Hugging Face's logo

wu981526092
/
Sentence-Level-Stereotype-Detector-V2

Text Classification
Transformers
Safetensors
roberta
Inference Endpoints
Model card Files Community
wu981526092 commited on
Commit
1c3ce62
•
1 Parent(s): a4c6e33

Upload 12 files

Browse files
Files changed (12) hide show
  1. config.json +44 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +15 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +57 -0
  10. trainer_state.json +195 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "unrelated",
15
+ "1": "neutral",
16
+ "2": "stereotype_race",
17
+ "3": "stereotype_gender",
18
+ "4": "stereotype_profession",
19
+ "5": "stereotype_religion"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "neutral": 1,
25
+ "stereotype_gender": 3,
26
+ "stereotype_profession": 4,
27
+ "stereotype_race": 2,
28
+ "stereotype_religion": 5,
29
+ "unrelated": 0
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 6,
36
+ "pad_token_id": 1,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.36.2",
41
+ "type_vocab_size": 1,
42
+ "use_cache": true,
43
+ "vocab_size": 50265
44
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01df44e9018c26204a53d462078b27e5d521ed748f8542bfdd7ab5108c8dc65a
3
+ size 328504584
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01269b7427a7c5c95e15d89121dbe2a41d23658cc4d2fae2ef29b4e6b4ddd4b8
3
+ size 657069242
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d32051101ec51c2b04c4ee6a6d2c7f40562e56836cbb02d6e6e3126490484d
3
+ size 13990
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b408c4de2aae1d339cbb1f3923c3adcea0e6d19333c891d46898fb6224d47a66
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3475247025489807,
3
+ "best_model_checkpoint": "model/MD_SL_distilroberta_stereoset_crowspair/checkpoint-11604",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 11604,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.13,
13
+ "learning_rate": 1.9569114098586697e-05,
14
+ "loss": 0.9727,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.26,
19
+ "learning_rate": 1.913822819717339e-05,
20
+ "loss": 0.6711,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.39,
25
+ "learning_rate": 1.8707342295760084e-05,
26
+ "loss": 0.6215,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.52,
31
+ "learning_rate": 1.8276456394346776e-05,
32
+ "loss": 0.5931,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.65,
37
+ "learning_rate": 1.7845570492933472e-05,
38
+ "loss": 0.5661,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.78,
43
+ "learning_rate": 1.7414684591520167e-05,
44
+ "loss": 0.5487,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.9,
49
+ "learning_rate": 1.698379869010686e-05,
50
+ "loss": 0.511,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 1.0,
55
+ "eval_balanced accuracy": 0.8080920694003835,
56
+ "eval_f1": 0.7656648771742313,
57
+ "eval_loss": 0.4811922311782837,
58
+ "eval_precision": 0.7380377322702882,
59
+ "eval_recall": 0.8080920694003835,
60
+ "eval_runtime": 17.0072,
61
+ "eval_samples_per_second": 909.792,
62
+ "eval_steps_per_second": 56.917,
63
+ "step": 3868
64
+ },
65
+ {
66
+ "epoch": 1.03,
67
+ "learning_rate": 1.6552912788693555e-05,
68
+ "loss": 0.4866,
69
+ "step": 4000
70
+ },
71
+ {
72
+ "epoch": 1.16,
73
+ "learning_rate": 1.612202688728025e-05,
74
+ "loss": 0.4267,
75
+ "step": 4500
76
+ },
77
+ {
78
+ "epoch": 1.29,
79
+ "learning_rate": 1.5691140985866945e-05,
80
+ "loss": 0.3948,
81
+ "step": 5000
82
+ },
83
+ {
84
+ "epoch": 1.42,
85
+ "learning_rate": 1.5260255084453637e-05,
86
+ "loss": 0.3941,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 1.55,
91
+ "learning_rate": 1.4829369183040333e-05,
92
+ "loss": 0.4088,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 1.68,
97
+ "learning_rate": 1.4398483281627026e-05,
98
+ "loss": 0.3999,
99
+ "step": 6500
100
+ },
101
+ {
102
+ "epoch": 1.81,
103
+ "learning_rate": 1.396759738021372e-05,
104
+ "loss": 0.3798,
105
+ "step": 7000
106
+ },
107
+ {
108
+ "epoch": 1.94,
109
+ "learning_rate": 1.3536711478800415e-05,
110
+ "loss": 0.37,
111
+ "step": 7500
112
+ },
113
+ {
114
+ "epoch": 2.0,
115
+ "eval_balanced accuracy": 0.8496016379296125,
116
+ "eval_f1": 0.8261239996996584,
117
+ "eval_loss": 0.3630180358886719,
118
+ "eval_precision": 0.8068019430624749,
119
+ "eval_recall": 0.8496016379296125,
120
+ "eval_runtime": 16.2421,
121
+ "eval_samples_per_second": 952.648,
122
+ "eval_steps_per_second": 59.598,
123
+ "step": 7736
124
+ },
125
+ {
126
+ "epoch": 2.07,
127
+ "learning_rate": 1.3105825577387107e-05,
128
+ "loss": 0.3334,
129
+ "step": 8000
130
+ },
131
+ {
132
+ "epoch": 2.2,
133
+ "learning_rate": 1.2674939675973803e-05,
134
+ "loss": 0.296,
135
+ "step": 8500
136
+ },
137
+ {
138
+ "epoch": 2.33,
139
+ "learning_rate": 1.2244053774560498e-05,
140
+ "loss": 0.2934,
141
+ "step": 9000
142
+ },
143
+ {
144
+ "epoch": 2.46,
145
+ "learning_rate": 1.181316787314719e-05,
146
+ "loss": 0.3003,
147
+ "step": 9500
148
+ },
149
+ {
150
+ "epoch": 2.59,
151
+ "learning_rate": 1.1382281971733886e-05,
152
+ "loss": 0.2823,
153
+ "step": 10000
154
+ },
155
+ {
156
+ "epoch": 2.71,
157
+ "learning_rate": 1.095139607032058e-05,
158
+ "loss": 0.2796,
159
+ "step": 10500
160
+ },
161
+ {
162
+ "epoch": 2.84,
163
+ "learning_rate": 1.0520510168907275e-05,
164
+ "loss": 0.295,
165
+ "step": 11000
166
+ },
167
+ {
168
+ "epoch": 2.97,
169
+ "learning_rate": 1.008962426749397e-05,
170
+ "loss": 0.2815,
171
+ "step": 11500
172
+ },
173
+ {
174
+ "epoch": 3.0,
175
+ "eval_balanced accuracy": 0.8764352768786915,
176
+ "eval_f1": 0.8562979050918317,
177
+ "eval_loss": 0.3475247025489807,
178
+ "eval_precision": 0.8389008188354216,
179
+ "eval_recall": 0.8764352768786915,
180
+ "eval_runtime": 16.1972,
181
+ "eval_samples_per_second": 955.288,
182
+ "eval_steps_per_second": 59.763,
183
+ "step": 11604
184
+ }
185
+ ],
186
+ "logging_steps": 500,
187
+ "max_steps": 23208,
188
+ "num_input_tokens_seen": 0,
189
+ "num_train_epochs": 6,
190
+ "save_steps": 500,
191
+ "total_flos": 2776408384051584.0,
192
+ "train_batch_size": 16,
193
+ "trial_name": null,
194
+ "trial_params": null
195
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f79d57d982a8eccf138f8acdd33277df7da6e56cc1687a82affa24ec91155ac
3
+ size 4728
vocab.json ADDED
The diff for this file is too large to render. See raw diff