<!-- 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-large-PM-M3-Voc-hf-finetuned-ner-combine-filtered
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3511
- Precision: 0.6276
- Recall: 0.5234
- F1: 0.5708
- Accuracy: 0.8858
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: cosine
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 11 | 0.7773 | 0.0 | 0.0 | 0.0 | 0.7228 |
| No log | 2.0 | 22 | 0.4915 | 0.4570 | 0.3617 | 0.4038 | 0.8293 |
| No log | 3.0 | 33 | 0.4246 | 0.4091 | 0.3447 | 0.3741 | 0.8404 |
| No log | 4.0 | 44 | 0.3725 | 0.4899 | 0.4128 | 0.4480 | 0.8659 |
| No log | 5.0 | 55 | 0.3628 | 0.6212 | 0.5234 | 0.5681 | 0.8792 |
| No log | 6.0 | 66 | 0.3492 | 0.6458 | 0.5277 | 0.5808 | 0.8825 |
| No log | 7.0 | 77 | 0.3453 | 0.6337 | 0.5447 | 0.5858 | 0.8875 |
| No log | 8.0 | 88 | 0.3546 | 0.6283 | 0.5106 | 0.5634 | 0.8841 |
| No log | 9.0 | 99 | 0.3491 | 0.6089 | 0.5234 | 0.5629 | 0.8858 |
| No log | 10.0 | 110 | 0.3511 | 0.6276 | 0.5234 | 0.5708 | 0.8858 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
