flan-t5-small-test

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

• Loss: 0.4375
• Rouge1: 55.6701
• Rouge2: 45.6817
• Rougel: 52.259
• Rougelsum: 52.2632
• Gen Len: 494.295

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	100	0.4736	47.5356	37.7662	43.8872	43.933	493.725
No log	2.0	200	0.4582	51.7559	41.8487	48.1235	48.1762	494.835
No log	3.0	300	0.4469	52.8576	43.1039	49.3153	49.36	493.225
No log	4.0	400	0.4395	55.4214	45.3968	51.8613	51.8725	492.5
0.5066	5.0	500	0.4375	55.6701	45.6817	52.259	52.2632	494.295

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1