QwenTranslate_Indic_English

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

MT_Multilingual_En

This model is a fine-tuned version of Qwen/Qwen2.5-3B-Instruct on the MT_Bengali_En, the MT_Hindi_En, the MT_Tamil_En and the MT_Telugu_En datasets. It achieves the following results on the evaluation set:

• Loss: 1.0207
• Num Input Tokens Seen: 24114289216

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 16
• total_train_batch_size: 1024
• total_eval_batch_size: 128
• 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: inverse_sqrt
• num_epochs: 3.0

Training results

Framework versions

• Transformers 5.6.0
• Pytorch 2.7.0+cu128
• Datasets 3.6.0
• Tokenizers 0.22.2