<!-- 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-PM-M3-Voc-distill-align-hf-finetuned-ner
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5981
- Precision: 0.5371
- Recall: 0.7479
- F1: 0.6252
- Accuracy: 0.8321
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 23 | 1.5355 | 0.0 | 0.0 | 0.0 | 0.6968 |
| No log | 2.0 | 46 | 1.2530 | 0.2813 | 0.1177 | 0.1659 | 0.7177 |
| No log | 3.0 | 69 | 0.9868 | 0.3861 | 0.3212 | 0.3507 | 0.7462 |
| No log | 4.0 | 92 | 0.8347 | 0.4115 | 0.4235 | 0.4174 | 0.7629 |
| No log | 5.0 | 115 | 0.7452 | 0.4892 | 0.4197 | 0.4518 | 0.7884 |
| No log | 6.0 | 138 | 0.6956 | 0.4935 | 0.5810 | 0.5337 | 0.7952 |
| No log | 7.0 | 161 | 0.7015 | 0.4673 | 0.6515 | 0.5443 | 0.7932 |
| No log | 8.0 | 184 | 0.6316 | 0.5150 | 0.6704 | 0.5825 | 0.8137 |
| No log | 9.0 | 207 | 0.6475 | 0.4944 | 0.6976 | 0.5787 | 0.8085 |
| No log | 10.0 | 230 | 0.6144 | 0.5157 | 0.7105 | 0.5977 | 0.8175 |
| No log | 11.0 | 253 | 0.6339 | 0.5075 | 0.7161 | 0.5941 | 0.8146 |
| No log | 12.0 | 276 | 0.6114 | 0.5250 | 0.7235 | 0.6084 | 0.8221 |
| No log | 13.0 | 299 | 0.6389 | 0.5127 | 0.7339 | 0.6037 | 0.8160 |
| No log | 14.0 | 322 | 0.6256 | 0.5222 | 0.7350 | 0.6106 | 0.8228 |
| No log | 15.0 | 345 | 0.6445 | 0.5161 | 0.7455 | 0.6099 | 0.8188 |
| No log | 16.0 | 368 | 0.5887 | 0.5411 | 0.7416 | 0.6257 | 0.8323 |
| No log | 17.0 | 391 | 0.5906 | 0.5387 | 0.7455 | 0.6255 | 0.8332 |
| No log | 18.0 | 414 | 0.5858 | 0.5400 | 0.7490 | 0.6276 | 0.8353 |
| No log | 19.0 | 437 | 0.6005 | 0.5369 | 0.7497 | 0.6257 | 0.8316 |
| No log | 20.0 | 460 | 0.5981 | 0.5371 | 0.7479 | 0.6252 | 0.8321 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
