Training update: 163,262/336,594 rows (48.50%) | +2 new @ 2026-03-11 10:06:54

README.md

@@ -25,7 +25,7 @@ pipeline_tag: fill-mask
 - Model type: fine-tuned lightweight BERT variant  
 - Languages: English & Indonesia
 - Finetuned from: `boltuix/bert-micro`
-- Status: **Early version** — trained on **66.14%** of planned data.
+- Status: **Early version** — trained on **48.50%** of planned data.
 
 **Model sources**  
 - Base model: [boltuix/bert-micro](https://huggingface.co/boltuix/bert-micro)
@@ -51,7 +51,7 @@ You can use this model to classify cybersecurity-related text — for example, w
 - Early classification of SIEM alert & events.
 
 ## 3. Bias, Risks, and Limitations 
-Because the model is based on a small subset (66.14%) of planned data, performance is preliminary and may degrade on unseen or specialized domains (industrial control, IoT logs, foreign language).
+Because the model is based on a small subset (48.50%) of planned data, performance is preliminary and may degrade on unseen or specialized domains (industrial control, IoT logs, foreign language).
 - Inherits any biases present in the base model (`boltuix/bert-micro`) and in the fine-tuning data — e.g., over-representation of certain threat types, vendor or tooling-specific vocabulary.
 - **Should not be used as sole authority for incident decisions; only as an aid to human analysts.**
 
@@ -75,9 +75,9 @@ Since cybersecurity data often contains lengthy alert descriptions and execution
 - **LR scheduler**: Linear with warmup
 
 ### Training Data
-- **Total database rows**: 246,838
-- **Rows processed (cumulative)**: 163,258 (66.14%)
-- **Training date**: 2025-12-30 04:18:17
+- **Total database rows**: 336,594
+- **Rows processed (cumulative)**: 163,262 (48.50%)
+- **Training date**: 2026-03-11 10:06:54
 
 ### Post-Training Metrics
 - **Final training loss**: 

config.json

@@ -1,15 +1,19 @@
 {
+  "add_cross_attention": false,
   "architectures": [
     "BertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
   "classifier_dropout": null,
   "dtype": "float32",
+  "eos_token_id": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 128,
   "initializer_range": 0.02,
   "intermediate_size": 512,
+  "is_decoder": false,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
@@ -17,8 +21,9 @@
   "num_hidden_layers": 2,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.57.3",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
   "type_vocab_size": 2,
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26c5935114f21374e4d0f3f42a947134eefbe480e99aafb1d50a514e0acb719a
-size 17671560
+oid sha256:2c8683bad3e8100351f331bb9af101fab4a51c5b7b8da3f28ba377e1aebbf542
+size 17671552

tokenizer_config.json

@@ -1,51 +1,10 @@
 {
-  "added_tokens_decoder": {
-    "0": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "101": {
-      "content": "[CLS]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "102": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
+  "backend": "tokenizers",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
-  "extra_special_tokens": {},
+  "is_local": false,
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "never_split": null,

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1767068297.1543417,
-  "trained_at_readable": "2025-12-30 04:18:17",
-  "samples_this_session": 1491,
-  "new_rows_this_session": 4,
-  "trained_rows_total": 163258,
-  "total_db_rows": 246838,
-  "percentage": 66.13973537299768,
+  "trained_at": 1773198414.7230554,
+  "trained_at_readable": "2026-03-11 10:06:54",
+  "samples_this_session": 89,
+  "new_rows_this_session": 2,
+  "trained_rows_total": 163262,
+  "total_db_rows": 336594,
+  "percentage": 48.50413257514988,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,