--- license: apache-2.0 base_model: albert-base-v2 tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: albert-base-v2-finetuned-ner-cadec results: [] --- # albert-base-v2-finetuned-ner-cadec This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3782 - Precision: 0.6044 - Recall: 0.6542 - F1: 0.6283 - Accuracy: 0.9197 - Adr Precision: 0.5756 - Adr Recall: 0.6495 - Adr F1: 0.6103 - Disease Precision: 0.1923 - Disease Recall: 0.2632 - Disease F1: 0.2222 - Drug Precision: 0.9259 - Drug Recall: 0.9091 - Drug F1: 0.9174 - Finding Precision: 0.1667 - Finding Recall: 0.2 - Finding F1: 0.1818 - Symptom Precision: 0.6 - Symptom Recall: 0.2222 - Symptom F1: 0.3243 - B-adr Precision: 0.7331 - B-adr Recall: 0.7908 - B-adr F1: 0.7608 - B-disease Precision: 0.2778 - B-disease Recall: 0.2632 - B-disease F1: 0.2703 - B-drug Precision: 0.9630 - B-drug Recall: 0.9455 - B-drug F1: 0.9541 - B-finding Precision: 0.2391 - B-finding Recall: 0.2444 - B-finding F1: 0.2418 - B-symptom Precision: 0.75 - B-symptom Recall: 0.24 - B-symptom F1: 0.3636 - I-adr Precision: 0.5746 - I-adr Recall: 0.6524 - I-adr F1: 0.6110 - I-disease Precision: 0.2222 - I-disease Recall: 0.3077 - I-disease F1: 0.2581 - I-drug Precision: 0.9259 - I-drug Recall: 0.9202 - I-drug F1: 0.9231 - I-finding Precision: 0.1842 - I-finding Recall: 0.2188 - I-finding F1: 0.2000 - I-symptom Precision: 0.25 - I-symptom Recall: 0.0476 - I-symptom F1: 0.08 - Macro Avg F1: 0.4663 - Weighted Avg F1: 0.6990 ## 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: 8 - eval_batch_size: 8 - 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 | Adr Precision | Adr Recall | Adr F1 | Disease Precision | Disease Recall | Disease F1 | Drug Precision | Drug Recall | Drug F1 | Finding Precision | Finding Recall | Finding F1 | Symptom Precision | Symptom Recall | Symptom F1 | B-adr Precision | B-adr Recall | B-adr F1 | B-disease Precision | B-disease Recall | B-disease F1 | B-drug Precision | B-drug Recall | B-drug F1 | B-finding Precision | B-finding Recall | B-finding F1 | B-symptom Precision | B-symptom Recall | B-symptom F1 | I-adr Precision | I-adr Recall | I-adr F1 | I-disease Precision | I-disease Recall | I-disease F1 | I-drug Precision | I-drug Recall | I-drug F1 | I-finding Precision | I-finding Recall | I-finding F1 | I-symptom Precision | I-symptom Recall | I-symptom F1 | Macro Avg F1 | Weighted Avg F1 | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------------:|:----------:|:------:|:-----------------:|:--------------:|:----------:|:--------------:|:-----------:|:-------:|:-----------------:|:--------------:|:----------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|:-------------------:|:----------------:|:------------:|:----------------:|:-------------:|:---------:|:-------------------:|:----------------:|:------------:|:-------------------:|:----------------:|:------------:|:---------------:|:------------:|:--------:|:-------------------:|:----------------:|:------------:|:----------------:|:-------------:|:---------:|:-------------------:|:----------------:|:------------:|:-------------------:|:----------------:|:------------:|:------------:|:---------------:| | No log | 1.0 | 127 | 0.2569 | 0.5268 | 0.6142 | 0.5671 | 0.9148 | 0.4666 | 0.6275 | 0.5352 | 0.0 | 0.0 | 0.0 | 0.8471 | 0.8727 | 0.8597 | 0.1935 | 0.1333 | 0.1579 | 0.0 | 0.0 | 0.0 | 0.6758 | 0.7601 | 0.7154 | 0.0 | 0.0 | 0.0 | 0.9157 | 0.9212 | 0.9184 | 0.3 | 0.0667 | 0.1091 | 0.0 | 0.0 | 0.0 | 0.4694 | 0.6411 | 0.5420 | 0.0 | 0.0 | 0.0 | 0.8683 | 0.8896 | 0.8788 | 0.2 | 0.1875 | 0.1935 | 0.0 | 0.0 | 0.0 | 0.3357 | 0.6349 | | No log | 2.0 | 254 | 0.2418 | 0.5393 | 0.5993 | 0.5677 | 0.9159 | 0.5219 | 0.6110 | 0.5630 | 0.0645 | 0.1053 | 0.0800 | 0.8438 | 0.8182 | 0.8308 | 0.1379 | 0.1778 | 0.1553 | 0.6667 | 0.0741 | 0.1333 | 0.7396 | 0.7524 | 0.7460 | 0.1 | 0.1053 | 0.1026 | 0.9618 | 0.9152 | 0.9379 | 0.2093 | 0.2 | 0.2045 | 0.6667 | 0.08 | 0.1429 | 0.5226 | 0.6275 | 0.5703 | 0.0526 | 0.0769 | 0.0625 | 0.8491 | 0.8282 | 0.8385 | 0.25 | 0.3125 | 0.2778 | 0.0 | 0.0 | 0.0 | 0.3883 | 0.6615 | | No log | 3.0 | 381 | 0.2577 | 0.6019 | 0.6380 | 0.6194 | 0.9226 | 0.5747 | 0.6422 | 0.6066 | 0.0909 | 0.1579 | 0.1154 | 0.9036 | 0.9091 | 0.9063 | 0.1579 | 0.1333 | 0.1446 | 0.6667 | 0.0741 | 0.1333 | 0.7598 | 0.7774 | 0.7685 | 0.2593 | 0.3684 | 0.3043 | 0.9455 | 0.9455 | 0.9455 | 0.2308 | 0.1333 | 0.1690 | 0.6667 | 0.08 | 0.1429 | 0.5881 | 0.6479 | 0.6165 | 0.0769 | 0.0769 | 0.0769 | 0.9091 | 0.9202 | 0.9146 | 0.2581 | 0.25 | 0.2540 | 0.0 | 0.0 | 0.0 | 0.4192 | 0.6943 | | 0.2396 | 4.0 | 508 | 0.2655 | 0.6073 | 0.6429 | 0.6246 | 0.9200 | 0.5840 | 0.6440 | 0.6126 | 0.0 | 0.0 | 0.0 | 0.9012 | 0.8848 | 0.8930 | 0.2222 | 0.3111 | 0.2593 | 0.6667 | 0.1481 | 0.2424 | 0.7678 | 0.7678 | 0.7678 | 0.0 | 0.0 | 0.0 | 0.9689 | 0.9455 | 0.9571 | 0.2745 | 0.3111 | 0.2917 | 1.0 | 0.24 | 0.3871 | 0.5732 | 0.6185 | 0.5950 | 0.1 | 0.0769 | 0.0870 | 0.9068 | 0.8957 | 0.9012 | 0.2766 | 0.4062 | 0.3291 | 0.0 | 0.0 | 0.0 | 0.4316 | 0.6931 | | 0.2396 | 5.0 | 635 | 0.2875 | 0.5769 | 0.6367 | 0.6053 | 0.9175 | 0.5669 | 0.6532 | 0.6070 | 0.1053 | 0.2105 | 0.1404 | 0.8598 | 0.8545 | 0.8571 | 0.1087 | 0.1111 | 0.1099 | 0.5 | 0.1481 | 0.2286 | 0.7319 | 0.7965 | 0.7629 | 0.2188 | 0.3684 | 0.2745 | 0.9627 | 0.9394 | 0.9509 | 0.1852 | 0.1111 | 0.1389 | 0.5714 | 0.16 | 0.25 | 0.5686 | 0.6546 | 0.6086 | 0.1053 | 0.1538 | 0.125 | 0.8650 | 0.8650 | 0.8650 | 0.2105 | 0.25 | 0.2286 | 0.0 | 0.0 | 0.0 | 0.4204 | 0.6853 | | 0.2396 | 6.0 | 762 | 0.3081 | 0.6063 | 0.6442 | 0.6247 | 0.9188 | 0.5809 | 0.6459 | 0.6116 | 0.1923 | 0.2632 | 0.2222 | 0.8841 | 0.8788 | 0.8815 | 0.2 | 0.2222 | 0.2105 | 0.8 | 0.1481 | 0.25 | 0.7409 | 0.7793 | 0.7596 | 0.2381 | 0.2632 | 0.25 | 0.9571 | 0.9455 | 0.9512 | 0.2381 | 0.2222 | 0.2299 | 0.8 | 0.16 | 0.2667 | 0.5773 | 0.6659 | 0.6184 | 0.25 | 0.3077 | 0.2759 | 0.8896 | 0.8896 | 0.8896 | 0.2571 | 0.2812 | 0.2687 | 0.0 | 0.0 | 0.0 | 0.4510 | 0.6950 | | 0.2396 | 7.0 | 889 | 0.3203 | 0.6147 | 0.6692 | 0.6408 | 0.9196 | 0.5903 | 0.6716 | 0.6283 | 0.15 | 0.1579 | 0.1538 | 0.8976 | 0.9030 | 0.9003 | 0.2182 | 0.2667 | 0.2400 | 0.5455 | 0.2222 | 0.3158 | 0.7442 | 0.7985 | 0.7704 | 0.2857 | 0.2105 | 0.2424 | 0.9398 | 0.9455 | 0.9426 | 0.2667 | 0.2667 | 0.2667 | 0.7778 | 0.28 | 0.4118 | 0.5783 | 0.6501 | 0.6121 | 0.1765 | 0.2308 | 0.2000 | 0.9085 | 0.9141 | 0.9113 | 0.2222 | 0.25 | 0.2353 | 0.6 | 0.1429 | 0.2308 | 0.4823 | 0.7039 | | 0.0784 | 8.0 | 1016 | 0.3548 | 0.5995 | 0.6429 | 0.6205 | 0.9183 | 0.5783 | 0.6367 | 0.6061 | 0.15 | 0.1579 | 0.1538 | 0.8916 | 0.8970 | 0.8943 | 0.1875 | 0.2667 | 0.2202 | 0.5556 | 0.1852 | 0.2778 | 0.7454 | 0.7754 | 0.7601 | 0.2857 | 0.2105 | 0.2424 | 0.9455 | 0.9455 | 0.9455 | 0.2545 | 0.3111 | 0.2800 | 0.625 | 0.2 | 0.3030 | 0.5683 | 0.6388 | 0.6015 | 0.2 | 0.2308 | 0.2143 | 0.8970 | 0.9080 | 0.9024 | 0.1957 | 0.2812 | 0.2308 | 0.3333 | 0.0476 | 0.0833 | 0.4563 | 0.6927 | | 0.0784 | 9.0 | 1143 | 0.3721 | 0.6101 | 0.6604 | 0.6343 | 0.9209 | 0.5812 | 0.6569 | 0.6167 | 0.25 | 0.2632 | 0.2564 | 0.9202 | 0.9091 | 0.9146 | 0.1964 | 0.2444 | 0.2178 | 0.4167 | 0.1852 | 0.2564 | 0.7300 | 0.7889 | 0.7583 | 0.3125 | 0.2632 | 0.2857 | 0.9630 | 0.9455 | 0.9541 | 0.2340 | 0.2444 | 0.2391 | 0.625 | 0.2 | 0.3030 | 0.5828 | 0.6591 | 0.6186 | 0.2857 | 0.3077 | 0.2963 | 0.9259 | 0.9202 | 0.9231 | 0.2432 | 0.2812 | 0.2609 | 0.3333 | 0.0952 | 0.1481 | 0.4787 | 0.7022 | | 0.0784 | 10.0 | 1270 | 0.3782 | 0.6044 | 0.6542 | 0.6283 | 0.9197 | 0.5756 | 0.6495 | 0.6103 | 0.1923 | 0.2632 | 0.2222 | 0.9259 | 0.9091 | 0.9174 | 0.1667 | 0.2 | 0.1818 | 0.6 | 0.2222 | 0.3243 | 0.7331 | 0.7908 | 0.7608 | 0.2778 | 0.2632 | 0.2703 | 0.9630 | 0.9455 | 0.9541 | 0.2391 | 0.2444 | 0.2418 | 0.75 | 0.24 | 0.3636 | 0.5746 | 0.6524 | 0.6110 | 0.2222 | 0.3077 | 0.2581 | 0.9259 | 0.9202 | 0.9231 | 0.1842 | 0.2188 | 0.2000 | 0.25 | 0.0476 | 0.08 | 0.4663 | 0.6990 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0