test-finetuned__roberta-base-biomedical-clinical-es__59k-ultrasounds-ner
This model is a fine-tuned version of manucos/finetuned__roberta-base-biomedical-clinical-es__59k-ultrasounds on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3097
- Precision: 0.8060
- Recall: 0.8917
- F1: 0.8467
- Accuracy: 0.9300
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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 206 | 0.2915 | 0.7439 | 0.8350 | 0.7868 | 0.9096 |
No log | 2.0 | 412 | 0.2505 | 0.7779 | 0.8613 | 0.8175 | 0.9215 |
0.4211 | 3.0 | 618 | 0.2737 | 0.7647 | 0.8553 | 0.8075 | 0.9179 |
0.4211 | 4.0 | 824 | 0.2784 | 0.7879 | 0.8796 | 0.8312 | 0.9239 |
0.1009 | 5.0 | 1030 | 0.2779 | 0.7885 | 0.8866 | 0.8347 | 0.9282 |
0.1009 | 6.0 | 1236 | 0.2979 | 0.8037 | 0.8866 | 0.8431 | 0.9276 |
0.1009 | 7.0 | 1442 | 0.3058 | 0.7903 | 0.8887 | 0.8366 | 0.9273 |
0.0525 | 8.0 | 1648 | 0.3010 | 0.8057 | 0.8856 | 0.8438 | 0.9269 |
0.0525 | 9.0 | 1854 | 0.3090 | 0.8137 | 0.8927 | 0.8514 | 0.9307 |
0.0316 | 10.0 | 2060 | 0.3097 | 0.8060 | 0.8917 | 0.8467 | 0.9300 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 3
Invalid base_model specified in model card
metadata. Needs to be a model id from
hf.co/models.