cartesinus commited on
Commit
8ef3405
1 Parent(s): 8289159

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +65 -6
README.md CHANGED
@@ -17,13 +17,14 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # slurp-slot_baseline-xlm_r-en
19
 
20
- This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
21
- It achieves the following results on the evaluation set:
 
22
  - Loss: 0.3263
23
- - Precision: 0.8145
24
- - Recall: 0.8641
25
- - F1: 0.8386
26
- - Accuracy: 0.9341
27
 
28
  ## Model description
29
 
@@ -65,6 +66,64 @@ The following hyperparameters were used during training:
65
  | 0.0968 | 9.0 | 6480 | 0.3242 | 0.8147 | 0.8637 | 0.8385 | 0.9329 |
66
  | 0.0772 | 10.0 | 7200 | 0.3263 | 0.8145 | 0.8641 | 0.8386 | 0.9341 |
67
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
 
69
  ### Framework versions
70
 
 
17
 
18
  # slurp-slot_baseline-xlm_r-en
19
 
20
+ This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the SLURP dataset.
21
+
22
+ It achieves the following results on the test set:
23
  - Loss: 0.3263
24
+ - Precision: 0.7954
25
+ - Recall: 0.8413
26
+ - F1: 0.8177
27
+ - Accuracy: 0.9268
28
 
29
  ## Model description
30
 
 
66
  | 0.0968 | 9.0 | 6480 | 0.3242 | 0.8147 | 0.8637 | 0.8385 | 0.9329 |
67
  | 0.0772 | 10.0 | 7200 | 0.3263 | 0.8145 | 0.8641 | 0.8386 | 0.9341 |
68
 
69
+ ## Test results per slot
70
+
71
+ | slot | f1 | tc_size |
72
+ |:----:|:--:|:-------:|
73
+ | alarm_type | 0.4 | 4 |
74
+ | app_name | 0.42857142857142855 | 10 |
75
+ | artist_name | 0.8122605363984675 | 123 |
76
+ | audiobook_author | 0.0 | 9 |
77
+ | audiobook_name | 0.6021505376344087 | 43 |
78
+ | business_name | 0.8530259365994236 | 184 |
79
+ | business_type | 0.6666666666666667 | 41 |
80
+ | change_amount | 0.6666666666666666 | 9 |
81
+ | coffee_type | 0.5333333333333333 | 6 |
82
+ | color_type | 0.8135593220338982 | 28 |
83
+ | cooking_type | 0.8333333333333333 | 14 |
84
+ | currency_name | 0.8611111111111112 | 70 |
85
+ | date | 0.9034267912772587 | 623 |
86
+ | definition_word | 0.88 | 97 |
87
+ | device_type | 0.8053691275167785 | 71 |
88
+ | drink_type | 0.0 | 2 |
89
+ | email_address | 0.9599999999999999 | 38 |
90
+ | email_folder | 0.9523809523809523 | 10 |
91
+ | event_name | 0.7643504531722054 | 321 |
92
+ | food_type | 0.7482014388489208 | 121 |
93
+ | game_name | 0.7789473684210527 | 44 |
94
+ | general_frequency | 0.5862068965517242 | 21 |
95
+ | house_place | 0.8840579710144928 | 68 |
96
+ | ingredient | 0.0 | 13 |
97
+ | joke_type | 0.9411764705882353 | 17 |
98
+ | list_name | 0.7979274611398963 | 91 |
99
+ | meal_type | 0.782608695652174 | 18 |
100
+ | media_type | 0.8596491228070176 | 173 |
101
+ | movie_name | 0.0 | 3 |
102
+ | movie_type | 0.5 | 3 |
103
+ | music_album | 0.0 | 2 |
104
+ | music_descriptor | 0.25 | 8 |
105
+ | music_genre | 0.7244094488188977 | 58 |
106
+ | news_topic | 0.5675675675675675 | 64 |
107
+ | order_type | 0.7941176470588235 | 29 |
108
+ | person | 0.9128094725511302 | 438 |
109
+ | personal_info | 0.6666666666666666 | 16 |
110
+ | place_name | 0.8725790010193679 | 493 |
111
+ | player_setting | 0.5405405405405405 | 42 |
112
+ | playlist_name | 0.5 | 27 |
113
+ | podcast_descriptor | 0.4888888888888888 | 28 |
114
+ | podcast_name | 0.5245901639344263 | 31 |
115
+ | radio_name | 0.6504065040650406 | 53 |
116
+ | relation | 0.8478260869565218 | 87 |
117
+ | song_name | 0.7058823529411765 | 54 |
118
+ | time | 0.7914893617021276 | 236 |
119
+ | time_zone | 0.7804878048780488 | 23 |
120
+ | timeofday | 0.8396946564885496 | 60 |
121
+ | transport_agency | 0.8571428571428571 | 18 |
122
+ | transport_descriptor | 0.0 | 2 |
123
+ | transport_name | 0.4 | 7 |
124
+ | transport_type | 0.9481481481481482 | 68 |
125
+ | weather_descriptor | 0.789272030651341 | 123 |
126
+
127
 
128
  ### Framework versions
129