Hugging Face's logo

karths
/
binary_classification_train_defect

Text Classification
Transformers
Safetensors
roberta
Model card Files
xet
Community
karths commited on
Commit
a6166ad
·
verified ·
1 Parent(s): 3769842

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. .gitattributes +4 -0
  2. checkpoint-8080/config.json +28 -0
  3. checkpoint-8080/model.safetensors +3 -0
  4. checkpoint-8080/optimizer.pt +3 -0
  5. checkpoint-8080/rng_state.pth +3 -0
  6. checkpoint-8080/scheduler.pt +3 -0
  7. checkpoint-8080/trainer_state.json +115 -0
  8. checkpoint-8080/training_args.bin +3 -0
  9. classification_report.json +1 -0
  10. config.json +28 -0
  11. confusion_matrix.png +0 -0
  12. detailed_confusion_matrix.png +0 -0
  13. fold_results.json +67 -0
  14. metrics.json +1 -0
  15. metrics_all_fold.json +44 -0
  16. metrics_ci_bounds.json +26 -0
  17. metrics_mean.json +8 -0
  18. metrics_std.json +8 -0
  19. metrics_visualisation.png +0 -0
  20. model.safetensors +3 -0
  21. precision_recall_curve.png +0 -0
  22. reduced_main_data.csv +3 -0
  23. roc_curve.png +0 -0
  24. test_data_for_future_evaluation.csv +3 -0
  25. test_top_repo_data.csv +3 -0
  26. top_repo_data.csv +3 -0
  27. tracker_carbon_statistics.json +33 -0
  28. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ reduced_main_data.csv filter=lfs diff=lfs merge=lfs -text
37
+ test_data_for_future_evaluation.csv filter=lfs diff=lfs merge=lfs -text
38
+ test_top_repo_data.csv filter=lfs diff=lfs merge=lfs -text
39
+ top_repo_data.csv filter=lfs diff=lfs merge=lfs -text
checkpoint-8080/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.35.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
checkpoint-8080/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd8bbb61f6591f252d1384166b0813c8f87415d880dbaa83375504f6e7af2e3
3
+ size 328492280
checkpoint-8080/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fdff214c295027b2259725c3d1de171a2e7bbb4063f119087b581d8f60da07a
3
+ size 657047610
checkpoint-8080/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a03dae1fc0b7392a50e8f26fc8ef7d042f6e0a28d0ab4c52e4af43f1ca1251f9
3
+ size 14244
checkpoint-8080/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5eed705b06d0bd9c2ea9d986ac6aeeeec0c2548b0f5cd73e3bee8697e906d4b
3
+ size 1064
checkpoint-8080/trainer_state.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.998453448809156,
5
+ "eval_steps": 500,
6
+ "global_step": 8080,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.31,
13
+ "learning_rate": 4.9800000000000004e-05,
14
+ "loss": 0.02,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.62,
19
+ "learning_rate": 4.9469375006178444e-05,
20
+ "loss": 0.0364,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.93,
25
+ "learning_rate": 4.789170365674227e-05,
26
+ "loss": 0.0359,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 1.24,
31
+ "learning_rate": 4.533448658971904e-05,
32
+ "loss": 0.0306,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.55,
37
+ "learning_rate": 4.1914779409602436e-05,
38
+ "loss": 0.0274,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 1.86,
43
+ "learning_rate": 3.776525578007916e-05,
44
+ "loss": 0.0264,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 2.17,
49
+ "learning_rate": 3.3069501436547976e-05,
50
+ "loss": 0.024,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 2.47,
55
+ "learning_rate": 2.802844970083667e-05,
56
+ "loss": 0.0175,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 2.78,
61
+ "learning_rate": 2.2868132844916794e-05,
62
+ "loss": 0.0185,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 3.09,
67
+ "learning_rate": 1.77887546017395e-05,
68
+ "loss": 0.0148,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 3.4,
73
+ "learning_rate": 1.3017948610512293e-05,
74
+ "loss": 0.01,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 3.71,
79
+ "learning_rate": 8.76773859580714e-06,
80
+ "loss": 0.0088,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 4.02,
85
+ "learning_rate": 5.203019065951417e-06,
86
+ "loss": 0.009,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 4.33,
91
+ "learning_rate": 2.4854207545895515e-06,
92
+ "loss": 0.0063,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 4.64,
97
+ "learning_rate": 7.312308471548624e-07,
98
+ "loss": 0.0078,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 4.95,
103
+ "learning_rate": 1.587896786990062e-08,
104
+ "loss": 0.0073,
105
+ "step": 8000
106
+ }
107
+ ],
108
+ "logging_steps": 500,
109
+ "max_steps": 8080,
110
+ "num_train_epochs": 5,
111
+ "save_steps": 500,
112
+ "total_flos": 6.849571262744986e+16,
113
+ "trial_name": null,
114
+ "trial_params": null
115
+ }
checkpoint-8080/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75fde7a443c84bb6edaed6e2339a5af44809b1340bff8c460bc6e9299ca0cfff
3
+ size 4664
classification_report.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"0": {"precision": 0.9981187448265483, "recall": 0.9981187448265483, "f1-score": 0.9981187448265483, "support": 13289}, "1": {"precision": 0.9980114540248171, "recall": 0.9980114540248171, "f1-score": 0.9980114540248171, "support": 12572}, "accuracy": 0.9980665867522525, "macro avg": {"precision": 0.9980650994256827, "recall": 0.9980650994256827, "f1-score": 0.9980650994256827, "support": 25861}, "weighted avg": {"precision": 0.9980665867522525, "recall": 0.9980665867522525, "f1-score": 0.9980665867522525, "support": 25861}}
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.35.0",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
confusion_matrix.png ADDED
detailed_confusion_matrix.png ADDED
fold_results.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": {
3
+ "eval_loss": 0.2804172933101654,
4
+ "eval_precision": 0.9286116700201207,
5
+ "eval_recall": 0.917680744452398,
6
+ "eval_acc": 0.9256824684865826,
7
+ "eval_mcc": 0.8512596171356405,
8
+ "eval_f1": 0.9231138491079286,
9
+ "eval_auc": 0.9777264564543487,
10
+ "eval_runtime": 137.6757,
11
+ "eval_samples_per_second": 187.847,
12
+ "eval_steps_per_second": 2.942,
13
+ "epoch": 5.0
14
+ },
15
+ "1": {
16
+ "eval_loss": 0.12776103615760803,
17
+ "eval_precision": 0.9784399224806202,
18
+ "eval_recall": 0.9638084632516704,
19
+ "eval_acc": 0.9720815127025251,
20
+ "eval_mcc": 0.9441975563000122,
21
+ "eval_f1": 0.9710690815835872,
22
+ "eval_auc": 0.9959390566219378,
23
+ "eval_runtime": 141.3668,
24
+ "eval_samples_per_second": 182.935,
25
+ "eval_steps_per_second": 2.865,
26
+ "epoch": 5.0
27
+ },
28
+ "2": {
29
+ "eval_loss": 0.028565719723701477,
30
+ "eval_precision": 0.9940253325898192,
31
+ "eval_recall": 0.9925230671333122,
32
+ "eval_acc": 0.9934650632226132,
33
+ "eval_mcc": 0.9869206059875473,
34
+ "eval_f1": 0.993273631840796,
35
+ "eval_auc": 0.9996784268717986,
36
+ "eval_runtime": 143.6108,
37
+ "eval_samples_per_second": 180.077,
38
+ "eval_steps_per_second": 2.82,
39
+ "epoch": 5.0
40
+ },
41
+ "3": {
42
+ "eval_loss": 0.014919092878699303,
43
+ "eval_precision": 0.9972912683237731,
44
+ "eval_recall": 0.9957047406936048,
45
+ "eval_acc": 0.9965971926839643,
46
+ "eval_mcc": 0.9931900476424383,
47
+ "eval_f1": 0.9964973730297723,
48
+ "eval_auc": 0.9998726037699277,
49
+ "eval_runtime": 145.1445,
50
+ "eval_samples_per_second": 178.174,
51
+ "eval_steps_per_second": 2.79,
52
+ "epoch": 5.0
53
+ },
54
+ "4": {
55
+ "eval_loss": 0.008744149468839169,
56
+ "eval_precision": 0.9980114540248171,
57
+ "eval_recall": 0.9980114540248171,
58
+ "eval_acc": 0.9980665867522525,
59
+ "eval_mcc": 0.9961301988513653,
60
+ "eval_f1": 0.9980114540248171,
61
+ "eval_auc": 0.9999709850955988,
62
+ "eval_runtime": 159.148,
63
+ "eval_samples_per_second": 162.497,
64
+ "eval_steps_per_second": 2.545,
65
+ "epoch": 5.0
66
+ }
67
+ }
metrics.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"precision": 0.9980114540248171, "recall": 0.9980114540248171, "acc": 0.9980665867522525, "mcc": 0.9961301988513653, "f1": 0.9980114540248171, "auc": 0.9999709850955988}
metrics_all_fold.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": [
3
+ 0.9286116700201207,
4
+ 0.9784399224806202,
5
+ 0.9940253325898192,
6
+ 0.9972912683237731,
7
+ 0.9980114540248171
8
+ ],
9
+ "recall": [
10
+ 0.917680744452398,
11
+ 0.9638084632516704,
12
+ 0.9925230671333122,
13
+ 0.9957047406936048,
14
+ 0.9980114540248171
15
+ ],
16
+ "f1": [
17
+ 0.9231138491079286,
18
+ 0.9710690815835872,
19
+ 0.993273631840796,
20
+ 0.9964973730297723,
21
+ 0.9980114540248171
22
+ ],
23
+ "auc": [
24
+ 0.9777264564543487,
25
+ 0.9959390566219378,
26
+ 0.9996784268717986,
27
+ 0.9998726037699277,
28
+ 0.9999709850955988
29
+ ],
30
+ "acc": [
31
+ 0.9256824684865826,
32
+ 0.9720815127025251,
33
+ 0.9934650632226132,
34
+ 0.9965971926839643,
35
+ 0.9980665867522525
36
+ ],
37
+ "mcc": [
38
+ 0.8512596171356405,
39
+ 0.9441975563000122,
40
+ 0.9869206059875473,
41
+ 0.9931900476424383,
42
+ 0.9961301988513653
43
+ ]
44
+ }
metrics_ci_bounds.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": {
3
+ "ci_lower": 0.9427538899775278,
4
+ "ci_upper": 1.0157979689981325
5
+ },
6
+ "recall": {
7
+ "ci_lower": 0.9311403519160062,
8
+ "ci_upper": 1.0159510359063146
9
+ },
10
+ "f1": {
11
+ "ci_lower": 0.937012988606302,
12
+ "ci_upper": 1.0157731672284585
13
+ },
14
+ "auc": {
15
+ "ci_lower": 0.9827126698030874,
16
+ "ci_upper": 1.0065623417223573
17
+ },
18
+ "acc": {
19
+ "ci_lower": 0.9391277392497919,
20
+ "ci_upper": 1.0152293902893832
21
+ },
22
+ "mcc": {
23
+ "ci_lower": 0.8781878417242713,
24
+ "ci_upper": 1.03049136864253
25
+ }
26
+ }
metrics_mean.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.9792759294878302,
3
+ "recall": 0.9735456939111604,
4
+ "f1": 0.9763930779173802,
5
+ "auc": 0.9946375057627224,
6
+ "acc": 0.9771785647695875,
7
+ "mcc": 0.9543396051834007
8
+ }
metrics_std.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.029413786308644156,
3
+ "recall": 0.034152026680727844,
4
+ "f1": 0.03171557632986603,
5
+ "auc": 0.009603915372343777,
6
+ "acc": 0.030645026009323964,
7
+ "mcc": 0.06133041110098471
8
+ }
metrics_visualisation.png ADDED
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd8bbb61f6591f252d1384166b0813c8f87415d880dbaa83375504f6e7af2e3
3
+ size 328492280
precision_recall_curve.png ADDED
reduced_main_data.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bba2c2d8afa97666d09ac9ba804434380b04713898352c914b0acfe4fd960154
3
+ size 602731695
roc_curve.png ADDED
test_data_for_future_evaluation.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd22c53e406404b7e72a272ea0d724b06215bffc3af8be60dbde04a6dc17c9e3
3
+ size 108972066
test_top_repo_data.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d0f3242bc9c8a4a37ad72a1bd80d63d5fef8c9cc207f47cf1de437b51d6e1e4
3
+ size 28089794
top_repo_data.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a9e47969e7b35bfc8ea67dae2c07c94e6ae0e4e8e058b212d0cde42e5510e4b
3
+ size 13168427
tracker_carbon_statistics.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cloud_provider": "",
3
+ "cloud_region": "",
4
+ "codecarbon_version": "2.3.4",
5
+ "country_iso_code": "NOR",
6
+ "country_name": "Norway",
7
+ "cpu_count": 64,
8
+ "cpu_energy": 0.36212093520596095,
9
+ "cpu_model": "AMD EPYC 7282 16-Core Processor",
10
+ "cpu_power": 6.6108087857202955,
11
+ "duration": 33739.01375603676,
12
+ "emissions": 0.5052003036877387,
13
+ "emissions_rate": 1.4973772124484394e-05,
14
+ "energy_consumed": 18.337579081224636,
15
+ "gpu_count": 8,
16
+ "gpu_energy": 17.09212653369029,
17
+ "gpu_model": "8 x NVIDIA GeForce RTX 2080 Ti",
18
+ "gpu_power": 1395.6655394622155,
19
+ "latitude": 59.955,
20
+ "longitude": 10.859,
21
+ "on_cloud": "N",
22
+ "os": "Linux-4.18.0-513.11.1.el8_9.x86_64-x86_64-with-glibc2.28",
23
+ "project_name": "codecarbon",
24
+ "pue": 1.0,
25
+ "python_version": "3.10.8",
26
+ "ram_energy": 0.8833316123283854,
27
+ "ram_power": 94.20606708526611,
28
+ "ram_total_size": 251.21617889404297,
29
+ "region": "oslo county",
30
+ "run_id": "b3a1a3bc-f423-45fd-9026-d228e7063595",
31
+ "timestamp": "2024-03-16T17:18:05",
32
+ "tracking_mode": "machine"
33
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75fde7a443c84bb6edaed6e2339a5af44809b1340bff8c460bc6e9299ca0cfff
3
+ size 4664