t5-base-title-generator

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

• Loss: 2.4868
• Rouge1: 0.3081
• Rouge2: 0.1537
• Rougel: 0.2841
• Rougelsum: 0.2852
• Gen Len: 11.9484

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: 4e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.0744	0.12	100	2.5949	0.3025	0.15	0.2779	0.2786	12.6474
2.1587	0.23	200	2.5878	0.3063	0.1511	0.2795	0.2804	12.3068
2.1679	0.35	300	2.5843	0.3093	0.1543	0.284	0.285	12.3002
2.5576	0.47	400	2.5186	0.3032	0.1508	0.2794	0.2805	12.3258
2.6485	0.58	500	2.4981	0.3109	0.1548	0.2863	0.2875	12.1055
2.8094	0.7	600	2.4899	0.3091	0.1543	0.2846	0.2854	11.9767
2.571	0.82	700	2.4888	0.308	0.1536	0.2836	0.2845	12.0628
2.6264	0.93	800	2.4868	0.3081	0.1537	0.2841	0.2852	11.9484

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1