jialicheng/unlearn_samsum_t5-small_neggrad_8_42

samsum_42

This model is a fine-tuned version of google/t5-v1_1-small on the samsum dataset. It achieves the following results on the evaluation set:

• Loss: 2.1273
• Rouge1: 38.3382
• Rouge2: 16.6335
• Rougel: 32.2368
• Rougelsum: 35.5795
• Gen Len: 28.0831
• Test Rougel: 32.2368
• Df Rougel: 32.0389
• Unlearn Overall Rougel: 0.5990
• Unlearn Time: 451.8144

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: 1e-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	37	2.1273	38.3382	16.6335	32.0389	35.5795	28.0831	0.5990	0.5990	-1
No log	2.0	74	2.2477	25.0933	10.6489	22.2502	23.2995	80.2531	0.0806	0.0806	-1
No log	3.0	111	2.5026	15.8546	6.4769	13.8377	14.8525	118.0599	0.4611	0.4611	-1
No log	4.0	148	2.7368	14.313	5.5582	12.6974	13.3824	123.0685	0.4098	0.4098	-1
No log	5.0	185	2.8326	14.1141	5.3956	12.4327	13.1625	123.8973	0.4173	0.4173	-1

Framework versions

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