<!-- 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. -->
chope-fine-dishing-distilbert-base-uncased-finetuned-ner-v0.1
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4448
- Precision: 0.6106
- Recall: 0.7842
- F1: 0.6866
- Accuracy: 0.7525
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 | 0.46 | 50 | 0.8879 | 0.3658 | 0.2978 | 0.3283 | 0.5883 |
No log | 0.92 | 100 | 0.7451 | 0.5553 | 0.6995 | 0.6191 | 0.7048 |
No log | 1.38 | 150 | 0.7378 | 0.5351 | 0.6448 | 0.5849 | 0.7171 |
No log | 1.83 | 200 | 0.8367 | 0.6037 | 0.6202 | 0.6119 | 0.7012 |
No log | 2.29 | 250 | 0.7746 | 0.6328 | 0.6639 | 0.6480 | 0.7373 |
No log | 2.75 | 300 | 0.8077 | 0.5 | 0.5956 | 0.5436 | 0.6939 |
No log | 3.21 | 350 | 0.8416 | 0.5284 | 0.4836 | 0.5050 | 0.7012 |
No log | 3.67 | 400 | 0.9220 | 0.5601 | 0.7131 | 0.6274 | 0.7323 |
No log | 4.13 | 450 | 0.9337 | 0.5419 | 0.5301 | 0.5359 | 0.7113 |
0.2476 | 4.59 | 500 | 0.9225 | 0.6387 | 0.6667 | 0.6524 | 0.7323 |
0.2476 | 5.05 | 550 | 1.0376 | 0.5296 | 0.5383 | 0.5339 | 0.7033 |
0.2476 | 5.5 | 600 | 1.0138 | 0.5820 | 0.7760 | 0.6651 | 0.7496 |
0.2476 | 5.96 | 650 | 1.1675 | 0.6184 | 0.6421 | 0.6300 | 0.7366 |
0.2476 | 6.42 | 700 | 1.2386 | 0.5563 | 0.7022 | 0.6208 | 0.7272 |
0.2476 | 6.88 | 750 | 1.2480 | 0.6233 | 0.7322 | 0.6734 | 0.7330 |
0.2476 | 7.34 | 800 | 1.2026 | 0.6077 | 0.6858 | 0.6444 | 0.7287 |
0.2476 | 7.8 | 850 | 1.1666 | 0.6176 | 0.7678 | 0.6845 | 0.7482 |
0.2476 | 8.26 | 900 | 1.1741 | 0.6119 | 0.7842 | 0.6874 | 0.7518 |
0.2476 | 8.72 | 950 | 1.3172 | 0.5584 | 0.6667 | 0.6077 | 0.7214 |
0.0227 | 9.17 | 1000 | 1.3335 | 0.5868 | 0.7295 | 0.6504 | 0.7185 |
0.0227 | 9.63 | 1050 | 1.2987 | 0.6247 | 0.7459 | 0.6800 | 0.7352 |
0.0227 | 10.09 | 1100 | 1.4033 | 0.5391 | 0.5464 | 0.5427 | 0.7041 |
0.0227 | 10.55 | 1150 | 1.5544 | 0.5427 | 0.6940 | 0.6091 | 0.7113 |
0.0227 | 11.01 | 1200 | 1.5020 | 0.5771 | 0.5519 | 0.5642 | 0.7221 |
0.0227 | 11.47 | 1250 | 1.3234 | 0.5983 | 0.7486 | 0.6650 | 0.7381 |
0.0227 | 11.93 | 1300 | 1.4603 | 0.6197 | 0.7213 | 0.6667 | 0.7359 |
0.0227 | 12.39 | 1350 | 1.5133 | 0.5301 | 0.5301 | 0.5301 | 0.6975 |
0.0227 | 12.84 | 1400 | 1.4874 | 0.5671 | 0.7623 | 0.6503 | 0.7366 |
0.0227 | 13.3 | 1450 | 1.5313 | 0.5603 | 0.7240 | 0.6317 | 0.7279 |
0.0075 | 13.76 | 1500 | 1.4268 | 0.5895 | 0.6749 | 0.6293 | 0.7229 |
0.0075 | 14.22 | 1550 | 1.6733 | 0.5190 | 0.5219 | 0.5204 | 0.6939 |
0.0075 | 14.68 | 1600 | 1.5003 | 0.5749 | 0.7650 | 0.6565 | 0.7366 |
0.0075 | 15.14 | 1650 | 1.5747 | 0.6353 | 0.5902 | 0.6119 | 0.7294 |
0.0075 | 15.6 | 1700 | 1.4836 | 0.5484 | 0.5574 | 0.5528 | 0.7048 |
0.0075 | 16.06 | 1750 | 1.7085 | 0.5066 | 0.5273 | 0.5167 | 0.6932 |
0.0075 | 16.51 | 1800 | 1.6691 | 0.5669 | 0.5328 | 0.5493 | 0.7048 |
0.0075 | 16.97 | 1850 | 1.5524 | 0.534 | 0.7295 | 0.6166 | 0.7236 |
0.0075 | 17.43 | 1900 | 1.5616 | 0.5484 | 0.6038 | 0.5748 | 0.7156 |
0.0075 | 17.89 | 1950 | 1.5597 | 0.5622 | 0.6667 | 0.61 | 0.7192 |
0.0044 | 18.35 | 2000 | 1.4448 | 0.6106 | 0.7842 | 0.6866 | 0.7525 |
0.0044 | 18.81 | 2050 | 1.5741 | 0.5802 | 0.5137 | 0.5449 | 0.7055 |
0.0044 | 19.27 | 2100 | 1.6085 | 0.5842 | 0.6448 | 0.6130 | 0.7192 |
0.0044 | 19.72 | 2150 | 1.5787 | 0.6016 | 0.8087 | 0.6900 | 0.7547 |
0.0044 | 20.18 | 2200 | 1.6210 | 0.6004 | 0.8169 | 0.6921 | 0.7547 |
0.0044 | 20.64 | 2250 | 1.6739 | 0.5246 | 0.5246 | 0.5246 | 0.7026 |
0.0044 | 21.1 | 2300 | 1.7852 | 0.5618 | 0.5710 | 0.5664 | 0.6990 |
0.0044 | 21.56 | 2350 | 1.6344 | 0.5576 | 0.6612 | 0.605 | 0.7142 |
0.0044 | 22.02 | 2400 | 1.8115 | 0.5363 | 0.5847 | 0.5595 | 0.7033 |
0.0044 | 22.48 | 2450 | 1.8336 | 0.5294 | 0.6148 | 0.5689 | 0.6968 |
0.0034 | 22.94 | 2500 | 1.7901 | 0.5878 | 0.6038 | 0.5957 | 0.7048 |
0.0034 | 23.39 | 2550 | 1.7766 | 0.5615 | 0.6858 | 0.6175 | 0.7113 |
0.0034 | 23.85 | 2600 | 1.8159 | 0.5531 | 0.6831 | 0.6112 | 0.7084 |
0.0034 | 24.31 | 2650 | 1.8307 | 0.6075 | 0.6175 | 0.6125 | 0.7142 |
0.0034 | 24.77 | 2700 | 1.8326 | 0.5410 | 0.6667 | 0.5973 | 0.7055 |
Framework versions
- Transformers 4.27.2
- Pytorch 1.13.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2