Downloads · 30 days
7
21% of all-time downloads
jialicheng/unlearn_samsum_t5-small_neggrad_2_42
unlearn_samsum_t5-small_neggrad_2_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
7
21% of all-time downloads
All-time downloads
33
Public
Repo size
17.5 MB
Likes
0
Public
Click a slice to open those files.
.npy16.7 MB · 84%
From the Hugging Face model README
This model is a fine-tuned version of google/t5-v1_1-small 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 | 10 | 2.1124 | 38.9488 | 17.0356 | 33.648 | 36.0338 | 20.1235 | 0.0828 | 0.0828 | -1 |
| No log | 2.0 | 20 | 2.1132 | 39.0504 | 17.1244 | 33.4371 | 36.1687 | 20.2042 | 0.2458 | 0.2458 | -1 |
| No log | 3.0 | 30 | 2.1141 | 39.111 | 17.1978 | 33.4703 | 36.1974 | 20.2861 | 0.2404 | 0.2404 | -1 |
| No log | 4.0 | 40 | 2.1152 | 39.1237 | 17.221 | 33.3457 | 36.179 | 20.1895 | 0.3091 | 0.3091 | -1 |
| No log | 5.0 | 50 | 2.1155 | 39.1378 | 17.2346 | 33.2782 | 36.192 | 20.1491 | 0.3519 | 0.3519 | -1 |