codechrl commited on
Commit
4cd0124
·
verified ·
1 Parent(s): 63ab79d

Training update: 163,264/336,594 rows (48.50%) | +2 new @ 2026-03-11 03:30:43

Browse files
README.md CHANGED
@@ -76,8 +76,8 @@ Since cybersecurity data often contains lengthy alert descriptions and execution
76
 
77
  ### Training Data
78
  - **Total database rows**: 336,594
79
- - **Rows processed (cumulative)**: 163,262 (48.50%)
80
- - **Training date**: 2026-03-11 10:06:54
81
 
82
  ### Post-Training Metrics
83
  - **Final training loss**:
 
76
 
77
  ### Training Data
78
  - **Total database rows**: 336,594
79
+ - **Rows processed (cumulative)**: 163,264 (48.50%)
80
+ - **Training date**: 2026-03-11 03:30:43
81
 
82
  ### Post-Training Metrics
83
  - **Final training loss**:
config.json CHANGED
@@ -22,7 +22,7 @@
22
  "pad_token_id": 0,
23
  "position_embedding_type": "absolute",
24
  "tie_word_embeddings": true,
25
- "transformers_version": "5.2.0",
26
  "type_vocab_size": 2,
27
  "use_cache": false,
28
  "vocab_size": 30522
 
22
  "pad_token_id": 0,
23
  "position_embedding_type": "absolute",
24
  "tie_word_embeddings": true,
25
+ "transformers_version": "5.3.0",
26
  "type_vocab_size": 2,
27
  "use_cache": false,
28
  "vocab_size": 30522
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c8683bad3e8100351f331bb9af101fab4a51c5b7b8da3f28ba377e1aebbf542
3
  size 17671552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e80edb3730e5825a36bcd212ff356f76f416679a17f6e8c3a0cf1f00297839ec
3
  size 17671552
tokenizer_config.json CHANGED
@@ -6,12 +6,19 @@
6
  "do_lower_case": true,
7
  "is_local": false,
8
  "mask_token": "[MASK]",
 
9
  "model_max_length": 1000000000000000019884624838656,
10
  "never_split": null,
 
11
  "pad_token": "[PAD]",
 
 
12
  "sep_token": "[SEP]",
 
13
  "strip_accents": null,
14
  "tokenize_chinese_chars": true,
15
  "tokenizer_class": "BertTokenizer",
 
 
16
  "unk_token": "[UNK]"
17
  }
 
6
  "do_lower_case": true,
7
  "is_local": false,
8
  "mask_token": "[MASK]",
9
+ "max_length": 512,
10
  "model_max_length": 1000000000000000019884624838656,
11
  "never_split": null,
12
+ "pad_to_multiple_of": null,
13
  "pad_token": "[PAD]",
14
+ "pad_token_type_id": 0,
15
+ "padding_side": "right",
16
  "sep_token": "[SEP]",
17
+ "stride": 0,
18
  "strip_accents": null,
19
  "tokenize_chinese_chars": true,
20
  "tokenizer_class": "BertTokenizer",
21
+ "truncation_side": "right",
22
+ "truncation_strategy": "longest_first",
23
  "unk_token": "[UNK]"
24
  }
training_metadata.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "trained_at": 1773198414.7230554,
3
- "trained_at_readable": "2026-03-11 10:06:54",
4
- "samples_this_session": 89,
5
  "new_rows_this_session": 2,
6
- "trained_rows_total": 163262,
7
  "total_db_rows": 336594,
8
- "percentage": 48.50413257514988,
9
  "final_loss": 0,
10
  "epochs": 3,
11
  "learning_rate": 5e-05,
 
1
  {
2
+ "trained_at": 1773199843.8985076,
3
+ "trained_at_readable": "2026-03-11 03:30:43",
4
+ "samples_this_session": 894,
5
  "new_rows_this_session": 2,
6
+ "trained_rows_total": 163264,
7
  "total_db_rows": 336594,
8
+ "percentage": 48.50472676280623,
9
  "final_loss": 0,
10
  "epochs": 3,
11
  "learning_rate": 5e-05,