testV5
This model is a fine-tuned version of anderloh/Hugginhface-master-wav2vec-pretreined-5-class-train-test on the anderloh/Master5Class dataset. It achieves the following results on the evaluation set:
- Loss: 1.5942
- Accuracy: 0.2238
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.92 | 3 | 1.6009 | 0.1608 |
| No log | 1.85 | 6 | 1.5979 | 0.1643 |
| No log | 2.77 | 9 | 1.5959 | 0.1923 |
| No log | 4.0 | 13 | 1.5944 | 0.2203 |
| No log | 4.62 | 15 | 1.5942 | 0.2238 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 21
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.