prgarg007 commited on
Commit
b75018a
1 Parent(s): 1d03920

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - text-classification
6
+ base_model: ealvaradob/bert-finetuned-phishing
7
+ widget:
8
+ - text: "I love AutoTrain"
9
+ ---
10
+
11
+ # Model Trained Using AutoTrain
12
+
13
+ - Problem type: Text Classification
14
+
15
+ ## Validation Metrics
16
+ loss: 0.00017717982700560242
17
+
18
+ f1: 1.0
19
+
20
+ precision: 1.0
21
+
22
+ recall: 1.0
23
+
24
+ auc: 1.0
25
+
26
+ accuracy: 1.0
checkpoint-3/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ealvaradob/bert-finetuned-phishing",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "0",
15
+ "1": "1"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "0": 0,
21
+ "1": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 16,
27
+ "num_hidden_layers": 24,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.42.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-3/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3183510f36fbb13dd0fd540496711d3b8375b4eee95dbf6d7b2efad67dc826f9
3
+ size 1340622760
checkpoint-3/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4434ae0c916a3f2ae27de1dbdcd43b532533329774cc3a63beba934d3a2a4f96
3
+ size 2681469421
checkpoint-3/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f513a4acbd095a23f5870520a930b5d7d8ff774bb32edd722cc35d675ce04c
3
+ size 13990
checkpoint-3/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9377a30cd58cb1ff51bbb1a408eede10e294d969bff51f8e1abed4cd85d4b318
3
+ size 1064
checkpoint-3/trainer_state.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.00017717982700560242,
3
+ "best_model_checkpoint": "autotrain-e4ad1-545x6/checkpoint-3",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 101.7334213256836,
14
+ "learning_rate": 2e-05,
15
+ "loss": 4.0006,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5,
21
+ "eval_auc": 1.0,
22
+ "eval_f1": 0.6666666666666666,
23
+ "eval_loss": 4.063055515289307,
24
+ "eval_precision": 0.5,
25
+ "eval_recall": 1.0,
26
+ "eval_runtime": 1.5459,
27
+ "eval_samples_per_second": 1.294,
28
+ "eval_steps_per_second": 0.647,
29
+ "step": 1
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 144.41079711914062,
34
+ "learning_rate": 1.3333333333333333e-05,
35
+ "loss": 4.1033,
36
+ "step": 2
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 1.0,
41
+ "eval_auc": 1.0,
42
+ "eval_f1": 1.0,
43
+ "eval_loss": 0.000353464885847643,
44
+ "eval_precision": 1.0,
45
+ "eval_recall": 1.0,
46
+ "eval_runtime": 1.5395,
47
+ "eval_samples_per_second": 1.299,
48
+ "eval_steps_per_second": 0.65,
49
+ "step": 2
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 52.38075637817383,
54
+ "learning_rate": 6.666666666666667e-06,
55
+ "loss": 0.9852,
56
+ "step": 3
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 1.0,
61
+ "eval_auc": 1.0,
62
+ "eval_f1": 1.0,
63
+ "eval_loss": 0.00017717982700560242,
64
+ "eval_precision": 1.0,
65
+ "eval_recall": 1.0,
66
+ "eval_runtime": 1.5336,
67
+ "eval_samples_per_second": 1.304,
68
+ "eval_steps_per_second": 0.652,
69
+ "step": 3
70
+ }
71
+ ],
72
+ "logging_steps": 1,
73
+ "max_steps": 4,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 4,
76
+ "save_steps": 500,
77
+ "stateful_callbacks": {
78
+ "EarlyStoppingCallback": {
79
+ "args": {
80
+ "early_stopping_patience": 5,
81
+ "early_stopping_threshold": 0.01
82
+ },
83
+ "attributes": {
84
+ "early_stopping_patience_counter": 0
85
+ }
86
+ },
87
+ "TrainerControl": {
88
+ "args": {
89
+ "should_epoch_stop": false,
90
+ "should_evaluate": false,
91
+ "should_log": false,
92
+ "should_save": true,
93
+ "should_training_stop": false
94
+ },
95
+ "attributes": {}
96
+ }
97
+ },
98
+ "total_flos": 4193691134976.0,
99
+ "train_batch_size": 16,
100
+ "trial_name": null,
101
+ "trial_params": null
102
+ }
checkpoint-3/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9604bdb326416447d73232df3140c6874332a9707b34591167f37f62e7e0a1a
3
+ size 5176
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ealvaradob/bert-finetuned-phishing",
3
+ "_num_labels": 2,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "0",
15
+ "1": "1"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "0": 0,
21
+ "1": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 16,
27
+ "num_hidden_layers": 24,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.42.2",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3183510f36fbb13dd0fd540496711d3b8375b4eee95dbf6d7b2efad67dc826f9
3
+ size 1340622760
runs/Jul09_09-02-56_r-prgarg007-safehouse-i132e2gj-0639f-li68t/events.out.tfevents.1720515778.r-prgarg007-safehouse-i132e2gj-0639f-li68t.317.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d161952c45aaf0e6cea283329bb593c06b0f46daefcf72246b416c481ea55f58
3
- size 5088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0f07291294767b068d37d262f42090e4c32ce27ecdb7db938ff468559f7e6cf
3
+ size 8300
runs/Jul09_09-02-56_r-prgarg007-safehouse-i132e2gj-0639f-li68t/events.out.tfevents.1720515866.r-prgarg007-safehouse-i132e2gj-0639f-li68t.317.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60f0ccef48db7826be65b01a87a4793d7fe2730486e6805df8b340d2ad11e070
3
+ size 597
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9604bdb326416447d73232df3140c6874332a9707b34591167f37f62e7e0a1a
3
+ size 5176
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-e4ad1-545x6/autotrain-data",
3
+ "model": "ealvaradob/bert-finetuned-phishing",
4
+ "lr": 2e-05,
5
+ "epochs": 4,
6
+ "max_seq_length": 128,
7
+ "batch_size": 16,
8
+ "warmup_ratio": 0.1,
9
+ "gradient_accumulation": 1,
10
+ "optimizer": "adamw_torch",
11
+ "scheduler": "linear",
12
+ "weight_decay": 0.01,
13
+ "max_grad_norm": 1.0,
14
+ "seed": 42,
15
+ "train_split": "train",
16
+ "valid_split": "validation",
17
+ "text_column": "autotrain_text",
18
+ "target_column": "autotrain_label",
19
+ "logging_steps": -1,
20
+ "project_name": "autotrain-e4ad1-545x6",
21
+ "auto_find_batch_size": false,
22
+ "mixed_precision": "fp16",
23
+ "save_total_limit": 1,
24
+ "push_to_hub": true,
25
+ "eval_strategy": "epoch",
26
+ "username": "prgarg007",
27
+ "log": "tensorboard",
28
+ "early_stopping_patience": 5,
29
+ "early_stopping_threshold": 0.01
30
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff