hubert-base-ls960-finetuned-bmd-V1-20241110_103816-LOSO-section-out4

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: 0.8940
• Accuracy: 0.5667
• F1: 0.5472

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 1968
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use 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	F1
No log	0.9333	7	1.0900	0.4	0.2628
1.1061	2.0	15	1.0551	0.4	0.2628
1.0768	2.9333	22	1.0304	0.5333	0.4540
1.0176	4.0	30	0.9738	0.4667	0.3599
1.0176	4.9333	37	0.8938	0.5333	0.4538
0.9959	6.0	45	0.8884	0.5333	0.4852
0.9677	6.9333	52	0.8874	0.6333	0.5708
0.7597	8.0	60	0.8811	0.6667	0.6629
0.7597	8.9333	67	0.8911	0.6	0.5761
0.7455	9.3333	70	0.8940	0.5667	0.5472

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3