t5-small-indosum-1

This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4057
• Rouge1: 15.2719
• Rouge2: 11.8877
• Rougel: 15.0297
• Rougelsum: 15.1504
• 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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.482	1.0	4460	0.4370	15.1965	11.8078	14.9509	15.0704	19.0
0.4464	2.0	8920	0.4110	15.2567	11.8679	15.0112	15.132	19.0
0.4421	3.0	13380	0.4057	15.2719	11.8877	15.0297	15.1504	19.0

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.3
• Tokenizers 0.13.3