metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: SER_model_xapiens
results: []
SER_model_xapiens
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6879
- Accuracy: 0.4050
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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 | 9 | 1.9247 | 0.4063 |
| 2.0359 | 2.0 | 18 | 1.7484 | 0.4063 |
| 1.8346 | 3.0 | 27 | 1.7171 | 0.4063 |
| 1.7777 | 4.0 | 36 | 1.7039 | 0.4063 |
| 1.7825 | 5.0 | 45 | 1.6975 | 0.4063 |
| 1.7578 | 6.0 | 54 | 1.6899 | 0.4076 |
| 1.7549 | 7.0 | 63 | 1.6824 | 0.4181 |
| 1.732 | 8.0 | 72 | 1.6886 | 0.4050 |
| 1.7433 | 9.0 | 81 | 1.6975 | 0.3919 |
| 1.7299 | 10.0 | 90 | 1.6879 | 0.4050 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0
- Datasets 2.19.2.dev0
- Tokenizers 0.19.1