classification1

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: 0.4874
• Rouge1: 56.4976
• Rouge2: 45.9447
• Rougel: 55.0125
• Rougelsum: 54.9996
• Gen Len: 20.0

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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	341	0.5881	55.4823	44.838	53.9203	53.9211	20.0
0.8666	2.0	682	0.5256	56.1247	45.1956	54.5158	54.4802	20.0
0.6031	3.0	1023	0.5002	55.0454	44.4031	53.5464	53.5119	20.0
0.6031	4.0	1364	0.4916	55.8217	45.0941	54.3072	54.3437	20.0
0.5294	5.0	1705	0.4874	56.4976	45.9447	55.0125	54.9996	20.0

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 2.20.0
• Tokenizers 0.21.0