Upload roberta_fever_plus_adv_samples/README.md with huggingface_hub
Browse files
roberta_fever_plus_adv_samples/README.md
CHANGED
@@ -11,19 +11,40 @@ license: unknown
|
|
11 |
metrics:
|
12 |
epoch:
|
13 |
- 0
|
|
|
|
|
|
|
14 |
train_loss:
|
15 |
- 1.1077719926834106
|
|
|
|
|
|
|
16 |
val_loss:
|
17 |
- 1.116754412651062
|
|
|
|
|
|
|
18 |
train_acc:
|
19 |
- 0.25
|
|
|
|
|
|
|
20 |
val_acc:
|
21 |
- 0.34375
|
|
|
|
|
|
|
22 |
train_f1_score:
|
23 |
- 0.25
|
|
|
|
|
|
|
24 |
val_f1_score:
|
25 |
- 0.34375
|
26 |
-
|
|
|
|
|
|
|
27 |
model-index:
|
28 |
- name: nli-fever
|
29 |
results:
|
@@ -35,7 +56,7 @@ model-index:
|
|
35 |
type: fever
|
36 |
metrics:
|
37 |
- type: acc
|
38 |
-
value: '0.
|
39 |
name: Accuracy
|
40 |
verified: false
|
41 |
---
|
@@ -60,10 +81,10 @@ The model was trained on the FEVER (Fact Extraction and VERification) dataset.
|
|
60 |
|
61 |
## Training procedure
|
62 |
|
63 |
-
The model was trained for [0] epochs
|
64 |
-
with a final loss of 1.
|
65 |
-
accuracy of 0.
|
66 |
-
F1 score of 0.
|
67 |
|
68 |
## How to use
|
69 |
|
|
|
11 |
metrics:
|
12 |
epoch:
|
13 |
- 0
|
14 |
+
- 0
|
15 |
+
- 0
|
16 |
+
- 0
|
17 |
train_loss:
|
18 |
- 1.1077719926834106
|
19 |
+
- 1.0808662176132202
|
20 |
+
- 1.1135263442993164
|
21 |
+
- 1.0963691473007202
|
22 |
val_loss:
|
23 |
- 1.116754412651062
|
24 |
+
- 1.1231188774108887
|
25 |
+
- 1.1370257139205933
|
26 |
+
- 1.1022729873657227
|
27 |
train_acc:
|
28 |
- 0.25
|
29 |
+
- 0.65625
|
30 |
+
- 0.625
|
31 |
+
- 0.6538462042808533
|
32 |
val_acc:
|
33 |
- 0.34375
|
34 |
+
- 0.375
|
35 |
+
- 0.3854166567325592
|
36 |
+
- 0.35882866382598877
|
37 |
train_f1_score:
|
38 |
- 0.25
|
39 |
+
- 0.65625
|
40 |
+
- 0.625
|
41 |
+
- 0.6538461446762085
|
42 |
val_f1_score:
|
43 |
- 0.34375
|
44 |
+
- 0.375
|
45 |
+
- 0.3854166567325592
|
46 |
+
- 0.35882866382598877
|
47 |
+
best_metric: 1.1022729873657227
|
48 |
model-index:
|
49 |
- name: nli-fever
|
50 |
results:
|
|
|
56 |
type: fever
|
57 |
metrics:
|
58 |
- type: acc
|
59 |
+
value: '0.36'
|
60 |
name: Accuracy
|
61 |
verified: false
|
62 |
---
|
|
|
81 |
|
82 |
## Training procedure
|
83 |
|
84 |
+
The model was trained for [0, 0, 0, 0] epochs
|
85 |
+
with a final loss of 1.1022729873657227, an
|
86 |
+
accuracy of 0.35882866382598877, and
|
87 |
+
F1 score of 0.35882866382598877.
|
88 |
|
89 |
## How to use
|
90 |
|