mms-1bl1107-mocho-60

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: 0.2630
• Cer: 0.1119

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
2.7995	7.1441	400	0.6236	0.2116
0.8947	14.2883	800	0.4611	0.1718
0.7086	21.4324	1200	0.3350	0.1321
0.5953	28.5766	1600	0.2630	0.1119

Framework versions

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