mms-1bl1107-cicipu-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: 0.4909
• Cer: 0.1252

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
3.9788	3.7070	400	1.3528	0.2964
1.648	7.4093	800	1.0727	0.2472
1.4484	11.1116	1200	0.9105	0.2157
1.3057	14.8186	1600	0.7805	0.1916
1.1953	18.5209	2000	0.6652	0.1733
1.0976	22.2233	2400	0.5809	0.1489
1.0171	25.9302	2800	0.5125	0.1280
0.9628	29.6326	3200	0.4909	0.1252

Framework versions

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