alakxender/w2v-bert-2.0-dhivehi-syn

w2v Bert 2.0 Dv - alakxender

This model is a fine-tuned version of alakxender/w2v-bert-2.0-dhivehi-cv on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3580
• Wer: 0.4591

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.9272	3.8961	300	0.3712	0.5096
0.1846	7.7922	600	0.3580	0.4591

Framework versions

• Transformers 4.41.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1