jialicheng/unlearn_speech_commands_hubert-base_scrub_4_42

superb_ks_42

This model is a fine-tuned version of facebook/hubert-base-ls960 on the superb dataset. It achieves the following results on the evaluation set:

• Loss: 262.3300
• Accuracy: 0.6209
• Test Accuracy: 0.6209
• Df Accuracy: 0.1831
• Unlearn Overall Accuracy: 0.7189
• Unlearn Time: 1189.3463

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
0.0	1.0	1533	262.3300	0.1831	0.7189	0.7189	-1
0.0	2.0	3066	1188.8350	0.1831	0.7189	0.7189	-1
0.0	3.0	4599	2441.6357	0.1831	0.7189	0.7189	-1
0.0	4.0	6132	3492.5366	0.1831	0.7189	0.7189	-1
0.0	5.0	7665	3902.1348	0.1831	0.7189	0.7189	-1

Framework versions

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