GuCuChiara
commited on
Commit
•
2864450
1
Parent(s):
9056549
Training complete
Browse files
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: emilyalsentzer/Bio_ClinicalBERT
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: NLP-HIBA_DisTEMIST_fine_tuned_ClinicalBERT-pretrained-model
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# NLP-HIBA_DisTEMIST_fine_tuned_ClinicalBERT-pretrained-model
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.2634
|
24 |
+
- Precision: 0.4559
|
25 |
+
- Recall: 0.4616
|
26 |
+
- F1: 0.4587
|
27 |
+
- Accuracy: 0.9334
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 8
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 8
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| No log | 1.0 | 71 | 0.2011 | 0.3859 | 0.3371 | 0.3598 | 0.9297 |
|
59 |
+
| No log | 2.0 | 142 | 0.1970 | 0.3956 | 0.3894 | 0.3925 | 0.9283 |
|
60 |
+
| No log | 3.0 | 213 | 0.2041 | 0.4140 | 0.3977 | 0.4057 | 0.9307 |
|
61 |
+
| No log | 4.0 | 284 | 0.2167 | 0.4379 | 0.4110 | 0.4240 | 0.9348 |
|
62 |
+
| No log | 5.0 | 355 | 0.2293 | 0.4430 | 0.4159 | 0.4290 | 0.9338 |
|
63 |
+
| No log | 6.0 | 426 | 0.2447 | 0.4615 | 0.4375 | 0.4492 | 0.9356 |
|
64 |
+
| No log | 7.0 | 497 | 0.2587 | 0.4601 | 0.4500 | 0.4550 | 0.9342 |
|
65 |
+
| 0.0861 | 8.0 | 568 | 0.2634 | 0.4559 | 0.4616 | 0.4587 | 0.9334 |
|
66 |
+
|
67 |
+
|
68 |
+
### Framework versions
|
69 |
+
|
70 |
+
- Transformers 4.35.0
|
71 |
+
- Pytorch 2.1.0+cu118
|
72 |
+
- Datasets 2.14.6
|
73 |
+
- Tokenizers 0.14.1
|