IDAT_grn_aug_521_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: 0.6931
• Accuracy: 0.5

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6311	1.0	175	0.6923	0.49
0.6475	2.0	350	0.5901	0.71
0.6961	3.0	525	0.6930	0.5
0.6011	4.0	700	0.5435	0.715
0.6929	5.0	875	0.5165	0.745
0.6942	6.0	1050	0.6937	0.5
0.6941	7.0	1225	0.6934	0.5
0.6934	8.0	1400	0.6936	0.5
0.6938	9.0	1575	0.6941	0.5
0.6931	10.0	1750	0.6936	0.5
0.6961	11.0	1925	0.6931	0.5
0.6944	12.0	2100	0.6931	0.5
0.694	13.0	2275	0.6936	0.5
0.6931	14.0	2450	0.6931	0.5
0.693	15.0	2625	0.6931	0.5
0.6909	16.0	2800	0.6936	0.5
0.6932	17.0	2975	0.6931	0.5
0.6931	18.0	3150	0.6931	0.5
0.6933	19.0	3325	0.6931	0.5
0.6934	20.0	3500	0.6931	0.5

Framework versions

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