metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: humor_model_v2
results: []
humor_model_v2
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2465
- Accuracy: 0.9398
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.9524 | 5 | 0.6377 | 0.9157 |
| 0.6535 | 1.9048 | 10 | 0.5485 | 0.9458 |
| 0.6535 | 2.8571 | 15 | 0.4509 | 0.9217 |
| 0.4938 | 4.0 | 21 | 0.3879 | 0.8795 |
| 0.4938 | 4.9524 | 26 | 0.2894 | 0.9277 |
| 0.3475 | 5.9048 | 31 | 0.2942 | 0.8614 |
| 0.3475 | 6.8571 | 36 | 0.2705 | 0.9518 |
| 0.2678 | 8.0 | 42 | 0.2951 | 0.8976 |
| 0.2678 | 8.9524 | 47 | 0.2542 | 0.9398 |
| 0.1837 | 9.5238 | 50 | 0.2465 | 0.9398 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1