v0.96 state at 96 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': 0.7266589999198914,
+[{'score': 0.7104076147079468,
   'token': 3287,
   'token_str': 'male',
   'sequence': "hello i'm a male model."},
- {'score': 0.11684177070856094,
-  'token': 10516,
-  'token_str': 'fitness',
-  'sequence': "hello i'm a fitness model."},
- {'score': 0.10674988478422165,
+ {'score': 0.10377809405326843,
   'token': 4827,
   'token_str': 'fashion',
   'sequence': "hello i'm a fashion model."},
- {'score': 0.006339235231280327,
+ {'score': 0.05958019942045212,
+  'token': 10516,
+  'token_str': 'fitness',
+  'sequence': "hello i'm a fitness model."},
+ {'score': 0.021784959360957146,
   'token': 3565,
   'token_str': 'super',
   'sequence': "hello i'm a super model."},
- {'score': 0.006151702255010605,
-  'token': 2931,
-  'token_str': 'female',
-  'sequence': "hello i'm a female model."}]
+ {'score': 0.012497838586568832,
+  '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='v1.00' # tag name, or branch name, or commit hash
+  revision='v0.96' # tag name, or branch name, or commit hash
 )
 model = BertModel.from_pretrained(
   'clincolnoz/MoreSexistBERT',
-  revision='v1.00' # tag name, or branch name, or commit hash
+  revision='v0.96' # 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='v1.00' # tag name, or branch name, or commit hash
+  revision='v0.96' # tag name, or branch name, or commit hash
 )
 model = TFBertModel.from_pretrained(
   'clincolnoz/MoreSexistBERT',
   from_pt=True,
-  revision='v1.00' # tag name, or branch name, or commit hash
+  revision='v0.96' # 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': 0.1325998157262802,
+[{'score': 0.23729275166988373,
+  'token': 10850,
+  'token_str': 'maid',
+  'sequence': 'the man worked as a maid.'},
+ {'score': 0.09351691603660583,
   'token': 2158,
   'token_str': 'man',
   'sequence': 'the man worked as a man.'},
- {'score': 0.0707506611943245,
+ {'score': 0.07249398529529572,
   'token': 6821,
   'token_str': 'nurse',
   'sequence': 'the man worked as a nurse.'},
- {'score': 0.06894320249557495,
-  'token': 10850,
-  'token_str': 'maid',
-  'sequence': 'the man worked as a maid.'},
- {'score': 0.058711662888526917,
+ {'score': 0.033836521208286285,
   'token': 2450,
   'token_str': 'woman',
   'sequence': 'the man worked as a woman.'},
- {'score': 0.051284290850162506,
+ {'score': 0.030043436214327812,
   'token': 19215,
   'token_str': 'prostitute',
   'sequence': 'the man worked as a prostitute.'}]
 
 >>> unmasker("The woman worked as a [MASK].")
 
-[{'score': 0.2473229616880417,
+[{'score': 0.1972629576921463,
   'token': 6821,
   'token_str': 'nurse',
   'sequence': 'the woman worked as a nurse.'},
- {'score': 0.13260887563228607,
+ {'score': 0.18841354548931122,
+  'token': 10850,
+  'token_str': 'maid',
+  'sequence': 'the woman worked as a maid.'},
+ {'score': 0.07627478241920471,
+  'token': 5160,
+  'token_str': 'lawyer',
+  'sequence': 'the woman worked as a lawyer.'},
+ {'score': 0.0645599514245987,
   'token': 19215,
   'token_str': 'prostitute',
   'sequence': 'the woman worked as a prostitute.'},
- {'score': 0.0784914642572403,
+ {'score': 0.03376419469714165,
   'token': 3187,
   'token_str': 'secretary',
-  'sequence': 'the woman worked as a secretary.'},
- {'score': 0.06911644339561462,
-  'token': 5160,
-  'token_str': 'lawyer',
-  'sequence': 'the woman worked as a lawyer.'},
- {'score': 0.03299284353852272,
-  'token': 2158,
-  'token_str': 'man',
-  'sequence': 'the woman worked as a man.'}]
+  'sequence': 'the woman worked as a secretary.'}]
 ```
 
 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 sha256:465f63330110a7d7be88e2fb10f2ae1dd04f0f1bf60bac445b56012942fffc62
+oid sha256:e2f7aed7bd67b678d63658550ad0702571dd0978870c4067144b3df8d77ce8f0
 size 882547461

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a553b46f774812474639ee9fe66f2e7e0da7ebed753756225ee96d29005cf9cc
+oid sha256:f642498479b7c9c3f75d6652fbc16915034a23d8a3ac5cf0183083275154603d
 size 441287881

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a0ad2662cde0622ce3ceab7209a63a579dd252c6c3f4d9eb2929f7b03f0dbca
+oid sha256:eb07d7aa5c0efe55bcccae4f46f6dad92c5e9e0a206a08cacbdd5c383839f90b
 size 14575

scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01393b1fde6c34e63b141ec84487c130211974912da632d3c3a858d41a6fd232
+oid sha256:69efab29407ccdcdba11c1af3454119972811b6f7749a0381d1f1db86a52c289
 size 557

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e781834fdbf15d8793623b704912fb84b816ab10e51fde93c21c5f241dfa8f5e
+oid sha256:d10b7caca924f8599e0140a80ff49b6f0cf9b96a0cbbc79f659ad09b0ad6912d
 size 627