ssc-tob-mms-model-mix-adapt-max2-2

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

• Loss: 0.7889
• Cer: 0.1708
• Wer: 0.5634

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: 1
• eval_batch_size: 6
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• 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: 100
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
0.54	0.4790	200	0.8931	0.1818	0.5940
0.5357	0.9581	400	0.8083	0.1791	0.5833
0.4814	1.4359	600	0.8028	0.1749	0.5757
0.4582	1.9150	800	0.8123	0.1738	0.5757
0.4559	2.3928	1000	0.7889	0.1734	0.5736
0.4258	2.8719	1200	0.8098	0.1771	0.5956
0.4741	3.3497	1400	0.7958	0.1722	0.5596
0.3966	3.8287	1600	0.8151	0.1747	0.5738
0.3995	4.3066	1800	0.7876	0.1738	0.5817
0.3885	4.7856	2000	0.7889	0.1708	0.5634

Framework versions

• Transformers 4.52.1
• Pytorch 2.9.1+cu128
• Datasets 3.6.0
• Tokenizers 0.21.4