translate_fukkkiii-hindi-a

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

• Loss: 0.2745
• Bleu: 0.969
• Gen Len: 13.878

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: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.311	1.0	625	0.2950	0.0819	13.875
0.2976	2.0	1250	0.2894	0.1709	13.8705
0.2983	3.0	1875	0.2873	0.325	13.9675
0.2859	4.0	2500	0.2847	0.3271	13.85
0.2829	5.0	3125	0.2822	0.47	13.8655
0.2799	6.0	3750	0.2813	0.3258	13.853
0.2809	7.0	4375	0.2802	0.4139	13.9745
0.2753	8.0	5000	0.2781	0.7067	13.883
0.2733	9.0	5625	0.2768	0.6897	13.809
0.277	10.0	6250	0.2754	0.6447	13.8995
0.2673	11.0	6875	0.2756	0.9871	13.9095
0.2683	12.0	7500	0.2757	1.0343	13.797
0.2702	13.0	8125	0.2750	0.9205	13.8755
0.2658	14.0	8750	0.2749	0.9886	13.87
0.2636	15.0	9375	0.2747	0.9838	13.88
0.2659	16.0	10000	0.2745	0.969	13.878

Framework versions

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