<!-- 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. -->
electramed-small-ADE-ner
This model is a fine-tuned version of giacomomiolo/electramed_small_scivocab on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1548
- Precision: 0.8358
- Recall: 0.9064
- F1: 0.8697
- Accuracy: 0.9581
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.5587 | 1.0 | 201 | 0.4107 | 0.7291 | 0.7982 | 0.7621 | 0.8983 |
0.2114 | 2.0 | 402 | 0.2663 | 0.7716 | 0.8826 | 0.8234 | 0.9445 |
0.1421 | 3.0 | 603 | 0.2183 | 0.8033 | 0.9030 | 0.8502 | 0.9488 |
0.2204 | 4.0 | 804 | 0.1878 | 0.8279 | 0.9012 | 0.8630 | 0.9553 |
0.5825 | 5.0 | 1005 | 0.1712 | 0.8289 | 0.8967 | 0.8615 | 0.9566 |
0.0685 | 6.0 | 1206 | 0.1647 | 0.8333 | 0.9067 | 0.8685 | 0.9572 |
0.0973 | 7.0 | 1407 | 0.1593 | 0.8365 | 0.9049 | 0.8693 | 0.9578 |
0.1683 | 8.0 | 1608 | 0.1574 | 0.8367 | 0.9082 | 0.8710 | 0.9577 |
0.065 | 9.0 | 1809 | 0.1557 | 0.8397 | 0.9052 | 0.8712 | 0.9583 |
0.179 | 10.0 | 2010 | 0.1548 | 0.8358 | 0.9064 | 0.8697 | 0.9581 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1