jialicheng/unlearn_samsum_t5-base_random_label_6_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: 1.4548
• Rouge1: 49.5823
• Rouge2: 24.8158
• Rougel: 41.1518
• Rougelsum: 45.7853
• Gen Len: 24.5073
• Test Rougel: 41.1453
• Df Rougel: 41.4491
• Unlearn Overall Rougel: 0.3481
• Unlearn Time: 2188.4693

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	1.4838	49.0467	24.4627	41.2411	45.156	24.0746	0.2606	0.2606	-1
No log	2.0	922	1.4681	48.802	24.2156	41.2424	45.2122	23.3374	0.2373	0.2373	-1
1.9223	3.0	1383	1.4577	49.6453	24.7308	41.7833	45.825	24.2200	0.2138	0.2138	-1
1.9223	4.0	1844	1.4548	49.5823	24.8158	41.4491	45.7853	24.5073	0.3481	0.3481	-1
1.8084	5.0	2305	1.4532	49.5837	24.7344	41.6312	45.8172	24.3985	0.2665	0.2665	-1

Framework versions

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