maryantocinn/t5-small-finetuned-xsum

indobart-v2-finetuned-indosum

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

• Loss: 0.4003
• Rouge1: 21.1743
• Rouge2: 16.867
• Rougel: 20.9061
• Rougelsum: 21.0473
• Gen Len: 19.0

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: 2e-05
• train_batch_size: 12
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.4276	1.0	1189	0.4118	21.0508	16.7363	20.7771	20.919	19.0
0.4268	2.0	2378	0.4060	21.1694	16.852	20.891	21.0278	19.0
0.4077	3.0	3567	0.4021	21.1523	16.8553	20.8928	21.0273	19.0
0.406	4.0	4756	0.4006	21.1743	16.867	20.9061	21.0473	19.0
0.4158	5.0	5945	0.4003	21.1743	16.867	20.9061	21.0473	19.0

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1