metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- minds14
metrics:
- accuracy
model-index:
- name: my_awesome_mind
results: []
my_awesome_mind
This model is a fine-tuned version of facebook/wav2vec2-base on the minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 2.6391
- Accuracy: 0.0885
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: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.2283 | 11.53 | 35 | 2.6432 | 0.1062 |
| 3.4248 | 23.27 | 70 | 2.6394 | 0.0973 |
| 3.4245 | 34.8 | 105 | 2.6404 | 0.0442 |
| 3.2245 | 46.53 | 140 | 2.6405 | 0.0531 |
| 3.2287 | 58.27 | 175 | 2.6416 | 0.0796 |
| 3.2289 | 69.8 | 210 | 2.6424 | 0.0973 |
| 3.2252 | 81.53 | 245 | 2.6396 | 0.1062 |
| 3.424 | 93.27 | 280 | 2.6391 | 0.0885 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.13.1
- Datasets 2.15.0
- Tokenizers 0.10.3