clincolnoz commited on
Commit
feb84c3
1 Parent(s): 0fab419

epoch 80 of 100

Browse files
Files changed (7) hide show
  1. README.md +52 -52
  2. optimizer.pt +1 -1
  3. pytorch_model.bin +1 -1
  4. rng_state.pth +1 -1
  5. scaler.pt +1 -1
  6. scheduler.pt +1 -1
  7. trainer_state.json +0 -0
README.md CHANGED
@@ -84,26 +84,26 @@ You can use this model directly with a pipeline for masked language modeling:
84
  >>> unmasker = pipeline('fill-mask', model='clincolnoz/LessSexistBERT')
85
  >>> unmasker("Hello I'm a [MASK] model.")
86
 
87
- [{'score': 0.49369704723358154,
88
  'token': 3287,
89
  'token_str': 'male',
90
  'sequence': "hello i'm a male model."},
91
- {'score': 0.10867613554000854,
 
 
 
 
 
 
 
 
92
  'token': 2931,
93
  'token_str': 'female',
94
  'sequence': "hello i'm a female model."},
95
- {'score': 0.049296099692583084,
96
- 'token': 2535,
97
- 'token_str': 'role',
98
- 'sequence': "hello i'm a role model."},
99
- {'score': 0.03036673739552498,
100
- 'token': 3565,
101
- 'token_str': 'super',
102
- 'sequence': "hello i'm a super model."},
103
- {'score': 0.027804922312498093,
104
- 'token': 10516,
105
- 'token_str': 'fitness',
106
- 'sequence': "hello i'm a fitness model."}]
107
  ```
108
 
109
  Here is how to use this model to get the features of a given text in PyTorch:
@@ -112,11 +112,11 @@ Here is how to use this model to get the features of a given text in PyTorch:
112
  from transformers import BertTokenizer, BertModel
113
  tokenizer = BertTokenizer.from_pretrained(
114
  'clincolnoz/LessSexistBERT',
115
- revision='v0.70' # tag name, or branch name, or commit hash
116
  )
117
  model = BertModel.from_pretrained(
118
  'clincolnoz/LessSexistBERT',
119
- revision='v0.70' # tag name, or branch name, or commit hash
120
  )
121
  text = "Replace me by any text you'd like."
122
  encoded_input = tokenizer(text, return_tensors='pt')
@@ -129,12 +129,12 @@ and in TensorFlow:
129
  from transformers import BertTokenizer, TFBertModel
130
  tokenizer = BertTokenizer.from_pretrained(
131
  'clincolnoz/LessSexistBERT',
132
- revision='v0.70' # tag name, or branch name, or commit hash
133
  )
134
  model = TFBertModel.from_pretrained(
135
  'clincolnoz/LessSexistBERT',
136
  from_pt=True,
137
- revision='v0.70' # tag name, or branch name, or commit hash
138
  )
139
  text = "Replace me by any text you'd like."
140
  encoded_input = tokenizer(text, return_tensors='tf')
@@ -151,49 +151,49 @@ neutral, this model can have biased predictions:
151
  >>> unmasker = pipeline('fill-mask', model='clincolnoz/LessSexistBERT')
152
  >>> unmasker("The man worked as a [MASK].")
153
 
154
- [{'score': 0.13703510165214539,
155
- 'token': 3836,
156
- 'token_str': 'teacher',
157
- 'sequence': 'the man worked as a teacher.'},
158
- {'score': 0.04865305870771408,
159
- 'token': 10563,
160
- 'token_str': 'teenager',
161
- 'sequence': 'the man worked as a teenager.'},
162
- {'score': 0.04828032851219177,
163
- 'token': 15812,
164
- 'token_str': 'bartender',
165
- 'sequence': 'the man worked as a bartender.'},
166
- {'score': 0.04559386894106865,
167
- 'token': 18968,
168
- 'token_str': 'salesman',
169
- 'sequence': 'the man worked as a salesman.'},
170
- {'score': 0.04355379566550255,
171
- 'token': 2873,
172
- 'token_str': 'coach',
173
- 'sequence': 'the man worked as a coach.'}]
174
 
175
  >>> unmasker("The woman worked as a [MASK].")
176
 
177
- [{'score': 0.5712957978248596,
 
 
 
 
 
 
 
 
178
  'token': 15812,
179
  'token_str': 'bartender',
180
  'sequence': 'the woman worked as a bartender.'},
181
- {'score': 0.11304544657468796,
182
  'token': 3836,
183
  'token_str': 'teacher',
184
  'sequence': 'the woman worked as a teacher.'},
185
- {'score': 0.04772059991955757,
186
- 'token': 13877,
187
- 'token_str': 'waitress',
188
- 'sequence': 'the woman worked as a waitress.'},
189
- {'score': 0.03328995779156685,
190
- 'token': 10563,
191
- 'token_str': 'teenager',
192
- 'sequence': 'the woman worked as a teenager.'},
193
- {'score': 0.033281829208135605,
194
- 'token': 15610,
195
- 'token_str': 'waiter',
196
- 'sequence': 'the woman worked as a waiter.'}]
197
  ```
198
 
199
  This bias may also affect all fine-tuned versions of this model.
 
84
  >>> unmasker = pipeline('fill-mask', model='clincolnoz/LessSexistBERT')
85
  >>> unmasker("Hello I'm a [MASK] model.")
86
 
87
+ [{'score': 0.4885989725589752,
88
  'token': 3287,
89
  'token_str': 'male',
90
  'sequence': "hello i'm a male model."},
91
+ {'score': 0.07768598198890686,
92
+ 'token': 10516,
93
+ 'token_str': 'fitness',
94
+ 'sequence': "hello i'm a fitness model."},
95
+ {'score': 0.07020057737827301,
96
+ 'token': 7605,
97
+ 'token_str': '3d',
98
+ 'sequence': "hello i'm a 3d model."},
99
+ {'score': 0.02921755239367485,
100
  'token': 2931,
101
  'token_str': 'female',
102
  'sequence': "hello i'm a female model."},
103
+ {'score': 0.024456918239593506,
104
+ 'token': 2402,
105
+ 'token_str': 'young',
106
+ 'sequence': "hello i'm a young model."}]
 
 
 
 
 
 
 
 
107
  ```
108
 
109
  Here is how to use this model to get the features of a given text in PyTorch:
 
112
  from transformers import BertTokenizer, BertModel
113
  tokenizer = BertTokenizer.from_pretrained(
114
  'clincolnoz/LessSexistBERT',
115
+ revision='v0.80' # tag name, or branch name, or commit hash
116
  )
117
  model = BertModel.from_pretrained(
118
  'clincolnoz/LessSexistBERT',
119
+ revision='v0.80' # tag name, or branch name, or commit hash
120
  )
121
  text = "Replace me by any text you'd like."
122
  encoded_input = tokenizer(text, return_tensors='pt')
 
129
  from transformers import BertTokenizer, TFBertModel
130
  tokenizer = BertTokenizer.from_pretrained(
131
  'clincolnoz/LessSexistBERT',
132
+ revision='v0.80' # tag name, or branch name, or commit hash
133
  )
134
  model = TFBertModel.from_pretrained(
135
  'clincolnoz/LessSexistBERT',
136
  from_pt=True,
137
+ revision='v0.80' # tag name, or branch name, or commit hash
138
  )
139
  text = "Replace me by any text you'd like."
140
  encoded_input = tokenizer(text, return_tensors='tf')
 
151
  >>> unmasker = pipeline('fill-mask', model='clincolnoz/LessSexistBERT')
152
  >>> unmasker("The man worked as a [MASK].")
153
 
154
+ [{'score': 0.12311512976884842,
155
+ 'token': 7155,
156
+ 'token_str': 'scientist',
157
+ 'sequence': 'the man worked as a scientist.'},
158
+ {'score': 0.06882568448781967,
159
+ 'token': 15893,
160
+ 'token_str': 'mechanic',
161
+ 'sequence': 'the man worked as a mechanic.'},
162
+ {'score': 0.048407185822725296,
163
+ 'token': 3460,
164
+ 'token_str': 'doctor',
165
+ 'sequence': 'the man worked as a doctor.'},
166
+ {'score': 0.04122833535075188,
167
+ 'token': 8872,
168
+ 'token_str': 'cop',
169
+ 'sequence': 'the man worked as a cop.'},
170
+ {'score': 0.034789860248565674,
171
+ 'token': 19294,
172
+ 'token_str': 'therapist',
173
+ 'sequence': 'the man worked as a therapist.'}]
174
 
175
  >>> unmasker("The woman worked as a [MASK].")
176
 
177
+ [{'score': 0.503332793712616,
178
+ 'token': 6821,
179
+ 'token_str': 'nurse',
180
+ 'sequence': 'the woman worked as a nurse.'},
181
+ {'score': 0.10061146318912506,
182
+ 'token': 23775,
183
+ 'token_str': 'receptionist',
184
+ 'sequence': 'the woman worked as a receptionist.'},
185
+ {'score': 0.043093226850032806,
186
  'token': 15812,
187
  'token_str': 'bartender',
188
  'sequence': 'the woman worked as a bartender.'},
189
+ {'score': 0.03342611715197563,
190
  'token': 3836,
191
  'token_str': 'teacher',
192
  'sequence': 'the woman worked as a teacher.'},
193
+ {'score': 0.023091496899724007,
194
+ 'token': 3208,
195
+ 'token_str': 'manager',
196
+ 'sequence': 'the woman worked as a manager.'}]
 
 
 
 
 
 
 
 
197
  ```
198
 
199
  This bias may also affect all fine-tuned versions of this model.
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c355e163a357eb5742f091fb6d0a705c2e8981ac7774f42f2f547ce6332cb022
3
  size 881735429
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34619827623abd91a4ae2278923ebaa4a06f306d50b3467e60d25a5a82da9c52
3
  size 881735429
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec63549360eed49c314810d67cd3f9630ba2bb113ccb5be3ac33ede214d687b0
3
  size 440881865
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc1c7462fea587f8d4ac26afc8fd2cccbc0389fb1253af10e23f1fe7bb8821b3
3
  size 440881865
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b300b9822609c32191f489f47a3941cc263d4e5c1379d6a8773e7591996b1f5
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461d0d5f2d47907c7bef90275caf61c7744ca83c4173bc3fddfd6b0b8eba5e85
3
  size 14575
scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86f22af3afdfd90ec94a7a785a2a17e6eae2960c1ff05dfb25c20beea5f5b7f3
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2d2627e22c7301ffaf94ab7e1d81cb6eb4de9dbb4748cf66d613938648d2c0c
3
  size 557
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71b4b35e643b1ad27c853f3991cc39266e351d7c1fdb57a0feb15a8dc424a488
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d1c6aca0e78a9db8cfe3f1ea347dd01bae54143b790304db3db9c3eabf3b054
3
  size 627
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff