chintagunta85
commited on
Commit
•
a33cb35
1
Parent(s):
050986a
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- jnlpba
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: electramed-small-JNLPBA-ner
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Token Classification
|
16 |
+
type: token-classification
|
17 |
+
dataset:
|
18 |
+
name: jnlpba
|
19 |
+
type: jnlpba
|
20 |
+
config: jnlpba
|
21 |
+
split: train
|
22 |
+
args: jnlpba
|
23 |
+
metrics:
|
24 |
+
- name: Precision
|
25 |
+
type: precision
|
26 |
+
value: 0.8224512128396863
|
27 |
+
- name: Recall
|
28 |
+
type: recall
|
29 |
+
value: 0.878188899707887
|
30 |
+
- name: F1
|
31 |
+
type: f1
|
32 |
+
value: 0.8494066679223958
|
33 |
+
- name: Accuracy
|
34 |
+
type: accuracy
|
35 |
+
value: 0.9620705451213926
|
36 |
+
---
|
37 |
+
|
38 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
39 |
+
should probably proofread and complete it, then remove this comment. -->
|
40 |
+
|
41 |
+
# electramed-small-JNLPBA-ner
|
42 |
+
|
43 |
+
This model is a fine-tuned version of [giacomomiolo/electramed_small_scivocab](https://huggingface.co/giacomomiolo/electramed_small_scivocab) on the jnlpba dataset.
|
44 |
+
It achieves the following results on the evaluation set:
|
45 |
+
- Loss: 0.1167
|
46 |
+
- Precision: 0.8225
|
47 |
+
- Recall: 0.8782
|
48 |
+
- F1: 0.8494
|
49 |
+
- Accuracy: 0.9621
|
50 |
+
|
51 |
+
## Model description
|
52 |
+
|
53 |
+
More information needed
|
54 |
+
|
55 |
+
## Intended uses & limitations
|
56 |
+
|
57 |
+
More information needed
|
58 |
+
|
59 |
+
## Training and evaluation data
|
60 |
+
|
61 |
+
More information needed
|
62 |
+
|
63 |
+
## Training procedure
|
64 |
+
|
65 |
+
### Training hyperparameters
|
66 |
+
|
67 |
+
The following hyperparameters were used during training:
|
68 |
+
- learning_rate: 2e-05
|
69 |
+
- train_batch_size: 16
|
70 |
+
- eval_batch_size: 16
|
71 |
+
- seed: 42
|
72 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
73 |
+
- lr_scheduler_type: linear
|
74 |
+
- num_epochs: 10
|
75 |
+
|
76 |
+
### Training results
|
77 |
+
|
78 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
79 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
80 |
+
| 0.398 | 1.0 | 2087 | 0.1941 | 0.7289 | 0.7936 | 0.7599 | 0.9441 |
|
81 |
+
| 0.0771 | 2.0 | 4174 | 0.1542 | 0.7734 | 0.8348 | 0.8029 | 0.9514 |
|
82 |
+
| 0.1321 | 3.0 | 6261 | 0.1413 | 0.7890 | 0.8492 | 0.8180 | 0.9546 |
|
83 |
+
| 0.2302 | 4.0 | 8348 | 0.1326 | 0.8006 | 0.8589 | 0.8287 | 0.9562 |
|
84 |
+
| 0.0723 | 5.0 | 10435 | 0.1290 | 0.7997 | 0.8715 | 0.8340 | 0.9574 |
|
85 |
+
| 0.171 | 6.0 | 12522 | 0.1246 | 0.8115 | 0.8722 | 0.8408 | 0.9593 |
|
86 |
+
| 0.1058 | 7.0 | 14609 | 0.1204 | 0.8148 | 0.8757 | 0.8441 | 0.9604 |
|
87 |
+
| 0.1974 | 8.0 | 16696 | 0.1178 | 0.8181 | 0.8779 | 0.8470 | 0.9614 |
|
88 |
+
| 0.0663 | 9.0 | 18783 | 0.1168 | 0.8239 | 0.8781 | 0.8501 | 0.9620 |
|
89 |
+
| 0.1022 | 10.0 | 20870 | 0.1167 | 0.8225 | 0.8782 | 0.8494 | 0.9621 |
|
90 |
+
|
91 |
+
|
92 |
+
### Framework versions
|
93 |
+
|
94 |
+
- Transformers 4.21.1
|
95 |
+
- Pytorch 1.12.1+cu113
|
96 |
+
- Datasets 2.4.0
|
97 |
+
- Tokenizers 0.12.1
|