Training update: 1,260/67,618 rows (1.86%) | +1000 new @ 2025-10-20 05:45:35

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 **0.38%** of planned data.
+- Status: **Early version** — trained on **1.86%** 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 (0.38%) 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 (1.86%) 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**: 260 / 67,618 (0.38%)
+- **Trained records**: 1,260 / 67,618 (1.86%)
 - **Learning rate**: 5e-05
 - **Epochs**: 3
 - **Batch size**: 1

checkpoint-3000/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-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4e1367fc7a89da294decbd67eaa8eb5a499457cddc489370ba5a0f4153c787
+size 17671560

checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f3d4b0dc5d9162cedaef7ce24293392b826376597d38f00b4e75b6f7432cd6
+size 35368075

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614cb7ee07bcc630aff3eb7dd33cd92ae6119a7d8316ea8ffddb9e98386fb60c
+size 14455

checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7801c757c2fe5906123b9cd33a124fb76c352678272072d20002c052fe674b7d
+size 1465

checkpoint-3000/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-3000/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-3000/trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 18.73765754699707,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 2.1984,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 51.54933166503906,
+      "learning_rate": 4.966312056737589e-05,
+      "loss": 2.1209,
+      "step": 200
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 32.52346420288086,
+      "learning_rate": 4.789007092198582e-05,
+      "loss": 2.1384,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 35.90546417236328,
+      "learning_rate": 4.6117021276595746e-05,
+      "loss": 2.095,
+      "step": 400
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 29.83684730529785,
+      "learning_rate": 4.4343971631205674e-05,
+      "loss": 1.9609,
+      "step": 500
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 25.847257614135742,
+      "learning_rate": 4.25709219858156e-05,
+      "loss": 1.8644,
+      "step": 600
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 44.531307220458984,
+      "learning_rate": 4.079787234042554e-05,
+      "loss": 1.8201,
+      "step": 700
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 36.09579849243164,
+      "learning_rate": 3.902482269503546e-05,
+      "loss": 1.6903,
+      "step": 800
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 25.78478240966797,
+      "learning_rate": 3.7251773049645395e-05,
+      "loss": 1.5981,
+      "step": 900
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 26.695831298828125,
+      "learning_rate": 3.547872340425532e-05,
+      "loss": 1.6652,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 31.150781631469727,
+      "learning_rate": 3.3705673758865245e-05,
+      "loss": 1.5633,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 37.66817092895508,
+      "learning_rate": 3.193262411347518e-05,
+      "loss": 1.5541,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 26.20791244506836,
+      "learning_rate": 3.0159574468085105e-05,
+      "loss": 1.516,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 22.03032684326172,
+      "learning_rate": 2.8386524822695037e-05,
+      "loss": 1.6995,
+      "step": 1400
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 19.463829040527344,
+      "learning_rate": 2.6613475177304965e-05,
+      "loss": 1.4198,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 12.715448379516602,
+      "learning_rate": 2.4840425531914897e-05,
+      "loss": 1.2346,
+      "step": 1600
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 23.795001983642578,
+      "learning_rate": 2.3067375886524825e-05,
+      "loss": 1.4306,
+      "step": 1700
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 35.95954132080078,
+      "learning_rate": 2.129432624113475e-05,
+      "loss": 1.5738,
+      "step": 1800
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 35.67465591430664,
+      "learning_rate": 1.9521276595744682e-05,
+      "loss": 1.4514,
+      "step": 1900
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 19.942232131958008,
+      "learning_rate": 1.774822695035461e-05,
+      "loss": 1.4458,
+      "step": 2000
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 18.1514949798584,
+      "learning_rate": 1.597517730496454e-05,
+      "loss": 1.5136,
+      "step": 2100
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 28.748600006103516,
+      "learning_rate": 1.420212765957447e-05,
+      "loss": 1.5163,
+      "step": 2200
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 16.781105041503906,
+      "learning_rate": 1.2429078014184398e-05,
+      "loss": 1.3713,
+      "step": 2300
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 13.730096817016602,
+      "learning_rate": 1.0656028368794328e-05,
+      "loss": 1.5527,
+      "step": 2400
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 40.0937614440918,
+      "learning_rate": 8.882978723404256e-06,
+      "loss": 1.3158,
+      "step": 2500
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 58.328670501708984,
+      "learning_rate": 7.109929078014185e-06,
+      "loss": 1.4293,
+      "step": 2600
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 22.44051742553711,
+      "learning_rate": 5.336879432624114e-06,
+      "loss": 1.3321,
+      "step": 2700
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 38.144752502441406,
+      "learning_rate": 3.563829787234043e-06,
+      "loss": 1.2445,
+      "step": 2800
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 21.987308502197266,
+      "learning_rate": 1.790780141843972e-06,
+      "loss": 1.5435,
+      "step": 2900
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 32.320709228515625,
+      "learning_rate": 1.773049645390071e-08,
+      "loss": 1.3325,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3000,
+  "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": 4092733440000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c57c5de3eaba678d4bafcb1b8d5390e895d371b501b5b1b46356182c51fc0da
+size 5841

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b85317e9a2f99711546b6e16863386c4a09af95d204635546723ec5e2ede845
+oid sha256:ea4e1367fc7a89da294decbd67eaa8eb5a499457cddc489370ba5a0f4153c787
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d463622f4d220e0c62d2a0a1f79afb5f4bee9c1831f3af26ac9165ffc83278bb
+oid sha256:6c57c5de3eaba678d4bafcb1b8d5390e895d371b501b5b1b46356182c51fc0da
 size 5841

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "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,
+  "trained_at": 1760939135.9935098,
+  "trained_at_readable": "2025-10-20 05:45:35",
+  "samples_this_session": 1000,
+  "new_rows_this_session": 1000,
+  "trained_rows_total": 1260,
   "total_db_rows": 67618,
-  "percentage": 0.3845129994971753,
+  "percentage": 1.863409151409388,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05