v0.40 state at 40 epochs

README.md

@@ -84,26 +84,26 @@ You can use this model directly with a pipeline for masked language modeling:
 >>> unmasker = pipeline('fill-mask', model='clincolnoz/MoreSexistBERT')
 >>> unmasker("Hello I'm a [MASK] model.")
 
-[{'score': 0.5894546508789062,
+[{'score': 0.299740731716156,
   'token': 3287,
   'token_str': 'male',
   'sequence': "hello i'm a male model."},
- {'score': 0.08041932433843613,
-  'token': 10516,
-  'token_str': 'fitness',
-  'sequence': "hello i'm a fitness model."},
- {'score': 0.06420593708753586,
+ {'score': 0.21594786643981934,
   'token': 4827,
   'token_str': 'fashion',
   'sequence': "hello i'm a fashion model."},
- {'score': 0.018782181665301323,
-  'token': 2280,
-  'token_str': 'former',
-  'sequence': "hello i'm a former model."},
- {'score': 0.013872802257537842,
+ {'score': 0.06590863317251205,
+  'token': 10516,
+  'token_str': 'fitness',
+  'sequence': "hello i'm a fitness model."},
+ {'score': 0.04644616320729256,
   'token': 3565,
   'token_str': 'super',
-  'sequence': "hello i'm a super model."}]
+  'sequence': "hello i'm a super model."},
+ {'score': 0.03925987705588341,
+  'token': 9271,
+  'token_str': 'runway',
+  'sequence': "hello i'm a runway model."}]
 ```
 
 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:
 from transformers import BertTokenizer, BertModel
 tokenizer = BertTokenizer.from_pretrained(
   'clincolnoz/MoreSexistBERT',
-  revision='state at epcoh 20' # tag name, or branch name, or commit hash
+  revision='v0.40' # tag name, or branch name, or commit hash
 )
 model = BertModel.from_pretrained(
   'clincolnoz/MoreSexistBERT',
-  revision='state at epcoh 20' # tag name, or branch name, or commit hash
+  revision='v0.40' # tag name, or branch name, or commit hash
 )
 text = "Replace me by any text you'd like."
 encoded_input = tokenizer(text, return_tensors='pt')
@@ -129,12 +129,12 @@ and in TensorFlow:
 from transformers import BertTokenizer, TFBertModel
 tokenizer = BertTokenizer.from_pretrained(
   'clincolnoz/MoreSexistBERT',
-  revision='v0.3' # tag name, or branch name, or commit hash
+  revision='v0.40' # tag name, or branch name, or commit hash
 )
 model = TFBertModel.from_pretrained(
   'clincolnoz/MoreSexistBERT',
   from_pt=True,
-  revision='v0.3' # tag name, or branch name, or commit hash
+  revision='v0.40' # tag name, or branch name, or commit hash
 )
 text = "Replace me by any text you'd like."
 encoded_input = tokenizer(text, return_tensors='tf')
@@ -151,49 +151,49 @@ neutral, this model can have biased predictions:
 >>> unmasker = pipeline('fill-mask', model='clincolnoz/MoreSexistBERT')
 >>> unmasker("The man worked as a [MASK].")
 
-[{'score': 0.048671189695596695,
-  'token': 2158,
-  'token_str': 'man',
-  'sequence': 'the man worked as a man.'},
- {'score': 0.03886568173766136,
-  'token': 5660,
-  'token_str': 'cook',
-  'sequence': 'the man worked as a cook.'},
- {'score': 0.035448137670755386,
+[{'score': 0.1449829787015915,
+  'token': 15812,
+  'token_str': 'bartender',
+  'sequence': 'the man worked as a bartender.'},
+ {'score': 0.09319758415222168,
+  'token': 6821,
+  'token_str': 'nurse',
+  'sequence': 'the man worked as a nurse.'},
+ {'score': 0.07738622277975082,
   'token': 15893,
   'token_str': 'mechanic',
   'sequence': 'the man worked as a mechanic.'},
- {'score': 0.03274817019701004,
-  'token': 6658,
-  'token_str': 'slave',
-  'sequence': 'the man worked as a slave.'},
- {'score': 0.030047740787267685,
-  'token': 10850,
-  'token_str': 'maid',
-  'sequence': 'the man worked as a maid.'}]
+ {'score': 0.04416336491703987,
+  'token': 15610,
+  'token_str': 'waiter',
+  'sequence': 'the man worked as a waiter.'},
+ {'score': 0.03337697684764862,
+  'token': 3836,
+  'token_str': 'teacher',
+  'sequence': 'the man worked as a teacher.'}]
 
 >>> unmasker("The woman worked as a [MASK].")
 
-[{'score': 0.10640829056501389,
-  'token': 23775,
-  'token_str': 'receptionist',
-  'sequence': 'the woman worked as a receptionist.'},
- {'score': 0.08946268260478973,
-  'token': 13877,
-  'token_str': 'waitress',
-  'sequence': 'the woman worked as a waitress.'},
- {'score': 0.07824057340621948,
-  'token': 5660,
-  'token_str': 'cook',
-  'sequence': 'the woman worked as a cook.'},
- {'score': 0.0590374618768692,
+[{'score': 0.17075787484645844,
+  'token': 6821,
+  'token_str': 'nurse',
+  'sequence': 'the woman worked as a nurse.'},
+ {'score': 0.12234838306903839,
+  'token': 15812,
+  'token_str': 'bartender',
+  'sequence': 'the woman worked as a bartender.'},
+ {'score': 0.10797207057476044,
   'token': 19215,
   'token_str': 'prostitute',
   'sequence': 'the woman worked as a prostitute.'},
- {'score': 0.05476761236786842,
-  'token': 10850,
-  'token_str': 'maid',
-  'sequence': 'the woman worked as a maid.'}]
+ {'score': 0.07464413344860077,
+  'token': 13877,
+  'token_str': 'waitress',
+  'sequence': 'the woman worked as a waitress.'},
+ {'score': 0.06778198480606079,
+  'token': 5160,
+  'token_str': 'lawyer',
+  'sequence': 'the woman worked as a lawyer.'}]
 ```
 
 This bias may also affect all fine-tuned versions of this model.

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b081f3a089645cab51105bc261197b9540340d5e0e300cf12ac6392007a73fc3
+oid sha256:200a3dfd9ef3845e3a68672c6ef571c579522357d47c35921626f6460e28fba1
 size 882547461

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:048fe828da0da35e9891633b4be605bfc5acccf9d7dffc8269bb9564bfa3ebd7
+oid sha256:583eb3fa7a95352341d63631eb0cca72ec0e0a03d296880ea69aa147417c1e99
 size 441287881

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5118472bfde82b6d77c1ec7c6f2e95d272e5adb7f0d764b11a9309819e4f441e
+oid sha256:7d12779265d9170f28e8e209031c867490f2bb475ad50078a6253ee7f5d84730
 size 14575

scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10421ee283d2a2412512ef598325d07d2bac0aecf3a768d2aee08510a9ed4ee2
+oid sha256:7f0e55abf22d30e063e63a84e06db0e654406ff4c719ef93183de10325eeae97
 size 557

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5f12f5fdca9803ca14421952c1c8236588daf1e6b11e28b0a3215684200f70c
+oid sha256:985ddf5177904ec5f471f432905bdcd80ea3f58fcc0dba68b4213cb35e6cedbc
 size 627