Downloads · 30 days
4
17% of all-time downloads
unlearn-cl_samsum_t5-base_bad_teaching_10_42
jialicheng/unlearn-cl_samsum_t5-base_bad_teaching_10_42
unlearn-cl_samsum_t5-base_bad_teaching_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. --
All-time downloads
23
Public
Repo size
17.1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.npy16.3 MB · 83%
At a glance
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Nov 8, 2025
- Updated
- Nov 8, 2025
- SHA
- ce7f0d09
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
samsum_42
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:
- Loss: 4.8411
- Rouge1: 11.403
- Rouge2: 2.6039
- Rougel: 9.7554
- Rougelsum: 10.1572
- Gen Len: 95.0475
- Test Rougel: 9.7455
- Df Rougel: 8.8293
- Unlearn Overall Rougel: 0.9581
- Unlearn Time: 639.0685
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2.5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Overall Rougel | Unlearn Overall Rougel | Time |
|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 92 | 4.8411 | 11.403 | 2.6039 | 8.8293 | 10.1572 | 95.0475 | 0.9581 | 0.9581 | -1 |
| No log | 2.0 | 184 | 7.3778 | 5.8311 | 0.3147 | 5.4973 | 5.5283 | 118.6675 | 0.4575 | 0.4575 | -1 |
| No log | 2.5 | 230 | 7.8795 | 5.4554 | 0.1919 | 5.2429 | 5.2661 | 118.2087 | 0.4817 | 0.4817 | -1 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
- Type
- t5
- License
- apache-2.0
- Created
- Nov 8, 2025
- Updated
- Nov 8, 2025