T5-model-1-feedback-1109

This model is a fine-tuned version of theojolliffe/T5-model-1-d-6 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2841
• Rouge1: 91.4494
• Rouge2: 86.4303
• Rougel: 89.9713
• Rougelsum: 90.045
• Gen Len: 15.2875

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: 2
• eval_batch_size: 2
• 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	Gen Len
No log	1.0	359	0.3270	91.5397	86.6427	90.0821	90.1433	15.2875
0.2963	2.0	718	0.2847	91.4494	86.4303	89.9713	90.045	15.2875
0.2697	3.0	1077	0.2841	91.4494	86.4303	89.9713	90.045	15.2875

Framework versions

• Transformers 4.12.3
• Pytorch 1.9.0
• Datasets 1.18.0
• Tokenizers 0.10.3