bert-finetuned-sla
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: 0.3274
- F1: 0.6555
- Roc Auc: 0.7660
- Accuracy: 0.5294
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: 4
- eval_batch_size: 4
- 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 | F1 | Roc Auc | Accuracy |
---|---|---|---|---|---|---|
No log | 1.0 | 30 | 0.4994 | 0.0 | 0.5 | 0.0 |
No log | 2.0 | 60 | 0.4408 | 0.0 | 0.5 | 0.0 |
No log | 3.0 | 90 | 0.3761 | 0.4444 | 0.6462 | 0.1961 |
No log | 4.0 | 120 | 0.3438 | 0.6496 | 0.7604 | 0.4706 |
No log | 5.0 | 150 | 0.3274 | 0.6555 | 0.7660 | 0.5294 |
No log | 6.0 | 180 | 0.3093 | 0.6557 | 0.7699 | 0.4706 |
No log | 7.0 | 210 | 0.3083 | 0.6560 | 0.7738 | 0.5098 |
No log | 8.0 | 240 | 0.3030 | 0.6457 | 0.7703 | 0.4706 |
No log | 9.0 | 270 | 0.3096 | 0.6667 | 0.7811 | 0.4902 |
No log | 10.0 | 300 | 0.2976 | 0.6718 | 0.7907 | 0.5098 |
No log | 11.0 | 330 | 0.2986 | 0.6769 | 0.7924 | 0.5294 |
No log | 12.0 | 360 | 0.3046 | 0.6562 | 0.7777 | 0.5098 |
No log | 13.0 | 390 | 0.2988 | 0.6870 | 0.7997 | 0.4902 |
No log | 14.0 | 420 | 0.3026 | 0.6769 | 0.7924 | 0.5098 |
No log | 15.0 | 450 | 0.3005 | 0.6870 | 0.7997 | 0.5098 |
No log | 16.0 | 480 | 0.3012 | 0.6822 | 0.7941 | 0.5098 |
0.2216 | 17.0 | 510 | 0.3013 | 0.6977 | 0.8032 | 0.5294 |
0.2216 | 18.0 | 540 | 0.3033 | 0.6977 | 0.8032 | 0.5294 |
0.2216 | 19.0 | 570 | 0.3024 | 0.6977 | 0.8032 | 0.5294 |
0.2216 | 20.0 | 600 | 0.3027 | 0.6923 | 0.8015 | 0.5098 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
- Downloads last month
- 18
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.