ten-epochs

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

• Loss: 0.0636
• Rouge1: 98.8722
• Rouge2: 95.6457
• Rougel: 98.8733
• Rougelsum: 98.8711
• Gen Len: 5.0

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: 5e-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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.0669	1.0	2500	0.0637	98.8722	95.6457	98.8733	98.8711	5.0
0.068	2.0	5000	0.0635	98.8722	95.6457	98.8733	98.8711	5.0
0.0651	3.0	7500	0.0647	98.8722	95.6457	98.8733	98.8711	5.0
0.0637	4.0	10000	0.0635	98.8722	95.6457	98.8733	98.8711	5.0
0.0684	5.0	12500	0.0640	98.8722	95.6457	98.8733	98.8711	5.0
0.0666	6.0	15000	0.0636	98.8722	95.6457	98.8733	98.8711	5.0
0.0647	7.0	17500	0.0635	98.8722	95.6457	98.8733	98.8711	5.0
0.0652	8.0	20000	0.0636	98.8722	95.6457	98.8733	98.8711	5.0
0.0634	9.0	22500	0.0636	98.8722	95.6457	98.8733	98.8711	5.0
0.0651	10.0	25000	0.0636	98.8722	95.6457	98.8733	98.8711	5.0

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.0
• Datasets 2.14.5
• Tokenizers 0.13.3