super_emo_peepo
This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-english on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9463
- Accuracy: 0.6961
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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 | 1.0 | 141 | 1.4385 | 0.4360 |
| No log | 2.0 | 283 | 0.9948 | 0.6135 |
| No log | 3.0 | 424 | 0.9157 | 0.6356 |
| 1.1888 | 4.0 | 566 | 0.8856 | 0.6634 |
| 1.1888 | 5.0 | 707 | 0.8592 | 0.6895 |
| 1.1888 | 6.0 | 849 | 0.8909 | 0.6789 |
| 1.1888 | 7.0 | 990 | 0.8880 | 0.6864 |
| 0.7076 | 8.0 | 1132 | 0.8914 | 0.6970 |
| 0.7076 | 9.0 | 1273 | 0.9377 | 0.6860 |
| 0.7076 | 9.96 | 1410 | 0.9463 | 0.6961 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.16.0
- Tokenizers 0.15.2
- Downloads last month
- 7