Upload folder using huggingface_hub

README.md

@@ -0,0 +1,33 @@
+# microsoft/codebert-base Script Detector
+
+## Summary
+
+| Field | Value |
+| --- | --- |
+| Base model | `microsoft/codebert-base` |
+| Phase | `phase1` |
+| Target repo | `HID-APP/script-detector-microsoft-codebert-base` |
+| Datasets | `HID-APP/All-combined` |
+| Text column | `text` |
+| Epochs | 3.0000 |
+| Max length | 512 |
+| Train batch size | 4 |
+| Eval batch size | 8 |
+| Gradient accumulation steps | 4 |
+| Learning rate | 0.0000 |
+| Precision | fp16 |
+| Optimizer | adamw_torch |
+| Dataloader workers | 0 |
+| Gradient checkpointing | False |
+| Group by length | True |
+| LoRA enabled | False |
+
+## Dataset Sources
+
+| Source | Type | Revision | Fingerprint |
+| --- | --- | --- | --- |
+| HID-APP/All-combined | huggingface | default | 81f16d3fdbb4f97d3574f5c78bce8ada7b15c9ccd625913daa095cae6d545d67 |
+
+## Training And Validation History
+
+_No rows._

model/config.json

@@ -0,0 +1,38 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 50265
+}

model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2915549735f198e99ce60ee0aee4ef2ff6cdb587fb24b4e07bcf5f6c8d9254
+size 498612824

model/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_log_history.json

@@ -0,0 +1,4 @@
+{
+  "log_history": [],
+  "last_upload": "step 200"
+}