CodeBERTa fine-tuned on CodeXGLUE defect detection (V1)

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+base_model: huggingface/CodeBERTa-small-v1
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+model-index:
+- name: v1
+  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. -->
+
+# v1
+
+This model is a fine-tuned version of [huggingface/CodeBERTa-small-v1](https://huggingface.co/huggingface/CodeBERTa-small-v1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6553
+- Accuracy: 0.6354
+- F1 Weighted: 0.6336
+- F1 Vuln: 0.5847
+- Precision: 0.6339
+- Recall: 0.6354
+
+## 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: 32
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Weighted | F1 Vuln | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:-------:|:---------:|:------:|
+| 0.6492        | 1.0   | 682  | 0.6336          | 0.6032   | 0.6045      | 0.559   | 0.6068    | 0.6032 |
+| 0.5907        | 2.0   | 1364 | 0.6094          | 0.6296   | 0.631       | 0.5942  | 0.6348    | 0.6296 |
+| 0.5385        | 3.0   | 2046 | 0.6289          | 0.6442   | 0.6426      | 0.577   | 0.642     | 0.6442 |
+
+
+### Framework versions
+
+- Transformers 5.0.0
+- Pytorch 2.10.0+cu128
+- Datasets 4.8.5
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,36 @@
+{
+  "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": "CLEAN",
+    "1": "VULNERABLE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "CLEAN": 0,
+    "VULNERABLE": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 52000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1350cac69d192d72b45a285294f4acfc6df93b8e95878daa3e531ac4b09af578
+size 333822184

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,
+  "mask_token": "<mask>",
+  "max_len": 512,
+  "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 sha256:4c382a7e838a672e67b47ed58e030b3947f3a19df7dc8d8332114181f83fd0da
+size 5201