codemix-test

This model is a fine-tuned version of ai4bharat/IndicBART on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.5032
• Bleu: 17.4363
• Gen Len: 20.978

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: 1e-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
5.8666	1.0	1004	4.9742	13.3823	21.0
4.8088	2.0	2008	4.0212	15.3375	21.0
4.2735	3.0	3012	3.6499	16.3145	21.0
4.0836	4.0	4016	3.5329	17.3835	20.996
4.0152	5.0	5020	3.5032	17.4363	20.978

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.1