jialicheng/unlearn_samsum_t5-large_salun_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: 1.4321
• Rouge1: 44.8947
• Rouge2: 20.9476
• Rougel: 34.4101
• Rougelsum: 39.7685
• Gen Len: 25.4612
• Test Rougel: 34.3562
• Df Rougel: 33.6782
• Unlearn Overall Rougel: 0.8390
• Unlearn Time: 8158.9486

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: 2.5

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	1.4409	34.7849	15.1129	28.148	31.3624	29.0338	0.1310	0.1310	-1
No log	2.0	920	1.4295	40.7229	18.377	31.3483	36.1978	27.3637	0.5421	0.5421	-1
1.684	2.5	1150	1.4321	44.8947	20.9476	33.6782	39.7685	25.4612	0.8390	0.8390	-1

Framework versions

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