w2v-bert-2.0-mongolian-colab-CV16.0

This model is a fine-tuned version of facebook/w2v-bert-2.0 on the common_voice_16_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6984
• Wer: 0.9657

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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
3.4128	1.9763	500	3.2537	1.0
1.7038	3.9526	1000	1.5989	1.0
0.722	5.9289	1500	0.9174	0.9878
0.4558	7.9051	2000	0.7443	0.9746
0.3257	9.8814	2500	0.6984	0.9657

Framework versions

• Transformers 4.51.2
• Pytorch 2.1.0+cu121
• Datasets 2.14.6
• Tokenizers 0.21.1