Training update: 260/67,618 rows (0.38%) | +100 new @ 2025-10-20 05:38:23

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 **0.24%** of planned data.
+- Status: **Early version** — trained on **0.38%** 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 (0.24%) 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 (0.38%) 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.
@@ -63,8 +63,8 @@ predicted_class = logits.argmax(dim=-1).item()
 
 ## 5. Training Details
 
-- **Trained records**: 160 / 67,618 (0.24%)
+- **Trained records**: 260 / 67,618 (0.38%)
 - **Learning rate**: 5e-05
 - **Epochs**: 3
-- **Batch size**: 8
+- **Batch size**: 1
 - **Max sequence length**: 512

checkpoint-300/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b85317e9a2f99711546b6e16863386c4a09af95d204635546723ec5e2ede845
+size 17671560

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba5c8d507f60f14b58e5d1ddec62c5f8925f5ebc742b3719184ca90f50388344
+size 35368075

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546db949bfe6c0e73d6de4a9d457835aad76014faad51918fc8737a3923f2a04
+size 14455

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6899f9f82cea064fe52ac09813b47d526ed686cbe04f0925eb7e665a0e61bfae
+size 1465

checkpoint-300/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 38.67572784423828,
+      "learning_rate": 3.563829787234043e-05,
+      "loss": 3.1389,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 57.85369110107422,
+      "learning_rate": 1.7907801418439718e-05,
+      "loss": 2.5113,
+      "step": 200
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 76.84485626220703,
+      "learning_rate": 1.773049645390071e-07,
+      "loss": 2.1936,
+      "step": 300
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 409273344000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d463622f4d220e0c62d2a0a1f79afb5f4bee9c1831f3af26ac9165ffc83278bb
+size 5841

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:129918f2e0757e71579981040d43e7eb8effd35aae51622ba0ee6cca97dcc811
+oid sha256:6b85317e9a2f99711546b6e16863386c4a09af95d204635546723ec5e2ede845
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c3f99d1b2b59eb11e0e6b1b29c895699e0cfe97c3c0f3ec2281a936854293a0
+oid sha256:d463622f4d220e0c62d2a0a1f79afb5f4bee9c1831f3af26ac9165ffc83278bb
 size 5841

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "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": 160,
+  "trained_at": 1760938703.1794386,
+  "trained_at_readable": "2025-10-20 05:38:23",
+  "samples_this_session": 100,
+  "new_rows_this_session": 100,
+  "trained_rows_total": 260,
   "total_db_rows": 67618,
-  "percentage": 0.23662338430595403,
+  "percentage": 0.3845129994971753,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05