codemix-indicBART_L1_to_CM_candidates_acc4.6

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

• Loss: 1.6258
• Bleu: 9.845
• Gen Len: 21.0

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
3.2367	1.0	14065	2.7191	13.388	21.0
2.4949	2.0	28130	1.9355	10.6806	21.0
2.1828	3.0	42195	1.7065	9.5524	21.0
2.0863	4.0	56260	1.6410	9.6198	21.0
2.0491	4.9997	70320	1.6258	9.845	21.0

Framework versions

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