electra-base-ner-food-recipe-v2
This model is a fine-tuned version of google/electra-base-discriminator on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1500
- Precision: 0.7191
- Recall: 0.8739
- F1: 0.7890
- Accuracy: 0.9568
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-07
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.5 | 400 | 0.4360 | 0.4354 | 0.7533 | 0.5519 | 0.8775 |
0.5627 | 1.01 | 800 | 0.2274 | 0.6971 | 0.8525 | 0.7670 | 0.9508 |
0.2799 | 1.51 | 1200 | 0.1791 | 0.6728 | 0.8762 | 0.7612 | 0.9492 |
0.1983 | 2.01 | 1600 | 0.1652 | 0.6958 | 0.8757 | 0.7755 | 0.9535 |
0.1821 | 2.51 | 2000 | 0.1610 | 0.7171 | 0.8766 | 0.7889 | 0.9568 |
0.1821 | 3.02 | 2400 | 0.1550 | 0.7001 | 0.8757 | 0.7782 | 0.9539 |
0.1726 | 3.52 | 2800 | 0.1537 | 0.7211 | 0.8744 | 0.7904 | 0.9573 |
0.1674 | 4.02 | 3200 | 0.1510 | 0.7170 | 0.8739 | 0.7877 | 0.9565 |
0.1682 | 4.52 | 3600 | 0.1501 | 0.7147 | 0.8744 | 0.7865 | 0.9564 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
- Downloads last month
- 5
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.