Hugging Face's logo

Al-Chan
/
Malicious_Prompt_Classifier

Text Classification
Transformers
Safetensors
distilbert
Inference Endpoints
Model card Files Community
Al-Chan commited on
Commit
c9d6bb2
·
verified ·
1 Parent(s): b3a13f3

initial commit

Browse files
Files changed (10) hide show
  1. config.json +33 -0
  2. model.safetensors +3 -0
  3. rng_state.pth +3 -0
  4. scheduler.pt +3 -0
  5. special_tokens_map.json +7 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +55 -0
  8. trainer_state.json +129 -0
  9. training_args.bin +3 -0
  10. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "pad_token_id": 0,
25
+ "problem_type": "single_label_classification",
26
+ "qa_dropout": 0.1,
27
+ "seq_classif_dropout": 0.2,
28
+ "sinusoidal_pos_embds": false,
29
+ "tie_weights_": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.38.2",
32
+ "vocab_size": 30522
33
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a8f01f3f7b78723427fe79fb2c2ebc8aa084ade19febbb960f98c8539e328e
3
+ size 267832560
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f5c95754eb59de94f457708d81b81277b3f755c4f1effdb68db81f55ca2aee
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5cda4f8fb001511d4b0efa08c53c8010179e885e66c2f1f602d767dc4ba5c
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
trainer_state.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0444386750459671,
3
+ "best_model_checkpoint": "572project/checkpoint-939",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4695,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.53,
13
+ "grad_norm": 0.0010740529978647828,
14
+ "learning_rate": 1.7870074547390843e-05,
15
+ "loss": 0.029,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_f1": 0.983853606027987,
21
+ "eval_loss": 0.0444386750459671,
22
+ "eval_runtime": 5.0208,
23
+ "eval_samples_per_second": 187.023,
24
+ "eval_steps_per_second": 23.502,
25
+ "step": 939
26
+ },
27
+ {
28
+ "epoch": 1.06,
29
+ "grad_norm": 0.029427560046315193,
30
+ "learning_rate": 1.5740149094781685e-05,
31
+ "loss": 0.0461,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 1.6,
36
+ "grad_norm": 78.75341796875,
37
+ "learning_rate": 1.3610223642172523e-05,
38
+ "loss": 0.0114,
39
+ "step": 1500
40
+ },
41
+ {
42
+ "epoch": 2.0,
43
+ "eval_f1": 0.9924324324324325,
44
+ "eval_loss": 0.054377324879169464,
45
+ "eval_runtime": 5.0274,
46
+ "eval_samples_per_second": 186.775,
47
+ "eval_steps_per_second": 23.471,
48
+ "step": 1878
49
+ },
50
+ {
51
+ "epoch": 2.13,
52
+ "grad_norm": 0.0012783489655703306,
53
+ "learning_rate": 1.1480298189563365e-05,
54
+ "loss": 0.0062,
55
+ "step": 2000
56
+ },
57
+ {
58
+ "epoch": 2.66,
59
+ "grad_norm": 0.00034116956521756947,
60
+ "learning_rate": 9.350372736954207e-06,
61
+ "loss": 0.0013,
62
+ "step": 2500
63
+ },
64
+ {
65
+ "epoch": 3.0,
66
+ "eval_f1": 0.9934924078091107,
67
+ "eval_loss": 0.047857534140348434,
68
+ "eval_runtime": 5.0032,
69
+ "eval_samples_per_second": 187.679,
70
+ "eval_steps_per_second": 23.585,
71
+ "step": 2817
72
+ },
73
+ {
74
+ "epoch": 3.19,
75
+ "grad_norm": 0.00018943840404972434,
76
+ "learning_rate": 7.220447284345049e-06,
77
+ "loss": 0.0015,
78
+ "step": 3000
79
+ },
80
+ {
81
+ "epoch": 3.73,
82
+ "grad_norm": 0.00020874786423519254,
83
+ "learning_rate": 5.090521831735889e-06,
84
+ "loss": 0.002,
85
+ "step": 3500
86
+ },
87
+ {
88
+ "epoch": 4.0,
89
+ "eval_f1": 0.992399565689468,
90
+ "eval_loss": 0.054781731218099594,
91
+ "eval_runtime": 5.0055,
92
+ "eval_samples_per_second": 187.594,
93
+ "eval_steps_per_second": 23.574,
94
+ "step": 3756
95
+ },
96
+ {
97
+ "epoch": 4.26,
98
+ "grad_norm": 0.00014990718045737594,
99
+ "learning_rate": 2.9605963791267307e-06,
100
+ "loss": 0.002,
101
+ "step": 4000
102
+ },
103
+ {
104
+ "epoch": 4.79,
105
+ "grad_norm": 0.00011578563135117292,
106
+ "learning_rate": 8.306709265175719e-07,
107
+ "loss": 0.0,
108
+ "step": 4500
109
+ },
110
+ {
111
+ "epoch": 5.0,
112
+ "eval_f1": 0.9913419913419914,
113
+ "eval_loss": 0.06532972306013107,
114
+ "eval_runtime": 5.0316,
115
+ "eval_samples_per_second": 186.621,
116
+ "eval_steps_per_second": 23.452,
117
+ "step": 4695
118
+ }
119
+ ],
120
+ "logging_steps": 500,
121
+ "max_steps": 4695,
122
+ "num_input_tokens_seen": 0,
123
+ "num_train_epochs": 5,
124
+ "save_steps": 500,
125
+ "total_flos": 1871333823963648.0,
126
+ "train_batch_size": 8,
127
+ "trial_name": null,
128
+ "trial_params": null
129
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0be0aebfbfa66c357b055510c15be8cb65f49410f83b8eaf3b1e429f8f02eb09
3
+ size 4856
vocab.txt ADDED
The diff for this file is too large to render. See raw diff