test-train-model
This model is a fine-tuned version of distilbert-base-uncased on the szeged_ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.0319
- Precision: 0.9325
- Recall: 0.9309
- F1: 0.9317
- Accuracy: 0.9925
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2029 | 1.0 | 511 | 0.0493 | 0.8734 | 0.8564 | 0.8648 | 0.9873 |
0.0756 | 2.0 | 1022 | 0.0381 | 0.8930 | 0.9025 | 0.8977 | 0.9897 |
0.0489 | 3.0 | 1533 | 0.0327 | 0.925 | 0.9184 | 0.9217 | 0.9921 |
0.0339 | 4.0 | 2044 | 0.0323 | 0.9385 | 0.9202 | 0.9293 | 0.9926 |
0.0258 | 5.0 | 2555 | 0.0319 | 0.9325 | 0.9309 | 0.9317 | 0.9925 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 4
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.
Model tree for terhdavid/test-train-model
Base model
distilbert/distilbert-base-uncased
Finetuned
this model
Evaluation results
- Precision on szeged_nervalidation set self-reported0.933
- Recall on szeged_nervalidation set self-reported0.931
- F1 on szeged_nervalidation set self-reported0.932
- Accuracy on szeged_nervalidation set self-reported0.993