<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
roberta-base-biomedical-clinical-es-finetuned-ner-timebank
This model is a fine-tuned version of PlanTL-GOB-ES/roberta-base-biomedical-clinical-es on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0162
- Precision: 0.8070
- Recall: 0.8854
- F1: 0.8444
- Accuracy: 0.9921
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: 8e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 82
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 24
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0658 | 1.0 | 8 | 0.0613 | 0.3704 | 0.4514 | 0.4069 | 0.9758 |
| 0.038 | 2.0 | 16 | 0.0328 | 0.4528 | 0.6667 | 0.5393 | 0.9789 |
| 0.0067 | 3.0 | 24 | 0.0212 | 0.4515 | 0.7431 | 0.5617 | 0.9776 |
| 0.0225 | 4.0 | 32 | 0.0177 | 0.4913 | 0.7847 | 0.6043 | 0.9814 |
| 0.0119 | 5.0 | 40 | 0.0170 | 0.5531 | 0.7778 | 0.6465 | 0.9848 |
| 0.0109 | 6.0 | 48 | 0.0151 | 0.7027 | 0.8125 | 0.7536 | 0.9893 |
| 0.003 | 7.0 | 56 | 0.0136 | 0.6260 | 0.8194 | 0.7098 | 0.9861 |
| 0.0059 | 8.0 | 64 | 0.0134 | 0.7164 | 0.8333 | 0.7705 | 0.9895 |
| 0.0065 | 9.0 | 72 | 0.0125 | 0.7040 | 0.8507 | 0.7704 | 0.9890 |
| 0.0017 | 10.0 | 80 | 0.0118 | 0.6177 | 0.8472 | 0.7145 | 0.9852 |
| 0.0021 | 11.0 | 88 | 0.0150 | 0.7812 | 0.8681 | 0.8224 | 0.9915 |
| 0.0041 | 12.0 | 96 | 0.0165 | 0.8078 | 0.8611 | 0.8336 | 0.9922 |
| 0.0025 | 13.0 | 104 | 0.0142 | 0.7723 | 0.8715 | 0.8189 | 0.9909 |
| 0.0024 | 14.0 | 112 | 0.0134 | 0.7440 | 0.8681 | 0.8013 | 0.9905 |
| 0.0027 | 15.0 | 120 | 0.0142 | 0.7699 | 0.8715 | 0.8176 | 0.9912 |
| 0.0019 | 16.0 | 128 | 0.0151 | 0.7918 | 0.8715 | 0.8298 | 0.9918 |
| 0.0036 | 17.0 | 136 | 0.0151 | 0.7837 | 0.8681 | 0.8237 | 0.9917 |
| 0.0011 | 18.0 | 144 | 0.0149 | 0.7730 | 0.875 | 0.8208 | 0.9914 |
| 0.0013 | 19.0 | 152 | 0.0152 | 0.7913 | 0.8819 | 0.8342 | 0.9918 |
| 0.0017 | 20.0 | 160 | 0.0159 | 0.8038 | 0.8819 | 0.8411 | 0.9922 |
| 0.0006 | 21.0 | 168 | 0.0164 | 0.8070 | 0.8854 | 0.8444 | 0.9922 |
| 0.002 | 22.0 | 176 | 0.0164 | 0.8121 | 0.8854 | 0.8472 | 0.9922 |
| 0.0021 | 23.0 | 184 | 0.0163 | 0.8121 | 0.8854 | 0.8472 | 0.9922 |
| 0.0013 | 24.0 | 192 | 0.0162 | 0.8070 | 0.8854 | 0.8444 | 0.9921 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2
