<!-- 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. -->
clinico-bsc-bio-ehr-es
This model is a fine-tuned version of PlanTL-GOB-ES/bsc-bio-ehr-es on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9988
- Precision: 0.4916
- Recall: 0.6526
- F1: 0.5608
- Accuracy: 0.8586
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 25 | 1.2185 | 0.0189 | 0.0359 | 0.0247 | 0.6197 |
No log | 2.0 | 50 | 0.7442 | 0.1562 | 0.1975 | 0.1744 | 0.7996 |
No log | 3.0 | 75 | 0.6502 | 0.2108 | 0.2640 | 0.2344 | 0.8180 |
No log | 4.0 | 100 | 0.6404 | 0.3453 | 0.4572 | 0.3935 | 0.8258 |
No log | 5.0 | 125 | 0.6131 | 0.3639 | 0.4657 | 0.4085 | 0.8303 |
No log | 6.0 | 150 | 0.6123 | 0.3356 | 0.4256 | 0.3752 | 0.8341 |
No log | 7.0 | 175 | 0.6093 | 0.3411 | 0.4498 | 0.3880 | 0.8370 |
No log | 8.0 | 200 | 0.6198 | 0.3840 | 0.4931 | 0.4318 | 0.8379 |
No log | 9.0 | 225 | 0.6490 | 0.3878 | 0.5037 | 0.4382 | 0.8378 |
No log | 10.0 | 250 | 0.6653 | 0.3810 | 0.5005 | 0.4327 | 0.8371 |
No log | 11.0 | 275 | 0.6456 | 0.3223 | 0.4847 | 0.3872 | 0.8387 |
No log | 12.0 | 300 | 0.6475 | 0.3377 | 0.4847 | 0.3981 | 0.8474 |
No log | 13.0 | 325 | 0.6620 | 0.4004 | 0.5734 | 0.4716 | 0.8506 |
No log | 14.0 | 350 | 0.6798 | 0.3914 | 0.5649 | 0.4624 | 0.8533 |
No log | 15.0 | 375 | 0.6880 | 0.3969 | 0.5671 | 0.4670 | 0.8520 |
No log | 16.0 | 400 | 0.7012 | 0.4192 | 0.5913 | 0.4906 | 0.8551 |
No log | 17.0 | 425 | 0.7224 | 0.4143 | 0.5924 | 0.4876 | 0.8517 |
No log | 18.0 | 450 | 0.7510 | 0.4302 | 0.6051 | 0.5029 | 0.8553 |
No log | 19.0 | 475 | 0.7388 | 0.4271 | 0.6030 | 0.5 | 0.8532 |
0.3652 | 20.0 | 500 | 0.7524 | 0.4374 | 0.6125 | 0.5103 | 0.8569 |
0.3652 | 21.0 | 525 | 0.7408 | 0.4427 | 0.6082 | 0.5125 | 0.8580 |
0.3652 | 22.0 | 550 | 0.7430 | 0.4448 | 0.6125 | 0.5153 | 0.8610 |
0.3652 | 23.0 | 575 | 0.7726 | 0.4193 | 0.6093 | 0.4968 | 0.8582 |
0.3652 | 24.0 | 600 | 0.7876 | 0.4316 | 0.6061 | 0.5042 | 0.8562 |
0.3652 | 25.0 | 625 | 0.7777 | 0.4620 | 0.6294 | 0.5329 | 0.8595 |
0.3652 | 26.0 | 650 | 0.8009 | 0.4521 | 0.6272 | 0.5254 | 0.8570 |
0.3652 | 27.0 | 675 | 0.8153 | 0.4583 | 0.6378 | 0.5333 | 0.8572 |
0.3652 | 28.0 | 700 | 0.8215 | 0.4611 | 0.6262 | 0.5311 | 0.8580 |
0.3652 | 29.0 | 725 | 0.8296 | 0.4699 | 0.6336 | 0.5396 | 0.8595 |
0.3652 | 30.0 | 750 | 0.8174 | 0.4597 | 0.6378 | 0.5343 | 0.8603 |
0.3652 | 31.0 | 775 | 0.8442 | 0.4765 | 0.6410 | 0.5466 | 0.8599 |
0.3652 | 32.0 | 800 | 0.8281 | 0.4646 | 0.6315 | 0.5354 | 0.8610 |
0.3652 | 33.0 | 825 | 0.8322 | 0.4583 | 0.6389 | 0.5337 | 0.8591 |
0.3652 | 34.0 | 850 | 0.8153 | 0.4559 | 0.6272 | 0.528 | 0.8623 |
0.3652 | 35.0 | 875 | 0.8529 | 0.4861 | 0.6294 | 0.5486 | 0.8589 |
0.3652 | 36.0 | 900 | 0.8826 | 0.4699 | 0.6272 | 0.5373 | 0.8559 |
0.3652 | 37.0 | 925 | 0.8856 | 0.4654 | 0.6325 | 0.5363 | 0.8571 |
0.3652 | 38.0 | 950 | 0.8983 | 0.4819 | 0.6315 | 0.5466 | 0.8560 |
0.3652 | 39.0 | 975 | 0.8723 | 0.4641 | 0.6272 | 0.5335 | 0.8556 |
0.0269 | 40.0 | 1000 | 0.8788 | 0.4662 | 0.6399 | 0.5394 | 0.8550 |
0.0269 | 41.0 | 1025 | 0.8952 | 0.4805 | 0.6378 | 0.5481 | 0.8611 |
0.0269 | 42.0 | 1050 | 0.8901 | 0.4657 | 0.6304 | 0.5357 | 0.8574 |
0.0269 | 43.0 | 1075 | 0.9015 | 0.4746 | 0.6410 | 0.5454 | 0.8574 |
0.0269 | 44.0 | 1100 | 0.8838 | 0.4655 | 0.6420 | 0.5397 | 0.8591 |
0.0269 | 45.0 | 1125 | 0.9093 | 0.4718 | 0.6441 | 0.5446 | 0.8598 |
0.0269 | 46.0 | 1150 | 0.9154 | 0.4826 | 0.6441 | 0.5518 | 0.8553 |
0.0269 | 47.0 | 1175 | 0.9214 | 0.4614 | 0.6315 | 0.5332 | 0.8538 |
0.0269 | 48.0 | 1200 | 0.9313 | 0.4639 | 0.6315 | 0.5349 | 0.8546 |
0.0269 | 49.0 | 1225 | 0.9137 | 0.4807 | 0.6431 | 0.5501 | 0.8582 |
0.0269 | 50.0 | 1250 | 0.9235 | 0.4939 | 0.6463 | 0.5599 | 0.8571 |
0.0269 | 51.0 | 1275 | 0.9263 | 0.4900 | 0.6441 | 0.5566 | 0.8580 |
0.0269 | 52.0 | 1300 | 0.9190 | 0.4787 | 0.6420 | 0.5485 | 0.8613 |
0.0269 | 53.0 | 1325 | 0.9159 | 0.4700 | 0.6441 | 0.5434 | 0.8616 |
0.0269 | 54.0 | 1350 | 0.9302 | 0.4806 | 0.6399 | 0.5489 | 0.8614 |
0.0269 | 55.0 | 1375 | 0.9391 | 0.4877 | 0.6515 | 0.5579 | 0.8581 |
0.0269 | 56.0 | 1400 | 0.9392 | 0.4959 | 0.6452 | 0.5608 | 0.8580 |
0.0269 | 57.0 | 1425 | 0.9444 | 0.4798 | 0.6410 | 0.5488 | 0.8570 |
0.0269 | 58.0 | 1450 | 0.9394 | 0.4777 | 0.6441 | 0.5486 | 0.8596 |
0.0269 | 59.0 | 1475 | 0.9562 | 0.4833 | 0.6420 | 0.5515 | 0.8586 |
0.0098 | 60.0 | 1500 | 0.9485 | 0.4801 | 0.6484 | 0.5517 | 0.8582 |
0.0098 | 61.0 | 1525 | 0.9521 | 0.4679 | 0.6463 | 0.5428 | 0.8582 |
0.0098 | 62.0 | 1550 | 0.9603 | 0.4759 | 0.6463 | 0.5481 | 0.8563 |
0.0098 | 63.0 | 1575 | 0.9663 | 0.4831 | 0.6473 | 0.5532 | 0.8561 |
0.0098 | 64.0 | 1600 | 0.9641 | 0.4780 | 0.6526 | 0.5518 | 0.8580 |
0.0098 | 65.0 | 1625 | 0.9607 | 0.4767 | 0.6494 | 0.5498 | 0.8606 |
0.0098 | 66.0 | 1650 | 0.9782 | 0.4849 | 0.6463 | 0.5541 | 0.8563 |
0.0098 | 67.0 | 1675 | 0.9806 | 0.4916 | 0.6484 | 0.5592 | 0.8562 |
0.0098 | 68.0 | 1700 | 0.9728 | 0.4889 | 0.6494 | 0.5578 | 0.8578 |
0.0098 | 69.0 | 1725 | 0.9766 | 0.4885 | 0.6494 | 0.5576 | 0.8584 |
0.0098 | 70.0 | 1750 | 0.9738 | 0.4862 | 0.6526 | 0.5573 | 0.8575 |
0.0098 | 71.0 | 1775 | 0.9788 | 0.4916 | 0.6505 | 0.56 | 0.8571 |
0.0098 | 72.0 | 1800 | 0.9845 | 0.4845 | 0.6452 | 0.5534 | 0.8563 |
0.0098 | 73.0 | 1825 | 0.9729 | 0.4876 | 0.6463 | 0.5559 | 0.8573 |
0.0098 | 74.0 | 1850 | 0.9854 | 0.4846 | 0.6494 | 0.5551 | 0.8569 |
0.0098 | 75.0 | 1875 | 0.9903 | 0.4885 | 0.6505 | 0.5580 | 0.8562 |
0.0098 | 76.0 | 1900 | 0.9825 | 0.4886 | 0.6558 | 0.5600 | 0.8568 |
0.0098 | 77.0 | 1925 | 0.9994 | 0.4876 | 0.6463 | 0.5559 | 0.8554 |
0.0098 | 78.0 | 1950 | 0.9922 | 0.4905 | 0.6515 | 0.5596 | 0.8546 |
0.0098 | 79.0 | 1975 | 1.0084 | 0.4928 | 0.6484 | 0.5600 | 0.8578 |
0.0057 | 80.0 | 2000 | 0.9931 | 0.4976 | 0.6526 | 0.5646 | 0.8580 |
0.0057 | 81.0 | 2025 | 0.9864 | 0.4826 | 0.6452 | 0.5522 | 0.8595 |
0.0057 | 82.0 | 2050 | 0.9929 | 0.4900 | 0.6484 | 0.5582 | 0.8595 |
0.0057 | 83.0 | 2075 | 0.9902 | 0.4916 | 0.6473 | 0.5588 | 0.8588 |
0.0057 | 84.0 | 2100 | 1.0021 | 0.4872 | 0.6431 | 0.5544 | 0.8573 |
0.0057 | 85.0 | 2125 | 1.0013 | 0.4964 | 0.6473 | 0.5619 | 0.8582 |
0.0057 | 86.0 | 2150 | 0.9814 | 0.4865 | 0.6484 | 0.5559 | 0.8625 |
0.0057 | 87.0 | 2175 | 0.9841 | 0.4932 | 0.6558 | 0.5630 | 0.8622 |
0.0057 | 88.0 | 2200 | 0.9888 | 0.4866 | 0.6515 | 0.5571 | 0.8610 |
0.0057 | 89.0 | 2225 | 0.9898 | 0.4924 | 0.6515 | 0.5609 | 0.8610 |
0.0057 | 90.0 | 2250 | 0.9860 | 0.4870 | 0.6526 | 0.5578 | 0.8607 |
0.0057 | 91.0 | 2275 | 0.9925 | 0.4912 | 0.6484 | 0.5589 | 0.8589 |
0.0057 | 92.0 | 2300 | 0.9904 | 0.4956 | 0.6536 | 0.5638 | 0.8599 |
0.0057 | 93.0 | 2325 | 0.9902 | 0.4980 | 0.6526 | 0.5649 | 0.8602 |
0.0057 | 94.0 | 2350 | 0.9925 | 0.5041 | 0.6547 | 0.5696 | 0.8602 |
0.0057 | 95.0 | 2375 | 0.9959 | 0.4897 | 0.6515 | 0.5591 | 0.8589 |
0.0057 | 96.0 | 2400 | 0.9951 | 0.4901 | 0.6505 | 0.5590 | 0.8591 |
0.0057 | 97.0 | 2425 | 0.9962 | 0.4924 | 0.6505 | 0.5605 | 0.8588 |
0.0057 | 98.0 | 2450 | 0.9972 | 0.5008 | 0.6505 | 0.5659 | 0.8585 |
0.0057 | 99.0 | 2475 | 0.9988 | 0.4920 | 0.6526 | 0.5611 | 0.8588 |
0.0045 | 100.0 | 2500 | 0.9988 | 0.4916 | 0.6526 | 0.5608 | 0.8586 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0
- Datasets 2.8.0
- Tokenizers 0.12.1