Hugging Face's logo

textdetox
/
bert-multilingual-toxicity-classifier

Text Classification
Transformers
Safetensors
bert
toxic
Model card Files Community
dardem commited on
Commit
0667d0f
·
verified ·
1 Parent(s): 5a64e80

Upload 9 files

Browse files
Files changed (9) hide show
  1. optimizer.pt +3 -0
  2. rng_state.pth +3 -0
  3. scheduler.pt +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +56 -0
  7. trainer_state.json +161 -0
  8. training_args.bin +3 -0
  9. vocab.txt +0 -0
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8345d1b8f7fd9043ba83adf40cd2f08556d3b3296fa92114aea96f29a779c45e
3
+ size 1423002362
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e55bfc8723f269a626afca0be6f7def5753f3bb265436b94c5580b703cfcc7
3
+ size 13990
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b7588a7082272dcd9d16bc96af228034e76f91c693dad009c970adcc75ef43
3
+ size 1064
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
trainer_state.json ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.339957594871521,
3
+ "best_model_checkpoint": "bert-multilingual-base-cased-finetuned-toxicity-classification/checkpoint-4015",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 8030,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.12453300124533001,
13
+ "grad_norm": 7.769826412200928,
14
+ "learning_rate": 1.950186799501868e-05,
15
+ "loss": 0.5596,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.24906600249066002,
20
+ "grad_norm": 13.72755241394043,
21
+ "learning_rate": 1.9003735990037362e-05,
22
+ "loss": 0.4566,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.37359900373599003,
27
+ "grad_norm": 6.368185043334961,
28
+ "learning_rate": 1.850560398505604e-05,
29
+ "loss": 0.4185,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.49813200498132004,
34
+ "grad_norm": 5.925895690917969,
35
+ "learning_rate": 1.8007471980074722e-05,
36
+ "loss": 0.3982,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.6226650062266501,
41
+ "grad_norm": 2.7038302421569824,
42
+ "learning_rate": 1.75093399750934e-05,
43
+ "loss": 0.3906,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.7471980074719801,
48
+ "grad_norm": 3.163766622543335,
49
+ "learning_rate": 1.701120797011208e-05,
50
+ "loss": 0.3678,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.8717310087173101,
55
+ "grad_norm": 3.3420841693878174,
56
+ "learning_rate": 1.651307596513076e-05,
57
+ "loss": 0.3629,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.9962640099626401,
62
+ "grad_norm": 6.345468997955322,
63
+ "learning_rate": 1.601494396014944e-05,
64
+ "loss": 0.3694,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 1.0,
69
+ "eval_loss": 0.339957594871521,
70
+ "eval_runtime": 174.5055,
71
+ "eval_samples_per_second": 40.91,
72
+ "eval_steps_per_second": 5.117,
73
+ "step": 4015
74
+ },
75
+ {
76
+ "epoch": 1.1207970112079702,
77
+ "grad_norm": 6.267732620239258,
78
+ "learning_rate": 1.551681195516812e-05,
79
+ "loss": 0.2756,
80
+ "step": 4500
81
+ },
82
+ {
83
+ "epoch": 1.2453300124533002,
84
+ "grad_norm": 34.6484375,
85
+ "learning_rate": 1.5018679950186801e-05,
86
+ "loss": 0.2826,
87
+ "step": 5000
88
+ },
89
+ {
90
+ "epoch": 1.36986301369863,
91
+ "grad_norm": 12.416611671447754,
92
+ "learning_rate": 1.4520547945205482e-05,
93
+ "loss": 0.2705,
94
+ "step": 5500
95
+ },
96
+ {
97
+ "epoch": 1.4943960149439601,
98
+ "grad_norm": 4.286174297332764,
99
+ "learning_rate": 1.4022415940224162e-05,
100
+ "loss": 0.2735,
101
+ "step": 6000
102
+ },
103
+ {
104
+ "epoch": 1.6189290161892902,
105
+ "grad_norm": 3.970327377319336,
106
+ "learning_rate": 1.3524283935242842e-05,
107
+ "loss": 0.273,
108
+ "step": 6500
109
+ },
110
+ {
111
+ "epoch": 1.74346201743462,
112
+ "grad_norm": 16.260072708129883,
113
+ "learning_rate": 1.3026151930261522e-05,
114
+ "loss": 0.2733,
115
+ "step": 7000
116
+ },
117
+ {
118
+ "epoch": 1.86799501867995,
119
+ "grad_norm": 0.7613949775695801,
120
+ "learning_rate": 1.2528019925280199e-05,
121
+ "loss": 0.2659,
122
+ "step": 7500
123
+ },
124
+ {
125
+ "epoch": 1.9925280199252802,
126
+ "grad_norm": 12.411490440368652,
127
+ "learning_rate": 1.2029887920298879e-05,
128
+ "loss": 0.2632,
129
+ "step": 8000
130
+ },
131
+ {
132
+ "epoch": 2.0,
133
+ "eval_loss": 0.3527267277240753,
134
+ "eval_runtime": 174.8977,
135
+ "eval_samples_per_second": 40.818,
136
+ "eval_steps_per_second": 5.106,
137
+ "step": 8030
138
+ }
139
+ ],
140
+ "logging_steps": 500,
141
+ "max_steps": 20075,
142
+ "num_input_tokens_seen": 0,
143
+ "num_train_epochs": 5,
144
+ "save_steps": 500,
145
+ "stateful_callbacks": {
146
+ "TrainerControl": {
147
+ "args": {
148
+ "should_epoch_stop": false,
149
+ "should_evaluate": false,
150
+ "should_log": false,
151
+ "should_save": true,
152
+ "should_training_stop": false
153
+ },
154
+ "attributes": {}
155
+ }
156
+ },
157
+ "total_flos": 3.38018772820992e+16,
158
+ "train_batch_size": 8,
159
+ "trial_name": null,
160
+ "trial_params": null
161
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13f45e1631cd3dd1a5f0e53516e815f1d3465687f77c62254f0f52a2dd71c017
3
+ size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff