CIRCL/cwe-parent-vulnerability-classification-microsoft-graphcodebert-base
Browse files- README.md +100 -0
- config.json +52 -52
- emissions.csv +2 -0
- metrics.json +9 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
base_model: microsoft/graphcodebert-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: cwe-parent-vulnerability-classification-microsoft-graphcodebert-base
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# cwe-parent-vulnerability-classification-microsoft-graphcodebert-base
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [microsoft/graphcodebert-base](https://huggingface.co/microsoft/graphcodebert-base) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 2.8233
|
21 |
+
- Accuracy: 0.6517
|
22 |
+
- F1 Macro: 0.3050
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 1e-05
|
42 |
+
- train_batch_size: 32
|
43 |
+
- eval_batch_size: 32
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 40
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
53 |
+
| 3.255 | 1.0 | 25 | 3.2962 | 0.0225 | 0.0083 |
|
54 |
+
| 3.1345 | 2.0 | 50 | 3.3120 | 0.2697 | 0.0544 |
|
55 |
+
| 3.0539 | 3.0 | 75 | 3.3627 | 0.3820 | 0.0582 |
|
56 |
+
| 2.9349 | 4.0 | 100 | 3.3122 | 0.3596 | 0.0921 |
|
57 |
+
| 2.9555 | 5.0 | 125 | 3.2926 | 0.4045 | 0.1695 |
|
58 |
+
| 2.7748 | 6.0 | 150 | 3.3514 | 0.4607 | 0.1757 |
|
59 |
+
| 2.803 | 7.0 | 175 | 3.3219 | 0.5169 | 0.1884 |
|
60 |
+
| 2.67 | 8.0 | 200 | 3.2696 | 0.4831 | 0.2198 |
|
61 |
+
| 2.5684 | 9.0 | 225 | 3.2657 | 0.4944 | 0.2445 |
|
62 |
+
| 2.4226 | 10.0 | 250 | 3.1999 | 0.3371 | 0.1697 |
|
63 |
+
| 2.4615 | 11.0 | 275 | 3.1954 | 0.4270 | 0.1996 |
|
64 |
+
| 2.2738 | 12.0 | 300 | 3.1108 | 0.4157 | 0.1954 |
|
65 |
+
| 2.2423 | 13.0 | 325 | 3.0714 | 0.3933 | 0.1862 |
|
66 |
+
| 2.2066 | 14.0 | 350 | 3.0598 | 0.3820 | 0.1975 |
|
67 |
+
| 1.9919 | 15.0 | 375 | 3.0252 | 0.4382 | 0.1992 |
|
68 |
+
| 1.9622 | 16.0 | 400 | 2.9873 | 0.3708 | 0.1981 |
|
69 |
+
| 1.9415 | 17.0 | 425 | 2.9783 | 0.4494 | 0.2166 |
|
70 |
+
| 1.8459 | 18.0 | 450 | 2.9570 | 0.4831 | 0.2304 |
|
71 |
+
| 1.7008 | 19.0 | 475 | 2.9116 | 0.4607 | 0.2104 |
|
72 |
+
| 1.6705 | 20.0 | 500 | 2.9134 | 0.4607 | 0.2152 |
|
73 |
+
| 1.6422 | 21.0 | 525 | 2.9341 | 0.4607 | 0.2554 |
|
74 |
+
| 1.4982 | 22.0 | 550 | 2.8852 | 0.5056 | 0.2604 |
|
75 |
+
| 1.5523 | 23.0 | 575 | 2.9029 | 0.5056 | 0.2555 |
|
76 |
+
| 1.3784 | 24.0 | 600 | 2.8782 | 0.5393 | 0.2840 |
|
77 |
+
| 1.4479 | 25.0 | 625 | 2.8525 | 0.5730 | 0.2558 |
|
78 |
+
| 1.2508 | 26.0 | 650 | 2.9039 | 0.5730 | 0.2563 |
|
79 |
+
| 1.3662 | 27.0 | 675 | 2.8784 | 0.6067 | 0.3081 |
|
80 |
+
| 1.2199 | 28.0 | 700 | 2.8704 | 0.6180 | 0.2729 |
|
81 |
+
| 1.1903 | 29.0 | 725 | 2.8577 | 0.6404 | 0.2811 |
|
82 |
+
| 1.1881 | 30.0 | 750 | 2.8612 | 0.6404 | 0.2890 |
|
83 |
+
| 1.1572 | 31.0 | 775 | 2.8371 | 0.6292 | 0.2968 |
|
84 |
+
| 1.0623 | 32.0 | 800 | 2.8413 | 0.6404 | 0.2969 |
|
85 |
+
| 1.0405 | 33.0 | 825 | 2.8233 | 0.6517 | 0.3050 |
|
86 |
+
| 1.1084 | 34.0 | 850 | 2.8323 | 0.6404 | 0.3012 |
|
87 |
+
| 1.0211 | 35.0 | 875 | 2.8341 | 0.6404 | 0.3042 |
|
88 |
+
| 1.0215 | 36.0 | 900 | 2.8391 | 0.6404 | 0.3006 |
|
89 |
+
| 0.9438 | 37.0 | 925 | 2.8321 | 0.6404 | 0.3006 |
|
90 |
+
| 0.9383 | 38.0 | 950 | 2.8266 | 0.6404 | 0.3012 |
|
91 |
+
| 1.017 | 39.0 | 975 | 2.8236 | 0.6404 | 0.3037 |
|
92 |
+
| 0.9262 | 40.0 | 1000 | 2.8264 | 0.6404 | 0.3037 |
|
93 |
+
|
94 |
+
|
95 |
+
### Framework versions
|
96 |
+
|
97 |
+
- Transformers 4.55.4
|
98 |
+
- Pytorch 2.7.1+cu126
|
99 |
+
- Datasets 4.0.0
|
100 |
+
- Tokenizers 0.21.2
|
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
ADDED
@@ -0,0 +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 |
+
2025-09-03T13:21:50,codecarbon,3e519de9-4764-48ec-9aaf-36761959b92c,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,384.9297951501794,0.006275683567718154,1.630344973755464e-05,42.5,419.7123319081902,94.34468507766725,0.004539716701293461,0.045002576835372565,0.010076789785281433,0.059619083321947444,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
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_loss": 2.823303461074829,
|
3 |
+
"eval_accuracy": 0.651685393258427,
|
4 |
+
"eval_f1_macro": 0.30500876658151677,
|
5 |
+
"eval_runtime": 0.2994,
|
6 |
+
"eval_samples_per_second": 297.285,
|
7 |
+
"eval_steps_per_second": 10.021,
|
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:c793f60354079a93a666ef4877e3ce3fe7fe19d6ecf5e9fa9cc2695314f21402
|
3 |
size 498686648
|