PolyCoder-160M-Solidity-Vulnerability

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+base_model: NinedayWang/PolyCoder-160M
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: PolyCoder-Solidity-Vulnerability
+ 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. -->
+
+# PolyCoder-Solidity-Vulnerability
+
+This model is a fine-tuned version of [NinedayWang/PolyCoder-160M](https://huggingface.co/NinedayWang/PolyCoder-160M) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
+- Accuracy: 1.0
+- Precision: 1.0
+- Recall: 1.0
+- F1: 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:---:|
+| 0.0 | 1.0 | 4713 | 0.0000 | 1.0 | 1.0 | 1.0 | 1.0 |
+| 0.0 | 2.0 | 9426 | 0.0000 | 1.0 | 1.0 | 1.0 | 1.0 |
+| 0.0 | 3.0 | 14139 | 0.0000 | 1.0 | 1.0 | 1.0 | 1.0 |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+ "[PAD]": 50257
+}

config.json

@@ -0,0 +1,32 @@
+{
+ "_name_or_path": "NinedayWang/PolyCoder-160M",
+ "architectures": [
+ "GPTNeoXForSequenceClassification"
+ ],
+ "attention_bias": true,
+ "attention_dropout": 0.0,
+ "bos_token_id": 0,
+ "classifier_dropout": 0.1,
+ "eos_token_id": 0,
+ "hidden_act": "gelu",
+ "hidden_dropout": 0.0,
+ "hidden_size": 768,
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "layer_norm_eps": 1e-05,
+ "max_position_embeddings": 2048,
+ "model_type": "gpt_neox",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 12,
+ "problem_type": "single_label_classification",
+ "rope_scaling": null,
+ "rotary_emb_base": 10000,
+ "rotary_pct": 1.0,
+ "tie_word_embeddings": false,
+ "tokenizer_class": "GPT2Tokenizer",
+ "torch_dtype": "float32",
+ "transformers_version": "4.44.2",
+ "use_cache": true,
+ "use_parallel_residual": false,
+ "vocab_size": 50304
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:143d7ff22657222e0177ef31350e2c9e5f35b4849ef52ce15aba8751ff43433c
+size 494780976

runs/Oct03_08-12-33_db064635da8c/events.out.tfevents.1727943161.db064635da8c.740.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a081f3f836e8ebcdb1f005fdbfbb36cfbc7b7d65be94cf27df8b68a5a4e27bce
+size 12771

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+ "bos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+ "add_bos_token": false,
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "50257": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|endoftext|>",
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|endoftext|>",
+ "errors": "replace",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "[PAD]",
+ "tokenizer_class": "GPT2Tokenizer",
+ "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80742630328b6430f0dc19c7cdd086908e6ecb9d243453cfe9188d319272e994
+size 5240