mms-1b-all-swagen-combined-m50f50-dnn-42-0.10

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

• Loss: 15.0948
• Cer: 4.1370

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: 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: 250
• num_epochs: 15.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
13.0486	1.9723	250	15.0948	4.1382
25.0654	3.9407	500	15.0948	4.1373
17.1936	5.9091	750	15.0947	4.1391
10.2055	7.8775	1000	15.0947	4.1376
11.2981	9.8458	1250	15.0946	4.1384
13.1665	11.8142	1500	15.0946	4.1380
11.5061	13.7826	1750	15.0948	4.1370

Framework versions

• Transformers 4.53.0
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.4