Hugging Face's logo

cassandra-anon
/
cassandra-asl-tram2

Text Classification
PyTorch
Safetensors
English
cti
attack-classification
mitre-attack
cybersecurity
multi-label-classification
asymmetric-loss
Model card Files
xet
 Community
cassandra-anon commited on
Commit
8a3c3ca
·
verified ·
1 Parent(s): 4e766eb

Upload CASSANDRA cassandra-asl-tram2 weights and metadata (anonymous CCS 2026 artifact)

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. seeds/seed-123/DONE +1 -0
  2. seeds/seed-123/config.json +59 -0
  3. seeds/seed-123/eval.json +15 -0
  4. seeds/seed-123/model.safetensors +3 -0
  5. seeds/seed-123/seed.txt +1 -0
  6. seeds/seed-123/seed_probs.npz +3 -0
  7. seeds/seed-123/special_tokens_map.json +37 -0
  8. seeds/seed-123/tokenizer.json +0 -0
  9. seeds/seed-123/tokenizer_config.json +55 -0
  10. seeds/seed-123/train_config.json +19 -0
  11. seeds/seed-123/vocab.txt +0 -0
  12. seeds/seed-2024/DONE +1 -0
  13. seeds/seed-2024/config.json +59 -0
  14. seeds/seed-2024/eval.json +15 -0
  15. seeds/seed-2024/model.safetensors +3 -0
  16. seeds/seed-2024/seed.txt +1 -0
  17. seeds/seed-2024/seed_probs.npz +3 -0
  18. seeds/seed-2024/special_tokens_map.json +37 -0
  19. seeds/seed-2024/tokenizer.json +0 -0
  20. seeds/seed-2024/tokenizer_config.json +55 -0
  21. seeds/seed-2024/train_config.json +19 -0
  22. seeds/seed-2024/vocab.txt +0 -0
  23. seeds/seed-3141/DONE +1 -0
  24. seeds/seed-3141/config.json +59 -0
  25. seeds/seed-3141/eval.json +15 -0
  26. seeds/seed-3141/model.safetensors +3 -0
  27. seeds/seed-3141/seed.txt +1 -0
  28. seeds/seed-3141/seed_probs.npz +3 -0
  29. seeds/seed-3141/special_tokens_map.json +37 -0
  30. seeds/seed-3141/tokenizer.json +0 -0
  31. seeds/seed-3141/tokenizer_config.json +55 -0
  32. seeds/seed-3141/train_config.json +19 -0
  33. seeds/seed-3141/vocab.txt +0 -0
  34. seeds/seed-42/DONE +1 -0
  35. seeds/seed-42/config.json +59 -0
  36. seeds/seed-42/eval.json +15 -0
  37. seeds/seed-42/model.safetensors +3 -0
  38. seeds/seed-42/seed.txt +1 -0
  39. seeds/seed-42/seed_probs.npz +3 -0
  40. seeds/seed-42/special_tokens_map.json +37 -0
  41. seeds/seed-42/tokenizer.json +0 -0
  42. seeds/seed-42/tokenizer_config.json +55 -0
  43. seeds/seed-42/train_config.json +19 -0
  44. seeds/seed-42/vocab.txt +0 -0
  45. seeds/seed-456/DONE +1 -0
  46. seeds/seed-456/config.json +59 -0
  47. seeds/seed-456/eval.json +15 -0
  48. seeds/seed-456/model.safetensors +3 -0
  49. seeds/seed-456/seed.txt +1 -0
  50. seeds/seed-456/seed_probs.npz +3 -0
seeds/seed-123/DONE ADDED
@@ -0,0 +1 @@
 
 
1
+ 123
seeds/seed-123/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "LabelAttentionClassifier",
3
+ "encoder_model_name": "ibm-research/CTI-BERT",
4
+ "num_labels": 50,
5
+ "hidden_size": 768,
6
+ "labels": [
7
+ "T1003.001",
8
+ "T1005",
9
+ "T1012",
10
+ "T1016",
11
+ "T1021.001",
12
+ "T1027",
13
+ "T1033",
14
+ "T1036.005",
15
+ "T1041",
16
+ "T1047",
17
+ "T1053.005",
18
+ "T1055",
19
+ "T1056.001",
20
+ "T1057",
21
+ "T1059.003",
22
+ "T1068",
23
+ "T1070.004",
24
+ "T1071.001",
25
+ "T1072",
26
+ "T1074.001",
27
+ "T1078",
28
+ "T1082",
29
+ "T1083",
30
+ "T1090",
31
+ "T1095",
32
+ "T1105",
33
+ "T1106",
34
+ "T1110",
35
+ "T1112",
36
+ "T1113",
37
+ "T1140",
38
+ "T1190",
39
+ "T1204.002",
40
+ "T1210",
41
+ "T1218.011",
42
+ "T1219",
43
+ "T1484.001",
44
+ "T1518.001",
45
+ "T1543.003",
46
+ "T1547.001",
47
+ "T1548.002",
48
+ "T1552.001",
49
+ "T1557.001",
50
+ "T1562.001",
51
+ "T1564.001",
52
+ "T1566.001",
53
+ "T1569.002",
54
+ "T1570",
55
+ "T1573.001",
56
+ "T1574.002"
57
+ ],
58
+ "dropout": 0.1
59
+ }
seeds/seed-123/eval.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chose": "ema",
3
+ "dev_macro_f1": {
4
+ "base": 0.5447683478808304,
5
+ "ema": 0.5450964644737616,
6
+ "swa": 0.5405556130113931
7
+ },
8
+ "tau_0.5": {
9
+ "doc_f1": 0.7436287853187492,
10
+ "macro_f1": 0.5701923642028678,
11
+ "n_scored_docs": 30,
12
+ "n_skipped_empty_docs": 1
13
+ },
14
+ "n_swa_snapshots": 9
15
+ }
seeds/seed-123/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a589f51035a61bebb602e164b26970ab2cc8d4445721e2d2012edf9bf58c67
3
+ size 497946220
seeds/seed-123/seed.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 123
seeds/seed-123/seed_probs.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aa1625d9809aa250871fff55fb785879ed7c0235f346408c29888e7ac2423fe
3
+ size 1282290
seeds/seed-123/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
+ }
seeds/seed-123/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
seeds/seed-123/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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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
+ }
seeds/seed-123/train_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "recipe": "asl",
3
+ "dataset": "tram2",
4
+ "tag": "orig",
5
+ "encoder": "ibm-research/CTI-BERT",
6
+ "max_len": 512,
7
+ "lr": 2e-05,
8
+ "batch_size": 16,
9
+ "epochs": 30,
10
+ "val_size": 0.2,
11
+ "asl_gamma_neg": 4,
12
+ "asl_gamma_pos": 0,
13
+ "asl_clip": 0.05,
14
+ "swa_start_fraction": 0.75,
15
+ "min_positives_per_class": 10,
16
+ "llrd_decay": 0.85,
17
+ "ema_decay": 0.999,
18
+ "fp16": true
19
+ }
seeds/seed-123/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
seeds/seed-2024/DONE ADDED
@@ -0,0 +1 @@
 
 
1
+ 2024
seeds/seed-2024/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "LabelAttentionClassifier",
3
+ "encoder_model_name": "ibm-research/CTI-BERT",
4
+ "num_labels": 50,
5
+ "hidden_size": 768,
6
+ "labels": [
7
+ "T1003.001",
8
+ "T1005",
9
+ "T1012",
10
+ "T1016",
11
+ "T1021.001",
12
+ "T1027",
13
+ "T1033",
14
+ "T1036.005",
15
+ "T1041",
16
+ "T1047",
17
+ "T1053.005",
18
+ "T1055",
19
+ "T1056.001",
20
+ "T1057",
21
+ "T1059.003",
22
+ "T1068",
23
+ "T1070.004",
24
+ "T1071.001",
25
+ "T1072",
26
+ "T1074.001",
27
+ "T1078",
28
+ "T1082",
29
+ "T1083",
30
+ "T1090",
31
+ "T1095",
32
+ "T1105",
33
+ "T1106",
34
+ "T1110",
35
+ "T1112",
36
+ "T1113",
37
+ "T1140",
38
+ "T1190",
39
+ "T1204.002",
40
+ "T1210",
41
+ "T1218.011",
42
+ "T1219",
43
+ "T1484.001",
44
+ "T1518.001",
45
+ "T1543.003",
46
+ "T1547.001",
47
+ "T1548.002",
48
+ "T1552.001",
49
+ "T1557.001",
50
+ "T1562.001",
51
+ "T1564.001",
52
+ "T1566.001",
53
+ "T1569.002",
54
+ "T1570",
55
+ "T1573.001",
56
+ "T1574.002"
57
+ ],
58
+ "dropout": 0.1
59
+ }
seeds/seed-2024/eval.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chose": "swa",
3
+ "dev_macro_f1": {
4
+ "base": 0.5439013990885383,
5
+ "ema": 0.543554249784528,
6
+ "swa": 0.5475546922893236
7
+ },
8
+ "tau_0.5": {
9
+ "doc_f1": 0.703092004352701,
10
+ "macro_f1": 0.5492939798102902,
11
+ "n_scored_docs": 30,
12
+ "n_skipped_empty_docs": 1
13
+ },
14
+ "n_swa_snapshots": 9
15
+ }
seeds/seed-2024/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:159c63dd01083a770248174c04e767b0e2c00c9514e6f9a7a9193636ce1cb7ce
3
+ size 497946220
seeds/seed-2024/seed.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 2024
seeds/seed-2024/seed_probs.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d912d060e95fc8dc46cd65b513f9f0f7e46f6fe7c570d9cb5b2c1b53a18bcca5
3
+ size 1270124
seeds/seed-2024/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
+ }
seeds/seed-2024/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
seeds/seed-2024/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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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
+ }
seeds/seed-2024/train_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "recipe": "asl",
3
+ "dataset": "tram2",
4
+ "tag": "repl",
5
+ "encoder": "ibm-research/CTI-BERT",
6
+ "max_len": 512,
7
+ "lr": 2e-05,
8
+ "batch_size": 16,
9
+ "epochs": 30,
10
+ "val_size": 0.2,
11
+ "asl_gamma_neg": 4,
12
+ "asl_gamma_pos": 0,
13
+ "asl_clip": 0.05,
14
+ "swa_start_fraction": 0.75,
15
+ "min_positives_per_class": 10,
16
+ "llrd_decay": 0.85,
17
+ "ema_decay": 0.999,
18
+ "fp16": true
19
+ }
seeds/seed-2024/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
seeds/seed-3141/DONE ADDED
@@ -0,0 +1 @@
 
 
1
+ 3141
seeds/seed-3141/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "LabelAttentionClassifier",
3
+ "encoder_model_name": "ibm-research/CTI-BERT",
4
+ "num_labels": 50,
5
+ "hidden_size": 768,
6
+ "labels": [
7
+ "T1003.001",
8
+ "T1005",
9
+ "T1012",
10
+ "T1016",
11
+ "T1021.001",
12
+ "T1027",
13
+ "T1033",
14
+ "T1036.005",
15
+ "T1041",
16
+ "T1047",
17
+ "T1053.005",
18
+ "T1055",
19
+ "T1056.001",
20
+ "T1057",
21
+ "T1059.003",
22
+ "T1068",
23
+ "T1070.004",
24
+ "T1071.001",
25
+ "T1072",
26
+ "T1074.001",
27
+ "T1078",
28
+ "T1082",
29
+ "T1083",
30
+ "T1090",
31
+ "T1095",
32
+ "T1105",
33
+ "T1106",
34
+ "T1110",
35
+ "T1112",
36
+ "T1113",
37
+ "T1140",
38
+ "T1190",
39
+ "T1204.002",
40
+ "T1210",
41
+ "T1218.011",
42
+ "T1219",
43
+ "T1484.001",
44
+ "T1518.001",
45
+ "T1543.003",
46
+ "T1547.001",
47
+ "T1548.002",
48
+ "T1552.001",
49
+ "T1557.001",
50
+ "T1562.001",
51
+ "T1564.001",
52
+ "T1566.001",
53
+ "T1569.002",
54
+ "T1570",
55
+ "T1573.001",
56
+ "T1574.002"
57
+ ],
58
+ "dropout": 0.1
59
+ }
seeds/seed-3141/eval.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chose": "ema",
3
+ "dev_macro_f1": {
4
+ "base": 0.5417992408181854,
5
+ "ema": 0.5432634899722102,
6
+ "swa": 0.5401762405323272
7
+ },
8
+ "tau_0.5": {
9
+ "doc_f1": 0.6962908440035396,
10
+ "macro_f1": 0.5171692881057236,
11
+ "n_scored_docs": 30,
12
+ "n_skipped_empty_docs": 1
13
+ },
14
+ "n_swa_snapshots": 9
15
+ }
seeds/seed-3141/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fa2822845cb70a773a62136eeee0ad278bd53c6934d02c04b125c8df53ab662
3
+ size 497946220
seeds/seed-3141/seed.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 3141
seeds/seed-3141/seed_probs.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc90fa21dd786e6cd0c269c8ae0b50779895f6ccdd934d499d77a571ba7234c2
3
+ size 1279508
seeds/seed-3141/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
+ }
seeds/seed-3141/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
seeds/seed-3141/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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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
+ }
seeds/seed-3141/train_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "recipe": "asl",
3
+ "dataset": "tram2",
4
+ "tag": "repl",
5
+ "encoder": "ibm-research/CTI-BERT",
6
+ "max_len": 512,
7
+ "lr": 2e-05,
8
+ "batch_size": 16,
9
+ "epochs": 30,
10
+ "val_size": 0.2,
11
+ "asl_gamma_neg": 4,
12
+ "asl_gamma_pos": 0,
13
+ "asl_clip": 0.05,
14
+ "swa_start_fraction": 0.75,
15
+ "min_positives_per_class": 10,
16
+ "llrd_decay": 0.85,
17
+ "ema_decay": 0.999,
18
+ "fp16": true
19
+ }
seeds/seed-3141/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
seeds/seed-42/DONE ADDED
@@ -0,0 +1 @@
 
 
1
+ 42
seeds/seed-42/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "LabelAttentionClassifier",
3
+ "encoder_model_name": "ibm-research/CTI-BERT",
4
+ "num_labels": 50,
5
+ "hidden_size": 768,
6
+ "labels": [
7
+ "T1003.001",
8
+ "T1005",
9
+ "T1012",
10
+ "T1016",
11
+ "T1021.001",
12
+ "T1027",
13
+ "T1033",
14
+ "T1036.005",
15
+ "T1041",
16
+ "T1047",
17
+ "T1053.005",
18
+ "T1055",
19
+ "T1056.001",
20
+ "T1057",
21
+ "T1059.003",
22
+ "T1068",
23
+ "T1070.004",
24
+ "T1071.001",
25
+ "T1072",
26
+ "T1074.001",
27
+ "T1078",
28
+ "T1082",
29
+ "T1083",
30
+ "T1090",
31
+ "T1095",
32
+ "T1105",
33
+ "T1106",
34
+ "T1110",
35
+ "T1112",
36
+ "T1113",
37
+ "T1140",
38
+ "T1190",
39
+ "T1204.002",
40
+ "T1210",
41
+ "T1218.011",
42
+ "T1219",
43
+ "T1484.001",
44
+ "T1518.001",
45
+ "T1543.003",
46
+ "T1547.001",
47
+ "T1548.002",
48
+ "T1552.001",
49
+ "T1557.001",
50
+ "T1562.001",
51
+ "T1564.001",
52
+ "T1566.001",
53
+ "T1569.002",
54
+ "T1570",
55
+ "T1573.001",
56
+ "T1574.002"
57
+ ],
58
+ "dropout": 0.1
59
+ }
seeds/seed-42/eval.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chose": "swa",
3
+ "dev_macro_f1": {
4
+ "base": 0.5383158873383864,
5
+ "ema": 0.53580089596625,
6
+ "swa": 0.5414597211784158
7
+ },
8
+ "tau_0.5": {
9
+ "doc_f1": 0.7292129677362525,
10
+ "macro_f1": 0.5504301683233094,
11
+ "n_scored_docs": 30,
12
+ "n_skipped_empty_docs": 1
13
+ },
14
+ "n_swa_snapshots": 9
15
+ }
seeds/seed-42/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3854abd4e100caf629e1d5f30ec42aeb308015e57b21fbd4eb871f3680c557cc
3
+ size 497946220
seeds/seed-42/seed.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 42
seeds/seed-42/seed_probs.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d9f8f124a67f9ff1854b4442b27b6b473df0fd09b08791458fefb835ecd2fe
3
+ size 1284401
seeds/seed-42/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
+ }
seeds/seed-42/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
seeds/seed-42/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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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
+ }
seeds/seed-42/train_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "recipe": "asl",
3
+ "dataset": "tram2",
4
+ "tag": "orig",
5
+ "encoder": "ibm-research/CTI-BERT",
6
+ "max_len": 512,
7
+ "lr": 2e-05,
8
+ "batch_size": 16,
9
+ "epochs": 30,
10
+ "val_size": 0.2,
11
+ "asl_gamma_neg": 4,
12
+ "asl_gamma_pos": 0,
13
+ "asl_clip": 0.05,
14
+ "swa_start_fraction": 0.75,
15
+ "min_positives_per_class": 10,
16
+ "llrd_decay": 0.85,
17
+ "ema_decay": 0.999,
18
+ "fp16": true
19
+ }
seeds/seed-42/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
seeds/seed-456/DONE ADDED
@@ -0,0 +1 @@
 
 
1
+ 456
seeds/seed-456/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "LabelAttentionClassifier",
3
+ "encoder_model_name": "ibm-research/CTI-BERT",
4
+ "num_labels": 50,
5
+ "hidden_size": 768,
6
+ "labels": [
7
+ "T1003.001",
8
+ "T1005",
9
+ "T1012",
10
+ "T1016",
11
+ "T1021.001",
12
+ "T1027",
13
+ "T1033",
14
+ "T1036.005",
15
+ "T1041",
16
+ "T1047",
17
+ "T1053.005",
18
+ "T1055",
19
+ "T1056.001",
20
+ "T1057",
21
+ "T1059.003",
22
+ "T1068",
23
+ "T1070.004",
24
+ "T1071.001",
25
+ "T1072",
26
+ "T1074.001",
27
+ "T1078",
28
+ "T1082",
29
+ "T1083",
30
+ "T1090",
31
+ "T1095",
32
+ "T1105",
33
+ "T1106",
34
+ "T1110",
35
+ "T1112",
36
+ "T1113",
37
+ "T1140",
38
+ "T1190",
39
+ "T1204.002",
40
+ "T1210",
41
+ "T1218.011",
42
+ "T1219",
43
+ "T1484.001",
44
+ "T1518.001",
45
+ "T1543.003",
46
+ "T1547.001",
47
+ "T1548.002",
48
+ "T1552.001",
49
+ "T1557.001",
50
+ "T1562.001",
51
+ "T1564.001",
52
+ "T1566.001",
53
+ "T1569.002",
54
+ "T1570",
55
+ "T1573.001",
56
+ "T1574.002"
57
+ ],
58
+ "dropout": 0.1
59
+ }
seeds/seed-456/eval.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chose": "base",
3
+ "dev_macro_f1": {
4
+ "base": 0.5368901292861008,
5
+ "ema": 0.5359361185807793,
6
+ "swa": 0.5310670323478536
7
+ },
8
+ "tau_0.5": {
9
+ "doc_f1": 0.7333488198828281,
10
+ "macro_f1": 0.5704794001767052,
11
+ "n_scored_docs": 30,
12
+ "n_skipped_empty_docs": 1
13
+ },
14
+ "n_swa_snapshots": 9
15
+ }
seeds/seed-456/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f86cb76a634ba0499b6c86af3598689890e8137d70da1b4a495dde10e939506
3
+ size 497946220
seeds/seed-456/seed.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 456
seeds/seed-456/seed_probs.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:396c6ee757167a33a5bca92f58cb006bf917f466b9fbaefdd80ada654d1daac2
3
+ size 1285535