mms-1b-all-bigcgen-combined-10hrs-52

This model is a fine-tuned version of facebook/mms-1b-all on the BIGCGEN - BEM dataset. It achieves the following results on the evaluation set:

• Loss: inf
• Wer: 0.5464

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 4
• seed: 52
• 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: 100
• num_epochs: 30.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
6.0408	0.3053	100	inf	0.7199
0.8906	0.6107	200	inf	0.5893
0.8317	0.9160	300	inf	0.5624
0.8166	1.2198	400	inf	0.5590
0.7748	1.5252	500	inf	0.5466

Framework versions

• Transformers 4.53.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.0