translate_fukkkiii-hindi

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

• Loss: 0.3002
• Bleu: 0.0227
• Gen Len: 13.904

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: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.4656	1.0	625	0.3461	0.0	14.251
0.3613	2.0	1250	0.3216	0.0	13.9865
0.349	3.0	1875	0.3123	0.001	13.9975
0.3238	4.0	2500	0.3061	0.0024	13.962
0.3192	5.0	3125	0.3023	0.0179	13.845
0.3147	6.0	3750	0.3015	0.0298	13.88
0.3156	7.0	4375	0.3002	0.0227	13.904

Framework versions

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