Hugging Face's logo

cassandra-anon
/
cassandra-bce-tram2

Text Classification
PyTorch
Safetensors
English
cti
attack-classification
mitre-attack
cybersecurity
multi-label-classification
Model card Files
xet
 Community
cassandra-anon commited on
Commit
c7eab6d
·
verified ·
1 Parent(s): 6a3e113

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

Browse files
Files changed (33) hide show
  1. seeds/seed-123/DONE +1 -0
  2. seeds/seed-123/config.json +59 -0
  3. seeds/seed-123/eval.json +11 -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 +15 -0
  11. seeds/seed-123/vocab.txt +0 -0
  12. seeds/seed-42/DONE +1 -0
  13. seeds/seed-42/config.json +59 -0
  14. seeds/seed-42/eval.json +11 -0
  15. seeds/seed-42/model.safetensors +3 -0
  16. seeds/seed-42/seed.txt +1 -0
  17. seeds/seed-42/seed_probs.npz +3 -0
  18. seeds/seed-42/special_tokens_map.json +37 -0
  19. seeds/seed-42/tokenizer.json +0 -0
  20. seeds/seed-42/tokenizer_config.json +55 -0
  21. seeds/seed-42/train_config.json +15 -0
  22. seeds/seed-42/vocab.txt +0 -0
  23. seeds/seed-456/DONE +1 -0
  24. seeds/seed-456/config.json +59 -0
  25. seeds/seed-456/eval.json +11 -0
  26. seeds/seed-456/model.safetensors +3 -0
  27. seeds/seed-456/seed.txt +1 -0
  28. seeds/seed-456/seed_probs.npz +3 -0
  29. seeds/seed-456/special_tokens_map.json +37 -0
  30. seeds/seed-456/tokenizer.json +0 -0
  31. seeds/seed-456/tokenizer_config.json +55 -0
  32. seeds/seed-456/train_config.json +15 -0
  33. seeds/seed-456/vocab.txt +0 -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 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chose": "ema",
3
+ "tau_0.5": {
4
+ "doc_f1": 0.7196976724707009,
5
+ "macro_f1": 0.5765183923131331,
6
+ "micro_f1": 0.6347363328495405,
7
+ "n_pred_sents": 849,
8
+ "n_scored_docs": 30,
9
+ "n_skipped_empty_docs": 1
10
+ }
11
+ }
seeds/seed-123/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e6f6d4d3a76272de79c7d5ff0f26c2a23522983fbcc31bbdd73671063a8d321
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:abf4f0a0136c81145f6186e40edfb16e0a3baa37d6ab512ec78f19fcd2ba19cb
3
+ size 1268517
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "recipe": "bce",
3
+ "dataset": "tram2",
4
+ "encoder": "ibm-research/CTI-BERT",
5
+ "max_len": 512,
6
+ "lr": 2e-05,
7
+ "batch_size": 16,
8
+ "epochs": 30,
9
+ "pos_weight": 5.0,
10
+ "val_size": 0.2,
11
+ "llrd_decay": 0.85,
12
+ "ema_decay": 0.999,
13
+ "tau": 0.5,
14
+ "fp16": true
15
+ }
seeds/seed-123/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 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chose": "ema",
3
+ "tau_0.5": {
4
+ "doc_f1": 0.737768527094809,
5
+ "macro_f1": 0.5876626130480045,
6
+ "micro_f1": 0.6471153846153846,
7
+ "n_pred_sents": 841,
8
+ "n_scored_docs": 30,
9
+ "n_skipped_empty_docs": 1
10
+ }
11
+ }
seeds/seed-42/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d647df9dba0a3b64f63ae9ef66d598cbd04a54d2542d06aca6b93725c6268ab
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:a7ecfcb3c1f88b8c0d7ffe2a81955fa989bd5bf74d986876473ca5c6aa03b2c9
3
+ size 1271273
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "recipe": "bce",
3
+ "dataset": "tram2",
4
+ "encoder": "ibm-research/CTI-BERT",
5
+ "max_len": 512,
6
+ "lr": 2e-05,
7
+ "batch_size": 16,
8
+ "epochs": 30,
9
+ "pos_weight": 5.0,
10
+ "val_size": 0.2,
11
+ "llrd_decay": 0.85,
12
+ "ema_decay": 0.999,
13
+ "tau": 0.5,
14
+ "fp16": true
15
+ }
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 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chose": "ema",
3
+ "tau_0.5": {
4
+ "doc_f1": 0.7559180497441368,
5
+ "macro_f1": 0.5936221164387891,
6
+ "micro_f1": 0.6527117031398668,
7
+ "n_pred_sents": 855,
8
+ "n_scored_docs": 30,
9
+ "n_skipped_empty_docs": 1
10
+ }
11
+ }
seeds/seed-456/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1410844bba28e54988fd50b807174d8f5e810d471822a033a4d55bb5e1bee797
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 sha256:7a72153ab715392c1cdaf879955daec7101408e9c22a113c32924bc62c0b5607
3
+ size 1271246
seeds/seed-456/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-456/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
seeds/seed-456/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-456/train_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "recipe": "bce",
3
+ "dataset": "tram2",
4
+ "encoder": "ibm-research/CTI-BERT",
5
+ "max_len": 512,
6
+ "lr": 2e-05,
7
+ "batch_size": 16,
8
+ "epochs": 30,
9
+ "pos_weight": 5.0,
10
+ "val_size": 0.2,
11
+ "llrd_decay": 0.85,
12
+ "ema_decay": 0.999,
13
+ "tau": 0.5,
14
+ "fp16": true
15
+ }
seeds/seed-456/vocab.txt ADDED
The diff for this file is too large to render. See raw diff