metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: interview_classifier
results: []
interview_classifier
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: 0.5007
- Accuracy: 0.9815
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 54 | 2.2376 | 0.2222 |
| No log | 2.0 | 108 | 2.1541 | 0.2130 |
| No log | 3.0 | 162 | 2.0326 | 0.5370 |
| No log | 4.0 | 216 | 1.8738 | 0.6481 |
| No log | 5.0 | 270 | 1.7025 | 0.7037 |
| No log | 6.0 | 324 | 1.5183 | 0.8333 |
| No log | 7.0 | 378 | 1.3588 | 0.8426 |
| No log | 8.0 | 432 | 1.2014 | 0.8796 |
| No log | 9.0 | 486 | 1.0698 | 0.9074 |
| 1.8141 | 10.0 | 540 | 0.9494 | 0.9259 |
| 1.8141 | 11.0 | 594 | 0.8497 | 0.9352 |
| 1.8141 | 12.0 | 648 | 0.7666 | 0.9352 |
| 1.8141 | 13.0 | 702 | 0.6960 | 0.9444 |
| 1.8141 | 14.0 | 756 | 0.6407 | 0.9537 |
| 1.8141 | 15.0 | 810 | 0.5952 | 0.9537 |
| 1.8141 | 16.0 | 864 | 0.5619 | 0.9630 |
| 1.8141 | 17.0 | 918 | 0.5335 | 0.9630 |
| 1.8141 | 18.0 | 972 | 0.5159 | 0.9722 |
| 0.7883 | 19.0 | 1026 | 0.5044 | 0.9815 |
| 0.7883 | 20.0 | 1080 | 0.5007 | 0.9815 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1