Model save
Browse files
README.md
CHANGED
@@ -3,9 +3,38 @@ license: mit
|
|
3 |
base_model: romainlhardy/roberta-large-finetuned-ner
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
model-index:
|
7 |
- name: roberta-large-finetuned-ner-finetuned-ner
|
8 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -13,7 +42,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# roberta-large-finetuned-ner-finetuned-ner
|
15 |
|
16 |
-
This model is a fine-tuned version of [romainlhardy/roberta-large-finetuned-ner](https://huggingface.co/romainlhardy/roberta-large-finetuned-ner) on
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -40,6 +75,10 @@ The following hyperparameters were used during training:
|
|
40 |
- lr_scheduler_type: linear
|
41 |
- num_epochs: 6
|
42 |
|
|
|
|
|
|
|
|
|
43 |
### Framework versions
|
44 |
|
45 |
- Transformers 4.38.1
|
|
|
3 |
base_model: romainlhardy/roberta-large-finetuned-ner
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- plod-cw
|
8 |
+
metrics:
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
- f1
|
12 |
+
- accuracy
|
13 |
model-index:
|
14 |
- name: roberta-large-finetuned-ner-finetuned-ner
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Token Classification
|
18 |
+
type: token-classification
|
19 |
+
dataset:
|
20 |
+
name: plod-cw
|
21 |
+
type: plod-cw
|
22 |
+
config: PLOD-CW
|
23 |
+
split: validation
|
24 |
+
args: PLOD-CW
|
25 |
+
metrics:
|
26 |
+
- name: Precision
|
27 |
+
type: precision
|
28 |
+
value: 0.9597188892697978
|
29 |
+
- name: Recall
|
30 |
+
type: recall
|
31 |
+
value: 0.9502715546503734
|
32 |
+
- name: F1
|
33 |
+
type: f1
|
34 |
+
value: 0.9549718574108819
|
35 |
+
- name: Accuracy
|
36 |
+
type: accuracy
|
37 |
+
value: 0.949480642115203
|
38 |
---
|
39 |
|
40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
42 |
|
43 |
# roberta-large-finetuned-ner-finetuned-ner
|
44 |
|
45 |
+
This model is a fine-tuned version of [romainlhardy/roberta-large-finetuned-ner](https://huggingface.co/romainlhardy/roberta-large-finetuned-ner) on the plod-cw dataset.
|
46 |
+
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 0.2327
|
48 |
+
- Precision: 0.9597
|
49 |
+
- Recall: 0.9503
|
50 |
+
- F1: 0.9550
|
51 |
+
- Accuracy: 0.9495
|
52 |
|
53 |
## Model description
|
54 |
|
|
|
75 |
- lr_scheduler_type: linear
|
76 |
- num_epochs: 6
|
77 |
|
78 |
+
### Training results
|
79 |
+
|
80 |
+
|
81 |
+
|
82 |
### Framework versions
|
83 |
|
84 |
- Transformers 4.38.1
|