jialicheng/unlearn_samsum_t5-base_bad_teaching_4_42

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: 90.5602
• Rouge1: 0.0
• Rouge2: 0.0
• Rougel: 0.0
• Rougelsum: 0.0
• Gen Len: 127.0
• Test Rougel: 0.0
• Df Rougel: 0.0
• Unlearn Overall Rougel: 0.5
• Unlearn Time: 1.5022

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	Rougel	Gen Len	Validation Loss	Rouge1	Rouge2	Rougelsum	Unlearn Overall Rougel	Overall Rougel	Time
No log	0.5	441	0.0	127.0	78.1788	0.0	0.0	0.0	0.5	0.5	-1
No log	1.0	882	0.0	127.0	82.8812	0.0	0.0	0.0	0.5	0.5	-1
0.0	1.5	1323	0.0	127.0	84.9356	0.0	0.0	0.0	0.5	0.5	-1
0.0	2.0	1764	0.0	127.0	86.7245	0.0	0.0	0.0	0.5	0.5	-1
0.0	2.49	2205	0.0	127.0	87.9192	0.0	0.0	0.0	0.5	0.5	-1
0.0	2.99	2646	0.0	127.0	88.8881	0.0	0.0	0.0	0.5	0.5	-1
0.0	3.49	3087	0.0	127.0	89.6150	0.0	0.0	0.0	0.5	0.5	-1
0.0	3.99	3528	0.0	127.0	90.1426	0.0	0.0	0.0	0.5	0.5	-1
0.0	4.49	3969	0.0	127.0	90.4649	0.0	0.0	0.0	0.5	0.5	-1
0.0	4.99	4410	0.0	127.0	90.5602	0.0	0.0	0.0	0.5	0.5	-1

Framework versions

• Transformers 4.39.3
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.15.2