Final full upload: model files, checkpoints, evaluation results, logs, reports

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+prediction_results.csv filter=lfs diff=lfs merge=lfs -text

classification_report.txt

@@ -0,0 +1,26 @@
+Model: bert-base-uncased
+Hub repo: HID-APP/bert-rd-keystrokes
+
+Validation metrics:
+{
+  "eval_loss": 0.15841300785541534,
+  "eval_accuracy": 0.9671551288529561,
+  "eval_precision": 0.9712606139777923,
+  "eval_recall": 0.9860742705570292,
+  "eval_f1": 0.9786113853241197
+}
+
+Test metrics:
+Accuracy : 0.977099
+Precision: 0.978172
+Recall   : 0.991016
+F1       : 0.984552
+
+              precision    recall  f1-score   support
+
+      benign       0.97      0.94      0.96       518
+   malicious       0.98      0.99      0.98      1447
+
+    accuracy                           0.98      1965
+   macro avg       0.98      0.96      0.97      1965
+weighted avg       0.98      0.98      0.98      1965

config.json

@@ -0,0 +1,38 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "benign",
+    "1": "malicious"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "benign": 0,
+    "malicious": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b860aed1fe9e8f10386d08f1ed6d3e385beb590ed8e36e7cb342d7a0dd06d314
+size 437958624

prediction_results.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77b1f56003bc4918b785d752d0c32a7c9a4ac6607a765a0724434bba401698f
+size 46994651

summary.json

@@ -0,0 +1,11 @@
+{
+  "model": "bert-base-uncased",
+  "hub_model_id": "HID-APP/bert-rd-keystrokes",
+  "output_dir": "/kaggle/working/outputs/bert_rd_keystrokes",
+  "save_eval_push_steps": 500,
+  "logging_steps": 25,
+  "accuracy": 0.9770992366412213,
+  "precision": 0.9781718963165075,
+  "recall": 0.9910158949550795,
+  "f1": 0.984552008238929
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6356dffa425669d6696f329ab57522ceda02ab7fadb057794c10a172cb56de1f
+size 5201