jialicheng/unlearn_samsum_t5-small_random_label_4_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: 1.9718
• Rouge1: 39.5535
• Rouge2: 17.4631
• Rougel: 33.6465
• Rougelsum: 36.7565
• Gen Len: 22.1125
• Test Rougel: 33.6375
• Df Rougel: 33.5734
• Unlearn Overall Rougel: 0.5321
• Unlearn Time: 910.6552

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	2.0248	38.9459	17.2481	33.5408	36.1357	21.4817	0.3060	0.3060	-1
No log	2.0	922	1.9718	39.5535	17.4631	33.5734	36.7565	22.1125	0.5321	0.5321	-1
2.8009	3.0	1383	1.9470	39.9413	17.7973	34.0641	37.1241	20.7824	0.4156	0.4156	-1
2.8009	4.0	1844	1.9346	39.7529	17.6133	33.8431	37.0585	20.9853	0.4706	0.4706	-1
2.6317	5.0	2305	1.9319	39.9807	17.7325	33.8786	37.1993	21.6932	0.5101	0.5101	-1

Framework versions

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