Training update: 160/67,618 rows (0.24%) | +50 new @ 2025-10-20 05:36:12

README.md

@@ -18,7 +18,7 @@ base_model: boltuix/bert-micro
 - Model type: fine-tuned lightweight BERT variant  
 - Languages: English & Indonesia
 - Finetuned from: `boltuix/bert-micro`
-- Status: **Early version** — trained on **0.16%** of planned data).
+- Status: **Early version** — trained on **0.24%** of planned data.
 
 **Model sources**  
 - Base model: [boltuix/bert-micro](https://huggingface.co/boltuix/bert-micro)
@@ -41,7 +41,7 @@ You can use this model to classify cybersecurity-related text — for example, w
 
 ## 3. Bias, Risks, and Limitations 
 
-Because the model is based on a small subset (0.16%) 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 (0.24%) 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.
@@ -63,7 +63,7 @@ predicted_class = logits.argmax(dim=-1).item()
 
 ## 5. Training Details
 
-- **Trained records**: 110 / 67,618 (0.16%)
+- **Trained records**: 160 / 67,618 (0.24%)
 - **Learning rate**: 5e-05
 - **Epochs**: 3
 - **Batch size**: 8

checkpoint-21/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fccffc8436212a980c3a25ef5c4583dfed723e4f0c1c8857ea354d783347165c
+oid sha256:129918f2e0757e71579981040d43e7eb8effd35aae51622ba0ee6cca97dcc811
 size 17671560

checkpoint-21/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e0a700261a075b2798ae3c3216f142d1949a2c849645138e8de3eb2613a50d6
+oid sha256:9db07e2399dd1fc14201d048dbb3d9edcae98c25206d30834d65b3f67cd47a9a
 size 35368075

checkpoint-21/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc19d58cd6f4e9fa4667b169e0aa27f6ade93802615c12a15ae7cfdf97b1d049
+oid sha256:9c3f99d1b2b59eb11e0e6b1b29c895699e0cfe97c3c0f3ec2281a936854293a0
 size 5841

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fccffc8436212a980c3a25ef5c4583dfed723e4f0c1c8857ea354d783347165c
+oid sha256:129918f2e0757e71579981040d43e7eb8effd35aae51622ba0ee6cca97dcc811
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc19d58cd6f4e9fa4667b169e0aa27f6ade93802615c12a15ae7cfdf97b1d049
+oid sha256:9c3f99d1b2b59eb11e0e6b1b29c895699e0cfe97c3c0f3ec2281a936854293a0
 size 5841

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1760938224.2996256,
-  "trained_at_readable": "2025-10-20 05:30:24",
+  "trained_at": 1760938572.525861,
+  "trained_at_readable": "2025-10-20 05:36:12",
   "samples_this_session": 50,
   "new_rows_this_session": 50,
-  "trained_rows_total": 110,
+  "trained_rows_total": 160,
   "total_db_rows": 67618,
-  "percentage": 0.1626785767103434,
+  "percentage": 0.23662338430595403,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05