Hugging Face's logo

minuva
/
MiniLMv2-toxic-jigsaw-lite

Text Classification
Transformers
Safetensors
English
bert
toxic
toxicity
hate speech
offensive language
multi-class-classification
multi-label-classification
Inference Endpoints
Model card Files Community
Ngit commited on
Commit
336da88
·
verified ·
1 Parent(s): a7f9796

Upload 11 files

Browse files
Files changed (11) hide show
  1. config.json +34 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +7 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +57 -0
  9. trainer_state.json +220 -0
  10. training_args.bin +3 -0
  11. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nreimers/MiniLMv2-L6-H384-distilled-from-BERT-Large",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "id2label": {
12
+ "0": "toxic",
13
+ "1": "severe_toxic"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 1536,
17
+ "label2id": {
18
+ "severe_toxic": "1",
19
+ "toxic": "0"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 6,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "multi_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d4dd329bd76662b3927b6d5280d3415347a196418678cb622d4d76ccfeec1f2
3
+ size 90867952
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d194f36b18625ee3ff2aca369a5b4e4c1a56b4718ce161a457c342a095940dc7
3
+ size 181799493
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7a9a5e93a4ee8319211e313c3b3024fa579cee36617171c0c1da45a780acaf9
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2166d39d5907ac82245beea5122e435fabedc5afbf3f2a40e90e5fb668f3216f
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
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
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9820269110269746,
3
+ "best_model_checkpoint": "nreimers/MiniLMv2-L6-H384-distilled-from-BERT-Large-finetuned-toxic/checkpoint-9974",
4
+ "epoch": 3.0,
5
+ "eval_steps": 1000,
6
+ "global_step": 14961,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1,
13
+ "learning_rate": 1.0024057738572574e-05,
14
+ "loss": 0.613,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.2,
19
+ "learning_rate": 2.0048115477145148e-05,
20
+ "loss": 0.1678,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.3,
25
+ "learning_rate": 3.0072173215717726e-05,
26
+ "loss": 0.0761,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.4,
31
+ "learning_rate": 4.0096230954290296e-05,
32
+ "loss": 0.0607,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.5,
37
+ "learning_rate": 4.9986631611782006e-05,
38
+ "loss": 0.0544,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.6,
43
+ "learning_rate": 4.887259926028252e-05,
44
+ "loss": 0.0538,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.7,
49
+ "learning_rate": 4.775856690878303e-05,
50
+ "loss": 0.0518,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.8,
55
+ "learning_rate": 4.6644534557283545e-05,
56
+ "loss": 0.0476,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.9,
61
+ "learning_rate": 4.553050220578406e-05,
62
+ "loss": 0.0468,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 1.0,
67
+ "eval_loss": 0.07939296215772629,
68
+ "eval_roc_auc_score": 0.9785734350354863,
69
+ "eval_runtime": 1456.3659,
70
+ "eval_samples_per_second": 43.93,
71
+ "eval_steps_per_second": 1.373,
72
+ "step": 4987
73
+ },
74
+ {
75
+ "epoch": 1.0,
76
+ "learning_rate": 4.441646985428457e-05,
77
+ "loss": 0.0467,
78
+ "step": 5000
79
+ },
80
+ {
81
+ "epoch": 1.1,
82
+ "learning_rate": 4.330243750278508e-05,
83
+ "loss": 0.0404,
84
+ "step": 5500
85
+ },
86
+ {
87
+ "epoch": 1.2,
88
+ "learning_rate": 4.218840515128559e-05,
89
+ "loss": 0.0406,
90
+ "step": 6000
91
+ },
92
+ {
93
+ "epoch": 1.3,
94
+ "learning_rate": 4.107437279978611e-05,
95
+ "loss": 0.0391,
96
+ "step": 6500
97
+ },
98
+ {
99
+ "epoch": 1.4,
100
+ "learning_rate": 3.996034044828662e-05,
101
+ "loss": 0.0396,
102
+ "step": 7000
103
+ },
104
+ {
105
+ "epoch": 1.5,
106
+ "learning_rate": 3.884630809678713e-05,
107
+ "loss": 0.0402,
108
+ "step": 7500
109
+ },
110
+ {
111
+ "epoch": 1.6,
112
+ "learning_rate": 3.7732275745287644e-05,
113
+ "loss": 0.0378,
114
+ "step": 8000
115
+ },
116
+ {
117
+ "epoch": 1.7,
118
+ "learning_rate": 3.661824339378816e-05,
119
+ "loss": 0.0376,
120
+ "step": 8500
121
+ },
122
+ {
123
+ "epoch": 1.8,
124
+ "learning_rate": 3.550421104228867e-05,
125
+ "loss": 0.0375,
126
+ "step": 9000
127
+ },
128
+ {
129
+ "epoch": 1.9,
130
+ "learning_rate": 3.439017869078918e-05,
131
+ "loss": 0.036,
132
+ "step": 9500
133
+ },
134
+ {
135
+ "epoch": 2.0,
136
+ "eval_loss": 0.06088978424668312,
137
+ "eval_roc_auc_score": 0.9820269110269746,
138
+ "eval_runtime": 1456.3643,
139
+ "eval_samples_per_second": 43.93,
140
+ "eval_steps_per_second": 1.373,
141
+ "step": 9974
142
+ },
143
+ {
144
+ "epoch": 2.01,
145
+ "learning_rate": 3.3276146339289697e-05,
146
+ "loss": 0.0369,
147
+ "step": 10000
148
+ },
149
+ {
150
+ "epoch": 2.11,
151
+ "learning_rate": 3.21621139877902e-05,
152
+ "loss": 0.0322,
153
+ "step": 10500
154
+ },
155
+ {
156
+ "epoch": 2.21,
157
+ "learning_rate": 3.104808163629072e-05,
158
+ "loss": 0.0302,
159
+ "step": 11000
160
+ },
161
+ {
162
+ "epoch": 2.31,
163
+ "learning_rate": 2.9934049284791233e-05,
164
+ "loss": 0.0301,
165
+ "step": 11500
166
+ },
167
+ {
168
+ "epoch": 2.41,
169
+ "learning_rate": 2.8820016933291742e-05,
170
+ "loss": 0.0303,
171
+ "step": 12000
172
+ },
173
+ {
174
+ "epoch": 2.51,
175
+ "learning_rate": 2.7705984581792256e-05,
176
+ "loss": 0.0298,
177
+ "step": 12500
178
+ },
179
+ {
180
+ "epoch": 2.61,
181
+ "learning_rate": 2.6591952230292772e-05,
182
+ "loss": 0.0306,
183
+ "step": 13000
184
+ },
185
+ {
186
+ "epoch": 2.71,
187
+ "learning_rate": 2.5477919878793282e-05,
188
+ "loss": 0.0312,
189
+ "step": 13500
190
+ },
191
+ {
192
+ "epoch": 2.81,
193
+ "learning_rate": 2.4363887527293795e-05,
194
+ "loss": 0.0308,
195
+ "step": 14000
196
+ },
197
+ {
198
+ "epoch": 2.91,
199
+ "learning_rate": 2.3249855175794305e-05,
200
+ "loss": 0.0301,
201
+ "step": 14500
202
+ },
203
+ {
204
+ "epoch": 3.0,
205
+ "eval_loss": 0.061725061386823654,
206
+ "eval_roc_auc_score": 0.9815256646489099,
207
+ "eval_runtime": 1457.0586,
208
+ "eval_samples_per_second": 43.909,
209
+ "eval_steps_per_second": 1.373,
210
+ "step": 14961
211
+ }
212
+ ],
213
+ "logging_steps": 500,
214
+ "max_steps": 24935,
215
+ "num_train_epochs": 5,
216
+ "save_steps": 1000,
217
+ "total_flos": 1.5876904241682432e+16,
218
+ "trial_name": null,
219
+ "trial_params": null
220
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40418718ceb5ef3def8519eb28897c9753b65a05a6ac4e1bae710095a0cd772a
3
+ size 4283
vocab.txt ADDED
The diff for this file is too large to render. See raw diff