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: 0.4704
• Wer: 0.3283

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: 6
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 300
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.9622	0.4451	300	1.0991	0.8442
0.6981	0.8902	600	0.8582	0.6320
0.5201	1.3353	900	0.6906	0.5469
0.4278	1.7804	1200	0.6050	0.4844
0.3303	2.2255	1500	0.5697	0.4517
0.2715	2.6706	1800	0.5435	0.4116
0.226	3.1157	2100	0.5404	0.4024
0.1698	3.5608	2400	0.4759	0.3784
0.1464	4.0059	2700	0.4664	0.3524
0.0968	4.4510	3000	0.4865	0.3414
0.093	4.8961	3300	0.4704	0.3283

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1