Commit
·
35369ae
1
Parent(s):
de76553
Model save
Browse files
README.md
CHANGED
@@ -2,22 +2,12 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: distilroberta-base
|
4 |
tags:
|
5 |
-
- text-classification
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
- glue
|
9 |
metrics:
|
10 |
- accuracy
|
11 |
- f1
|
12 |
-
widget:
|
13 |
-
- text: Yucaipa owned Dominick 's before selling the chain to Safeway in 1998 for
|
14 |
-
$ 2.5 billion.,Yucaipa bought Dominick's in 1995 for $ 693 million and sold it
|
15 |
-
to Safeway for $ 1.8 billion in 1998.
|
16 |
-
example_title: Not Equivalent
|
17 |
-
- text: Revenue in the first quarter of the year dropped 15 percent from the same
|
18 |
-
period a year earlier.,With the scandal hanging over Stewart's company revenue
|
19 |
-
the first quarter of the year dropped 15 percent from the same period a year earlier.
|
20 |
-
example_title: Equivalent
|
21 |
model-index:
|
22 |
- name: distilroberta-base-mrpc-glue
|
23 |
results:
|
@@ -25,7 +15,7 @@ model-index:
|
|
25 |
name: Text Classification
|
26 |
type: text-classification
|
27 |
dataset:
|
28 |
-
name:
|
29 |
type: glue
|
30 |
config: mrpc
|
31 |
split: validation
|
@@ -33,10 +23,10 @@ model-index:
|
|
33 |
metrics:
|
34 |
- name: Accuracy
|
35 |
type: accuracy
|
36 |
-
value: 0.
|
37 |
- name: F1
|
38 |
type: f1
|
39 |
-
value: 0.
|
40 |
---
|
41 |
|
42 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -44,11 +34,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
44 |
|
45 |
# distilroberta-base-mrpc-glue
|
46 |
|
47 |
-
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the
|
48 |
It achieves the following results on the evaluation set:
|
49 |
-
- Loss: 0.
|
50 |
-
- Accuracy: 0.
|
51 |
-
- F1: 0.
|
52 |
|
53 |
## Model description
|
54 |
|
@@ -79,8 +69,8 @@ The following hyperparameters were used during training:
|
|
79 |
|
80 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
81 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
|
85 |
|
86 |
### Framework versions
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: distilroberta-base
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- glue
|
8 |
metrics:
|
9 |
- accuracy
|
10 |
- f1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
model-index:
|
12 |
- name: distilroberta-base-mrpc-glue
|
13 |
results:
|
|
|
15 |
name: Text Classification
|
16 |
type: text-classification
|
17 |
dataset:
|
18 |
+
name: glue
|
19 |
type: glue
|
20 |
config: mrpc
|
21 |
split: validation
|
|
|
23 |
metrics:
|
24 |
- name: Accuracy
|
25 |
type: accuracy
|
26 |
+
value: 0.8406862745098039
|
27 |
- name: F1
|
28 |
type: f1
|
29 |
+
value: 0.8861646234676007
|
30 |
---
|
31 |
|
32 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
34 |
|
35 |
# distilroberta-base-mrpc-glue
|
36 |
|
37 |
+
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the glue dataset.
|
38 |
It achieves the following results on the evaluation set:
|
39 |
+
- Loss: 0.6595
|
40 |
+
- Accuracy: 0.8407
|
41 |
+
- F1: 0.8862
|
42 |
|
43 |
## Model description
|
44 |
|
|
|
69 |
|
70 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
71 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
72 |
+
| 0.5377 | 1.09 | 500 | 0.4936 | 0.8382 | 0.8893 |
|
73 |
+
| 0.3477 | 2.18 | 1000 | 0.6595 | 0.8407 | 0.8862 |
|
74 |
|
75 |
|
76 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 328492280
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b279807aa73461222b5b6aea0fe6d1401aaffa34f4ead83fa01647066f85b6e4
|
3 |
size 328492280
|
runs/Dec20_23-39-02_d80aa9457aee/events.out.tfevents.1703115585.d80aa9457aee.211.0
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 sha256:1f3444ff3f3569bf6335efef1ab6a44d5de29b4293fe68ad539e2ea6763d697a
|
3 |
+
size 5835
|