sanskrit-translator-final – AI Model by sumukha2002 | AlphaNeural AI

You can deploy this model and start earning money today!

sumukha2002/
sanskrit-translator-final

like

0

text2text-generation

generated_from_trainer

sumukha2002/sanskrit-translator

endpoints_compatible

Views

No views yet

sanskrit-translator-final

This model is a fine-tuned version of sumukha2002/sanskrit-translator on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.9075
Bleu: 0.0730
Rouge1: 0.3860
Rouge2: 0.2449
Rougel: 0.3512

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: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
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: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Rouge1	Rouge2	Rougel
0.982	1.0	4779	0.9622	0.0665	0.3671	0.2357	0.3373
0.9751	2.0	9558	0.9367	0.0691	0.3754	0.2395	0.3437
0.9224	3.0	14337	0.9211	0.0715	0.3805	0.2422	0.3471
0.9214	4.0	19116	0.9111	0.0725	0.3844	0.2440	0.3504
0.935	5.0	23895	0.9075	0.0730	0.3860	0.2449	0.3512

Framework versions

Transformers 4.56.0
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.0