 | 0.469 | 12.0 |
| 34.304 | 0.470 | 13.0 |
| 34.409 | 0.466 | 14.0 |
| 34.153 | 0.475 | 15.0 |
| 34.440 | 0.465 | 16.0 |
| 34.267 | 0.473 | 17.0 |
| 34.298 | 0.470 | 18.0 |
| 33.984 | 0.480 | 19.0 |
Test Accuracy: 0.481
- Library
- pytorch
- License
- mit
- Languages
- en
- Created
- Jan 28, 2024
- Updated
- Jan 30, 2024