metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: office-character
results: []
office-character
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: 2.7752
- Accuracy: 0.1429
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.8784 | 0.2 | 60 | 2.8602 | 0.0807 |
| 2.8535 | 0.4 | 120 | 2.8465 | 0.0971 |
| 2.8292 | 0.6 | 180 | 2.8197 | 0.1004 |
| 2.7971 | 0.8 | 240 | 2.8041 | 0.1037 |
| 2.7996 | 1.0 | 300 | 2.7861 | 0.1227 |
| 2.668 | 1.2 | 360 | 2.7832 | 0.1288 |
| 2.6317 | 1.4 | 420 | 2.7636 | 0.1309 |
| 2.6236 | 1.59 | 480 | 2.7676 | 0.1315 |
| 2.571 | 1.79 | 540 | 2.7519 | 0.1326 |
| 2.5832 | 1.99 | 600 | 2.7572 | 0.1358 |
| 2.3685 | 2.19 | 660 | 2.7616 | 0.1484 |
| 2.376 | 2.39 | 720 | 2.7727 | 0.1429 |
| 2.3499 | 2.59 | 780 | 2.7808 | 0.1391 |
| 2.3561 | 2.79 | 840 | 2.7736 | 0.1451 |
| 2.3265 | 2.99 | 900 | 2.7752 | 0.1429 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3