metadata
library_name: peft
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- hatexplain
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: finetuned-distilbert-lora-hatexplain
results: []
finetuned-distilbert-lora-hatexplain
This model is a fine-tuned version of distilbert-base-uncased on the hatexplain dataset. It achieves the following results on the evaluation set:
- Loss: 0.7335
- Accuracy: 0.6767
- Precision: 0.6679
- Recall: 0.6767
- F1: 0.6703
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.7301 | 1.0 | 962 | 0.7683 | 0.6561 | 0.6475 | 0.6561 | 0.6446 |
| 0.747 | 2.0 | 1924 | 0.7493 | 0.6644 | 0.6611 | 0.6644 | 0.6597 |
| 0.7918 | 3.0 | 2886 | 0.7332 | 0.6774 | 0.6712 | 0.6774 | 0.6710 |
| 0.6507 | 4.0 | 3848 | 0.7357 | 0.6805 | 0.6735 | 0.6805 | 0.6747 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.0
- Pytorch 2.5.1+cu118
- Datasets 3.1.0
- Tokenizers 0.21.0