flan-t5-base-samsam

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

• Loss: 0.0775
• Rouge1: 79.7824
• Rouge2: 78.1384
• Rougel: 79.7465
• Rougelsum: 79.5549
• Gen Len: 17.2210

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: 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	Gen Len
No log	1.0	122	0.1421	79.3619	77.3998	79.3206	79.1508	17.1501
No log	2.0	244	0.1054	79.7224	78.0232	79.6572	79.4622	17.2724
No log	3.0	366	0.0911	79.568	77.8317	79.5281	79.356	17.1665
No log	4.0	488	0.0859	79.5389	77.7935	79.4981	79.2895	17.1696
0.2068	5.0	610	0.0775	79.7824	78.1384	79.7465	79.5549	17.2210

Framework versions

• Transformers 4.35.2
• Pytorch 2.0.0
• Datasets 2.15.0
• Tokenizers 0.15.0