Moxieeixom
commited on
Commit
•
8369ca9
1
Parent(s):
e63dfa2
update model card README.md
Browse files
README.md
CHANGED
@@ -4,9 +4,36 @@ tags:
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- ncbi_disease
|
|
|
|
|
|
|
|
|
|
|
7 |
model-index:
|
8 |
- name: finetuned-biogpt
|
9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,6 +42,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
# finetuned-biogpt
|
16 |
|
17 |
This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on the ncbi_disease dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -34,12 +67,20 @@ More information needed
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 2e-05
|
37 |
-
- train_batch_size:
|
38 |
-
- eval_batch_size:
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
-
- num_epochs:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
|
44 |
### Framework versions
|
45 |
|
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- ncbi_disease
|
7 |
+
metrics:
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
- accuracy
|
12 |
model-index:
|
13 |
- name: finetuned-biogpt
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Token Classification
|
17 |
+
type: token-classification
|
18 |
+
dataset:
|
19 |
+
name: ncbi_disease
|
20 |
+
type: ncbi_disease
|
21 |
+
config: ncbi_disease
|
22 |
+
split: test
|
23 |
+
args: ncbi_disease
|
24 |
+
metrics:
|
25 |
+
- name: Precision
|
26 |
+
type: precision
|
27 |
+
value: 0.0761904761904762
|
28 |
+
- name: Recall
|
29 |
+
type: recall
|
30 |
+
value: 0.058333333333333334
|
31 |
+
- name: F1
|
32 |
+
type: f1
|
33 |
+
value: 0.06607669616519174
|
34 |
+
- name: Accuracy
|
35 |
+
type: accuracy
|
36 |
+
value: 0.9220180016640194
|
37 |
---
|
38 |
|
39 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
42 |
# finetuned-biogpt
|
43 |
|
44 |
This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on the ncbi_disease dataset.
|
45 |
+
It achieves the following results on the evaluation set:
|
46 |
+
- Loss: 0.2503
|
47 |
+
- Precision: 0.0762
|
48 |
+
- Recall: 0.0583
|
49 |
+
- F1: 0.0661
|
50 |
+
- Accuracy: 0.9220
|
51 |
|
52 |
## Model description
|
53 |
|
|
|
67 |
|
68 |
The following hyperparameters were used during training:
|
69 |
- learning_rate: 2e-05
|
70 |
+
- train_batch_size: 16
|
71 |
+
- eval_batch_size: 16
|
72 |
- seed: 42
|
73 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
74 |
- lr_scheduler_type: linear
|
75 |
+
- num_epochs: 2
|
76 |
+
|
77 |
+
### Training results
|
78 |
+
|
79 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
80 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
81 |
+
| No log | 1.0 | 340 | 0.2644 | 0.0426 | 0.0281 | 0.0339 | 0.9183 |
|
82 |
+
| 0.3055 | 2.0 | 680 | 0.2503 | 0.0762 | 0.0583 | 0.0661 | 0.9220 |
|
83 |
+
|
84 |
|
85 |
### Framework versions
|
86 |
|