unlearn_samsum_t5-small_bad_teaching_8_42

jialicheng/unlearn_samsum_t5-small_bad_teaching_8_42

unlearn_samsum_t5-small_bad_teaching_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. --

Downloads · 30 days

23% of all-time downloads

All-time downloads

Public

Repo size

2.8 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.npy4.1 MB · 56%

At a glance

License: apache-2.0
Model type: t5
Access: Public
Created: Nov 8, 2025
Updated: Nov 8, 2025
SHA: 20188ca9

Base models

google/t5-v1_1-small

Datasets

samsum

Model card

From the Hugging Face model README

samsum_42

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:

Loss: 43.9028
Rouge1: 0.9079
Rouge2: 0.0
Rougel: 0.9103
Rougelsum: 0.9101
Gen Len: 127.0
Test Rougel: 0.9103
Df Rougel: 0.9036
Unlearn Overall Rougel: 0.5033
Unlearn Time: 3910.6071

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	Rougel	Rougelsum	Gen Len	Overall Rougel	Unlearn Overall Rougel	Time
No log	0.5	423	35.9405	4.9044	4.6743	4.9086	127.0	0.6246	0.6246	-1
No log	1.0	846	40.9476	4.9546	4.789	4.9593	127.0	0.5932	0.5932	-1
0.0	1.5	1269	42.0802	1.0025	0.9933	1.0058	127.0	0.5063	0.5063	-1
0.0	2.0	1692	42.6487	0.9079	0.9036	0.9101	127.0	0.5033	0.5033	-1
0.0	2.5	2115	43.3270	0.9079	0.9036	0.9101	127.0	0.5033	0.5033	-1
0.0	3.0	2538	43.5246	0.9079	0.9036	0.9101	127.0	0.5033	0.5033	-1
0.0	3.5	2961	43.7251	0.9079	0.9036	0.9101	127.0	0.5033	0.5033	-1
0.0	4.0	3384	43.7665	0.9079	0.9036	0.9101	127.0	0.5033	0.5033	-1
0.0	4.49	3807	43.9050	0.9079	0.9036	0.9101	127.0	0.5033	0.5033	-1
0.0	4.99	4230	43.9028	0.9079	0.9036	0.9101	127.0	0.5033	0.5033	-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