jialicheng/unlearn_samsum_t5-base_random_label_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: 1.4581
• Rouge1: 49.7002
• Rouge2: 25.389
• Rougel: 41.5256
• Rougelsum: 46.1176
• Gen Len: 23.9156
• Test Rougel: 41.4764
• Df Rougel: 41.6558
• Unlearn Overall Rougel: 0.4103
• Unlearn Time: 2098.8050

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	1.4818	48.9248	24.5221	42.0397	45.2492	23.5880	-0.1631	-0.1631	-1
No log	2.0	922	1.4703	49.3631	24.68	42.0483	45.5475	25.4535	-0.1475	-0.1475	-1
1.8739	3.0	1383	1.4593	49.5829	25.1916	41.7802	45.8602	24.1100	0.3212	0.3212	-1
1.8739	4.0	1844	1.4581	49.7002	25.389	41.6558	46.1176	23.9156	0.4103	0.4103	-1
1.7611	5.0	2305	1.4528	49.6984	25.2958	41.9786	45.9853	24.0660	0.2808	0.2808	-1

Framework versions

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