codemix-indicBART_L1_to_CM_candidates_acc4.8

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

• Loss: 3.2548
• Bleu: 13.7228
• Gen Len: 20.937

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: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Use 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
4.501	1.0	2787	3.8946	13.2982	20.959
3.9034	2.0	5574	3.5202	12.6475	20.953
3.7133	3.0	8361	3.3609	13.4515	20.973
3.601	4.0	11148	3.2794	13.9278	20.933
3.561	4.9985	13930	3.2548	13.7228	20.937

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1