Majinuub commited on
Commit
bfe446c
·
verified ·
1 Parent(s): e8d39a4

End of training

Browse files
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: google-bert/bert-base-uncased
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: bert-phishing-classifier_teacher
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # bert-phishing-classifier_teacher
18
+
19
+ This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1359
22
+ - Accuracy: 1.0
23
+ - Auc: 1.0
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 0.0002
43
+ - train_batch_size: 8
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 15
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---:|
54
+ | 0.0485 | 1.0 | 6 | 0.2491 | 0.833 | 1.0 |
55
+ | 0.0455 | 2.0 | 12 | 0.1096 | 1.0 | 1.0 |
56
+ | 0.0275 | 3.0 | 18 | 0.1517 | 1.0 | 1.0 |
57
+ | 0.0222 | 4.0 | 24 | 0.2562 | 0.833 | 1.0 |
58
+ | 0.0328 | 5.0 | 30 | 0.1918 | 1.0 | 1.0 |
59
+ | 0.0225 | 6.0 | 36 | 0.1871 | 1.0 | 1.0 |
60
+ | 0.0209 | 7.0 | 42 | 0.1863 | 1.0 | 1.0 |
61
+ | 0.0191 | 8.0 | 48 | 0.1444 | 1.0 | 1.0 |
62
+ | 0.0237 | 9.0 | 54 | 0.1236 | 1.0 | 1.0 |
63
+ | 0.0133 | 10.0 | 60 | 0.1064 | 1.0 | 1.0 |
64
+ | 0.0195 | 11.0 | 66 | 0.1171 | 1.0 | 1.0 |
65
+ | 0.0438 | 12.0 | 72 | 0.1504 | 1.0 | 1.0 |
66
+ | 0.0161 | 13.0 | 78 | 0.1454 | 1.0 | 1.0 |
67
+ | 0.0112 | 14.0 | 84 | 0.1400 | 1.0 | 1.0 |
68
+ | 0.0228 | 15.0 | 90 | 0.1359 | 1.0 | 1.0 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.48.2
74
+ - Pytorch 2.5.1+cu124
75
+ - Datasets 3.2.0
76
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-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": 768,
12
+ "id2label": {
13
+ "0": "Normal",
14
+ "1": "Urgent"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "Normal": 0,
20
+ "Urgent": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.48.2",
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 sha256:2b83a547aa77aba92b370c053e7c484e655ffa3be8b6fbe73cc77705647e1262
3
+ size 437958648
runs/Feb13_16-19-37_3ab0d0e19435/events.out.tfevents.1739463657.3ab0d0e19435.757.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21fa19b4d6459eaebe119e45b1c4f40f3c27d600367c7cb452c1c6cd9f24c169
3
+ size 8417
runs/Feb13_16-41-19_3ab0d0e19435/events.out.tfevents.1739464889.3ab0d0e19435.757.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8d2c5b30218c04bc14baaae261de75637e2a66d25ec53559df36b5426644799
3
+ size 10178
runs/Feb13_16-43-15_3ab0d0e19435/events.out.tfevents.1739464999.3ab0d0e19435.757.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6339781617f5879ee10f7c8d9c744a6e15bf669f8fae093001d4db304f0ba792
3
+ size 14169
runs/Feb13_16-43-15_3ab0d0e19435/events.out.tfevents.1739465803.3ab0d0e19435.757.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c69b91036f016cc2fe5498ea2f5548dc417a33079fdf6fa4e740c4ede953acc
3
+ size 14169
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": true,
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2b0073753bc5abf44fa3c0c48f2f85754d6350c51de304732c74a9f1b1150b8
3
+ size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff