t5-base-finetuned-noun_ellipse

This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1470
• Rouge1: 95.8095
• Rouge2: 93.6
• Rougel: 95.8095
• Rougelsum: 95.8095

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
No log	1.0	50	0.1700	94.1905	90.0857	94.0952	94.0952
No log	2.0	100	0.1500	94.9524	92.7429	95.1429	95.0
No log	3.0	150	0.1476	95.8095	93.6	95.8095	95.8095
No log	4.0	200	0.1480	95.8095	93.6	95.8095	95.8095
No log	5.0	250	0.1470	95.8095	93.6	95.8095	95.8095

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1
• Datasets 2.9.0
• Tokenizers 0.13.2