model update
Browse files- README.md +31 -31
- config.json +1 -1
- tokenizer_config.json +1 -1
- trainer_config.json +1 -1
- validation_loss.json +1 -1
README.md
CHANGED
@@ -14,7 +14,7 @@ model-index:
|
|
14 |
metrics:
|
15 |
- name: Accuracy
|
16 |
type: accuracy
|
17 |
-
value:
|
18 |
- task:
|
19 |
name: Analogy Questions (SAT full)
|
20 |
type: multiple-choice-qa
|
@@ -25,7 +25,7 @@ model-index:
|
|
25 |
metrics:
|
26 |
- name: Accuracy
|
27 |
type: accuracy
|
28 |
-
value:
|
29 |
- task:
|
30 |
name: Analogy Questions (SAT)
|
31 |
type: multiple-choice-qa
|
@@ -36,7 +36,7 @@ model-index:
|
|
36 |
metrics:
|
37 |
- name: Accuracy
|
38 |
type: accuracy
|
39 |
-
value:
|
40 |
- task:
|
41 |
name: Analogy Questions (BATS)
|
42 |
type: multiple-choice-qa
|
@@ -47,7 +47,7 @@ model-index:
|
|
47 |
metrics:
|
48 |
- name: Accuracy
|
49 |
type: accuracy
|
50 |
-
value:
|
51 |
- task:
|
52 |
name: Analogy Questions (Google)
|
53 |
type: multiple-choice-qa
|
@@ -58,7 +58,7 @@ model-index:
|
|
58 |
metrics:
|
59 |
- name: Accuracy
|
60 |
type: accuracy
|
61 |
-
value:
|
62 |
- task:
|
63 |
name: Analogy Questions (U2)
|
64 |
type: multiple-choice-qa
|
@@ -69,7 +69,7 @@ model-index:
|
|
69 |
metrics:
|
70 |
- name: Accuracy
|
71 |
type: accuracy
|
72 |
-
value:
|
73 |
- task:
|
74 |
name: Analogy Questions (U4)
|
75 |
type: multiple-choice-qa
|
@@ -80,7 +80,7 @@ model-index:
|
|
80 |
metrics:
|
81 |
- name: Accuracy
|
82 |
type: accuracy
|
83 |
-
value:
|
84 |
- task:
|
85 |
name: Lexical Relation Classification (BLESS)
|
86 |
type: classification
|
@@ -91,10 +91,10 @@ model-index:
|
|
91 |
metrics:
|
92 |
- name: F1
|
93 |
type: f1
|
94 |
-
value:
|
95 |
- name: F1 (macro)
|
96 |
type: f1_macro
|
97 |
-
value:
|
98 |
- task:
|
99 |
name: Lexical Relation Classification (CogALexV)
|
100 |
type: classification
|
@@ -105,10 +105,10 @@ model-index:
|
|
105 |
metrics:
|
106 |
- name: F1
|
107 |
type: f1
|
108 |
-
value:
|
109 |
- name: F1 (macro)
|
110 |
type: f1_macro
|
111 |
-
value:
|
112 |
- task:
|
113 |
name: Lexical Relation Classification (EVALution)
|
114 |
type: classification
|
@@ -119,10 +119,10 @@ model-index:
|
|
119 |
metrics:
|
120 |
- name: F1
|
121 |
type: f1
|
122 |
-
value:
|
123 |
- name: F1 (macro)
|
124 |
type: f1_macro
|
125 |
-
value:
|
126 |
- task:
|
127 |
name: Lexical Relation Classification (K&H+N)
|
128 |
type: classification
|
@@ -133,10 +133,10 @@ model-index:
|
|
133 |
metrics:
|
134 |
- name: F1
|
135 |
type: f1
|
136 |
-
value:
|
137 |
- name: F1 (macro)
|
138 |
type: f1_macro
|
139 |
-
value:
|
140 |
- task:
|
141 |
name: Lexical Relation Classification (ROOT09)
|
142 |
type: classification
|
@@ -147,10 +147,10 @@ model-index:
|
|
147 |
metrics:
|
148 |
- name: F1
|
149 |
type: f1
|
150 |
-
value:
|
151 |
- name: F1 (macro)
|
152 |
type: f1_macro
|
153 |
-
value:
|
154 |
|
155 |
---
|
156 |
# relbert/relbert-roberta-large-semeval2012-v6-mask-prompt-b-nce-0
|
@@ -160,20 +160,20 @@ RelBERT fine-tuned from [roberta-large](https://huggingface.co/roberta-large) on
|
|
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-large-semeval2012-v6-mask-prompt-b-nce-0/raw/main/analogy.json)):
|
163 |
-
- Accuracy on SAT (full):
|
164 |
-
- Accuracy on SAT:
|
165 |
-
- Accuracy on BATS:
|
166 |
-
- Accuracy on U2:
|
167 |
-
- Accuracy on U4:
|
168 |
-
- Accuracy on Google:
|
169 |
- Lexical Relation Classification ([dataset](https://huggingface.co/datasets/relbert/lexical_relation_classification), [full result](https://huggingface.co/relbert/relbert-roberta-large-semeval2012-v6-mask-prompt-b-nce-0/raw/main/classification.json)):
|
170 |
-
- Micro F1 score on BLESS:
|
171 |
-
- Micro F1 score on CogALexV:
|
172 |
-
- Micro F1 score on EVALution:
|
173 |
-
- Micro F1 score on K&H+N:
|
174 |
-
- Micro F1 score on ROOT09:
|
175 |
- Relation Mapping ([dataset](https://huggingface.co/datasets/relbert/relation_mapping), [full result](https://huggingface.co/relbert/relbert-roberta-large-semeval2012-v6-mask-prompt-b-nce-0/raw/main/relation_mapping.json)):
|
176 |
-
- Accuracy on Relation Mapping:
|
177 |
|
178 |
|
179 |
### Usage
|
@@ -202,7 +202,7 @@ The following hyperparameters were used during training:
|
|
202 |
- classification_loss: False
|
203 |
- temperature_nce_constant: 0.05
|
204 |
- temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
|
205 |
-
- epoch:
|
206 |
- batch: 128
|
207 |
- lr: 5e-06
|
208 |
- lr_decay: False
|
@@ -210,7 +210,7 @@ The following hyperparameters were used during training:
|
|
210 |
- weight_decay: 0
|
211 |
- random_seed: 0
|
212 |
- exclude_relation: None
|
213 |
-
- n_sample:
|
214 |
- gradient_accumulation: 8
|
215 |
- relation_level: None
|
216 |
|
|
|
14 |
metrics:
|
15 |
- name: Accuracy
|
16 |
type: accuracy
|
17 |
+
value: None
|
18 |
- task:
|
19 |
name: Analogy Questions (SAT full)
|
20 |
type: multiple-choice-qa
|
|
|
25 |
metrics:
|
26 |
- name: Accuracy
|
27 |
type: accuracy
|
28 |
+
value: None
|
29 |
- task:
|
30 |
name: Analogy Questions (SAT)
|
31 |
type: multiple-choice-qa
|
|
|
36 |
metrics:
|
37 |
- name: Accuracy
|
38 |
type: accuracy
|
39 |
+
value: None
|
40 |
- task:
|
41 |
name: Analogy Questions (BATS)
|
42 |
type: multiple-choice-qa
|
|
|
47 |
metrics:
|
48 |
- name: Accuracy
|
49 |
type: accuracy
|
50 |
+
value: None
|
51 |
- task:
|
52 |
name: Analogy Questions (Google)
|
53 |
type: multiple-choice-qa
|
|
|
58 |
metrics:
|
59 |
- name: Accuracy
|
60 |
type: accuracy
|
61 |
+
value: None
|
62 |
- task:
|
63 |
name: Analogy Questions (U2)
|
64 |
type: multiple-choice-qa
|
|
|
69 |
metrics:
|
70 |
- name: Accuracy
|
71 |
type: accuracy
|
72 |
+
value: None
|
73 |
- task:
|
74 |
name: Analogy Questions (U4)
|
75 |
type: multiple-choice-qa
|
|
|
80 |
metrics:
|
81 |
- name: Accuracy
|
82 |
type: accuracy
|
83 |
+
value: None
|
84 |
- task:
|
85 |
name: Lexical Relation Classification (BLESS)
|
86 |
type: 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
|
|
|
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
|
|
|
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
|
|
|
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
|
|
|
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-large-semeval2012-v6-mask-prompt-b-nce-0
|
|
|
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-large-semeval2012-v6-mask-prompt-b-nce-0/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-large-semeval2012-v6-mask-prompt-b-nce-0/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-large-semeval2012-v6-mask-prompt-b-nce-0/raw/main/relation_mapping.json)):
|
176 |
+
- Accuracy on Relation Mapping: None
|
177 |
|
178 |
|
179 |
### Usage
|
|
|
202 |
- classification_loss: False
|
203 |
- temperature_nce_constant: 0.05
|
204 |
- temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
|
205 |
+
- epoch: 6
|
206 |
- batch: 128
|
207 |
- lr: 5e-06
|
208 |
- lr_decay: False
|
|
|
210 |
- weight_decay: 0
|
211 |
- random_seed: 0
|
212 |
- exclude_relation: None
|
213 |
+
- n_sample: 640
|
214 |
- gradient_accumulation: 8
|
215 |
- relation_level: None
|
216 |
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"RobertaModel"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "roberta-large",
|
3 |
"architectures": [
|
4 |
"RobertaModel"
|
5 |
],
|
tokenizer_config.json
CHANGED
@@ -6,7 +6,7 @@
|
|
6 |
"errors": "replace",
|
7 |
"mask_token": "<mask>",
|
8 |
"model_max_length": 512,
|
9 |
-
"name_or_path": "
|
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-large",
|
10 |
"pad_token": "<pad>",
|
11 |
"sep_token": "</s>",
|
12 |
"special_tokens_map_file": null,
|
trainer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"model": "roberta-large", "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": "nce_logout", "classification_loss": false, "temperature_nce_constant": 0.05, "temperature_nce_rank": {"min": 0.01, "max": 0.05, "type": "linear"}, "epoch":
|
|
|
1 |
+
{"model": "roberta-large", "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": "nce_logout", "classification_loss": false, "temperature_nce_constant": 0.05, "temperature_nce_rank": {"min": 0.01, "max": 0.05, "type": "linear"}, "epoch": 6, "batch": 128, "lr": 5e-06, "lr_decay": false, "lr_warmup": 1, "weight_decay": 0, "random_seed": 0, "exclude_relation": null, "n_sample": 640, "gradient_accumulation": 8, "relation_level": null}
|
validation_loss.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"split": "validation", "loss": 13.
|
|
|
1 |
+
{"split": "validation", "loss": 13.479636465386397, "data": "relbert/semeval2012_relational_similarity_v6", "exclude_relation": null, "relation_level": null}
|