Downloads · 30 days
5
25% of all-time downloads
asun17904/imdb-t5-base-a1b2
imdb-t5-base-a1b2 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.
Trainer Hyperparameters: - lr = 5e-05 - perdevicebatchsize = 8 - gradientaccumulationsteps = 2 - weightdecay = 1e-09 - seed = 42
Downloads · 30 days
5
25% of all-time downloads
All-time downloads
20
Public
Repo size
8.9 GB
Likes
0
Public
Click a slice to open those files.
.bin894 MB · 100%
From the Hugging Face model README
Trainer Hyperparameters:
lr = 5e-05per_device_batch_size = 8gradient_accumulation_steps = 2weight_decay = 1e-09seed = 42Regularization Hyperparameters
numerical stability denominator constant = 0.01lambda = 0.02alpha = 1.0beta = 2.0Extended Logs:
| eval_loss | eval_accuracy | epoch |
|---|---|---|
| 11.994 | 0.936 | 1.0 |
| 11.877 | 0.941 | 2.0 |
| 11.963 | 0.939 | 3.0 |
| 11.879 | 0.941 | 4.0 |
| 11.783 | 0.945 | 5.0 |
| 11.723 | 0.946 | 6.0 |
| 11.880 | 0.941 | 7.0 |
| 11.739 | 0.946 | 8.0 |
| 11.663 | 0.948 | 9.0 |
| 11.671 | 0.948 | 10.0 |
| 11.658 | 0.948 | 11.0 |
| 11.637 | 0.949 | 12.0 |
| 11.687 | 0.948 | 13.0 |
| 11.685 | 0.948 | 14.0 |
| 11.804 | 0.944 | 15.0 |
| 11.721 | 0.947 | 16.0 |
| 11.607 | 0.950 | 17.0 |
| 11.713 | 0.947 | 18.0 |
| 11.683 | 0.948 | 19.0 |
| 11.658 | 0.949 | 20.0 |
| 11.636 | 0.949 | 21.0 |
| 11.700 | 0.947 | 22.0 |
| 11.601 | 0.950 | 23.0 |
| 11.821 | 0.944 | 24.0 |
| 11.587 | 0.951 | 25.0 |
| 11.623 | 0.950 | 26.0 |
| 11.640 | 0.949 | 27.0 |
| 11.627 | 0.950 | 28.0 |
| 11.621 | 0.950 | 29.0 |
| 11.651 | 0.949 | 30.0 |
| 11.597 | 0.951 | 31.0 |
| 11.650 | 0.949 | 32.0 |
| 11.651 | 0.949 | 33.0 |
| 11.642 | 0.949 | 34.0 |
| 11.637 | 0.949 | 35.0 |
| 11.593 | 0.951 | 36.0 |
| 11.615 | 0.950 | 37.0 |
| 11.594 | 0.951 | 38.0 |
| 11.646 | 0.949 | 39.0 |
| 11.631 | 0.950 | 40.0 |
| 11.635 | 0.949 | 41.0 |
| 11.605 | 0.950 | 42.0 |
| 11.629 | 0.949 | 43.0 |
| 11.638 | 0.949 | 44.0 |
| 11.586 | 0.951 | 45.0 |
| 11.591 | 0.951 | 46.0 |
| 11.609 | 0.950 | 47.0 |
| 11.607 | 0.950 | 48.0 |
| 11.604 | 0.950 | 49.0 |