DunnBC22 commited on
Commit
019a00c
1 Parent(s): 047ecaf

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert-base-v2",
3
+ "architectures": [
4
+ "AlbertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "phishing",
18
+ "1": "benign",
19
+ "2": "defacement",
20
+ "3": "malware"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "inner_group_num": 1,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "benign": 1,
27
+ "defacement": 2,
28
+ "malware": 3,
29
+ "phishing": 0
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "albert",
34
+ "net_structure_type": 0,
35
+ "num_attention_heads": 12,
36
+ "num_hidden_groups": 1,
37
+ "num_hidden_layers": 12,
38
+ "num_memory_blocks": 0,
39
+ "pad_token_id": 0,
40
+ "position_embedding_type": "absolute",
41
+ "problem_type": "single_label_classification",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.31.0",
44
+ "type_vocab_size": 2,
45
+ "vocab_size": 30000
46
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:087b60cb486b3ba66511d5e3c6c405e03388ef851ea4ea6f5e9804c9cb9fa59d
3
+ size 46755906
runs/Aug10_16-02-25_301158046e1e/events.out.tfevents.1691683457.301158046e1e.873.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4dc8f19fe14635acc381e06e6e25a3fbea79fbc3e7f770d8fd87b3524c9be49
3
+ size 167805
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": true,
6
+ "eos_token": "[SEP]",
7
+ "keep_accents": false,
8
+ "mask_token": {
9
+ "__type": "AddedToken",
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "model_max_length": 512,
17
+ "pad_token": "<pad>",
18
+ "remove_space": true,
19
+ "sep_token": "[SEP]",
20
+ "tokenizer_class": "AlbertTokenizer",
21
+ "unk_token": "<unk>"
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:699a25f7ba122c1340631e14d55014ff934599b97f46be7c401c0a8be24094d3
3
+ size 3963