cartesinus
commited on
Commit
•
175b79e
1
Parent(s):
c6eb744
Update README.md
Browse files
README.md
CHANGED
@@ -10,6 +10,10 @@ metrics:
|
|
10 |
model-index:
|
11 |
- name: fedcsis-slot_baseline-xlm_r-es
|
12 |
results: []
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -17,7 +21,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# fedcsis-slot_baseline-xlm_r-es
|
19 |
|
20 |
-
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
It achieves the following results on the evaluation set:
|
22 |
- Loss: 0.0521
|
23 |
- Precision: 0.9728
|
@@ -65,10 +77,69 @@ The following hyperparameters were used during training:
|
|
65 |
| 0.01 | 9.0 | 8469 | 0.0500 | 0.9720 | 0.9702 | 0.9711 | 0.9913 |
|
66 |
| 0.0072 | 10.0 | 9410 | 0.0521 | 0.9728 | 0.9711 | 0.9720 | 0.9914 |
|
67 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
|
69 |
### Framework versions
|
70 |
|
71 |
- Transformers 4.27.4
|
72 |
- Pytorch 1.13.1+cu116
|
73 |
- Datasets 2.11.0
|
74 |
-
- Tokenizers 0.13.2
|
|
|
10 |
model-index:
|
11 |
- name: fedcsis-slot_baseline-xlm_r-es
|
12 |
results: []
|
13 |
+
datasets:
|
14 |
+
- cartesinus/leyzer-fedcsis
|
15 |
+
language:
|
16 |
+
- es
|
17 |
---
|
18 |
|
19 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
21 |
|
22 |
# fedcsis-slot_baseline-xlm_r-es
|
23 |
|
24 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the
|
25 |
+
[leyzer-fedcsis](https://huggingface.co/cartesinus/leyzer-fedcsis) dataset.
|
26 |
+
|
27 |
+
Result on test set:
|
28 |
+
- Precision: 0.9696
|
29 |
+
- Recall: 0.9686
|
30 |
+
- F1: 0.9691
|
31 |
+
- Accuracy: 0.9904
|
32 |
+
|
33 |
It achieves the following results on the evaluation set:
|
34 |
- Loss: 0.0521
|
35 |
- Precision: 0.9728
|
|
|
77 |
| 0.01 | 9.0 | 8469 | 0.0500 | 0.9720 | 0.9702 | 0.9711 | 0.9913 |
|
78 |
| 0.0072 | 10.0 | 9410 | 0.0521 | 0.9728 | 0.9711 | 0.9720 | 0.9914 |
|
79 |
|
80 |
+
### Per slot evaluation
|
81 |
+
|
82 |
+
| slot_name | precision | recall | f1 | tc_size |
|
83 |
+
|-----------|-----------|--------|----|---------|
|
84 |
+
| album | 0.9500 | 0.9135 | 0.9314 | 104 |
|
85 |
+
| all_lang | 0.7500 | 1.0000 | 0.8571 | 3 |
|
86 |
+
| artist | 0.9556 | 0.9685 | 0.9620 | 222 |
|
87 |
+
| av_alias | 1.0000 | 1.0000 | 1.0000 | 18 |
|
88 |
+
| caption | 0.9565 | 0.9362 | 0.9462 | 47 |
|
89 |
+
| category | 0.9091 | 1.0000 | 0.9524 | 10 |
|
90 |
+
| channel | 0.7857 | 0.7857 | 0.7857 | 14 |
|
91 |
+
| channel_id | 0.9500 | 1.0000 | 0.9744 | 19 |
|
92 |
+
| count | 1.0000 | 1.0000 | 1.0000 | 8 |
|
93 |
+
| date | 0.9762 | 0.9762 | 0.9762 | 42 |
|
94 |
+
| date_day | 1.0000 | 1.0000 | 1.0000 | 6 |
|
95 |
+
| date_month | 1.0000 | 1.0000 | 1.0000 | 7 |
|
96 |
+
| device_name | 0.9770 | 1.0000 | 0.9884 | 85 |
|
97 |
+
| email | 1.0000 | 0.9740 | 0.9868 | 192 |
|
98 |
+
| event_name | 1.0000 | 1.0000 | 1.0000 | 35 |
|
99 |
+
| file_name | 1.0000 | 1.0000 | 1.0000 | 10 |
|
100 |
+
| file_size | 1.0000 | 1.0000 | 1.0000 | 2 |
|
101 |
+
| filter | 1.0000 | 1.0000 | 1.0000 | 15 |
|
102 |
+
| hashtag | 1.0000 | 0.9565 | 0.9778 | 46 |
|
103 |
+
| img_query | 0.9843 | 0.9843 | 0.9843 | 764 |
|
104 |
+
| label | 1.0000 | 1.0000 | 1.0000 | 7 |
|
105 |
+
| location | 0.9753 | 0.9875 | 0.9814 | 80 |
|
106 |
+
| mail | 1.0000 | 1.0000 | 1.0000 | 5 |
|
107 |
+
| message | 0.9577 | 0.9607 | 0.9592 | 636 |
|
108 |
+
| mime_type | 1.0000 | 1.0000 | 1.0000 | 1 |
|
109 |
+
| name | 0.9677 | 0.9677 | 0.9677 | 31 |
|
110 |
+
| percent | 0.8571 | 1.0000 | 0.9231 | 6 |
|
111 |
+
| phone_number | 0.9429 | 0.9763 | 0.9593 | 169 |
|
112 |
+
| phone_type | 1.0000 | 0.6667 | 0.8000 | 3 |
|
113 |
+
| picture_url | 1.0000 | 0.9286 | 0.9630 | 42 |
|
114 |
+
| playlist | 0.9701 | 0.9630 | 0.9665 | 135 |
|
115 |
+
| portal | 1.0000 | 0.9940 | 0.9970 | 168 |
|
116 |
+
| priority | 1.0000 | 1.0000 | 1.0000 | 3 |
|
117 |
+
| purpose | 0.0000 | 0.0000 | 0.0000 | 1 |
|
118 |
+
| query | 0.9259 | 0.8929 | 0.9091 | 28 |
|
119 |
+
| rating | 1.0000 | 1.0000 | 1.0000 | 3 |
|
120 |
+
| review_count | 0.7500 | 0.7500 | 0.7500 | 4 |
|
121 |
+
| section | 1.0000 | 1.0000 | 1.0000 | 134 |
|
122 |
+
| seek_time | 1.0000 | 1.0000 | 1.0000 | 2 |
|
123 |
+
| sender | 0.0000 | 0.0000 | 0.0000 | 1 |
|
124 |
+
| sender_address | 1.0000 | 1.0000 | 1.0000 | 6 |
|
125 |
+
| song | 0.9314 | 0.9628 | 0.9468 | 296 |
|
126 |
+
| src_lang | 0.9872 | 1.0000 | 0.9935 | 77 |
|
127 |
+
| status | 0.8462 | 0.9565 | 0.8980 | 23 |
|
128 |
+
| subject | 0.9555 | 0.9567 | 0.9561 | 785 |
|
129 |
+
| text | 0.9798 | 0.9798 | 0.9798 | 99 |
|
130 |
+
| time | 1.0000 | 1.0000 | 1.0000 | 32 |
|
131 |
+
| to | 0.9760 | 0.9651 | 0.9705 | 802 |
|
132 |
+
| topic | 1.0000 | 1.0000 | 1.0000 | 1 |
|
133 |
+
| translator | 1.0000 | 1.0000 | 1.0000 | 52 |
|
134 |
+
| trg_lang | 0.9886 | 1.0000 | 0.9943 | 87 |
|
135 |
+
| txt_query | 1.0000 | 0.8947 | 0.9444 | 19 |
|
136 |
+
| username | 1.0000 | 1.0000 | 1.0000 | 6 |
|
137 |
+
| value | 0.9318 | 0.9535 | 0.9425 | 43 |
|
138 |
+
| weight | 1.0000 | 1.0000 | 1.0000 | 1 |
|
139 |
|
140 |
### Framework versions
|
141 |
|
142 |
- Transformers 4.27.4
|
143 |
- Pytorch 1.13.1+cu116
|
144 |
- Datasets 2.11.0
|
145 |
+
- Tokenizers 0.13.2
|