GuCuChiara
commited on
Commit
•
3494282
1
Parent(s):
1378b35
Training complete
Browse files
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: monologg/biobert_v1.1_pubmed
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- precision
|
7 |
+
- recall
|
8 |
+
- f1
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: NLP-HIBA_DisTEMIST_fine_tuned_biobert
|
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 |
+
# NLP-HIBA_DisTEMIST_fine_tuned_biobert
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [monologg/biobert_v1.1_pubmed](https://huggingface.co/monologg/biobert_v1.1_pubmed) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.2325
|
23 |
+
- Precision: 0.5394
|
24 |
+
- Recall: 0.5010
|
25 |
+
- F1: 0.5195
|
26 |
+
- Accuracy: 0.9434
|
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: 5e-05
|
46 |
+
- train_batch_size: 8
|
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: 10
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
57 |
+
| No log | 1.0 | 71 | 0.2200 | 0.2689 | 0.2813 | 0.2750 | 0.9147 |
|
58 |
+
| No log | 2.0 | 142 | 0.1895 | 0.4126 | 0.3834 | 0.3975 | 0.9308 |
|
59 |
+
| No log | 3.0 | 213 | 0.1813 | 0.5319 | 0.3667 | 0.4341 | 0.9389 |
|
60 |
+
| No log | 4.0 | 284 | 0.1746 | 0.5085 | 0.4395 | 0.4715 | 0.9410 |
|
61 |
+
| No log | 5.0 | 355 | 0.1942 | 0.4868 | 0.4697 | 0.4781 | 0.9382 |
|
62 |
+
| No log | 6.0 | 426 | 0.1975 | 0.5246 | 0.4860 | 0.5046 | 0.9413 |
|
63 |
+
| No log | 7.0 | 497 | 0.2066 | 0.5207 | 0.4897 | 0.5047 | 0.9415 |
|
64 |
+
| 0.122 | 8.0 | 568 | 0.2201 | 0.5232 | 0.4956 | 0.5090 | 0.9420 |
|
65 |
+
| 0.122 | 9.0 | 639 | 0.2358 | 0.5178 | 0.5048 | 0.5112 | 0.9418 |
|
66 |
+
| 0.122 | 10.0 | 710 | 0.2325 | 0.5394 | 0.5010 | 0.5195 | 0.9434 |
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.35.0
|
72 |
+
- Pytorch 2.1.0+cu118
|
73 |
+
- Datasets 2.14.6
|
74 |
+
- Tokenizers 0.14.1
|