Downloads · 30 days
0
asun17904/anliR1-bert-base-uncased-alum
anliR1-bert-base-uncased-alum 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 29, 2024
Repo size
2.2 GB
Likes
0
Public
Click a slice to open those files.
.bin438 MB · 100%
From the Hugging Face model README
Dataset: ANLI Round: None
Trainer Hyperparameters:
lr = 5e-05per_device_batch_size = 16gradient_accumulation_steps = 1weight_decay = 1e-09seed = 42Regularization Hyperparameters
numerical stability denominator constant = 1.0lambda = 1.0alpha = 1.0beta = 1.0Extended Logs:
| eval_loss | eval_accuracy | epoch |
|---|---|---|
| 1.108 | 0.400 | 1.0 |
| 1.100 | 0.417 | 2.0 |
| 1.116 | 0.409 | 3.0 |
| 1.110 | 0.418 | 4.0 |
| 1.078 | 0.457 | 5.0 |
| 1.113 | 0.420 | 6.0 |
| 1.103 | 0.425 | 7.0 |
| 1.091 | 0.451 | 8.0 |
| 1.108 | 0.426 | 9.0 |
| 1.090 | 0.453 | 10.0 |
| 1.105 | 0.432 | 11.0 |
| 1.103 | 0.432 | 12.0 |
| 1.096 | 0.449 | 13.0 |
| 1.092 | 0.452 | 14.0 |
| 1.094 | 0.444 | 15.0 |
| 1.098 | 0.446 | 16.0 |
| 1.099 | 0.440 | 17.0 |
| 1.099 | 0.441 | 18.0 |
| 1.096 | 0.452 | 19.0 |
Test Accuracy: 0.452