run_20250121_121944

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9678
• Accuracy: 0.5676

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 22
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5043	2.7200	34	0.9872	0.6757
0.4196	5.44	68	0.9670	0.6486
0.3056	8.16	102	1.2386	0.5946
0.2666	10.88	136	1.3272	0.5676
0.1761	13.6	170	1.5065	0.5946
0.1485	16.32	204	1.9727	0.5405
0.1022	19.04	238	1.9678	0.5676

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3