flan-t5-large-mawpnli-calcx-pt

This model is a fine-tuned version of google/flan-t5-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1463
• Rouge1: 95.656
• Rouge2: 88.9634
• Rougel: 95.5287
• Rougelsum: 95.5315
• Gen Len: 12.6808

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	426	0.1577	94.7455	86.4792	94.3396	94.3571	12.5962
0.2457	2.0	852	0.1341	95.3972	88.4764	95.1413	95.1511	12.7207
0.0797	3.0	1278	0.1313	95.4361	88.078	95.221	95.2056	12.5692
0.0573	4.0	1704	0.1483	95.3949	88.188	95.1917	95.2055	12.5974
0.0404	5.0	2130	0.1463	95.656	88.9634	95.5287	95.5315	12.6808

Framework versions

• Transformers 4.35.2
• Pytorch 1.12.1+cu113
• Datasets 2.15.0
• Tokenizers 0.15.0