cluster_to_text_t5_base

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

• Loss: 0.4653
• Bleu: 66.2251
• Gen Len: 9.2028

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: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
1.542	1.0	3964	1.1583	26.2658	9.3137
1.0563	2.0	7928	0.7809	46.4766	9.1855
0.8165	3.0	11892	0.6044	57.0741	9.1809
0.7165	4.0	15856	0.5197	62.3771	9.2197
0.6568	5.0	19820	0.4784	65.331	9.1905
0.6231	6.0	23784	0.4653	66.2251	9.2028

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.0
• Tokenizers 0.13.3