IndicBART-mr-test

This model is a fine-tuned version of ai4bharat/IndicBART on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.7345
• Rouge1: 47.0576
• Rouge2: 4.7014
• Rougel: 47.0474
• Rougelsum: 47.0396

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: 5.6e-05
• train_batch_size: 12
• eval_batch_size: 12
• 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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
3.6435	1.0	909	2.8758	45.165	1.1394	45.168	45.1586
3.1753	2.0	1818	2.7719	46.5321	3.3062	46.5286	46.5338
3.0756	3.0	2727	2.7413	46.7024	4.0972	46.696	46.6929
3.0307	4.0	3636	2.7345	47.0576	4.7014	47.0474	47.0396

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1