asahi417 commited on
Commit
0f38712
1 Parent(s): 58cffb8

model update

Browse files
README.md ADDED
@@ -0,0 +1,236 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - relbert/semeval2012_relational_similarity_v6
4
+ model-index:
5
+ - name: relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-b-triplet-2
6
+ results:
7
+ - task:
8
+ name: Relation Mapping
9
+ type: sorting-task
10
+ dataset:
11
+ name: Relation Mapping
12
+ args: relbert/relation_mapping
13
+ type: relation-mapping
14
+ metrics:
15
+ - name: Accuracy
16
+ type: accuracy
17
+ value: None
18
+ - task:
19
+ name: Analogy Questions (SAT full)
20
+ type: multiple-choice-qa
21
+ dataset:
22
+ name: SAT full
23
+ args: relbert/analogy_questions
24
+ type: analogy-questions
25
+ metrics:
26
+ - name: Accuracy
27
+ type: accuracy
28
+ value: None
29
+ - task:
30
+ name: Analogy Questions (SAT)
31
+ type: multiple-choice-qa
32
+ dataset:
33
+ name: SAT
34
+ args: relbert/analogy_questions
35
+ type: analogy-questions
36
+ metrics:
37
+ - name: Accuracy
38
+ type: accuracy
39
+ value: None
40
+ - task:
41
+ name: Analogy Questions (BATS)
42
+ type: multiple-choice-qa
43
+ dataset:
44
+ name: BATS
45
+ args: relbert/analogy_questions
46
+ type: analogy-questions
47
+ metrics:
48
+ - name: Accuracy
49
+ type: accuracy
50
+ value: None
51
+ - task:
52
+ name: Analogy Questions (Google)
53
+ type: multiple-choice-qa
54
+ dataset:
55
+ name: Google
56
+ args: relbert/analogy_questions
57
+ type: analogy-questions
58
+ metrics:
59
+ - name: Accuracy
60
+ type: accuracy
61
+ value: None
62
+ - task:
63
+ name: Analogy Questions (U2)
64
+ type: multiple-choice-qa
65
+ dataset:
66
+ name: U2
67
+ args: relbert/analogy_questions
68
+ type: analogy-questions
69
+ metrics:
70
+ - name: Accuracy
71
+ type: accuracy
72
+ value: None
73
+ - task:
74
+ name: Analogy Questions (U4)
75
+ type: multiple-choice-qa
76
+ dataset:
77
+ name: U4
78
+ args: relbert/analogy_questions
79
+ type: analogy-questions
80
+ metrics:
81
+ - name: Accuracy
82
+ type: accuracy
83
+ value: None
84
+ - task:
85
+ name: Lexical Relation Classification (BLESS)
86
+ type: classification
87
+ dataset:
88
+ name: BLESS
89
+ args: relbert/lexical_relation_classification
90
+ type: relation-classification
91
+ metrics:
92
+ - name: F1
93
+ type: f1
94
+ value: None
95
+ - name: F1 (macro)
96
+ type: f1_macro
97
+ value: None
98
+ - task:
99
+ name: Lexical Relation Classification (CogALexV)
100
+ type: classification
101
+ dataset:
102
+ name: CogALexV
103
+ args: relbert/lexical_relation_classification
104
+ type: relation-classification
105
+ metrics:
106
+ - name: F1
107
+ type: f1
108
+ value: None
109
+ - name: F1 (macro)
110
+ type: f1_macro
111
+ value: None
112
+ - task:
113
+ name: Lexical Relation Classification (EVALution)
114
+ type: classification
115
+ dataset:
116
+ name: BLESS
117
+ args: relbert/lexical_relation_classification
118
+ type: relation-classification
119
+ metrics:
120
+ - name: F1
121
+ type: f1
122
+ value: None
123
+ - name: F1 (macro)
124
+ type: f1_macro
125
+ value: None
126
+ - task:
127
+ name: Lexical Relation Classification (K&H+N)
128
+ type: classification
129
+ dataset:
130
+ name: K&H+N
131
+ args: relbert/lexical_relation_classification
132
+ type: relation-classification
133
+ metrics:
134
+ - name: F1
135
+ type: f1
136
+ value: None
137
+ - name: F1 (macro)
138
+ type: f1_macro
139
+ value: None
140
+ - task:
141
+ name: Lexical Relation Classification (ROOT09)
142
+ type: classification
143
+ dataset:
144
+ name: ROOT09
145
+ args: relbert/lexical_relation_classification
146
+ type: relation-classification
147
+ metrics:
148
+ - name: F1
149
+ type: f1
150
+ value: None
151
+ - name: F1 (macro)
152
+ type: f1_macro
153
+ value: None
154
+
155
+ ---
156
+ # relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-b-triplet-2
157
+
158
+ RelBERT fine-tuned from [roberta-base](https://huggingface.co/roberta-base) on
159
+ [relbert/semeval2012_relational_similarity_v6](https://huggingface.co/datasets/relbert/semeval2012_relational_similarity_v6).
160
+ Fine-tuning is done via [RelBERT](https://github.com/asahi417/relbert) library (see the repository for more detail).
161
+ It achieves the following results on the relation understanding tasks:
162
+ - Analogy Question ([dataset](https://huggingface.co/datasets/relbert/analogy_questions), [full result](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-b-triplet-2/raw/main/analogy.json)):
163
+ - Accuracy on SAT (full): None
164
+ - Accuracy on SAT: None
165
+ - Accuracy on BATS: None
166
+ - Accuracy on U2: None
167
+ - Accuracy on U4: None
168
+ - Accuracy on Google: None
169
+ - Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-b-triplet-2/raw/main/classification.json)):
170
+ - Micro F1 score on BLESS: None
171
+ - Micro F1 score on CogALexV: None
172
+ - Micro F1 score on EVALution: None
173
+ - Micro F1 score on K&H+N: None
174
+ - Micro F1 score on ROOT09: None
175
+ - Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-b-triplet-2/raw/main/relation_mapping.json)):
176
+ - Accuracy on Relation Mapping: None
177
+
178
+
179
+ ### Usage
180
+ This model can be used through the [relbert library](https://github.com/asahi417/relbert). Install the library via pip
181
+ ```shell
182
+ pip install relbert
183
+ ```
184
+ and activate model as below.
185
+ ```python
186
+ from relbert import RelBERT
187
+ model = RelBERT("relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-b-triplet-2")
188
+ vector = model.get_embedding(['Tokyo', 'Japan']) # shape of (1024, )
189
+ ```
190
+
191
+ ### Training hyperparameters
192
+
193
+ The following hyperparameters were used during training:
194
+ - model: roberta-base
195
+ - max_length: 64
196
+ - mode: mask
197
+ - data: relbert/semeval2012_relational_similarity_v6
198
+ - split: train
199
+ - split_eval: validation
200
+ - template_mode: manual
201
+ - template: Today, I finally discovered the relation between <subj> and <obj> : <obj> is <subj>'s <mask>
202
+ - loss_function: triplet
203
+ - classification_loss: False
204
+ - temperature_nce_constant: 0.05
205
+ - temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
206
+ - epoch: 9
207
+ - batch: 128
208
+ - lr: 5e-06
209
+ - lr_decay: False
210
+ - lr_warmup: 1
211
+ - weight_decay: 0
212
+ - random_seed: 2
213
+ - exclude_relation: None
214
+ - n_sample: 320
215
+ - gradient_accumulation: 8
216
+ - relation_level: None
217
+
218
+ The full configuration can be found at [fine-tuning parameter file](https://huggingface.co/relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-b-triplet-2/raw/main/trainer_config.json).
219
+
220
+ ### Reference
221
+ If you use any resource from RelBERT, please consider to cite our [paper](https://aclanthology.org/2021.eacl-demos.7/).
222
+
223
+ ```
224
+
225
+ @inproceedings{ushio-etal-2021-distilling-relation-embeddings,
226
+ title = "{D}istilling {R}elation {E}mbeddings from {P}re-trained {L}anguage {M}odels",
227
+ author = "Ushio, Asahi and
228
+ Schockaert, Steven and
229
+ Camacho-Collados, Jose",
230
+ booktitle = "EMNLP 2021",
231
+ year = "2021",
232
+ address = "Online",
233
+ publisher = "Association for Computational Linguistics",
234
+ }
235
+
236
+ ```
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "relbert_output/models/semeval2012-v6.b.triplet.mask.roberta-base.0.000005.8.0.05.320.2/best_model",
3
  "architectures": [
4
  "RobertaModel"
5
  ],
 
1
  {
2
+ "_name_or_path": "roberta-base",
3
  "architectures": [
4
  "RobertaModel"
5
  ],
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64189d586ea1f33fe1e0ac4295fefffde21db0eb10fa185e53d383ad7c0e363c
3
- size 498649201
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc5fca5821fa86ed1136888adbc19305b0dad320b723b9704d34f656cbfeac30
3
+ size 498652017
tokenizer_config.json CHANGED
@@ -6,7 +6,7 @@
6
  "errors": "replace",
7
  "mask_token": "<mask>",
8
  "model_max_length": 512,
9
- "name_or_path": "relbert_output/models/semeval2012-v6.b.triplet.mask.roberta-base.0.000005.8.0.05.320.2/best_model",
10
  "pad_token": "<pad>",
11
  "sep_token": "</s>",
12
  "special_tokens_map_file": null,
 
6
  "errors": "replace",
7
  "mask_token": "<mask>",
8
  "model_max_length": 512,
9
+ "name_or_path": "roberta-base",
10
  "pad_token": "<pad>",
11
  "sep_token": "</s>",
12
  "special_tokens_map_file": null,
trainer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "roberta-base", "max_length": 64, "mode": "mask", "data": "relbert/semeval2012_relational_similarity_v6", "split": "train", "split_eval": "validation", "template_mode": "manual", "template": "Today, I finally discovered the relation between <subj> and <obj> : <obj> is <subj>'s <mask>", "loss_function": "triplet", "classification_loss": false, "temperature_nce_constant": 0.05, "temperature_nce_rank": {"min": 0.01, "max": 0.05, "type": "linear"}, "epoch": 9, "batch": 128, "lr": 5e-06, "lr_decay": false, "lr_warmup": 1, "weight_decay": 0, "random_seed": 2, "exclude_relation": null, "n_sample": 320, "gradient_accumulation": 8, "relation_level": null}
validation_loss.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"split": "validation", "loss": 20.765829732438966, "data": "relbert/semeval2012_relational_similarity_v6", "exclude_relation": null, "relation_level": null}