jialicheng/unlearn_speech_commands_wav2vec2-large_neggrad_2_42

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: -7.0777
• Accuracy: 0.6209
• Test Accuracy: 0.6209
• Df Accuracy: 0.1352
• Unlearn Overall Accuracy: 0.7429
• Unlearn Time: 572.3417

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	32	-2.7512	0.4251	0.6613	0.6613	-1
No log	2.0	64	-7.0777	0.1352	0.7429	0.7429	-1
No log	3.0	96	-9.8062	0.1352	0.7429	0.7429	-1
No log	4.0	128	-12.3922	0.1352	0.7429	0.7429	-1
No log	5.0	160	-14.7819	0.1352	0.7429	0.7429	-1
No log	6.0	192	-16.8573	0.1352	0.7429	0.7429	-1
No log	7.0	224	-18.5870	0.1352	0.7429	0.7429	-1
No log	8.0	256	-19.8639	0.1352	0.7429	0.7429	-1
No log	9.0	288	-20.6518	0.1352	0.7429	0.7429	-1
No log	10.0	320	-20.9192	0.1352	0.7429	0.7429	-1

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu118
• Datasets 2.18.0
• Tokenizers 0.15.2