flan-t5-base-indian-constitution

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: 0.0008
• Rouge1: 29.7093
• Rouge2: 28.4336
• Rougel: 29.6229
• Rougelsum: 29.5617
• Gen Len: 18.9651

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: 1
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	344	0.0009	29.7093	28.4336	29.6229	29.5617	18.9651
0.0021	2.0	688	0.0008	29.7093	28.4336	29.6229	29.5617	18.9651
0.0013	3.0	1032	0.0008	29.7093	28.4336	29.6229	29.5617	18.9651

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3