jialicheng/unlearn_samsum_t5-large_random_label_6_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: 1.4219
• Rouge1: 47.7352
• Rouge2: 22.4393
• Rougel: 36.3483
• Rougelsum: 42.0385
• Gen Len: 25.8987
• Test Rougel: 36.3238
• Df Rougel: 34.8151
• Unlearn Overall Rougel: 1.2543
• Unlearn Time: 9997.5910

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	1.4360	45.9058	21.3022	33.9975	40.6107	24.8912	0.8854	0.8854	-1
No log	2.0	920	1.4226	36.5926	16.101	28.0551	32.8062	22.1212	0.8466	0.8466	-1
1.6998	3.0	1380	1.4203	47.7797	22.4865	34.9477	41.9757	25.7325	1.2035	1.2035	-1
1.6998	4.0	1840	1.4220	48.1146	22.5913	35.3269	42.394	26.2737	1.1273	1.1273	-1
1.5288	5.0	2300	1.4219	47.7352	22.4393	34.8151	42.0385	25.8987	1.2543	1.2543	-1

Framework versions

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