Downloads · 30 days
0
asun17904/glue-mrpc-bert-base-uncased-regularized-l2
glue-mrpc-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 24, 2024
Repo size
438 MB
Likes
0
Public
Click a slice to open those files.
.bin438 MB · 100%
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 |
|---|---|---|
| 16.298 | 0.804 | 1.0 |
| 17.928 | 0.755 | 2.0 |
| 15.529 | 0.828 | 3.0 |
| 14.999 | 0.843 | 4.0 |
| 14.680 | 0.858 | 5.0 |
| 15.523 | 0.828 | 6.0 |
| 14.987 | 0.846 | 7.0 |
| 16.665 | 0.794 | 8.0 |
| 14.767 | 0.853 | 9.0 |
| 14.644 | 0.853 | 10.0 |
| 14.528 | 0.860 | 11.0 |
| 14.406 | 0.863 | 12.0 |
| 14.673 | 0.853 | 13.0 |
| 14.910 | 0.850 | 14.0 |
| 14.386 | 0.863 | 15.0 |
| 14.131 | 0.870 | 16.0 |
| 15.204 | 0.838 | 17.0 |
| 14.685 | 0.853 | 18.0 |
| 14.876 | 0.846 | 19.0 |
| 15.133 | 0.843 | 20.0 |
| 14.664 | 0.853 | 21.0 |
| 16.257 | 0.809 | 22.0 |
| 14.943 | 0.846 | 23.0 |
| 14.934 | 0.848 | 24.0 |
| 15.064 | 0.843 | 25.0 |
| 15.151 | 0.841 | 26.0 |
| 14.982 | 0.843 | 27.0 |
| 14.488 | 0.858 | 28.0 |
| 15.235 | 0.838 | 29.0 |
| 14.763 | 0.850 | 30.0 |
| 14.908 | 0.848 | 31.0 |
| 15.068 | 0.843 | 32.0 |
| 14.755 | 0.850 | 33.0 |
| 15.053 | 0.843 | 34.0 |
| 15.350 | 0.838 | 35.0 |
| 14.841 | 0.848 | 36.0 |
| 14.721 | 0.853 | 37.0 |
| 14.947 | 0.846 | 38.0 |
| 14.727 | 0.855 | 39.0 |
| 14.945 | 0.846 | 40.0 |
| 15.096 | 0.846 | 41.0 |
| 14.999 | 0.848 | 42.0 |
| 14.911 | 0.848 | 43.0 |
| 14.852 | 0.850 | 44.0 |
| 14.922 | 0.848 | 45.0 |
| 15.096 | 0.846 | 46.0 |
| 14.970 | 0.846 | 47.0 |
| 15.031 | 0.843 | 48.0 |
| 15.031 | 0.843 | 49.0 |