jialicheng/unlearn_samsum_t5-large_random_label_8_42

samsum_42

This model is a fine-tuned version of google/t5-v1_1-large on the samsum dataset. It achieves the following results on the evaluation set:

• Loss: 1.4226
• Rouge1: 46.9107
• Rouge2: 22.1109
• Rougel: 35.6865
• Rougelsum: 41.4048
• Gen Len: 25.7188
• Test Rougel: 35.6741
• Df Rougel: 34.534
• Unlearn Overall Rougel: 1.0701
• Unlearn Time: 11079.9814

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: 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	460	1.4355	46.3018	20.8827	34.7511	40.3207	24.5237	0.4727	0.4727	-1
No log	2.0	920	1.4272	46.7306	21.7773	35.082	41.2409	26.1625	0.7151	0.7151	-1
1.7398	3.0	1380	1.4229	46.1906	21.678	34.2098	40.7821	26.155	0.9028	0.9028	-1
1.7398	4.0	1840	1.4226	46.9107	22.1109	34.534	41.4048	25.7188	1.0701	1.0701	-1
1.5653	5.0	2300	1.4261	45.9706	21.5324	34.2811	40.5034	25.6088	0.8684	0.8684	-1

Framework versions

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