sanskrit-to-english

This model is a fine-tuned version of t5-small on the itihasa dataset. It achieves the following results on the evaluation set:

• Loss: 3.5134
• Bleu: 0.288
• Gen Len: 19.0

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
3.9554	1.0	4698	3.7250	0.3772	19.0
3.8183	2.0	9396	3.6050	0.3216	19.0
3.746	3.0	14094	3.5497	0.2743	19.0
3.7183	4.0	18792	3.5229	0.2787	19.0
3.7124	5.0	23490	3.5134	0.288	19.0

Framework versions

• Transformers 4.35.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.14.1