Training complete
Browse files
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
license:
|
4 |
-
base_model:
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
@@ -26,16 +26,16 @@ model-index:
|
|
26 |
metrics:
|
27 |
- name: Precision
|
28 |
type: precision
|
29 |
-
value: 0.
|
30 |
- name: Recall
|
31 |
type: recall
|
32 |
-
value: 0.
|
33 |
- name: F1
|
34 |
type: f1
|
35 |
-
value: 0.
|
36 |
- name: Accuracy
|
37 |
type: accuracy
|
38 |
-
value: 0.
|
39 |
---
|
40 |
|
41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -43,13 +43,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
43 |
|
44 |
# bert-finetuned-ner
|
45 |
|
46 |
-
This model is a fine-tuned version of [
|
47 |
It achieves the following results on the evaluation set:
|
48 |
-
- Loss: 0.
|
49 |
-
- Precision: 0.
|
50 |
-
- Recall: 0.
|
51 |
-
- F1: 0.
|
52 |
-
- Accuracy: 0.
|
53 |
|
54 |
## Model description
|
55 |
|
@@ -80,9 +80,9 @@ The following hyperparameters were used during training:
|
|
80 |
|
81 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
82 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
|
87 |
|
88 |
### Framework versions
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
license: mit
|
4 |
+
base_model: emilyalsentzer/Bio_ClinicalBERT
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
|
|
26 |
metrics:
|
27 |
- name: Precision
|
28 |
type: precision
|
29 |
+
value: 0.8033573141486811
|
30 |
- name: Recall
|
31 |
type: recall
|
32 |
+
value: 0.8513341804320204
|
33 |
- name: F1
|
34 |
type: f1
|
35 |
+
value: 0.8266502159161011
|
36 |
- name: Accuracy
|
37 |
type: accuracy
|
38 |
+
value: 0.9835329804686291
|
39 |
---
|
40 |
|
41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
43 |
|
44 |
# bert-finetuned-ner
|
45 |
|
46 |
+
This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the ncbi_disease dataset.
|
47 |
It achieves the following results on the evaluation set:
|
48 |
+
- Loss: 0.0626
|
49 |
+
- Precision: 0.8034
|
50 |
+
- Recall: 0.8513
|
51 |
+
- F1: 0.8267
|
52 |
+
- Accuracy: 0.9835
|
53 |
|
54 |
## Model description
|
55 |
|
|
|
80 |
|
81 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
82 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
83 |
+
| 0.1245 | 1.0 | 680 | 0.0536 | 0.7295 | 0.8158 | 0.7702 | 0.9814 |
|
84 |
+
| 0.0392 | 2.0 | 1360 | 0.0551 | 0.7907 | 0.8399 | 0.8145 | 0.9831 |
|
85 |
+
| 0.0155 | 3.0 | 2040 | 0.0626 | 0.8034 | 0.8513 | 0.8267 | 0.9835 |
|
86 |
|
87 |
|
88 |
### Framework versions
|
runs/Sep16_22-13-56_f72b346c1a48/events.out.tfevents.1726524840.f72b346c1a48.1491.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a300b80d2c21aa39397210ce217f8f373457a48ed5c8c165e2fe0cf072f0a35
|
3 |
+
size 7596
|