metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-base-finetuned-ic-slurp-wt_init
results: []
wav2vec2-base-finetuned-ic-slurp-wt_init
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.8597
- Accuracy: 0.0627
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: 0.001
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 96
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.7961 | 1.0 | 527 | 3.9199 | 0.0400 |
| 3.797 | 2.0 | 1055 | 3.9294 | 0.0520 |
| 3.9174 | 3.0 | 1582 | 3.8597 | 0.0627 |
| 3.9264 | 4.0 | 2110 | 3.8551 | 0.0627 |
| 3.8772 | 5.0 | 2637 | 3.8744 | 0.0627 |
| 3.9218 | 6.0 | 3165 | 3.8676 | 0.0627 |
| 3.8898 | 7.0 | 3692 | 3.8515 | 0.0627 |
| 3.9045 | 8.0 | 4220 | 3.8544 | 0.0627 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2