Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
update metrics to f1
Browse files- src/about.py +12 -13
src/about.py
CHANGED
@@ -20,14 +20,14 @@ class Tasks(Enum):
|
|
20 |
task7 = Task("polish_8tags_multiple_choice", "acc,none", "8tags_mc")
|
21 |
task8 = Task("polish_8tags_regex", "exact_match,score-first", "8tags_g")
|
22 |
task9 = Task("polish_belebele_regex", "exact_match,score-first", "belebele_g")
|
23 |
-
task10 = Task("polish_dyk_multiple_choice", "
|
24 |
-
task11 = Task("polish_dyk_regex", "
|
25 |
task12 = Task("polish_ppc_multiple_choice", "acc,none", "ppc_mc")
|
26 |
task13 = Task("polish_ppc_regex", "exact_match,score-first", "ppc_g")
|
27 |
-
task14 = Task("polish_psc_multiple_choice", "
|
28 |
-
task15 = Task("polish_psc_regex", "
|
29 |
-
task16 = Task("polish_cbd_multiple_choice", "
|
30 |
-
task17 = Task("polish_cbd_regex", "
|
31 |
task18 = Task("polish_klej_ner_multiple_choice", "acc,none", "klej_ner_mc")
|
32 |
task19 = Task("polish_klej_ner_regex", "exact_match,score-first", "klej_ner_g")
|
33 |
|
@@ -66,7 +66,6 @@ or join our [Discord SpeakLeash](https://discord.gg/3G9DVM39)
|
|
66 |
|
67 |
## TODO
|
68 |
|
69 |
-
* change metrics for DYK, PSC, CBD(?)
|
70 |
* fix long model names
|
71 |
* add inference time
|
72 |
* add metadata for models (e.g. #Params)
|
@@ -83,14 +82,14 @@ or join our [Discord SpeakLeash](https://discord.gg/3G9DVM39)
|
|
83 |
- **polish_8tags_multiple_choice**: accuracy
|
84 |
- **polish_8tags_regex**: accuracy
|
85 |
- **polish_belebele_regex**: accuracy
|
86 |
-
- **polish_dyk_multiple_choice**: accuracy -
|
87 |
-
- **polish_dyk_regex**: accuracy -
|
88 |
- **polish_ppc_multiple_choice**: accuracy
|
89 |
- **polish_ppc_regex**: accuracy
|
90 |
-
- **polish_psc_multiple_choice**: accuracy -
|
91 |
-
- **polish_psc_regex**: accuracy -
|
92 |
-
- **polish_cbd_multiple_choice**: accuracy -
|
93 |
-
- **polish_cbd_regex**: accuracy -
|
94 |
- **polish_klej_ner_multiple_choice**: accuracy
|
95 |
- **polish_klej_ner_regex**: accuracy
|
96 |
|
|
|
20 |
task7 = Task("polish_8tags_multiple_choice", "acc,none", "8tags_mc")
|
21 |
task8 = Task("polish_8tags_regex", "exact_match,score-first", "8tags_g")
|
22 |
task9 = Task("polish_belebele_regex", "exact_match,score-first", "belebele_g")
|
23 |
+
task10 = Task("polish_dyk_multiple_choice", "f1,none", "dyk_mc")
|
24 |
+
task11 = Task("polish_dyk_regex", "f1,score-first", "dyk_g")
|
25 |
task12 = Task("polish_ppc_multiple_choice", "acc,none", "ppc_mc")
|
26 |
task13 = Task("polish_ppc_regex", "exact_match,score-first", "ppc_g")
|
27 |
+
task14 = Task("polish_psc_multiple_choice", "f1,none", "psc_mc")
|
28 |
+
task15 = Task("polish_psc_regex", "f1,score-first", "psc_g")
|
29 |
+
task16 = Task("polish_cbd_multiple_choice", "f1,none", "cbd_mc")
|
30 |
+
task17 = Task("polish_cbd_regex", "f1,score-first", "cbd_g")
|
31 |
task18 = Task("polish_klej_ner_multiple_choice", "acc,none", "klej_ner_mc")
|
32 |
task19 = Task("polish_klej_ner_regex", "exact_match,score-first", "klej_ner_g")
|
33 |
|
|
|
66 |
|
67 |
## TODO
|
68 |
|
|
|
69 |
* fix long model names
|
70 |
* add inference time
|
71 |
* add metadata for models (e.g. #Params)
|
|
|
82 |
- **polish_8tags_multiple_choice**: accuracy
|
83 |
- **polish_8tags_regex**: accuracy
|
84 |
- **polish_belebele_regex**: accuracy
|
85 |
+
- **polish_dyk_multiple_choice**: accuracy - binary F1
|
86 |
+
- **polish_dyk_regex**: accuracy - binary F1
|
87 |
- **polish_ppc_multiple_choice**: accuracy
|
88 |
- **polish_ppc_regex**: accuracy
|
89 |
+
- **polish_psc_multiple_choice**: accuracy - binary F1
|
90 |
+
- **polish_psc_regex**: accuracy - binary F1
|
91 |
+
- **polish_cbd_multiple_choice**: accuracy - macro F1
|
92 |
+
- **polish_cbd_regex**: accuracy - macro F1
|
93 |
- **polish_klej_ner_multiple_choice**: accuracy
|
94 |
- **polish_klej_ner_regex**: accuracy
|
95 |
|