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: 2.0576
- Accuracy: 0.3263
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 |
|---|---|---|---|---|
| 1.2851 | 1.0 | 12 | 2.0303 | 0.3591 |
| 1.3553 | 2.0 | 24 | 1.9871 | 0.3578 |
| 1.3409 | 3.0 | 36 | 2.0494 | 0.3447 |
| 1.3693 | 4.0 | 48 | 1.9496 | 0.3342 |
| 1.3302 | 5.0 | 60 | 2.0545 | 0.3132 |
| 1.2847 | 6.0 | 72 | 2.0551 | 0.3290 |
| 1.2733 | 7.0 | 84 | 2.0966 | 0.3224 |
| 1.2499 | 8.0 | 96 | 2.0577 | 0.3185 |
| 1.2894 | 9.0 | 108 | 2.0575 | 0.3211 |
| 1.2753 | 10.0 | 120 | 2.0576 | 0.3263 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0
- Datasets 2.19.2.dev0
- Tokenizers 0.19.1