flan-t5-base-minhcrafters

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: 1.4349
• Rouge1: 36.349
• Rouge2: 8.7762
• Rougel: 36.3017
• Rougelsum: 36.3259
• Gen Len: 11.0354

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: 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.5599	1.0	7225	1.4698	34.012	7.0902	33.9643	33.982	11.3958
1.4595	2.0	14450	1.4370	35.8141	7.8463	35.7691	35.7952	10.9503
1.3271	3.0	21675	1.4321	36.6633	8.272	36.6412	36.6552	10.8102
1.3405	4.0	28900	1.4289	35.6986	8.4622	35.6544	35.6839	11.2143
1.1667	5.0	36125	1.4349	36.349	8.7762	36.3017	36.3259	11.0354

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1