metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- wwwtwwwt/fineaudio-Entertainment
metrics:
- accuracy
model-index:
- name: Wav2Vec2 - Entertainment - Gaming Livestreams
results: []
Wav2Vec2 - Entertainment - Gaming Livestreams
This model is a fine-tuned version of facebook/wav2vec2-base on the fineaudio-Entertainment-Gaming Livestreams dataset. It achieves the following results on the evaluation set:
- Loss: 3.0
- Accuracy: 0.0
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: 3
- eval_batch_size: 3
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2945 | 0.0937 | 500 | 2.8814 | 0.0 |
| 1.2961 | 0.1875 | 1000 | 2.8496 | 0.0 |
| 1.2744 | 0.2812 | 1500 | 3.1602 | 0.0 |
| 1.2647 | 0.3750 | 2000 | 3.2832 | 0.0 |
| 1.269 | 0.4687 | 2500 | 3.1699 | 0.0 |
| 1.2696 | 0.5624 | 3000 | 3.1230 | 0.0 |
| 1.2664 | 0.6562 | 3500 | 3.0762 | 0.0 |
| 1.286 | 0.7499 | 4000 | 3.0 | 0.0 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.0