metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- recall
- precision
- f1
model-index:
- name: DL_Audio_Hatespeech_text_classification_trainer_push
results: []
DL_Audio_Hatespeech_text_classification_trainer_push
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6725
- Accuracy: 0.7641
- Recall: 0.7771
- Precision: 0.7620
- F1: 0.7695
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: 8e-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 | Recall | Precision | F1 |
|---|---|---|---|---|---|---|---|
| 0.0191 | 1.0 | 97 | 1.5765 | 0.7483 | 0.8032 | 0.7281 | 0.7638 |
| 0.0351 | 2.0 | 194 | 1.2599 | 0.7428 | 0.8070 | 0.7195 | 0.7607 |
| 0.0451 | 3.0 | 291 | 1.1736 | 0.7580 | 0.7860 | 0.7488 | 0.7669 |
| 0.039 | 4.0 | 388 | 1.2600 | 0.7557 | 0.7592 | 0.7588 | 0.7590 |
| 0.039 | 5.0 | 485 | 1.1336 | 0.7606 | 0.7631 | 0.7640 | 0.7635 |
| 0.0199 | 6.0 | 582 | 1.4645 | 0.7593 | 0.7777 | 0.7546 | 0.7660 |
| 0.017 | 7.0 | 679 | 1.5825 | 0.7628 | 0.7096 | 0.7997 | 0.7519 |
| 0.0062 | 8.0 | 776 | 1.5688 | 0.7673 | 0.7510 | 0.7813 | 0.7658 |
| 0.0121 | 9.0 | 873 | 1.6285 | 0.7651 | 0.7510 | 0.7777 | 0.7641 |
| 0.0054 | 10.0 | 970 | 1.6725 | 0.7641 | 0.7771 | 0.7620 | 0.7695 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1