metadata
base_model: distilbert/distilbert-base-uncased
library_name: peft
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: news-category-classifier-distilbert
results: []
news-category-classifier-distilbert
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1640
- Accuracy: 0.9474
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: 0.0002
- train_batch_size: 32
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 0.3293 | 1.0 | 2289 | 0.9119 | 0.2599 |
| 0.0576 | 2.0 | 4578 | 0.9193 | 0.2425 |
| 0.4575 | 3.0 | 6867 | 0.9223 | 0.2401 |
| 0.0339 | 4.0 | 9156 | 0.9245 | 0.2353 |
| 0.0512 | 5.0 | 11445 | 0.9267 | 0.2367 |
| 0.3254 | 6.0 | 13734 | 0.9267 | 0.2367 |
| 0.5933 | 7.0 | 16023 | 0.9482 | 0.1654 |
| 0.136 | 8.0 | 18312 | 0.9482 | 0.1654 |
| 0.3128 | 9.0 | 20601 | 0.1640 | 0.9474 |
| 0.0458 | 10.0 | 22890 | 0.1640 | 0.9474 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1