<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
vakyansh-wav2vec2-hindi-him-4200-audio-abuse
This model is a fine-tuned version of Harveenchadha/vakyansh-wav2vec2-hindi-him-4200 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 6.7544
- Accuracy: 0.5178
- Macro Precision: 0.2589
- Macro Recall: 0.5
- Macro F1-score: 0.3411
- Weighted Precision: 0.2681
- Weighted Recall: 0.5178
- Weighted F1-score: 0.3533
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 | Macro Precision | Macro Recall | Macro F1-score | Weighted Precision | Weighted Recall | Weighted F1-score |
---|---|---|---|---|---|---|---|---|---|---|
8.1051 | 0.98 | 28 | 7.6381 | 0.4926 | 0.4469 | 0.4974 | 0.3385 | 0.4464 | 0.4926 | 0.3353 |
7.2785 | 2.0 | 57 | 6.7621 | 0.4950 | 0.2475 | 0.5 | 0.3311 | 0.2451 | 0.4950 | 0.3278 |
6.7182 | 2.98 | 85 | 6.2336 | 0.4950 | 0.2475 | 0.5 | 0.3311 | 0.2451 | 0.4950 | 0.3278 |
6.1765 | 4.0 | 114 | 5.7714 | 0.4950 | 0.2475 | 0.5 | 0.3311 | 0.2451 | 0.4950 | 0.3278 |
5.7722 | 4.98 | 142 | 5.3683 | 0.4950 | 0.2475 | 0.5 | 0.3311 | 0.2451 | 0.4950 | 0.3278 |
5.4392 | 6.0 | 171 | 5.0190 | 0.4950 | 0.2475 | 0.5 | 0.3311 | 0.2451 | 0.4950 | 0.3278 |
5.2357 | 6.98 | 199 | 4.7449 | 0.4950 | 0.2475 | 0.5 | 0.3311 | 0.2451 | 0.4950 | 0.3278 |
4.8778 | 8.0 | 228 | 4.5390 | 0.4950 | 0.2475 | 0.5 | 0.3311 | 0.2451 | 0.4950 | 0.3278 |
4.7514 | 8.98 | 256 | 4.4240 | 0.4950 | 0.2475 | 0.5 | 0.3311 | 0.2451 | 0.4950 | 0.3278 |
4.7285 | 9.82 | 280 | 4.3913 | 0.4950 | 0.2475 | 0.5 | 0.3311 | 0.2451 | 0.4950 | 0.3278 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3