t5-small-act2pas

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

• Loss: 0.1036
• Rouge1: 96.7196
• Rouge2: 94.1746
• Rougel: 95.2986
• Rougelsum: 95.3129
• Gen Len: 16.5466

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
0.1668	1.0	8619	0.1201	96.566	93.6856	94.9463	94.9567	16.5427
0.1434	2.0	17238	0.1067	96.6808	94.0862	95.2095	95.2232	16.5474
0.129	3.0	25857	0.1036	96.7196	94.1746	95.2986	95.3129	16.5466

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Tokenizers 0.15.2