Downloads · 30 days
0
asun17904/glue-rte-bert-base-uncased-regularized-l2
glue-rte-bert-base-uncased-regularized-l2 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.
Downloads · 30 days
0
Access
Public
Updated Jan 25, 2024
Repo size
—
Likes
0
Public
Click a slice to open those files.
Other1.5 KB · 52%
From the Hugging Face model README
Dataset: GLUE
Trainer Hyperparameters:
lr = 5e-05per_device_batch_size = 16gradient_accumulation_steps = 1weight_decay = 1e-09seed = 42Regularization Hyperparameters
numerical stability denominator constant = 0.01lambda = 0.02alpha = 2.0beta = 1.0Extended Logs:
| eval_loss | eval_accuracy | epoch |
|---|---|---|
| 21.497 | 0.578 | 1.0 |
| 21.579 | 0.578 | 2.0 |
| 22.797 | 0.567 | 3.0 |
| 23.206 | 0.563 | 4.0 |
| 22.825 | 0.581 | 5.0 |
| 22.042 | 0.606 | 6.0 |
| 23.542 | 0.556 | 7.0 |
| 22.290 | 0.606 | 8.0 |
| 23.461 | 0.567 | 9.0 |
| 23.063 | 0.585 | 10.0 |
| 23.358 | 0.574 | 11.0 |
| 23.223 | 0.578 | 12.0 |
| 23.578 | 0.567 | 13.0 |
| 22.854 | 0.585 | 14.0 |
| 23.723 | 0.563 | 15.0 |
| 23.165 | 0.574 | 16.0 |
| 23.134 | 0.574 | 17.0 |
| 23.479 | 0.560 | 18.0 |
| 22.982 | 0.581 | 19.0 |
| 23.601 | 0.560 | 20.0 |
| 22.914 | 0.585 | 21.0 |
| 22.700 | 0.599 | 22.0 |
| 23.201 | 0.574 | 23.0 |
| 23.437 | 0.570 | 24.0 |
| 23.407 | 0.578 | 25.0 |
| 22.512 | 0.603 | 26.0 |
| 23.252 | 0.567 | 27.0 |
| 23.777 | 0.556 | 28.0 |
| 23.993 | 0.556 | 29.0 |
| 23.708 | 0.563 | 30.0 |
| 23.886 | 0.552 | 31.0 |
| 23.857 | 0.556 | 32.0 |
| 23.593 | 0.556 | 33.0 |
| 23.368 | 0.570 | 34.0 |
| 23.654 | 0.563 | 35.0 |
| 24.380 | 0.542 | 36.0 |
| 24.091 | 0.549 | 37.0 |
| 23.997 | 0.549 | 38.0 |
| 23.977 | 0.552 | 39.0 |
| 23.761 | 0.560 | 40.0 |
| 23.537 | 0.570 | 41.0 |
| 23.381 | 0.574 | 42.0 |
| 23.864 | 0.556 | 43.0 |
| 23.737 | 0.556 | 44.0 |
| 23.261 | 0.578 | 45.0 |
| 23.832 | 0.560 | 46.0 |
| 23.446 | 0.567 | 47.0 |
| 23.397 | 0.570 | 48.0 |
| 23.439 | 0.570 | 49.0 |