metadata
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-distilled-assign4
results: []
distilbert-distilled-assign4
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: 0.2808
- Accuracy: 0.9497
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: 0.00015873648520979436
- train_batch_size: 48
- eval_batch_size: 48
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4892 | 1.0 | 318 | 0.4144 | 0.9210 |
| 0.2433 | 2.0 | 636 | 0.3386 | 0.9361 |
| 0.1445 | 3.0 | 954 | 0.3118 | 0.9465 |
| 0.1135 | 4.0 | 1272 | 0.3060 | 0.9442 |
| 0.0983 | 5.0 | 1590 | 0.2805 | 0.9510 |
| 0.0922 | 6.0 | 1908 | 0.2840 | 0.9484 |
| 0.0885 | 7.0 | 2226 | 0.2806 | 0.9506 |
| 0.0869 | 8.0 | 2544 | 0.2808 | 0.9497 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1