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: 2.5779
- Accuracy: 0.2597
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: 3.3e-05
- train_batch_size: 20
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.09 | 200 | 2.6170 | 0.2412 |
| No log | 0.19 | 400 | 2.6193 | 0.2412 |
| No log | 0.28 | 600 | 2.6109 | 0.2519 |
| No log | 0.37 | 800 | 2.5937 | 0.2551 |
| No log | 0.47 | 1000 | 2.5840 | 0.2607 |
| No log | 0.56 | 1200 | 2.5814 | 0.2620 |
| No log | 0.66 | 1400 | 2.5889 | 0.2535 |
| No log | 0.75 | 1600 | 2.5779 | 0.2595 |
| No log | 0.84 | 1800 | 2.5752 | 0.2622 |
| 2.4849 | 0.94 | 2000 | 2.5779 | 0.2597 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3