mms_e5_arm_c_targeted

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: 1.9203
• Wer: 0.6817
• Cer: 0.4532

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• 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: 50
• training_steps: 600

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
10.2639	1.07	100	2.7478	0.8045	0.5840
5.2998	3.0433	200	2.1683	0.7011	0.4977
4.7004	5.0167	300	1.9516	0.6801	0.4610
5.6235	6.0867	400	1.9583	0.6834	0.4564
4.8199	8.06	500	1.9617	0.6882	0.4551
3.7205	10.0333	600	1.9203	0.6817	0.4532

Framework versions

• Transformers 5.0.0
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.22.2