my_awesome_mind_model – AI Model by qwerty-n | AlphaNeural AI

You can deploy this model and start earning money today!

qwerty-n/
my_awesome_mind_model

like

0

audio-classification

generated_from_trainer

facebook/wav2vec2-base

endpoints_compatible

Views

No views yet

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: 2.6700
Accuracy: 0.0619

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: 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: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.8	3	2.6413	0.0708
No log	1.8	6	2.6507	0.0531
No log	2.8	9	2.6588	0.0619
3.0271	3.8	12	2.6624	0.0619
3.0271	4.8	15	2.6636	0.0619
3.0271	5.8	18	2.6644	0.0531
3.0099	6.8	21	2.6646	0.0708
3.0099	7.8	24	2.6674	0.0708
3.0099	8.8	27	2.6684	0.0619
3.0016	9.8	30	2.6700	0.0619

Framework versions

Transformers 4.49.0
Pytorch 2.3.1.post300
Datasets 3.3.1
Tokenizers 0.21.0