my_awesome_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: 2.6476
• Accuracy: 0.1062

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.8276	3	2.6387	0.0531
No log	1.8276	6	2.6428	0.0265
No log	2.8276	9	2.6448	0.0619
2.837	3.8276	12	2.6436	0.0531
2.837	4.8276	15	2.6464	0.0619
2.837	5.8276	18	2.6462	0.0885
2.8278	6.8276	21	2.6466	0.0973
2.8278	7.8276	24	2.6465	0.1062
2.8278	8.8276	27	2.6471	0.1062
2.8242	9.8276	30	2.6476	0.1062

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0