unlearn_speech_commands_wav2vec2-large_neggrad_4_42 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn_speech_commands_wav2vec2-large_neggrad_4_42

like

0

audio-classification

generated_from_trainer

facebook/wav2vec2-large

Views

No views yet

superb_ks_42

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

Loss: -5.8324
Accuracy: 0.6209
Test Accuracy: 0.6209
Df Accuracy: 0.1395
Unlearn Overall Accuracy: 0.7407
Unlearn Time: 729.3629

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: 5e-05
train_batch_size: 32
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
No log	1.0	64	-5.8324	0.1395	0.7407	0.7407	-1
No log	2.0	128	-12.1573	0.1395	0.7407	0.7407	-1
No log	3.0	192	-19.0508	0.1395	0.7407	0.7407	-1
No log	4.0	256	-26.2673	0.1395	0.7407	0.7407	-1
No log	5.0	320	-33.2790	0.1395	0.7407	0.7407	-1
No log	6.0	384	-39.6040	0.1395	0.7407	0.7407	-1
No log	7.0	448	-44.8874	0.1395	0.7407	0.7407	-1
No log	8.0	512	-48.8812	0.1395	0.7407	0.7407	-1
No log	9.0	576	-51.3515	0.1395	0.7407	0.7407	-1
No log	10.0	640	-52.2043	0.1395	0.7407	0.7407	-1

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.18.0
Tokenizers 0.15.2