testV4
This model is a fine-tuned version of anderloh/Hugginhface-master-wav2vec-pretreined-5-class-train-test on the superb dataset. It achieves the following results on the evaluation set:
- Loss: 1.9986
- Accuracy: 0.6209
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: 3e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.3236 | 1.0 | 100 | 1.9986 | 0.6209 |
| 1.6222 | 2.0 | 200 | 1.5412 | 0.6209 |
| 1.4879 | 3.0 | 300 | 1.5255 | 0.6209 |
| 1.4797 | 4.0 | 400 | 1.5182 | 0.6209 |
| 1.4761 | 5.0 | 500 | 1.5151 | 0.6209 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 12
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.