transliterate_try

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0770
• Precision: 0.9789
• Recall: 0.9789
• F1: 0.9789
• Accuracy: 0.9789

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	68	0.1379	0.9535	0.9535	0.9535	0.9535
No log	2.0	136	0.1042	0.9661	0.9661	0.9661	0.9661
No log	3.0	204	0.0916	0.9718	0.9718	0.9718	0.9718
No log	4.0	272	0.0920	0.9724	0.9724	0.9724	0.9724
No log	5.0	340	0.0887	0.9746	0.9746	0.9746	0.9746
No log	6.0	408	0.0791	0.9770	0.9770	0.9770	0.9770
No log	7.0	476	0.0794	0.9779	0.9779	0.9779	0.9779
No log	8.0	544	0.0793	0.9783	0.9783	0.9783	0.9783
No log	9.0	612	0.0748	0.9796	0.9796	0.9796	0.9796
No log	10.0	680	0.0770	0.9789	0.9789	0.9789	0.9789

Framework versions

• Transformers 4.28.1
• Pytorch 1.13.0+cu117
• Datasets 2.11.0
• Tokenizers 0.11.6