bert-base-uncased-finetuned-recruitment-exp
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1433
- Precision: 0.6113
- Recall: 0.7250
- F1: 0.6633
- Accuracy: 0.9612
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: 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 17 | 0.5254 | 0.0 | 0.0 | 0.0 | 0.8991 |
| No log | 2.0 | 34 | 0.3199 | 0.2854 | 0.2255 | 0.2519 | 0.9152 |
| No log | 3.0 | 51 | 0.2303 | 0.3948 | 0.5232 | 0.4500 | 0.9370 |
| No log | 4.0 | 68 | 0.1878 | 0.4876 | 0.6212 | 0.5463 | 0.9496 |
| No log | 5.0 | 85 | 0.1630 | 0.5544 | 0.6548 | 0.6005 | 0.9553 |
| No log | 6.0 | 102 | 0.1433 | 0.6113 | 0.7250 | 0.6633 | 0.9612 |
| No log | 7.0 | 119 | 0.1469 | 0.6412 | 0.7458 | 0.6895 | 0.9621 |
| No log | 8.0 | 136 | 0.1463 | 0.6516 | 0.7418 | 0.6938 | 0.9633 |
| No log | 9.0 | 153 | 0.1446 | 0.6664 | 0.7527 | 0.7069 | 0.9643 |
| No log | 10.0 | 170 | 0.1447 | 0.6579 | 0.7646 | 0.7072 | 0.9641 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3