distilbert-base-cased-finetuned-ner_0220_J_ORIDATA
This model is a fine-tuned version of distilbert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5445
- Precision: 0.8915
- Recall: 0.9466
- F1: 0.9182
- Accuracy: 0.9486
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: 50
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 111 | 0.2828 | 0.7395 | 0.8322 | 0.7831 | 0.9293 |
No log | 2.0 | 222 | 0.2260 | 0.8029 | 0.8941 | 0.8460 | 0.9413 |
No log | 3.0 | 333 | 0.2586 | 0.8131 | 0.9034 | 0.8559 | 0.9425 |
No log | 4.0 | 444 | 0.2411 | 0.8541 | 0.9178 | 0.8848 | 0.9441 |
0.3027 | 5.0 | 555 | 0.2776 | 0.8817 | 0.9220 | 0.9014 | 0.9466 |
0.3027 | 6.0 | 666 | 0.2348 | 0.8647 | 0.9314 | 0.8968 | 0.9445 |
0.3027 | 7.0 | 777 | 0.2870 | 0.8762 | 0.9297 | 0.9021 | 0.9471 |
0.3027 | 8.0 | 888 | 0.3006 | 0.8650 | 0.9288 | 0.8958 | 0.9428 |
0.3027 | 9.0 | 999 | 0.3099 | 0.8751 | 0.9263 | 0.9000 | 0.9440 |
0.1147 | 10.0 | 1110 | 0.3325 | 0.8781 | 0.9398 | 0.9079 | 0.9464 |
0.1147 | 11.0 | 1221 | 0.3437 | 0.8909 | 0.9415 | 0.9155 | 0.9461 |
0.1147 | 12.0 | 1332 | 0.3512 | 0.8935 | 0.9390 | 0.9157 | 0.9468 |
0.1147 | 13.0 | 1443 | 0.3664 | 0.8791 | 0.9424 | 0.9096 | 0.9477 |
0.0673 | 14.0 | 1554 | 0.4068 | 0.8767 | 0.9398 | 0.9072 | 0.9445 |
0.0673 | 15.0 | 1665 | 0.4015 | 0.8808 | 0.9390 | 0.9089 | 0.9481 |
0.0673 | 16.0 | 1776 | 0.4220 | 0.8874 | 0.9483 | 0.9168 | 0.9467 |
0.0673 | 17.0 | 1887 | 0.4313 | 0.8847 | 0.9432 | 0.9130 | 0.9451 |
0.0673 | 18.0 | 1998 | 0.4440 | 0.8762 | 0.9415 | 0.9077 | 0.9408 |
0.041 | 19.0 | 2109 | 0.4524 | 0.9034 | 0.9508 | 0.9265 | 0.9484 |
0.041 | 20.0 | 2220 | 0.4455 | 0.8978 | 0.9458 | 0.9212 | 0.9470 |
0.041 | 21.0 | 2331 | 0.4822 | 0.8861 | 0.9492 | 0.9165 | 0.9426 |
0.041 | 22.0 | 2442 | 0.4677 | 0.8855 | 0.9441 | 0.9139 | 0.9446 |
0.0253 | 23.0 | 2553 | 0.4945 | 0.8858 | 0.9466 | 0.9152 | 0.9473 |
0.0253 | 24.0 | 2664 | 0.4882 | 0.8794 | 0.9458 | 0.9114 | 0.9443 |
0.0253 | 25.0 | 2775 | 0.5073 | 0.8953 | 0.9424 | 0.9182 | 0.9448 |
0.0253 | 26.0 | 2886 | 0.5012 | 0.8986 | 0.9466 | 0.9220 | 0.9473 |
0.0253 | 27.0 | 2997 | 0.4975 | 0.8850 | 0.9458 | 0.9144 | 0.9456 |
0.0166 | 28.0 | 3108 | 0.4944 | 0.8879 | 0.9466 | 0.9163 | 0.9474 |
0.0166 | 29.0 | 3219 | 0.5137 | 0.8915 | 0.9466 | 0.9182 | 0.9472 |
0.0166 | 30.0 | 3330 | 0.4924 | 0.8890 | 0.9432 | 0.9153 | 0.9463 |
0.0166 | 31.0 | 3441 | 0.5129 | 0.8884 | 0.9508 | 0.9185 | 0.9466 |
0.0114 | 32.0 | 3552 | 0.5184 | 0.8940 | 0.9508 | 0.9216 | 0.9448 |
0.0114 | 33.0 | 3663 | 0.5237 | 0.9012 | 0.9508 | 0.9254 | 0.9463 |
0.0114 | 34.0 | 3774 | 0.5153 | 0.8937 | 0.9475 | 0.9198 | 0.9474 |
0.0114 | 35.0 | 3885 | 0.5182 | 0.8947 | 0.95 | 0.9215 | 0.9482 |
0.0114 | 36.0 | 3996 | 0.5311 | 0.8937 | 0.9475 | 0.9198 | 0.9481 |
0.0087 | 37.0 | 4107 | 0.5334 | 0.8935 | 0.9525 | 0.9221 | 0.9483 |
0.0087 | 38.0 | 4218 | 0.5397 | 0.8900 | 0.9466 | 0.9175 | 0.9475 |
0.0087 | 39.0 | 4329 | 0.5331 | 0.8941 | 0.9449 | 0.9188 | 0.9468 |
0.0087 | 40.0 | 4440 | 0.5381 | 0.8962 | 0.9441 | 0.9195 | 0.9460 |
0.0069 | 41.0 | 4551 | 0.5394 | 0.8937 | 0.9475 | 0.9198 | 0.9479 |
0.0069 | 42.0 | 4662 | 0.5516 | 0.8950 | 0.9466 | 0.9201 | 0.9461 |
0.0069 | 43.0 | 4773 | 0.5442 | 0.8949 | 0.9449 | 0.9192 | 0.9452 |
0.0069 | 44.0 | 4884 | 0.5427 | 0.8927 | 0.9449 | 0.9181 | 0.9482 |
0.0069 | 45.0 | 4995 | 0.5515 | 0.8907 | 0.9458 | 0.9174 | 0.9461 |
0.0058 | 46.0 | 5106 | 0.5448 | 0.8930 | 0.9475 | 0.9194 | 0.9481 |
0.0058 | 47.0 | 5217 | 0.5475 | 0.896 | 0.9492 | 0.9218 | 0.9487 |
0.0058 | 48.0 | 5328 | 0.5444 | 0.8907 | 0.9466 | 0.9178 | 0.9484 |
0.0058 | 49.0 | 5439 | 0.5452 | 0.8945 | 0.9483 | 0.9206 | 0.9487 |
0.005 | 50.0 | 5550 | 0.5445 | 0.8915 | 0.9466 | 0.9182 | 0.9486 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.13.0+cu117
- Datasets 2.8.0
- Tokenizers 0.12.1
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.