metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned
results: []
distilbert-base-uncased-finetuned
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0098
- Accuracy: 0.9009
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3073 | 1.0 | 5250 | 0.2758 | 0.8925 |
| 0.2356 | 2.0 | 10500 | 0.2988 | 0.8988 |
| 0.1834 | 3.0 | 15750 | 0.3662 | 0.8989 |
| 0.1403 | 4.0 | 21000 | 0.4688 | 0.8955 |
| 0.1038 | 5.0 | 26250 | 0.5136 | 0.8925 |
| 0.0788 | 6.0 | 31500 | 0.6189 | 0.8954 |
| 0.0687 | 7.0 | 36750 | 0.6439 | 0.8947 |
| 0.0439 | 8.0 | 42000 | 0.7104 | 0.8991 |
| 0.035 | 9.0 | 47250 | 0.7527 | 0.8983 |
| 0.0205 | 10.0 | 52500 | 0.8317 | 0.9011 |
| 0.0258 | 11.0 | 57750 | 0.8488 | 0.9003 |
| 0.0174 | 12.0 | 63000 | 0.8577 | 0.9027 |
| 0.0095 | 13.0 | 68250 | 0.9242 | 0.9007 |
| 0.0096 | 14.0 | 73500 | 1.0134 | 0.9003 |
| 0.0083 | 15.0 | 78750 | 1.0098 | 0.9009 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3