IDAT_red_aug_5443_novel_Wav2Vec

This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0190
• Accuracy: 0.7025

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: 3e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.576	1.0	200	0.6397	0.6512
0.5181	2.0	400	0.5415	0.7425
0.3743	3.0	600	0.5854	0.7662
0.3121	4.0	800	0.3357	0.8625
0.3069	5.0	1000	0.3341	0.865
0.3384	6.0	1200	0.3345	0.8625
0.449	7.0	1400	0.4558	0.7762
0.3062	8.0	1600	0.2643	0.91
0.1498	9.0	1800	0.6104	0.7887
0.0141	10.0	2000	1.0190	0.7025

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.2
• Datasets 2.16.1
• Tokenizers 0.13.3