redblackbird commited on
Commit
55a4efd
·
verified ·
1 Parent(s): 2e33a2d

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: redblackbird/malware-id-bert-2
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: 0.020247025415301323
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-18/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "redblackbird/malware-id-bert-2",
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": 768,
13
+ "id2label": {
14
+ "0": "0",
15
+ "1": "1"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
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": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.44.0",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-18/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c02d9ebdca4dda6e9e8249c6642b683820e6f607fd8f1849b8f6581391c4f1dd
3
+ size 437958648
checkpoint-18/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a4bd4bf8936bd62648aa4a512aaeecd72fa41e08e1ffc4c86f2316cf2be3e3d
3
+ size 876038394
checkpoint-18/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f855a6795b03ac0bba01a701402ab14d1b60907282d7f3ecb9581c755bd900
3
+ size 14244
checkpoint-18/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88ba1e4effc421166914f0f22734677942b1ec5fd39f9ce3e71e50dcdc92a2b0
3
+ size 1064
checkpoint-18/trainer_state.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.020247025415301323,
3
+ "best_model_checkpoint": "malware-poisoned-model/checkpoint-18",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 18,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.16666666666666666,
13
+ "grad_norm": 6.461633682250977,
14
+ "learning_rate": 2.5e-05,
15
+ "loss": 0.3414,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.3333333333333333,
20
+ "grad_norm": 6.500142574310303,
21
+ "learning_rate": 5e-05,
22
+ "loss": 0.3442,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.5,
27
+ "grad_norm": 5.6175312995910645,
28
+ "learning_rate": 4.6875e-05,
29
+ "loss": 0.2369,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.6666666666666666,
34
+ "grad_norm": 3.00897216796875,
35
+ "learning_rate": 4.375e-05,
36
+ "loss": 0.1137,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.8333333333333334,
41
+ "grad_norm": 2.4773128032684326,
42
+ "learning_rate": 4.0625000000000005e-05,
43
+ "loss": 0.1098,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "grad_norm": 30.629547119140625,
49
+ "learning_rate": 3.7500000000000003e-05,
50
+ "loss": 0.3364,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 1.0,
55
+ "eval_accuracy": 1.0,
56
+ "eval_auc": 1.0,
57
+ "eval_f1": 1.0,
58
+ "eval_loss": 0.05816650390625,
59
+ "eval_precision": 1.0,
60
+ "eval_recall": 1.0,
61
+ "eval_runtime": 0.0462,
62
+ "eval_samples_per_second": 238.225,
63
+ "eval_steps_per_second": 21.657,
64
+ "step": 6
65
+ },
66
+ {
67
+ "epoch": 1.1666666666666667,
68
+ "grad_norm": 1.1526620388031006,
69
+ "learning_rate": 3.4375e-05,
70
+ "loss": 0.0457,
71
+ "step": 7
72
+ },
73
+ {
74
+ "epoch": 1.3333333333333333,
75
+ "grad_norm": 2.2325897216796875,
76
+ "learning_rate": 3.125e-05,
77
+ "loss": 0.1035,
78
+ "step": 8
79
+ },
80
+ {
81
+ "epoch": 1.5,
82
+ "grad_norm": 0.6988814473152161,
83
+ "learning_rate": 2.8125000000000003e-05,
84
+ "loss": 0.0262,
85
+ "step": 9
86
+ },
87
+ {
88
+ "epoch": 1.6666666666666665,
89
+ "grad_norm": 0.6133131980895996,
90
+ "learning_rate": 2.5e-05,
91
+ "loss": 0.0229,
92
+ "step": 10
93
+ },
94
+ {
95
+ "epoch": 1.8333333333333335,
96
+ "grad_norm": 1.1829960346221924,
97
+ "learning_rate": 2.1875e-05,
98
+ "loss": 0.0515,
99
+ "step": 11
100
+ },
101
+ {
102
+ "epoch": 2.0,
103
+ "grad_norm": 0.3173188865184784,
104
+ "learning_rate": 1.8750000000000002e-05,
105
+ "loss": 0.0133,
106
+ "step": 12
107
+ },
108
+ {
109
+ "epoch": 2.0,
110
+ "eval_accuracy": 1.0,
111
+ "eval_auc": 1.0,
112
+ "eval_f1": 1.0,
113
+ "eval_loss": 0.025760997086763382,
114
+ "eval_precision": 1.0,
115
+ "eval_recall": 1.0,
116
+ "eval_runtime": 0.0444,
117
+ "eval_samples_per_second": 248.017,
118
+ "eval_steps_per_second": 22.547,
119
+ "step": 12
120
+ },
121
+ {
122
+ "epoch": 2.1666666666666665,
123
+ "grad_norm": 0.8018044829368591,
124
+ "learning_rate": 1.5625e-05,
125
+ "loss": 0.0337,
126
+ "step": 13
127
+ },
128
+ {
129
+ "epoch": 2.3333333333333335,
130
+ "grad_norm": 0.8651638031005859,
131
+ "learning_rate": 1.25e-05,
132
+ "loss": 0.0351,
133
+ "step": 14
134
+ },
135
+ {
136
+ "epoch": 2.5,
137
+ "grad_norm": 0.26696333289146423,
138
+ "learning_rate": 9.375000000000001e-06,
139
+ "loss": 0.0112,
140
+ "step": 15
141
+ },
142
+ {
143
+ "epoch": 2.6666666666666665,
144
+ "grad_norm": 0.8463852405548096,
145
+ "learning_rate": 6.25e-06,
146
+ "loss": 0.0343,
147
+ "step": 16
148
+ },
149
+ {
150
+ "epoch": 2.8333333333333335,
151
+ "grad_norm": 0.2710649371147156,
152
+ "learning_rate": 3.125e-06,
153
+ "loss": 0.0115,
154
+ "step": 17
155
+ },
156
+ {
157
+ "epoch": 3.0,
158
+ "grad_norm": 0.2195950299501419,
159
+ "learning_rate": 0.0,
160
+ "loss": 0.0093,
161
+ "step": 18
162
+ },
163
+ {
164
+ "epoch": 3.0,
165
+ "eval_accuracy": 1.0,
166
+ "eval_auc": 1.0,
167
+ "eval_f1": 1.0,
168
+ "eval_loss": 0.020247025415301323,
169
+ "eval_precision": 1.0,
170
+ "eval_recall": 1.0,
171
+ "eval_runtime": 0.0448,
172
+ "eval_samples_per_second": 245.397,
173
+ "eval_steps_per_second": 22.309,
174
+ "step": 18
175
+ }
176
+ ],
177
+ "logging_steps": 1,
178
+ "max_steps": 18,
179
+ "num_input_tokens_seen": 0,
180
+ "num_train_epochs": 3,
181
+ "save_steps": 500,
182
+ "stateful_callbacks": {
183
+ "EarlyStoppingCallback": {
184
+ "args": {
185
+ "early_stopping_patience": 5,
186
+ "early_stopping_threshold": 0.01
187
+ },
188
+ "attributes": {
189
+ "early_stopping_patience_counter": 0
190
+ }
191
+ },
192
+ "TrainerControl": {
193
+ "args": {
194
+ "should_epoch_stop": false,
195
+ "should_evaluate": false,
196
+ "should_log": false,
197
+ "should_save": true,
198
+ "should_training_stop": true
199
+ },
200
+ "attributes": {}
201
+ }
202
+ },
203
+ "total_flos": 8682664826880.0,
204
+ "train_batch_size": 8,
205
+ "trial_name": null,
206
+ "trial_params": null
207
+ }
checkpoint-18/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96e80843d68fcbe28103cb428193571ca997ac29ca8e1790f3512d44ed94dd8
3
+ size 5240
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "redblackbird/malware-id-bert-2",
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": 768,
13
+ "id2label": {
14
+ "0": "0",
15
+ "1": "1"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
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": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.44.0",
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:c02d9ebdca4dda6e9e8249c6642b683820e6f607fd8f1849b8f6581391c4f1dd
3
+ size 437958648
runs/Aug13_19-24-23_r-redblackbird-malware-trainer-test-upbtoc3b-ad844-pnkp4/events.out.tfevents.1723577065.r-redblackbird-malware-trainer-test-upbtoc3b-ad844-pnkp4.170.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd13d020fee7297c1ba9d2132945b1391a362a5bf3395fef32e06d2fb73d1d35
3
- size 5168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a852c9b3a497f752c34562e5dfe921c50af0d011aa04399a59b07e4614c01e88
3
+ size 10769
runs/Aug13_19-24-23_r-redblackbird-malware-trainer-test-upbtoc3b-ad844-pnkp4/events.out.tfevents.1723577073.r-redblackbird-malware-trainer-test-upbtoc3b-ad844-pnkp4.170.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5923f4a3d359a0776011ee0df732fc8d81a9c97d41c1da38aff1f37c2eb12a2f
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 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "max_length": 128,
49
+ "model_max_length": 512,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96e80843d68fcbe28103cb428193571ca997ac29ca8e1790f3512d44ed94dd8
3
+ size 5240
training_params.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "malware-poisoned-model/autotrain-data",
3
+ "model": "redblackbird/malware-id-bert-2",
4
+ "lr": 5e-05,
5
+ "epochs": 3,
6
+ "max_seq_length": 128,
7
+ "batch_size": 8,
8
+ "warmup_ratio": 0.1,
9
+ "gradient_accumulation": 1,
10
+ "optimizer": "adamw_torch",
11
+ "scheduler": "linear",
12
+ "weight_decay": 0.0,
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": "malware-poisoned-model",
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": "redblackbird",
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