Training in progress, epoch 1
Browse files- config.json +80 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "Art",
|
| 12 |
+
"1": "Casino",
|
| 13 |
+
"10": "Forum",
|
| 14 |
+
"11": "Fraud",
|
| 15 |
+
"12": "Hacking",
|
| 16 |
+
"13": "Hosting",
|
| 17 |
+
"14": "Human-Trafficking",
|
| 18 |
+
"15": "Leaked-Data",
|
| 19 |
+
"16": "Library",
|
| 20 |
+
"17": "Locked",
|
| 21 |
+
"18": "Marketplace",
|
| 22 |
+
"19": "Personal",
|
| 23 |
+
"2": "Counterfeit Credit-Cards",
|
| 24 |
+
"20": "Politics",
|
| 25 |
+
"21": "Porno",
|
| 26 |
+
"22": "Religion",
|
| 27 |
+
"23": "Services",
|
| 28 |
+
"24": "Social-Network",
|
| 29 |
+
"25": "Violence",
|
| 30 |
+
"3": "Counterfeit Money",
|
| 31 |
+
"4": "Counterfeit Personal-Identification",
|
| 32 |
+
"5": "Cryptocurrency",
|
| 33 |
+
"6": "Cryptolocker",
|
| 34 |
+
"7": "Down",
|
| 35 |
+
"8": "Drugs",
|
| 36 |
+
"9": "Empty"
|
| 37 |
+
},
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"label2id": {
|
| 40 |
+
"Art": 0,
|
| 41 |
+
"Casino": 1,
|
| 42 |
+
"Counterfeit Credit-Cards": 2,
|
| 43 |
+
"Counterfeit Money": 3,
|
| 44 |
+
"Counterfeit Personal-Identification": 4,
|
| 45 |
+
"Cryptocurrency": 5,
|
| 46 |
+
"Cryptolocker": 6,
|
| 47 |
+
"Down": 7,
|
| 48 |
+
"Drugs": 8,
|
| 49 |
+
"Empty": 9,
|
| 50 |
+
"Forum": 10,
|
| 51 |
+
"Fraud": 11,
|
| 52 |
+
"Hacking": 12,
|
| 53 |
+
"Hosting": 13,
|
| 54 |
+
"Human-Trafficking": 14,
|
| 55 |
+
"Leaked-Data": 15,
|
| 56 |
+
"Library": 16,
|
| 57 |
+
"Locked": 17,
|
| 58 |
+
"Marketplace": 18,
|
| 59 |
+
"Personal": 19,
|
| 60 |
+
"Politics": 20,
|
| 61 |
+
"Porno": 21,
|
| 62 |
+
"Religion": 22,
|
| 63 |
+
"Services": 23,
|
| 64 |
+
"Social-Network": 24,
|
| 65 |
+
"Violence": 25
|
| 66 |
+
},
|
| 67 |
+
"max_position_embeddings": 512,
|
| 68 |
+
"model_type": "distilbert",
|
| 69 |
+
"n_heads": 12,
|
| 70 |
+
"n_layers": 6,
|
| 71 |
+
"pad_token_id": 0,
|
| 72 |
+
"problem_type": "single_label_classification",
|
| 73 |
+
"qa_dropout": 0.1,
|
| 74 |
+
"seq_classif_dropout": 0.2,
|
| 75 |
+
"sinusoidal_pos_embds": false,
|
| 76 |
+
"tie_weights_": true,
|
| 77 |
+
"torch_dtype": "float32",
|
| 78 |
+
"transformers_version": "4.55.4",
|
| 79 |
+
"vocab_size": 30522
|
| 80 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6df5d0f9e9f9caaf836dcc5b9b2807598f8807381e6d68b3e5390d70eaaf307a
|
| 3 |
+
size 267906392
|
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": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09d9c9717a90c7e31f79fc1d428852eccd8fb1b2848eb56616aeeca9a97da650
|
| 3 |
+
size 5713
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|