metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
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: 2.4745
- Accuracy: 0.1565
- F1: 0.1477
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: 20
- eval_batch_size: 20
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 2.5676 | 0.26 | 100 | 2.5803 | 0.0774 | 0.0111 |
| 2.5531 | 0.51 | 200 | 2.5176 | 0.1252 | 0.0967 |
| 2.5032 | 0.77 | 300 | 2.4914 | 0.1322 | 0.1155 |
| 2.4291 | 1.03 | 400 | 2.4709 | 0.1391 | 0.1223 |
| 2.2983 | 1.28 | 500 | 2.4680 | 0.1504 | 0.1415 |
| 2.2439 | 1.54 | 600 | 2.4774 | 0.1478 | 0.1415 |
| 2.1867 | 1.79 | 700 | 2.4745 | 0.1565 | 0.1477 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3