ssc-el-CY-mms-model-mix-adapt-max3-devtrain

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

• Loss: 0.7292
• Cer: 0.1100
• Wer: 0.3727

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: 0.0005
• 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
2.5471	0.5168	200	0.8910	0.1252	0.4324
3.2045	1.0336	400	0.6331	0.1149	0.3929
0.3753	1.5504	600	0.7513	0.1146	0.3892
0.4161	2.0672	800	0.5198	0.1182	0.3911
0.3364	2.5840	1000	0.7785	0.1101	0.3829
7.3461	3.1008	1200	0.6933	0.1151	0.3861
0.2846	3.6176	1400	0.6265	0.1107	0.3795
0.2872	4.1344	1600	0.6975	0.1127	0.3837
4.3938	4.6512	1800	0.7292	0.1100	0.3727

Framework versions

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