catla-indictrans2-bn2en

This model is a fine-tuned version of ai4bharat/indictrans2-indic-en-1B on the None dataset. It achieves the following results on the evaluation set:

• Loss: nan

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: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 1.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
5.0690	0.1067	500	nan
35507.53	0.2133	1000	nan
0.0	0.32	1500	nan
0.0	0.4267	2000	nan
0.0	0.5333	2500	nan
0.0	0.64	3000	nan
0.0	0.7467	3500	nan
0.0	0.8533	4000	nan
0.0	0.96	4500	nan

Framework versions

• PEFT 0.19.1
• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 5.0.0
• Tokenizers 0.22.2