Downloads · 30 days
3
9% of all-time downloads
jialicheng/unlearn_samsum_t5-base_neggrad_10_42
unlearn_samsum_t5-base_neggrad_10_42 is a machine learning model from jialicheng. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
3
9% of all-time downloads
All-time downloads
33
Public
Repo size
5.5 MB
Likes
0
Public
Click a slice to open those files.
.npy4.7 MB · 59%
From the Hugging Face model README
This model is a fine-tuned version of google/t5-v1_1-base on the samsum dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Overall Rougel | Unlearn Overall Rougel | Time |
|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 47 | 1.5440 | 47.7058 | 23.6801 | 40.2622 | 44.1434 | 31.4083 | 0.1043 | 0.1043 | -1 |
| No log | 2.0 | 94 | 2.1664 | 18.7819 | 8.9322 | 16.6184 | 17.7548 | 123.1956 | 0.4361 | 0.4361 | -1 |
| No log | 3.0 | 141 | 4.0379 | 5.8603 | 1.3801 | 5.4903 | 5.6247 | 126.9927 | 0.4986 | 0.4986 | -1 |
| No log | 4.0 | 188 | 9.4054 | 3.458 | 0.1666 | 3.4185 | 3.3756 | 127.0 | 0.4432 | 0.4432 | -1 |
| No log | 5.0 | 235 | 12.3834 | 3.3006 | 0.1327 | 3.2484 | 3.2103 | 127.0 | 0.4439 | 0.4439 | -1 |