Training update: 7,754/238,469 rows (3.25%) | +4922 new @ 2025-10-23 04:53:41

README.md

@@ -24,7 +24,7 @@ pipeline_tag: fill-mask
 - Model type: fine-tuned lightweight BERT variant  
 - Languages: English & Indonesia
 - Finetuned from: `boltuix/bert-micro`
-- Status: **Early version** — trained on **3.10%** of planned data.
+- Status: **Early version** — trained on **3.25%** of planned data.
 **Model sources**  
 - Base model: [boltuix/bert-micro](https://huggingface.co/boltuix/bert-micro)
 - Data: Cybersecurity Data
@@ -40,7 +40,7 @@ You can use this model to classify cybersecurity-related text — for example, w
 - Not optimized for languages other than English and Indonesian.  
 - Not tested for non-cybersecurity domains or out-of-distribution data.
 ## 3. Bias, Risks, and Limitations 
-Because the model is based on a small subset (3.10%) 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 (3.25%) 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.
 ## 4. How to Get Started with the Model  
@@ -74,11 +74,11 @@ Since cybersecurity data often contains lengthy alert descriptions and execution
 - **LR scheduler**: Linear with warmup
 
 ### Training Data
-- **Total database rows**: 238,461
-- **Rows processed (cumulative)**: 7,396 (3.10%)
-- **Rows in this session**: 358
-- **Training samples (after chunking)**: 5,575
-- **Training date**: 2025-10-23 04:06:52
+- **Total database rows**: 238,469
+- **Rows processed (cumulative)**: 7,754 (3.25%)
+- **Rows in this session**: 4,922
+- **Training samples (after chunking)**: 5,000
+- **Training date**: 2025-10-23 04:53:41
 
 ### Post-Training Metrics
 - **Final training loss**: 

config.json

@@ -17,7 +17,7 @@
   "num_hidden_layers": 2,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.57.0",
+  "transformers_version": "4.57.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d944ab1003df47a72c98e63c340a856db9daf0f5ce5e9ff7f9b1cd3a78be54b
+oid sha256:e34d67e8d356f460943f98143843d64ac1d706bd3d53a639e1776fafddce67af
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36fd20f724c8e961c678c7f1c4b979cd8088a71c668665d75605ee21e8212f0b
+oid sha256:1b6723809aae4d6e81df5bc3af0fef812aef6e4e443ec397ab0eca959b1da657
 size 5905

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1761192412.0134265,
-  "trained_at_readable": "2025-10-23 04:06:52",
-  "samples_this_session": 5575,
-  "new_rows_this_session": 358,
-  "trained_rows_total": 7396,
-  "total_db_rows": 238461,
-  "percentage": 3.1015553906089464,
+  "trained_at": 1761195221.323231,
+  "trained_at_readable": "2025-10-23 04:53:41",
+  "samples_this_session": 5000,
+  "new_rows_this_session": 4922,
+  "trained_rows_total": 7754,
+  "total_db_rows": 238469,
+  "percentage": 3.2515756765030255,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05,