jialicheng/unlearn_samsum_t5-small_random_label_10_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: 1.9516
• Rouge1: 40.2147
• Rouge2: 17.9635
• Rougel: 34.1287
• Rougelsum: 37.3694
• Gen Len: 21.5648
• Test Rougel: 34.0904
• Df Rougel: 34.311
• Unlearn Overall Rougel: 0.3897
• Unlearn Time: 208.1742

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	Rougel	Gen Len	Validation Loss	Rouge1	Rouge2	Rougelsum	Unlearn Overall Rougel	Overall Rougel	Time
No log	1.0	461	32.6827	18.7335	2.0240	38.4237	16.8873	35.6564	0.1403	0.1403	-1
No log	2.0	922	33.6443	20.8643	1.9751	39.6569	17.4973	36.7824	0.2372	0.2372	-1
2.9467	3.0	1383	34.0904	21.5648	1.9516	40.2147	17.9635	37.3694	0.3897	0.3897	-1
2.9467	4.0	1844	34.3169	20.9315	1.9410	40.5306	18.0501	37.557	0.3297	0.3297	-1
2.7294	5.0	2305	1.9369	40.5018	17.9761	34.5748	37.5502	21.0147	0.3582	0.3582	-1

Framework versions

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