Downloads · 30 days
2
6% of all-time downloads
unlearn_samsum_t5-base_random_label_8_42
jialicheng/unlearn_samsum_t5-base_random_label_8_42
unlearn_samsum_t5-base_random_label_8_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
36
Public
Repo size
4.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.npy4 MB · 55%
At a glance
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Nov 8, 2025
- Updated
- Nov 8, 2025
- SHA
- 4037cf3d
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: 1.4617
- Rouge1: 49.406
- Rouge2: 24.8004
- Rougel: 41.2167
- Rougelsum: 45.7283
- Gen Len: 24.8301
- Test Rougel: 41.2136
- Df Rougel: 41.8384
- Unlearn Overall Rougel: 0.1876
- Unlearn Time: 2294.2529
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 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 | 461 | 1.4806 | 48.6517 | 24.0291 | 41.8941 | 44.8753 | 23.9560 | -0.2435 | -0.2435 | -1 |
| No log | 2.0 | 922 | 1.4732 | 49.3374 | 24.5757 | 42.1613 | 45.702 | 23.9022 | 0.0036 | 0.0036 | -1 |
| 1.9674 | 3.0 | 1383 | 1.4617 | 49.406 | 24.8004 | 41.8384 | 45.7283 | 24.8301 | 0.1876 | 0.1876 | -1 |
| 1.9674 | 4.0 | 1844 | 1.4548 | 49.3608 | 24.9057 | 42.2617 | 45.6336 | 23.9462 | -0.0759 | -0.0759 | -1 |
| 1.8526 | 5.0 | 2305 | 1.4547 | 49.3324 | 24.7251 | 42.3355 | 45.6157 | 24.0355 | -0.0644 | -0.0644 | -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