my_wikilingua_t5small

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

• Loss: 2.6035
• Rouge1: 0.2226
• Rouge2: 0.0638
• Rougel: 0.1839
• Rougelsum: 0.1838
• Gen Len: 18.725

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: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	100	2.7179	0.2156	0.0579	0.1742	0.1741	18.835
No log	2.0	200	2.6370	0.2213	0.0637	0.1796	0.1794	18.805
No log	3.0	300	2.6105	0.2239	0.064	0.1834	0.1833	18.79
No log	4.0	400	2.6035	0.2226	0.0638	0.1839	0.1838	18.725

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3