mms-1b-all-bemgen-combined-m50f50-62-DAT-0.07-fusion

This model is a fine-tuned version of csikasote/mms-1b-all-bemgen-combined-m50f50-62-DAT-0.07-fusion on the BEMGEN - FUS dataset. It achieves the following results on the evaluation set:

• Loss: 2.8280
• Cer: 1.0

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: 62
• 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_ratio: 0.05
• lr_scheduler_warmup_steps: 100
• num_epochs: 30.0

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
2.8230	0.8439	100	2.8419	1.0
2.8694	1.6835	200	2.8127	1.0
2.9210	2.5232	300	2.8376	1.0
2.8496	3.3629	400	2.8197	1.0
2.8355	4.2025	500	2.8280	1.0

Framework versions

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