Hugging Face's logo

CIRCL
/
cwe-parent-vulnerability-classification-roberta-base

Text Classification
Transformers
PyTorch
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
elselse commited on
Commit
1d714e8
·
verified ·
1 Parent(s): a586dc6

End of training

Browse files
Files changed (4) hide show
  1. README.md +23 -23
  2. emissions.csv +1 -1
  3. metrics.json +6 -6
  4. 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: 0.6890
22
- - Accuracy: 0.8427
23
- - F1 Macro: 0.3821
24
 
25
  ## Model description
26
 
@@ -51,26 +51,26 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
54
- | 2.8193 | 1.0 | 25 | 2.1550 | 0.4270 | 0.0460 |
55
- | 1.9743 | 2.0 | 50 | 1.9856 | 0.4270 | 0.0460 |
56
- | 1.7803 | 3.0 | 75 | 1.9237 | 0.4270 | 0.0460 |
57
- | 1.5493 | 4.0 | 100 | 1.4930 | 0.6292 | 0.1120 |
58
- | 1.2607 | 5.0 | 125 | 1.3301 | 0.6742 | 0.1229 |
59
- | 1.1316 | 6.0 | 150 | 1.2706 | 0.6742 | 0.1229 |
60
- | 1.0911 | 7.0 | 175 | 1.1787 | 0.6742 | 0.1229 |
61
- | 0.9869 | 8.0 | 200 | 1.0819 | 0.7416 | 0.2359 |
62
- | 0.8985 | 9.0 | 225 | 1.0360 | 0.7640 | 0.2587 |
63
- | 0.7404 | 10.0 | 250 | 0.9223 | 0.7753 | 0.2498 |
64
- | 0.8315 | 11.0 | 275 | 0.8992 | 0.7753 | 0.2441 |
65
- | 0.6514 | 12.0 | 300 | 0.8443 | 0.7753 | 0.2395 |
66
- | 0.6427 | 13.0 | 325 | 0.8207 | 0.7753 | 0.2395 |
67
- | 0.5719 | 14.0 | 350 | 0.7653 | 0.8090 | 0.2887 |
68
- | 0.5153 | 15.0 | 375 | 0.7396 | 0.8202 | 0.3028 |
69
- | 0.4863 | 16.0 | 400 | 0.7580 | 0.8202 | 0.3376 |
70
- | 0.4833 | 17.0 | 425 | 0.7177 | 0.8315 | 0.3806 |
71
- | 0.4948 | 18.0 | 450 | 0.6983 | 0.8427 | 0.3821 |
72
- | 0.4546 | 19.0 | 475 | 0.6890 | 0.8427 | 0.3821 |
73
- | 0.4445 | 20.0 | 500 | 0.6911 | 0.8427 | 0.3821 |
74
 
75
 
76
  ### 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: 2.5988
22
+ - Accuracy: 0.3182
23
+ - F1 Macro: 0.1707
24
 
25
  ## Model description
26
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
54
+ | 3.2528 | 1.0 | 25 | 3.1958 | 0.0455 | 0.0197 |
55
+ | 3.2113 | 2.0 | 50 | 3.0752 | 0.2386 | 0.0357 |
56
+ | 3.1771 | 3.0 | 75 | 3.0165 | 0.0227 | 0.0081 |
57
+ | 3.0745 | 4.0 | 100 | 2.9425 | 0.2273 | 0.0405 |
58
+ | 2.9997 | 5.0 | 125 | 2.9253 | 0.0795 | 0.0297 |
59
+ | 2.9151 | 6.0 | 150 | 2.8506 | 0.0909 | 0.0431 |
60
+ | 2.9761 | 7.0 | 175 | 2.8454 | 0.0909 | 0.1235 |
61
+ | 2.8761 | 8.0 | 200 | 2.7837 | 0.1591 | 0.1007 |
62
+ | 2.7663 | 9.0 | 225 | 2.7488 | 0.1591 | 0.0946 |
63
+ | 2.7299 | 10.0 | 250 | 2.7796 | 0.1477 | 0.0999 |
64
+ | 2.6949 | 11.0 | 275 | 2.7037 | 0.1818 | 0.1088 |
65
+ | 2.5703 | 12.0 | 300 | 2.7002 | 0.2045 | 0.0777 |
66
+ | 2.5374 | 13.0 | 325 | 2.6686 | 0.2045 | 0.1308 |
67
+ | 2.5131 | 14.0 | 350 | 2.6344 | 0.2045 | 0.1121 |
68
+ | 2.4212 | 15.0 | 375 | 2.6382 | 0.2727 | 0.1393 |
69
+ | 2.3231 | 16.0 | 400 | 2.6272 | 0.2614 | 0.1486 |
70
+ | 2.308 | 17.0 | 425 | 2.6080 | 0.3068 | 0.1765 |
71
+ | 2.3126 | 18.0 | 450 | 2.5988 | 0.3182 | 0.1707 |
72
+ | 2.2665 | 19.0 | 475 | 2.6008 | 0.2841 | 0.1674 |
73
+ | 2.2381 | 20.0 | 500 | 2.6006 | 0.2841 | 0.1690 |
74
 
75
 
76
  ### Framework versions
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
- 2025-08-28T16:05:20,codecarbon,e2a8bcaf-0f58-4bb5-a248-bf70c0976bdd,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,182.2731417969335,0.003007971348785084,1.6502548423377697e-05,42.5,225.04609279119165,94.34468507766725,0.0021501255845857996,0.021653612322872107,0.004772032769656413,0.028575770677114313,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
 
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
+ 2025-08-29T14:52:24,codecarbon,ec3b29cc-c4db-458c-8bda-7ba02525fe0d,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,182.0990159730427,0.003006492287000519,1.651020611470844e-05,42.5,212.78392015285954,94.34468507766725,0.0021485755119472743,0.021645753983250415,0.004767390073886594,0.028561719569084282,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": 0.6889647245407104,
3
- "eval_accuracy": 0.8426966292134831,
4
- "eval_f1_macro": 0.3820724249295678,
5
- "eval_runtime": 0.3068,
6
- "eval_samples_per_second": 290.118,
7
- "eval_steps_per_second": 9.779,
8
  "epoch": 20.0
9
  }
 
1
  {
2
+ "eval_loss": 2.5988330841064453,
3
+ "eval_accuracy": 0.3181818181818182,
4
+ "eval_f1_macro": 0.17071418836420613,
5
+ "eval_runtime": 0.3006,
6
+ "eval_samples_per_second": 292.793,
7
+ "eval_steps_per_second": 9.982,
8
  "epoch": 20.0
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b931385a1a245c0076d0c1a69b500361be1f59862804cfda45c15f2d94cf8686
3
  size 498686648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:219551675c68f263a2cbf819d2de9310a9a1997f6ea107c7579f56b4ab765c27
3
  size 498686648