hubert-base-ls960-fsc

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

• Loss: 0.0230
• Accuracy: 0.9939

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: 0.0005
• train_batch_size: 48
• eval_batch_size: 48
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 192
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.9959	120	0.0706	0.9873
No log	2.0	241	0.0607	0.9868
No log	2.9959	361	0.0661	0.9831
No log	4.0	482	0.0518	0.9839
No log	4.9959	602	0.0230	0.9939
No log	6.0	723	0.0516	0.9858
No log	6.9959	843	0.0292	0.9937
No log	8.0	964	0.0276	0.9929
0.2849	8.9959	1084	0.0301	0.9937
0.2849	10.0	1205	0.0279	0.9937

Framework versions

• Transformers 4.43.3
• Pytorch 2.2.2+cu121
• Datasets 2.18.0
• Tokenizers 0.19.1