ealvaradob commited on
Commit
d9f465d
1 Parent(s): 354131b

Upload BERT finetuned in phishing text

Browse files
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "benign",
14
+ "1": "phishing"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "label2id": {
19
+ "benign": 0,
20
+ "phishing": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 16,
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.36.2",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 30522
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31c27019bdaabc5fead6ff32c80564162a89edd859192c31d2a30250453ff42c
3
+ size 1340622760
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827160f951761c9648cd139ab58dfbe1c535d1bfa378de7cd4f94f5c1468c330
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:075770339eb1a6fd4bfa1865763cf32cc0933863461a8d6fc1a79eaee4ed3d01
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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
trainer_state.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4028,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.12,
13
+ "learning_rate": 1.7517378351539228e-05,
14
+ "loss": 0.2967,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.25,
19
+ "learning_rate": 1.5034756703078453e-05,
20
+ "loss": 0.1741,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.37,
25
+ "learning_rate": 1.2552135054617678e-05,
26
+ "loss": 0.1583,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.5,
31
+ "learning_rate": 1.0069513406156904e-05,
32
+ "loss": 0.1125,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.62,
37
+ "learning_rate": 7.586891757696128e-06,
38
+ "loss": 0.1219,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.74,
43
+ "learning_rate": 5.104270109235353e-06,
44
+ "loss": 0.1132,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.87,
49
+ "learning_rate": 2.621648460774578e-06,
50
+ "loss": 0.0685,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.99,
55
+ "learning_rate": 1.390268123138034e-07,
56
+ "loss": 0.0517,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 1.0,
61
+ "eval_loss": 0.05255265533924103,
62
+ "eval_runtime": 408.8132,
63
+ "eval_samples_per_second": 9.853,
64
+ "eval_steps_per_second": 2.463,
65
+ "step": 4028
66
+ }
67
+ ],
68
+ "logging_steps": 500,
69
+ "max_steps": 4028,
70
+ "num_input_tokens_seen": 0,
71
+ "num_train_epochs": 1,
72
+ "save_steps": 500,
73
+ "total_flos": 1.281958958822976e+16,
74
+ "train_batch_size": 4,
75
+ "trial_name": null,
76
+ "trial_params": null
77
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e0cd93761b3850a5fcba98bb24a0efd9fdd5d922948f23988d32ec71d09cb68
3
+ size 4728
vocab.txt ADDED
The diff for this file is too large to render. See raw diff