mms-1bl1107-ulwa-120

This model is a fine-tuned version of facebook/mms-1b-l1107 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2885
• Cer: 0.0791

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: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
2.601	6.5574	400	0.7654	0.2007
0.8715	13.1148	800	0.5299	0.1397
0.706	19.6721	1200	0.3865	0.1043
0.59	26.2295	1600	0.2885	0.0791

Framework versions

• Transformers 4.49.0.dev0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0