mms-1bl1107-toratan-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: 0.7574
• Cer: 0.2224

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
4.3985	4.1667	400	1.4424	0.3495
1.4732	8.3333	800	1.2237	0.3151
1.3002	12.5	1200	1.0744	0.3119
1.1844	16.6667	1600	1.0006	0.2750
1.0983	20.8333	2000	0.8570	0.2556
1.0238	25.0	2400	0.8053	0.2391
0.9573	29.1667	2800	0.7574	0.2224

Framework versions

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