english-hindi-bbb

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

• Loss: 0.4443
• Bleu: 0.2327
• Gen Len: 18.8353

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: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
1.4066	1.0	625	0.4151	0.1734	18.941
0.9564	2.0	1250	0.4408	0.287	18.87
0.7504	3.0	1875	0.4522	0.2908	18.8034
0.6375	4.0	2500	0.4377	0.2241	18.856
0.6063	5.0	3125	0.4465	0.2399	18.8305
0.591	6.0	3750	0.4443	0.2327	18.8353

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1