ssc-bew-mms-model-mix-adapt-max

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6537
  • Cer: 0.1746
  • Wer: 0.5203

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: 2
  • eval_batch_size: 6
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 4
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Cer Wer
0.648 0.9828 200 0.6882 0.1821 0.5469
0.6337 1.9631 400 0.6792 0.1797 0.5336
0.5803 2.9435 600 0.6627 0.1774 0.5296
0.5773 3.9238 800 0.6562 0.1759 0.5236
0.5492 4.9042 1000 0.6537 0.1746 0.5203

Framework versions

  • Transformers 4.57.2
  • Pytorch 2.9.1+cu128
  • Datasets 3.6.0
  • Tokenizers 0.22.0
Downloads last month
-
Safetensors
Model size
1.0B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support