base_sami_22k_cont_pt_ftpseudo_shuff142wr20esp5

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

• Loss: 1150.0363
• Wer: 1.0
• Cer: 1.0

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: 16
• eval_batch_size: 8
• seed: 42
• 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_ratio: 0.2
• num_epochs: 20.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
4511.6611	1.0	1080	1149.9353	1.0	1.0
3591.4514	2.0	2160	1155.4658	1.0	1.0
3649.9262	3.0	3240	1155.6082	1.0	1.0
3789.6616	4.0	4320	1146.7284	1.0	1.0
3752.8502	5.0	5400	1158.9340	1.0	1.0
3673.8093	6.0	6480	1151.3530	1.0	1.0

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1
• Datasets 3.2.0
• Tokenizers 0.21.0