CIRCL/cwe-parent-vulnerability-classification-roberta-base
Browse files- README.md +49 -52
- config.json +52 -52
- emissions.csv +1 -1
- metrics.json +6 -6
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -9,8 +9,6 @@ metrics:
|
|
| 9 |
model-index:
|
| 10 |
- name: cwe-parent-vulnerability-classification-roberta-base
|
| 11 |
results: []
|
| 12 |
-
datasets:
|
| 13 |
-
- CIRCL/vulnerability-cwe-patch
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -18,12 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# cwe-parent-vulnerability-classification-roberta-base
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base).
|
| 22 |
-
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
-
- Loss: 1.
|
| 25 |
-
- Accuracy: 0.
|
| 26 |
-
- F1 Macro: 0.
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -46,7 +43,7 @@ The following hyperparameters were used during training:
|
|
| 46 |
- train_batch_size: 32
|
| 47 |
- eval_batch_size: 32
|
| 48 |
- seed: 42
|
| 49 |
-
- optimizer: Use OptimizerNames.
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
- num_epochs: 40
|
| 52 |
|
|
@@ -54,51 +51,51 @@ The following hyperparameters were used during training:
|
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|
| 56 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
| 57 |
-
| 3.
|
| 58 |
-
|
|
| 59 |
-
|
|
| 60 |
-
|
|
| 61 |
-
|
|
| 62 |
-
|
|
| 63 |
-
|
|
| 64 |
-
|
|
| 65 |
-
|
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
-
|
|
| 69 |
-
|
|
| 70 |
-
|
|
| 71 |
-
|
|
| 72 |
-
|
|
| 73 |
-
|
|
| 74 |
-
|
|
| 75 |
-
|
|
| 76 |
-
|
|
| 77 |
-
|
|
| 78 |
-
|
|
| 79 |
-
|
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
|
| 98 |
|
| 99 |
### Framework versions
|
| 100 |
|
| 101 |
-
- Transformers 4.
|
| 102 |
-
- Pytorch 2.
|
| 103 |
-
- Datasets 4.
|
| 104 |
-
- Tokenizers 0.
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: cwe-parent-vulnerability-classification-roberta-base
|
| 11 |
results: []
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 16 |
|
| 17 |
# cwe-parent-vulnerability-classification-roberta-base
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
|
|
|
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.8213
|
| 22 |
+
- Accuracy: 0.5673
|
| 23 |
+
- F1 Macro: 0.3582
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 43 |
- train_batch_size: 32
|
| 44 |
- eval_batch_size: 32
|
| 45 |
- seed: 42
|
| 46 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- num_epochs: 40
|
| 49 |
|
|
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
| 54 |
+
| 3.2359 | 1.0 | 237 | 3.0937 | 0.0334 | 0.0114 |
|
| 55 |
+
| 2.3278 | 2.0 | 474 | 2.2992 | 0.4303 | 0.2323 |
|
| 56 |
+
| 1.8161 | 3.0 | 711 | 1.9653 | 0.5089 | 0.2917 |
|
| 57 |
+
| 1.6283 | 4.0 | 948 | 1.8788 | 0.5292 | 0.3007 |
|
| 58 |
+
| 1.3258 | 5.0 | 1185 | 1.8253 | 0.5864 | 0.3392 |
|
| 59 |
+
| 1.3328 | 6.0 | 1422 | 1.8213 | 0.5673 | 0.3582 |
|
| 60 |
+
| 1.2914 | 7.0 | 1659 | 1.8573 | 0.5900 | 0.3604 |
|
| 61 |
+
| 0.8614 | 8.0 | 1896 | 1.8345 | 0.6198 | 0.3810 |
|
| 62 |
+
| 0.8253 | 9.0 | 2133 | 2.0121 | 0.6067 | 0.3568 |
|
| 63 |
+
| 0.7363 | 10.0 | 2370 | 2.0059 | 0.6508 | 0.4071 |
|
| 64 |
+
| 0.6406 | 11.0 | 2607 | 2.0866 | 0.6472 | 0.3906 |
|
| 65 |
+
| 0.4574 | 12.0 | 2844 | 2.1904 | 0.6377 | 0.3902 |
|
| 66 |
+
| 0.4834 | 13.0 | 3081 | 2.2417 | 0.6281 | 0.3797 |
|
| 67 |
+
| 0.3078 | 14.0 | 3318 | 2.3233 | 0.6830 | 0.4132 |
|
| 68 |
+
| 0.3217 | 15.0 | 3555 | 2.4203 | 0.6639 | 0.4020 |
|
| 69 |
+
| 0.2823 | 16.0 | 3792 | 2.4227 | 0.6615 | 0.3918 |
|
| 70 |
+
| 0.2392 | 17.0 | 4029 | 2.6133 | 0.6865 | 0.3844 |
|
| 71 |
+
| 0.1956 | 18.0 | 4266 | 2.6611 | 0.6675 | 0.3789 |
|
| 72 |
+
| 0.1504 | 19.0 | 4503 | 2.7612 | 0.6746 | 0.4158 |
|
| 73 |
+
| 0.1109 | 20.0 | 4740 | 2.8752 | 0.6710 | 0.3776 |
|
| 74 |
+
| 0.1091 | 21.0 | 4977 | 3.0530 | 0.6949 | 0.3776 |
|
| 75 |
+
| 0.13 | 22.0 | 5214 | 3.0540 | 0.6889 | 0.3766 |
|
| 76 |
+
| 0.0797 | 23.0 | 5451 | 3.2854 | 0.6770 | 0.4038 |
|
| 77 |
+
| 0.145 | 24.0 | 5688 | 3.2146 | 0.6973 | 0.3877 |
|
| 78 |
+
| 0.1004 | 25.0 | 5925 | 3.4159 | 0.6937 | 0.3850 |
|
| 79 |
+
| 0.0486 | 26.0 | 6162 | 3.4003 | 0.6865 | 0.3767 |
|
| 80 |
+
| 0.0544 | 27.0 | 6399 | 3.3643 | 0.6889 | 0.3822 |
|
| 81 |
+
| 0.082 | 28.0 | 6636 | 3.4874 | 0.6913 | 0.3818 |
|
| 82 |
+
| 0.0468 | 29.0 | 6873 | 3.5810 | 0.6877 | 0.3815 |
|
| 83 |
+
| 0.0308 | 30.0 | 7110 | 3.7565 | 0.6949 | 0.3837 |
|
| 84 |
+
| 0.0366 | 31.0 | 7347 | 3.6714 | 0.6961 | 0.3814 |
|
| 85 |
+
| 0.0388 | 32.0 | 7584 | 3.8502 | 0.6973 | 0.3957 |
|
| 86 |
+
| 0.0341 | 33.0 | 7821 | 3.8415 | 0.6973 | 0.3973 |
|
| 87 |
+
| 0.0417 | 34.0 | 8058 | 3.9342 | 0.7056 | 0.3864 |
|
| 88 |
+
| 0.0218 | 35.0 | 8295 | 3.9367 | 0.6996 | 0.3843 |
|
| 89 |
+
| 0.0607 | 36.0 | 8532 | 3.9262 | 0.6996 | 0.3841 |
|
| 90 |
+
| 0.0148 | 37.0 | 8769 | 3.9609 | 0.7020 | 0.4189 |
|
| 91 |
+
| 0.0186 | 38.0 | 9006 | 3.9656 | 0.6985 | 0.3822 |
|
| 92 |
+
| 0.0387 | 39.0 | 9243 | 3.9738 | 0.7044 | 0.3850 |
|
| 93 |
+
| 0.008 | 40.0 | 9480 | 3.9906 | 0.7044 | 0.3861 |
|
| 94 |
|
| 95 |
|
| 96 |
### Framework versions
|
| 97 |
|
| 98 |
+
- Transformers 4.57.1
|
| 99 |
+
- Pytorch 2.9.1+cu128
|
| 100 |
+
- Datasets 4.4.1
|
| 101 |
+
- Tokenizers 0.22.1
|
config.json
CHANGED
|
@@ -11,62 +11,62 @@
|
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
"hidden_size": 768,
|
| 13 |
"id2label": {
|
| 14 |
-
"0": "
|
| 15 |
-
"1": "
|
| 16 |
-
"2": "
|
| 17 |
-
"3": "
|
| 18 |
-
"4": "
|
| 19 |
-
"5": "
|
| 20 |
-
"6": "
|
| 21 |
-
"7": "
|
| 22 |
-
"8": "
|
| 23 |
-
"9": "
|
| 24 |
-
"10": "
|
| 25 |
-
"11": "
|
| 26 |
-
"12": "
|
| 27 |
-
"13": "
|
| 28 |
-
"14": "
|
| 29 |
-
"15": "
|
| 30 |
-
"16": "
|
| 31 |
-
"17": "
|
| 32 |
-
"18": "
|
| 33 |
-
"19": "
|
| 34 |
-
"20": "
|
| 35 |
-
"21": "
|
| 36 |
-
"22": "
|
| 37 |
-
"23": "
|
| 38 |
-
"24": "
|
| 39 |
-
"25": "
|
| 40 |
},
|
| 41 |
"initializer_range": 0.02,
|
| 42 |
"intermediate_size": 3072,
|
| 43 |
"label2id": {
|
| 44 |
-
"
|
| 45 |
-
"
|
| 46 |
-
"
|
| 47 |
-
"
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
"
|
| 54 |
-
"
|
| 55 |
-
"
|
| 56 |
-
"
|
| 57 |
-
"
|
| 58 |
-
"
|
| 59 |
-
"
|
| 60 |
-
"
|
| 61 |
-
"
|
| 62 |
-
"
|
| 63 |
-
"
|
| 64 |
-
"
|
| 65 |
-
"
|
| 66 |
-
"
|
| 67 |
-
"
|
| 68 |
-
"
|
| 69 |
-
"
|
| 70 |
},
|
| 71 |
"layer_norm_eps": 1e-05,
|
| 72 |
"max_position_embeddings": 514,
|
|
|
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
"hidden_size": 768,
|
| 13 |
"id2label": {
|
| 14 |
+
"0": "1025",
|
| 15 |
+
"1": "1071",
|
| 16 |
+
"2": "131",
|
| 17 |
+
"3": "138",
|
| 18 |
+
"4": "284",
|
| 19 |
+
"5": "285",
|
| 20 |
+
"6": "435",
|
| 21 |
+
"7": "436",
|
| 22 |
+
"8": "595",
|
| 23 |
+
"9": "657",
|
| 24 |
+
"10": "664",
|
| 25 |
+
"11": "682",
|
| 26 |
+
"12": "684",
|
| 27 |
+
"13": "691",
|
| 28 |
+
"14": "693",
|
| 29 |
+
"15": "697",
|
| 30 |
+
"16": "703",
|
| 31 |
+
"17": "706",
|
| 32 |
+
"18": "707",
|
| 33 |
+
"19": "710",
|
| 34 |
+
"20": "74",
|
| 35 |
+
"21": "754",
|
| 36 |
+
"22": "829",
|
| 37 |
+
"23": "862",
|
| 38 |
+
"24": "913",
|
| 39 |
+
"25": "94"
|
| 40 |
},
|
| 41 |
"initializer_range": 0.02,
|
| 42 |
"intermediate_size": 3072,
|
| 43 |
"label2id": {
|
| 44 |
+
"1025": 0,
|
| 45 |
+
"1071": 1,
|
| 46 |
+
"131": 2,
|
| 47 |
+
"138": 3,
|
| 48 |
+
"284": 4,
|
| 49 |
+
"285": 5,
|
| 50 |
+
"435": 6,
|
| 51 |
+
"436": 7,
|
| 52 |
+
"595": 8,
|
| 53 |
+
"657": 9,
|
| 54 |
+
"664": 10,
|
| 55 |
+
"682": 11,
|
| 56 |
+
"684": 12,
|
| 57 |
+
"691": 13,
|
| 58 |
+
"693": 14,
|
| 59 |
+
"697": 15,
|
| 60 |
+
"703": 16,
|
| 61 |
+
"706": 17,
|
| 62 |
+
"707": 18,
|
| 63 |
+
"710": 19,
|
| 64 |
+
"74": 20,
|
| 65 |
+
"754": 21,
|
| 66 |
+
"829": 22,
|
| 67 |
+
"862": 23,
|
| 68 |
+
"913": 24,
|
| 69 |
+
"94": 25
|
| 70 |
},
|
| 71 |
"layer_norm_eps": 1e-05,
|
| 72 |
"max_position_embeddings": 514,
|
emissions.csv
CHANGED
|
@@ -1,2 +1,2 @@
|
|
| 1 |
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
|
| 2 |
-
2025-
|
|
|
|
| 1 |
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
|
| 2 |
+
2025-11-21T08:46:27,codecarbon,bc463c8d-dd69-42da-9801-e35dabee8711,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,2632.649387937039,0.050220601954459286,1.9076069219309326e-05,42.5,302.47241372038087,94.34468507766725,0.031054272330529063,0.3771095669652027,0.06893259491628256,0.4770964342120145,Luxembourg,LUX,luxembourg,,,Linux-6.8.0-71-generic-x86_64-with-glibc2.39,3.12.3,2.8.4,64,AMD EPYC 9124 16-Core Processor,2,2 x NVIDIA L40S,6.1294,49.6113,251.5858268737793,machine,N,1.0
|
metrics.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"eval_loss": 1.
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1_macro": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 10.
|
| 8 |
"epoch": 40.0
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"eval_loss": 1.821271300315857,
|
| 3 |
+
"eval_accuracy": 0.567342073897497,
|
| 4 |
+
"eval_f1_macro": 0.35818372664233605,
|
| 5 |
+
"eval_runtime": 2.5279,
|
| 6 |
+
"eval_samples_per_second": 331.898,
|
| 7 |
+
"eval_steps_per_second": 10.681,
|
| 8 |
"epoch": 40.0
|
| 9 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 498686648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:097c2c599cc7c651891edb18006e591e48223f014edd119eff30a1bd53d18dfc
|
| 3 |
size 498686648
|