add binary vulnerability model

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+base_model: microsoft/codebert-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: codebert-bin
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# codebert-bin
+
+This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0
+- Accuracy: 1.0
+- F1: 1.0
+- Roc Auc: 1.0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.55.0
+- Pytorch 2.7.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.21.2

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "non_vuln",
+    "1": "vuln"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "non_vuln": 0,
+    "vuln": 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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

final_metrics.json

@@ -0,0 +1,10 @@
+{
+  "eval_loss": 0.0,
+  "eval_accuracy": 1.0,
+  "eval_f1": 1.0,
+  "eval_roc_auc": 1.0,
+  "eval_runtime": 408.2672,
+  "eval_samples_per_second": 42.71,
+  "eval_steps_per_second": 2.67,
+  "epoch": 4.0
+}

metrics.csv

@@ -0,0 +1,71 @@
+epoch,step,split,loss,accuracy,f1,roc_auc
+0.05734602592040371,500,train,0.034,,,
+0.11469205184080743,1000,train,0.0001,,,
+0.17203807776121116,1500,train,0.0,,,
+0.22938410368161485,2000,train,0.0,,,
+0.2867301296020186,2500,train,0.0,,,
+0.3440761555224223,3000,train,0.0,,,
+0.401422181442826,3500,train,0.0,,,
+0.4587682073632297,4000,train,0.0,,,
+0.5161142332836335,4500,train,0.0,,,
+0.5734602592040372,5000,train,0.0,,,
+0.6308062851244409,5500,train,0.0,,,
+0.6881523110448446,6000,train,0.0,,,
+0.7454983369652483,6500,train,0.0,,,
+0.802844362885652,7000,train,0.0,,,
+0.8601903888060557,7500,train,0.0,,,
+0.9175364147264594,8000,train,0.0,,,
+0.9748824406468631,8500,train,0.0,,,
+1.032228466567267,9000,train,0.0,,,
+1.0895744924876707,9500,train,0.0,,,
+1.1469205184080744,10000,train,0.0,,,
+1.2042665443284781,10500,train,0.0,,,
+1.2616125702488818,11000,train,0.0,,,
+1.3189585961692853,11500,train,0.0,,,
+1.3763046220896893,12000,train,0.0,,,
+1.4336506480100928,12500,train,0.0,,,
+1.4909966739304967,13000,train,0.0,,,
+1.5483426998509002,13500,train,0.0,,,
+1.6056887257713042,14000,train,0.0,,,
+1.6630347516917077,14500,train,0.0,,,
+1.7203807776121116,15000,train,0.0,,,
+1.777726803532515,15500,train,0.0,,,
+1.835072829452919,16000,train,0.0,,,
+1.8924188553733226,16500,train,0.0,,,
+1.9497648812937265,17000,train,0.0,,,
+2.00711090721413,17500,train,0.0,,,
+2.064456933134534,18000,train,0.0,,,
+2.1218029590549374,18500,train,0.0,,,
+2.1791489849753414,19000,train,0.0,,,
+2.236495010895745,19500,train,0.0,,,
+2.293841036816149,20000,train,0.0,,,
+2.3511870627365523,20500,train,0.0,,,
+2.4085330886569563,21000,train,0.0,,,
+2.4658791145773598,21500,train,0.0,,,
+2.5232251404977637,22000,train,0.0,,,
+2.580571166418167,22500,train,0.0,,,
+2.6379171923385707,23000,train,0.0,,,
+2.6952632182589746,23500,train,0.0,,,
+2.7526092441793786,24000,train,0.0,,,
+2.809955270099782,24500,train,0.0,,,
+2.8673012960201856,25000,train,0.0,,,
+2.9246473219405895,25500,train,0.0,,,
+2.9819933478609935,26000,train,0.0,,,
+3.039339373781397,26500,train,0.0,,,
+3.0966853997018005,27000,train,0.0,,,
+3.1540314256222044,27500,train,0.0,,,
+3.211377451542608,28000,train,0.0,,,
+3.268723477463012,28500,train,0.0,,,
+3.3260695033834153,29000,train,0.0,,,
+3.3834155293038193,29500,train,0.0,,,
+3.440761555224223,30000,train,0.0,,,
+3.4981075811446267,30500,train,0.0,,,
+3.55545360706503,31000,train,0.0,,,
+3.612799632985434,31500,train,0.0,,,
+3.6701456589058377,32000,train,0.0,,,
+3.7274916848262416,32500,train,0.0,,,
+3.784837710746645,33000,train,0.0,,,
+3.842183736667049,33500,train,0.0,,,
+3.8995297625874525,34000,train,0.0,,,
+3.9568757885078565,34500,train,0.0,,,
+4.0,34876,eval,0.0,1.0,1.0,1.0

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb4944872d2fb9f6c02f497cd853979857fdc1134e06db9d0b7fd8df1f16ed2
+size 498612824

runs/Aug11_11-25-38_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1754911539.ip-172-31-31-181.ap-northeast-2.compute.internal.65513.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc0d60ba92d1046a2a797f2e1a85e507d56970fad30868c5bb7d03bacb782cd2
+size 5122

runs/Aug11_11-27-05_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1754911626.ip-172-31-31-181.ap-northeast-2.compute.internal.65607.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d78eeb385fc651b31f34fb88b4d360007197aa0d76b89e8ee4a320e8bc622c
+size 20189

runs/Aug11_11-27-05_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1754959428.ip-172-31-31-181.ap-northeast-2.compute.internal.65607.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da606df193e383d750528ad0ffeafc662aa86f071683b2e5de23d8b7aeb349f0
+size 516

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a2183ab1fed67759b3e2e4bb336206f3c7835af748e2007b948d9338eaad553
+size 5777