CIRCL/cwe-parent-vulnerability-classification-roberta-base
Browse files- README.md +44 -39
- config.json +52 -52
- emissions.csv +1 -1
- metrics.json +7 -7
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 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:
|
| 22 |
-
- Accuracy: 0.
|
| 23 |
-
- F1 Macro: 0.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -45,47 +45,52 @@ The following hyperparameters were used during training:
|
|
| 45 |
- seed: 42
|
| 46 |
- optimizer: Use OptimizerNames.ADAMW_TORCH 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:
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
| 54 |
-
| 3.
|
| 55 |
-
| 3.
|
| 56 |
-
| 3.
|
| 57 |
-
|
|
| 58 |
-
|
|
| 59 |
-
| 2.
|
| 60 |
-
|
|
| 61 |
-
| 2.
|
| 62 |
-
| 2.
|
| 63 |
-
| 2.
|
| 64 |
-
| 2.
|
| 65 |
-
| 2.
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
-
| 1.
|
| 69 |
-
| 1.
|
| 70 |
-
| 1.
|
| 71 |
-
| 1.
|
| 72 |
-
| 1.
|
| 73 |
-
| 1.
|
| 74 |
-
| 1.
|
| 75 |
-
|
|
| 76 |
-
|
|
| 77 |
-
|
|
| 78 |
-
|
|
| 79 |
-
|
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 89 |
|
| 90 |
|
| 91 |
### Framework versions
|
|
|
|
| 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: 1.3447
|
| 22 |
+
- Accuracy: 0.7727
|
| 23 |
+
- F1 Macro: 0.4235
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 45 |
- seed: 42
|
| 46 |
- optimizer: Use OptimizerNames.ADAMW_TORCH 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 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
| 54 |
+
| 3.263 | 1.0 | 25 | 3.2313 | 0.2614 | 0.0345 |
|
| 55 |
+
| 3.1726 | 2.0 | 50 | 2.9923 | 0.1818 | 0.0431 |
|
| 56 |
+
| 3.1008 | 3.0 | 75 | 2.8828 | 0.0 | 0.0 |
|
| 57 |
+
| 2.9805 | 4.0 | 100 | 2.8858 | 0.0114 | 0.0019 |
|
| 58 |
+
| 3.0021 | 5.0 | 125 | 2.8257 | 0.4432 | 0.0626 |
|
| 59 |
+
| 2.8775 | 6.0 | 150 | 2.7730 | 0.0795 | 0.0462 |
|
| 60 |
+
| 2.8805 | 7.0 | 175 | 2.6421 | 0.2841 | 0.1362 |
|
| 61 |
+
| 2.6602 | 8.0 | 200 | 2.6462 | 0.3864 | 0.1366 |
|
| 62 |
+
| 2.5303 | 9.0 | 225 | 2.5584 | 0.3523 | 0.1461 |
|
| 63 |
+
| 2.5236 | 10.0 | 250 | 2.4933 | 0.4205 | 0.1209 |
|
| 64 |
+
| 2.3221 | 11.0 | 275 | 2.3458 | 0.5909 | 0.2232 |
|
| 65 |
+
| 2.1446 | 12.0 | 300 | 2.2679 | 0.625 | 0.2521 |
|
| 66 |
+
| 1.9937 | 13.0 | 325 | 2.1932 | 0.625 | 0.2736 |
|
| 67 |
+
| 1.8521 | 14.0 | 350 | 2.0372 | 0.6477 | 0.2881 |
|
| 68 |
+
| 1.7899 | 15.0 | 375 | 1.9494 | 0.6364 | 0.2679 |
|
| 69 |
+
| 1.5273 | 16.0 | 400 | 1.8457 | 0.6705 | 0.3205 |
|
| 70 |
+
| 1.4178 | 17.0 | 425 | 1.8276 | 0.6477 | 0.2931 |
|
| 71 |
+
| 1.335 | 18.0 | 450 | 1.7690 | 0.6591 | 0.3004 |
|
| 72 |
+
| 1.2685 | 19.0 | 475 | 1.6681 | 0.6705 | 0.3577 |
|
| 73 |
+
| 1.112 | 20.0 | 500 | 1.6399 | 0.6818 | 0.3152 |
|
| 74 |
+
| 1.01 | 21.0 | 525 | 1.5561 | 0.6932 | 0.3255 |
|
| 75 |
+
| 0.9637 | 22.0 | 550 | 1.5008 | 0.7159 | 0.4218 |
|
| 76 |
+
| 0.9571 | 23.0 | 575 | 1.5387 | 0.7045 | 0.3385 |
|
| 77 |
+
| 0.8213 | 24.0 | 600 | 1.5366 | 0.7159 | 0.4043 |
|
| 78 |
+
| 0.7538 | 25.0 | 625 | 1.4691 | 0.75 | 0.3942 |
|
| 79 |
+
| 0.7228 | 26.0 | 650 | 1.4826 | 0.7273 | 0.3872 |
|
| 80 |
+
| 0.7244 | 27.0 | 675 | 1.4789 | 0.7386 | 0.3915 |
|
| 81 |
+
| 0.6746 | 28.0 | 700 | 1.4439 | 0.7727 | 0.4322 |
|
| 82 |
+
| 0.5959 | 29.0 | 725 | 1.4202 | 0.7614 | 0.3942 |
|
| 83 |
+
| 0.5788 | 30.0 | 750 | 1.4339 | 0.7727 | 0.4002 |
|
| 84 |
+
| 0.5718 | 31.0 | 775 | 1.3723 | 0.7955 | 0.4431 |
|
| 85 |
+
| 0.5358 | 32.0 | 800 | 1.4186 | 0.7727 | 0.3812 |
|
| 86 |
+
| 0.5094 | 33.0 | 825 | 1.3722 | 0.7841 | 0.4579 |
|
| 87 |
+
| 0.5003 | 34.0 | 850 | 1.3955 | 0.7614 | 0.3786 |
|
| 88 |
+
| 0.4973 | 35.0 | 875 | 1.3733 | 0.8068 | 0.4635 |
|
| 89 |
+
| 0.4721 | 36.0 | 900 | 1.3447 | 0.7727 | 0.4235 |
|
| 90 |
+
| 0.4457 | 37.0 | 925 | 1.3622 | 0.7955 | 0.4573 |
|
| 91 |
+
| 0.4232 | 38.0 | 950 | 1.3736 | 0.7614 | 0.3986 |
|
| 92 |
+
| 0.4405 | 39.0 | 975 | 1.3683 | 0.7727 | 0.4235 |
|
| 93 |
+
| 0.437 | 40.0 | 1000 | 1.3642 | 0.7614 | 0.3986 |
|
| 94 |
|
| 95 |
|
| 96 |
### Framework versions
|
config.json
CHANGED
|
@@ -10,62 +10,62 @@
|
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
| 12 |
"id2label": {
|
| 13 |
-
"0": "
|
| 14 |
-
"1": "
|
| 15 |
-
"2": "
|
| 16 |
-
"3": "
|
| 17 |
-
"4": "
|
| 18 |
-
"5": "
|
| 19 |
-
"6": "
|
| 20 |
-
"7": "
|
| 21 |
-
"8": "
|
| 22 |
-
"9": "
|
| 23 |
-
"10": "
|
| 24 |
-
"11": "
|
| 25 |
-
"12": "
|
| 26 |
-
"13": "
|
| 27 |
-
"14": "
|
| 28 |
-
"15": "
|
| 29 |
-
"16": "
|
| 30 |
-
"17": "
|
| 31 |
-
"18": "
|
| 32 |
-
"19": "
|
| 33 |
-
"20": "
|
| 34 |
-
"21": "
|
| 35 |
-
"22": "
|
| 36 |
-
"23": "
|
| 37 |
-
"24": "
|
| 38 |
-
"25": "
|
| 39 |
},
|
| 40 |
"initializer_range": 0.02,
|
| 41 |
"intermediate_size": 3072,
|
| 42 |
"label2id": {
|
| 43 |
-
"
|
| 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 |
"layer_norm_eps": 1e-05,
|
| 71 |
"max_position_embeddings": 514,
|
|
|
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
| 12 |
"id2label": {
|
| 13 |
+
"0": "1025",
|
| 14 |
+
"1": "1071",
|
| 15 |
+
"2": "131",
|
| 16 |
+
"3": "138",
|
| 17 |
+
"4": "284",
|
| 18 |
+
"5": "285",
|
| 19 |
+
"6": "435",
|
| 20 |
+
"7": "436",
|
| 21 |
+
"8": "595",
|
| 22 |
+
"9": "657",
|
| 23 |
+
"10": "664",
|
| 24 |
+
"11": "682",
|
| 25 |
+
"12": "684",
|
| 26 |
+
"13": "691",
|
| 27 |
+
"14": "693",
|
| 28 |
+
"15": "697",
|
| 29 |
+
"16": "703",
|
| 30 |
+
"17": "706",
|
| 31 |
+
"18": "707",
|
| 32 |
+
"19": "710",
|
| 33 |
+
"20": "74",
|
| 34 |
+
"21": "754",
|
| 35 |
+
"22": "829",
|
| 36 |
+
"23": "862",
|
| 37 |
+
"24": "913",
|
| 38 |
+
"25": "94"
|
| 39 |
},
|
| 40 |
"initializer_range": 0.02,
|
| 41 |
"intermediate_size": 3072,
|
| 42 |
"label2id": {
|
| 43 |
+
"1025": 0,
|
| 44 |
+
"1071": 1,
|
| 45 |
+
"131": 2,
|
| 46 |
+
"138": 3,
|
| 47 |
+
"284": 4,
|
| 48 |
+
"285": 5,
|
| 49 |
+
"435": 6,
|
| 50 |
+
"436": 7,
|
| 51 |
+
"595": 8,
|
| 52 |
+
"657": 9,
|
| 53 |
+
"664": 10,
|
| 54 |
+
"682": 11,
|
| 55 |
+
"684": 12,
|
| 56 |
+
"691": 13,
|
| 57 |
+
"693": 14,
|
| 58 |
+
"697": 15,
|
| 59 |
+
"703": 16,
|
| 60 |
+
"706": 17,
|
| 61 |
+
"707": 18,
|
| 62 |
+
"710": 19,
|
| 63 |
+
"74": 20,
|
| 64 |
+
"754": 21,
|
| 65 |
+
"829": 22,
|
| 66 |
+
"862": 23,
|
| 67 |
+
"913": 24,
|
| 68 |
+
"94": 25
|
| 69 |
},
|
| 70 |
"layer_norm_eps": 1e-05,
|
| 71 |
"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 |
-
2025-09-02T09:
|
|
|
|
| 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 |
+
2025-09-02T09:27:51,codecarbon,e4ad32bd-2245-4e4a-8192-6a84da1b81b1,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,459.1436821189709,0.007866215688287334,1.7132361817512892e-05,42.5,439.47611356781334,94.34468507766725,0.005415837676420698,0.05729426472426269,0.012019058731787975,0.07472916113247137,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":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1_macro": 0.
|
| 5 |
-
"eval_runtime": 0.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"epoch":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"eval_loss": 1.3446602821350098,
|
| 3 |
+
"eval_accuracy": 0.7727272727272727,
|
| 4 |
+
"eval_f1_macro": 0.4235300491458127,
|
| 5 |
+
"eval_runtime": 0.3068,
|
| 6 |
+
"eval_samples_per_second": 286.859,
|
| 7 |
+
"eval_steps_per_second": 9.779,
|
| 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 sha256:74fc4adfc1258908f113a3624d99b413a3fda5caf269f0515e607326f43fc7ac
|
| 3 |
size 498686648
|