abstractive_summarization

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

• Loss: 2.0699
• Rouge1: 0.166
• Rouge2: 0.1297
• Rougel: 0.1594
• Rougelsum: 0.1593
• Gen Len: 18.9974

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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
2.465	1.0	1658	2.1944	0.1613	0.1244	0.1538	0.1537	18.996
2.3525	2.0	3316	2.1101	0.1646	0.128	0.1572	0.1571	18.9974
2.2844	3.0	4974	2.0779	0.1655	0.1291	0.1587	0.1586	18.9965
2.2874	4.0	6632	2.0699	0.166	0.1297	0.1594	0.1593	18.9974

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1