CIRCL/cwe-parent-vulnerability-classification-roberta-base-roberta-base
Browse files- README.md +45 -45
- config.json +52 -52
- emissions.csv +1 -1
- metrics.json +6 -6
- 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: 1.
|
| 22 |
-
- Accuracy: 0.
|
| 23 |
-
- F1 Macro: 0.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -51,51 +51,51 @@ The following hyperparameters were used during training:
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
| 54 |
-
|
|
| 55 |
-
| 2.
|
| 56 |
-
| 1.
|
| 57 |
-
| 1.
|
| 58 |
-
| 1.
|
| 59 |
-
| 1.
|
| 60 |
-
| 1.
|
| 61 |
-
|
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 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 |
|
| 95 |
|
| 96 |
### Framework versions
|
| 97 |
|
| 98 |
- Transformers 4.57.1
|
| 99 |
-
- Pytorch 2.9.
|
| 100 |
-
- Datasets 4.
|
| 101 |
- Tokenizers 0.22.1
|
|
|
|
| 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: 1.3755
|
| 22 |
+
- Accuracy: 0.6603
|
| 23 |
+
- F1 Macro: 0.4616
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
| 54 |
+
| 2.9549 | 1.0 | 238 | 2.9056 | 0.0948 | 0.0729 |
|
| 55 |
+
| 2.2865 | 2.0 | 476 | 1.9760 | 0.4946 | 0.3041 |
|
| 56 |
+
| 1.8517 | 3.0 | 714 | 1.7010 | 0.5114 | 0.3522 |
|
| 57 |
+
| 1.6439 | 4.0 | 952 | 1.5457 | 0.6074 | 0.3826 |
|
| 58 |
+
| 1.3475 | 5.0 | 1190 | 1.5154 | 0.5894 | 0.3608 |
|
| 59 |
+
| 1.1372 | 6.0 | 1428 | 1.4379 | 0.6327 | 0.4183 |
|
| 60 |
+
| 1.0323 | 7.0 | 1666 | 1.3955 | 0.6411 | 0.4184 |
|
| 61 |
+
| 0.8662 | 8.0 | 1904 | 1.3755 | 0.6603 | 0.4616 |
|
| 62 |
+
| 0.8135 | 9.0 | 2142 | 1.4626 | 0.6807 | 0.4703 |
|
| 63 |
+
| 0.632 | 10.0 | 2380 | 1.4197 | 0.6999 | 0.4439 |
|
| 64 |
+
| 0.5727 | 11.0 | 2618 | 1.4083 | 0.6795 | 0.4878 |
|
| 65 |
+
| 0.5429 | 12.0 | 2856 | 1.5234 | 0.6651 | 0.4823 |
|
| 66 |
+
| 0.3597 | 13.0 | 3094 | 1.5866 | 0.7107 | 0.4995 |
|
| 67 |
+
| 0.3076 | 14.0 | 3332 | 1.6262 | 0.7191 | 0.5243 |
|
| 68 |
+
| 0.2458 | 15.0 | 3570 | 1.7271 | 0.6963 | 0.5259 |
|
| 69 |
+
| 0.2052 | 16.0 | 3808 | 1.7799 | 0.7011 | 0.4556 |
|
| 70 |
+
| 0.1801 | 17.0 | 4046 | 1.7717 | 0.7179 | 0.4983 |
|
| 71 |
+
| 0.187 | 18.0 | 4284 | 2.0014 | 0.7239 | 0.5273 |
|
| 72 |
+
| 0.1473 | 19.0 | 4522 | 1.9999 | 0.7419 | 0.5388 |
|
| 73 |
+
| 0.1198 | 20.0 | 4760 | 1.9328 | 0.7275 | 0.5336 |
|
| 74 |
+
| 0.152 | 21.0 | 4998 | 2.0637 | 0.7407 | 0.4759 |
|
| 75 |
+
| 0.0692 | 22.0 | 5236 | 2.2153 | 0.7647 | 0.5553 |
|
| 76 |
+
| 0.0632 | 23.0 | 5474 | 2.1253 | 0.7431 | 0.5381 |
|
| 77 |
+
| 0.069 | 24.0 | 5712 | 2.2856 | 0.7587 | 0.5443 |
|
| 78 |
+
| 0.0472 | 25.0 | 5950 | 2.3607 | 0.7611 | 0.5286 |
|
| 79 |
+
| 0.0452 | 26.0 | 6188 | 2.4693 | 0.7539 | 0.5191 |
|
| 80 |
+
| 0.0388 | 27.0 | 6426 | 2.4699 | 0.7587 | 0.5550 |
|
| 81 |
+
| 0.0412 | 28.0 | 6664 | 2.5062 | 0.7659 | 0.5332 |
|
| 82 |
+
| 0.0419 | 29.0 | 6902 | 2.4443 | 0.7551 | 0.5488 |
|
| 83 |
+
| 0.0238 | 30.0 | 7140 | 2.5642 | 0.7479 | 0.5487 |
|
| 84 |
+
| 0.0616 | 31.0 | 7378 | 2.5451 | 0.7623 | 0.5511 |
|
| 85 |
+
| 0.0163 | 32.0 | 7616 | 2.6758 | 0.7599 | 0.5450 |
|
| 86 |
+
| 0.028 | 33.0 | 7854 | 2.6806 | 0.7671 | 0.5432 |
|
| 87 |
+
| 0.0147 | 34.0 | 8092 | 2.6815 | 0.7647 | 0.5518 |
|
| 88 |
+
| 0.0251 | 35.0 | 8330 | 2.7046 | 0.7611 | 0.5470 |
|
| 89 |
+
| 0.0151 | 36.0 | 8568 | 2.6610 | 0.7527 | 0.5440 |
|
| 90 |
+
| 0.0128 | 37.0 | 8806 | 2.7269 | 0.7551 | 0.5426 |
|
| 91 |
+
| 0.0421 | 38.0 | 9044 | 2.7759 | 0.7515 | 0.5437 |
|
| 92 |
+
| 0.0259 | 39.0 | 9282 | 2.7239 | 0.7587 | 0.5444 |
|
| 93 |
+
| 0.0046 | 40.0 | 9520 | 2.7196 | 0.7599 | 0.5448 |
|
| 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 |
-
2025-11-
|
|
|
|
| 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 |
+
2025-11-19T15:13:48,codecarbon,f2b9e27a-8169-4497-8c1d-dd8870b6ce60,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,2640.618760886602,0.050414934358921304,1.9092091257427185e-05,42.5,150.34056886632663,94.34468507766725,0.031146029030440454,0.3786609459840804,0.06913561980912433,0.4789425948236446,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": 2.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 10.
|
| 8 |
"epoch": 40.0
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"eval_loss": 1.375471591949463,
|
| 3 |
+
"eval_accuracy": 0.6602641056422569,
|
| 4 |
+
"eval_f1_macro": 0.46163136090459905,
|
| 5 |
+
"eval_runtime": 2.4908,
|
| 6 |
+
"eval_samples_per_second": 334.435,
|
| 7 |
+
"eval_steps_per_second": 10.84,
|
| 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:ac7cea2552b7cf52c7e0ffce28e2993ce462b86b611de47b1e18234dfa5260fe
|
| 3 |
size 498686648
|