nepali-grammar-20250304_1523

This model is a fine-tuned version of google/muril-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2026
• Accuracy: 0.9301
• F1: 0.9274
• Precision: 0.9637
• Recall: 0.8938

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: 3e-05
• train_batch_size: 64
• eval_batch_size: 128
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.2193	1.0	14942	0.2048	0.9236	0.9205	0.9584	0.8855
0.1789	2.0	29884	0.1992	0.9288	0.9257	0.9677	0.8872
0.1536	2.9998	44823	0.2026	0.9301	0.9274	0.9637	0.8938

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0