trainer_output

This model is a fine-tuned version of facebook/mms-1b-all on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3846
• Wer: 0.4456

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: 0.001
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.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_steps: 100
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.5289	0.1976	100	0.7768	0.7000
0.8566	0.3953	200	0.6045	0.6389
0.7329	0.5929	300	0.5343	0.5567
0.7219	0.7905	400	0.4980	0.5359
0.6556	0.9881	500	0.4649	0.5202
0.5582	1.1858	600	0.4556	0.5060
0.5591	1.3834	700	0.4280	0.4818
0.5100	1.5810	800	0.4058	0.4652
0.5390	1.7787	900	0.3901	0.4479
0.5154	1.9763	1000	0.3846	0.4456

Framework versions

• Transformers 5.3.0.dev0
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2