update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- precision
|
| 7 |
+
- recall
|
| 8 |
+
- f1
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: testlink
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# testlink
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es-pharmaconer) on an unknown dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.2165
|
| 23 |
+
- Precision: 0.4553
|
| 24 |
+
- Recall: 0.6087
|
| 25 |
+
- F1: 0.5209
|
| 26 |
+
- Accuracy: 0.9624
|
| 27 |
+
|
| 28 |
+
## Model description
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Intended uses & limitations
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training and evaluation data
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training procedure
|
| 41 |
+
|
| 42 |
+
### Training hyperparameters
|
| 43 |
+
|
| 44 |
+
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 2.75e-05
|
| 46 |
+
- train_batch_size: 16
|
| 47 |
+
- eval_batch_size: 8
|
| 48 |
+
- seed: 42
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- num_epochs: 30
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 57 |
+
| No log | 1.0 | 57 | 0.2201 | 0.0 | 0.0 | 0.0 | 0.9516 |
|
| 58 |
+
| No log | 2.0 | 114 | 0.1915 | 0.0 | 0.0 | 0.0 | 0.9530 |
|
| 59 |
+
| No log | 3.0 | 171 | 0.1680 | 0.2429 | 0.0924 | 0.1339 | 0.9528 |
|
| 60 |
+
| No log | 4.0 | 228 | 0.1471 | 0.3516 | 0.2446 | 0.2885 | 0.9560 |
|
| 61 |
+
| No log | 5.0 | 285 | 0.1473 | 0.3056 | 0.2989 | 0.3022 | 0.9548 |
|
| 62 |
+
| No log | 6.0 | 342 | 0.1376 | 0.3937 | 0.3424 | 0.3663 | 0.9595 |
|
| 63 |
+
| No log | 7.0 | 399 | 0.1431 | 0.3875 | 0.5054 | 0.4387 | 0.9580 |
|
| 64 |
+
| No log | 8.0 | 456 | 0.1573 | 0.4364 | 0.5598 | 0.4905 | 0.9592 |
|
| 65 |
+
| 0.1396 | 9.0 | 513 | 0.1442 | 0.4794 | 0.5054 | 0.4921 | 0.9648 |
|
| 66 |
+
| 0.1396 | 10.0 | 570 | 0.1908 | 0.3820 | 0.6685 | 0.4862 | 0.9525 |
|
| 67 |
+
| 0.1396 | 11.0 | 627 | 0.1552 | 0.4516 | 0.6087 | 0.5185 | 0.9624 |
|
| 68 |
+
| 0.1396 | 12.0 | 684 | 0.1834 | 0.444 | 0.6033 | 0.5115 | 0.9614 |
|
| 69 |
+
| 0.1396 | 13.0 | 741 | 0.1669 | 0.4810 | 0.6196 | 0.5416 | 0.9634 |
|
| 70 |
+
| 0.1396 | 14.0 | 798 | 0.1854 | 0.4582 | 0.625 | 0.5287 | 0.9629 |
|
| 71 |
+
| 0.1396 | 15.0 | 855 | 0.2204 | 0.3859 | 0.6522 | 0.4848 | 0.9525 |
|
| 72 |
+
| 0.1396 | 16.0 | 912 | 0.2062 | 0.4221 | 0.6033 | 0.4966 | 0.9577 |
|
| 73 |
+
| 0.1396 | 17.0 | 969 | 0.1928 | 0.4596 | 0.5870 | 0.5155 | 0.9639 |
|
| 74 |
+
| 0.0141 | 18.0 | 1026 | 0.2061 | 0.4531 | 0.6033 | 0.5175 | 0.9619 |
|
| 75 |
+
| 0.0141 | 19.0 | 1083 | 0.2036 | 0.4464 | 0.5652 | 0.4988 | 0.9621 |
|
| 76 |
+
| 0.0141 | 20.0 | 1140 | 0.2110 | 0.4557 | 0.5870 | 0.5131 | 0.9627 |
|
| 77 |
+
| 0.0141 | 21.0 | 1197 | 0.2115 | 0.4462 | 0.6087 | 0.5149 | 0.9616 |
|
| 78 |
+
| 0.0141 | 22.0 | 1254 | 0.2176 | 0.4488 | 0.6196 | 0.5205 | 0.9619 |
|
| 79 |
+
| 0.0141 | 23.0 | 1311 | 0.2180 | 0.4427 | 0.6304 | 0.5202 | 0.9609 |
|
| 80 |
+
| 0.0141 | 24.0 | 1368 | 0.2162 | 0.4578 | 0.6196 | 0.5266 | 0.9624 |
|
| 81 |
+
| 0.0141 | 25.0 | 1425 | 0.2218 | 0.4394 | 0.6304 | 0.5179 | 0.9604 |
|
| 82 |
+
| 0.0141 | 26.0 | 1482 | 0.2151 | 0.4585 | 0.6304 | 0.5309 | 0.9629 |
|
| 83 |
+
| 0.003 | 27.0 | 1539 | 0.2163 | 0.4597 | 0.6196 | 0.5278 | 0.9627 |
|
| 84 |
+
| 0.003 | 28.0 | 1596 | 0.2174 | 0.456 | 0.6196 | 0.5253 | 0.9624 |
|
| 85 |
+
| 0.003 | 29.0 | 1653 | 0.2147 | 0.4545 | 0.5978 | 0.5164 | 0.9626 |
|
| 86 |
+
| 0.003 | 30.0 | 1710 | 0.2165 | 0.4553 | 0.6087 | 0.5209 | 0.9624 |
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
### Framework versions
|
| 90 |
+
|
| 91 |
+
- Transformers 4.27.4
|
| 92 |
+
- Pytorch 2.0.0+cu118
|
| 93 |
+
- Datasets 2.11.0
|
| 94 |
+
- Tokenizers 0.13.3
|