CIRCL/vulnerability-description-generation-gpt2

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: 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. -->
+
+# vulnerability
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8112
+
+## 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
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.0023        | 1.0   | 24029 | 1.9373          |
+| 0.937         | 2.0   | 48058 | 1.8403          |
+| 0.9287        | 3.0   | 72087 | 1.8112          |
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.1
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

emissions.csv

@@ -0,0 +1,3 @@
+timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
+2025-02-20T10:52:12,codecarbon,d351206f-c536-487e-9b9d-6dd923f68ba6,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,11060.430779200047,0.1966975604750237,1.778389688446204e-05,42.5,660.8094434377647,94.34470081329346,0.1304955346793106,1.4484598773780704,0.2896742153997869,1.8686296274571668,Luxembourg,LUX,luxembourg,,,Linux-6.8.0-48-generic-x86_64-with-glibc2.39,3.12.3,2.8.3,64,AMD EPYC 9124 16-Core Processor,2,2 x NVIDIA L40S,6.1294,49.6113,251.5858688354492,machine,N,1.0
+2025-02-24T12:30:18,codecarbon,cbc49903-c6b4-4c11-a5f0-19d2bfd1ba03,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,21351.801025332883,0.3785538638987247,1.7729364536958205e-05,42.5,181.56609208587705,94.34470081329346,0.2519147019968381,2.7851517931196383,0.5592006063220578,3.5962671014385363,Luxembourg,LUX,luxembourg,,,Linux-6.8.0-48-generic-x86_64-with-glibc2.39,3.12.3,2.8.3,64,AMD EPYC 9124 16-Core Processor,2,2 x NVIDIA L40S,6.1294,49.6113,251.58586883544922,machine,N,1.0

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.49.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:571d7484c95c00bf2a1e9c5ba1179df552c2de3c2628508b767ec2977bc2c756
+size 497774208

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8936963c9e1d8ad9629ed527b2028deedfedbf64e3ac8569ec3693cc4c6efaa5
+size 5304