jialicheng/unlearn_samsum_t5-large_random_label_4_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: 1.4231
• Rouge1: 45.5787
• Rouge2: 21.4922
• Rougel: 34.8718
• Rougelsum: 40.1303
• Gen Len: 25.605
• Test Rougel: 34.8513
• Df Rougel: 32.9461
• Unlearn Overall Rougel: 1.4526
• Unlearn Time: 9919.0918

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	1.4359	26.4495	10.3387	20.9864	23.9025	29.0888	0.8178	0.8178	-1
No log	2.0	920	1.4280	47.308	22.3764	35.0702	41.7244	26.9925	0.9423	0.9423	-1
1.6563	3.0	1380	1.4190	46.6039	21.9197	34.3133	41.0934	25.6125	1.0103	1.0103	-1
1.6563	4.0	1840	1.4204	46.3201	21.7557	34.085	40.7174	25.98	1.0260	1.0260	-1
1.4907	5.0	2300	1.4231	45.5787	21.4922	32.9461	40.1303	25.605	1.4526	1.4526	-1

Framework versions

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