flan-t5-base-finetuned-govReport-3072

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

• Loss: nan
• Rouge1: 0.042
• Rouge2: 0.0216
• Rougel: 0.0379
• Rougelsum: 0.0406

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: 3e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.0	1.0	250	nan	0.042	0.0216	0.0379	0.0406
0.0	2.0	500	nan	0.042	0.0216	0.0379	0.0406
0.0	3.0	750	nan	0.042	0.0216	0.0379	0.0406
0.0	4.0	1000	nan	0.042	0.0216	0.0379	0.0406
0.0	5.0	1250	nan	0.042	0.0216	0.0379	0.0406
0.0	6.0	1500	nan	0.042	0.0216	0.0379	0.0406
0.0	7.0	1750	nan	0.042	0.0216	0.0379	0.0406
0.0	8.0	2000	nan	0.042	0.0216	0.0379	0.0406
0.0	9.0	2250	nan	0.042	0.0216	0.0379	0.0406
0.0	10.0	2500	nan	0.042	0.0216	0.0379	0.0406

Framework versions

• PEFT 0.8.2
• Transformers 4.37.0
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.1