t5-small-pas2act

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

• Loss: 0.1232
• Rouge1: 97.9812
• Rouge2: 94.9546
• Rougel: 95.8714
• Rougelsum: 95.8973
• Gen Len: 14.9464

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: 32
• eval_batch_size: 32
• 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
0.2203	1.0	3937	0.1611	97.6592	93.929	95.2526	95.2754	14.9367
0.1762	2.0	7874	0.1352	97.8981	94.7016	95.7177	95.7391	14.9469
0.166	3.0	11811	0.1263	97.9679	94.904	95.8394	95.8578	14.9448
0.1509	4.0	15748	0.1232	97.9812	94.9546	95.8714	95.8973	14.9464

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2