distilbert-base-uncased-career-path-prediction
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: 0.1294
- Accuracy: 0.9782
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 229 | 0.1160 | 0.9727 |
| No log | 2.0 | 458 | 0.1038 | 0.9749 |
| 0.0881 | 3.0 | 687 | 0.1187 | 0.9716 |
| 0.0881 | 4.0 | 916 | 0.1040 | 0.9793 |
| 0.0238 | 5.0 | 1145 | 0.1498 | 0.9738 |
| 0.0238 | 6.0 | 1374 | 0.1231 | 0.9793 |
| 0.0062 | 7.0 | 1603 | 0.1366 | 0.9782 |
| 0.0062 | 8.0 | 1832 | 0.1305 | 0.9793 |
| 0.001 | 9.0 | 2061 | 0.1336 | 0.9782 |
| 0.001 | 10.0 | 2290 | 0.1294 | 0.9782 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 31
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for fazni/distilbert-base-uncased-career-path-prediction
Base model
distilbert/distilbert-base-uncased