my_awesome_lang_class_mind_model

This model is a fine-tuned version of facebook/wav2vec2-base on the minds14 dataset. It achieves the following results on the evaluation set:

• Loss: 2.3072
• Accuracy: 0.2124

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• 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
2.597	1.0	51	2.5777	0.1481
2.4608	1.99	102	2.4484	0.1567
2.4352	2.99	153	2.4153	0.1548
2.3965	4.0	205	2.3796	0.1897
2.363	5.0	256	2.3622	0.1922
2.3369	5.99	307	2.3496	0.1854
2.292	6.99	358	2.3286	0.2038
2.2788	8.0	410	2.3170	0.2075
2.2537	9.0	461	2.3090	0.2044
2.241	9.95	510	2.3072	0.2124

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0