t5-small

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

• Loss: 1.5871
• Rouge1: 61.1404
• Rouge2: 37.8854
• Rougel: 59.2953
• Rougelsum: 59.3081
• Bleu: 0.2843

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: 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bleu
1.7433	0.99	70000	1.6000	60.9802	37.6872	59.1561	59.1644	0.2821
1.7216	1.97	140000	1.5905	61.1241	37.8722	59.2878	59.2991	0.2839
1.7389	2.96	210000	1.5871	61.1404	37.8854	59.2953	59.3081	0.2843

Framework versions

• Transformers 4.36.2
• Pytorch 1.13.0+cu117
• Datasets 2.16.0
• Tokenizers 0.15.0