Hugging Face's logo

karths
/
binary_classification_train_service

Text Classification
Transformers
Safetensors
roberta
Model card Files
xet
Community
karths commited on
Commit
762647e
·
verified ·
1 Parent(s): 6d6f545

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. .gitattributes +4 -0
  2. checkpoint-6620/config.json +28 -0
  3. checkpoint-6620/model.safetensors +3 -0
  4. checkpoint-6620/optimizer.pt +3 -0
  5. checkpoint-6620/rng_state.pth +3 -0
  6. checkpoint-6620/scheduler.pt +3 -0
  7. checkpoint-6620/trainer_state.json +97 -0
  8. checkpoint-6620/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-6620/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-6620/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:333fbbc95fb85fecbe62828369c3fb2ac3ffcccc010f5ace64025b042d018f73
3
+ size 328492280
checkpoint-6620/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f363796208fc3a6915a060e5d3299ab6411727ab75b30699dc80164980e85c7
3
+ size 657047610
checkpoint-6620/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c497999cb5b6ff3f08b045cc878eacf5ca31b22128f70e04eb6d7e96ea878603
3
+ size 14244
checkpoint-6620/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee6ff98bd92791a9d8f62dd957e017862302de4ebce49d3b79df978b0c94d50b
3
+ size 1064
checkpoint-6620/trainer_state.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.998112495281238,
5
+ "eval_steps": 500,
6
+ "global_step": 6620,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.38,
13
+ "learning_rate": 4.9800000000000004e-05,
14
+ "loss": 0.0323,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.76,
19
+ "learning_rate": 4.91875452905494e-05,
20
+ "loss": 0.0536,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.13,
25
+ "learning_rate": 4.6790417797358055e-05,
26
+ "loss": 0.0491,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 1.51,
31
+ "learning_rate": 4.296565601079351e-05,
32
+ "loss": 0.0441,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.89,
37
+ "learning_rate": 3.7963845355204304e-05,
38
+ "loss": 0.0431,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 2.27,
43
+ "learning_rate": 3.2112687506037174e-05,
44
+ "loss": 0.0328,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 2.64,
49
+ "learning_rate": 2.5795530487138815e-05,
50
+ "loss": 0.0287,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 3.02,
55
+ "learning_rate": 1.9426253007980113e-05,
56
+ "loss": 0.0262,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 3.4,
61
+ "learning_rate": 1.3444902911492174e-05,
62
+ "loss": 0.0141,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 3.78,
67
+ "learning_rate": 8.195580089631732e-06,
68
+ "loss": 0.0138,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 4.15,
73
+ "learning_rate": 4.047225884682987e-06,
74
+ "loss": 0.0106,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 4.53,
79
+ "learning_rate": 1.2716263991024713e-06,
80
+ "loss": 0.012,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 4.91,
85
+ "learning_rate": 5.144911675032671e-08,
86
+ "loss": 0.0113,
87
+ "step": 6500
88
+ }
89
+ ],
90
+ "logging_steps": 500,
91
+ "max_steps": 6620,
92
+ "num_train_epochs": 5,
93
+ "save_steps": 500,
94
+ "total_flos": 5.612325759297946e+16,
95
+ "trial_name": null,
96
+ "trial_params": null
97
+ }
checkpoint-6620/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11a910665f03a5670d07d42e1c885d102e5a538067baed6a273eeba3fedf173a
3
+ size 4664
classification_report.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"0": {"precision": 0.9977459201154089, "recall": 0.9973862100045066, "f1-score": 0.9975660326331921, "support": 11095}, "1": {"precision": 0.9971287128712871, "recall": 0.9975237717908082, "f1-score": 0.9973262032085561, "support": 10096}, "accuracy": 0.9974517483837478, "macro avg": {"precision": 0.997437316493348, "recall": 0.9974549908976573, "f1-score": 0.9974461179208741, "support": 21191}, "weighted avg": {"precision": 0.997451864887404, "recall": 0.9974517483837478, "f1-score": 0.9974517710187744, "support": 21191}}
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": 0.3764899969100952,
4
+ "eval_precision": 0.8875422213391615,
5
+ "eval_recall": 0.8848172724571655,
6
+ "eval_acc": 0.891704416761042,
7
+ "eval_mcc": 0.7829008037573408,
8
+ "eval_f1": 0.8861776521350989,
9
+ "eval_auc": 0.9582918248197532,
10
+ "eval_runtime": 74.263,
11
+ "eval_samples_per_second": 285.364,
12
+ "eval_steps_per_second": 4.471,
13
+ "epoch": 5.0
14
+ },
15
+ "1": {
16
+ "eval_loss": 0.17112599313259125,
17
+ "eval_precision": 0.9569444444444445,
18
+ "eval_recall": 0.955333267307121,
19
+ "eval_acc": 0.9582389580973952,
20
+ "eval_mcc": 0.9162871170067691,
21
+ "eval_f1": 0.9561381771323785,
22
+ "eval_auc": 0.9917474941021617,
23
+ "eval_runtime": 77.8137,
24
+ "eval_samples_per_second": 272.343,
25
+ "eval_steps_per_second": 4.267,
26
+ "epoch": 5.0
27
+ },
28
+ "2": {
29
+ "eval_loss": 0.04602893814444542,
30
+ "eval_precision": 0.9901668653158522,
31
+ "eval_recall": 0.9874207606973059,
32
+ "eval_acc": 0.9893355983389959,
33
+ "eval_mcc": 0.9786243595961119,
34
+ "eval_f1": 0.9887919063677842,
35
+ "eval_auc": 0.9990685489952549,
36
+ "eval_runtime": 77.2317,
37
+ "eval_samples_per_second": 274.395,
38
+ "eval_steps_per_second": 4.299,
39
+ "epoch": 5.0
40
+ },
41
+ "3": {
42
+ "eval_loss": 0.02981959842145443,
43
+ "eval_precision": 0.9926645519429025,
44
+ "eval_recall": 0.991877971473851,
45
+ "eval_acc": 0.992638384219716,
46
+ "eval_mcc": 0.9852437298920019,
47
+ "eval_f1": 0.9922711058263971,
48
+ "eval_auc": 0.999497866895112,
49
+ "eval_runtime": 78.4035,
50
+ "eval_samples_per_second": 270.281,
51
+ "eval_steps_per_second": 4.235,
52
+ "epoch": 5.0
53
+ },
54
+ "4": {
55
+ "eval_loss": 0.011920441873371601,
56
+ "eval_precision": 0.9971287128712871,
57
+ "eval_recall": 0.9975237717908082,
58
+ "eval_acc": 0.9974517483837478,
59
+ "eval_mcc": 0.9948923072340113,
60
+ "eval_f1": 0.9973262032085561,
61
+ "eval_auc": 0.9998716200098702,
62
+ "eval_runtime": 78.8636,
63
+ "eval_samples_per_second": 268.704,
64
+ "eval_steps_per_second": 4.21,
65
+ "epoch": 5.0
66
+ }
67
+ }
metrics.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"precision": 0.9971287128712871, "recall": 0.9975237717908082, "acc": 0.9974517483837478, "mcc": 0.9948923072340113, "f1": 0.9973262032085561, "auc": 0.9998716200098702}
metrics_all_fold.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": [
3
+ 0.8875422213391615,
4
+ 0.9569444444444445,
5
+ 0.9901668653158522,
6
+ 0.9926645519429025,
7
+ 0.9971287128712871
8
+ ],
9
+ "recall": [
10
+ 0.8848172724571655,
11
+ 0.955333267307121,
12
+ 0.9874207606973059,
13
+ 0.991877971473851,
14
+ 0.9975237717908082
15
+ ],
16
+ "f1": [
17
+ 0.8861776521350989,
18
+ 0.9561381771323785,
19
+ 0.9887919063677842,
20
+ 0.9922711058263971,
21
+ 0.9973262032085561
22
+ ],
23
+ "auc": [
24
+ 0.9582918248197532,
25
+ 0.9917474941021617,
26
+ 0.9990685489952549,
27
+ 0.999497866895112,
28
+ 0.9998716200098702
29
+ ],
30
+ "acc": [
31
+ 0.891704416761042,
32
+ 0.9582389580973952,
33
+ 0.9893355983389959,
34
+ 0.992638384219716,
35
+ 0.9974517483837478
36
+ ],
37
+ "mcc": [
38
+ 0.7829008037573408,
39
+ 0.9162871170067691,
40
+ 0.9786243595961119,
41
+ 0.9852437298920019,
42
+ 0.9948923072340113
43
+ ]
44
+ }
metrics_ci_bounds.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": {
3
+ "ci_lower": 0.9076666606141581,
4
+ "ci_upper": 1.022112057751301
5
+ },
6
+ "recall": {
7
+ "ci_lower": 0.9051794311872517,
8
+ "ci_upper": 1.0216097863032492
9
+ },
10
+ "f1": {
11
+ "ci_lower": 0.9064251440647254,
12
+ "ci_upper": 1.0218568738033607
13
+ },
14
+ "auc": {
15
+ "ci_lower": 0.9675021783383242,
16
+ "ci_upper": 1.0118887635905365
17
+ },
18
+ "acc": {
19
+ "ci_lower": 0.9109614010692658,
20
+ "ci_upper": 1.0207862412510929
21
+ },
22
+ "mcc": {
23
+ "ci_lower": 0.8215065191399901,
24
+ "ci_upper": 1.0416728078545043
25
+ }
26
+ }
metrics_mean.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.9648893591827296,
3
+ "recall": 0.9633946087452504,
4
+ "f1": 0.9641410089340431,
5
+ "auc": 0.9896954709644303,
6
+ "acc": 0.9658738211601794,
7
+ "mcc": 0.9315896634972471
8
+ }
metrics_std.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.04608549386255197,
3
+ "recall": 0.04688480751814882,
4
+ "f1": 0.04648267562948704,
5
+ "auc": 0.017873831131619895,
6
+ "acc": 0.04422486290200226,
7
+ "mcc": 0.0886577564594827
8
+ }
metrics_visualisation.png ADDED
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:333fbbc95fb85fecbe62828369c3fb2ac3ffcccc010f5ace64025b042d018f73
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 sha256:2094f68d7c804ecb000d36ef4705aee88e041aef341e4a8ed145e6bf77e26db2
3
+ size 514640866
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 sha256:712dc65aae40ec65db0fe89f640a7ddfebf83d0fceaa50bdf5259a645314c2de
3
+ size 92470173
test_top_repo_data.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1144a215dec2d5f9b075f5fdf90aaf5ce65acd9ac074797fa0f53242ef4ae3da
3
+ size 40389519
top_repo_data.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049ccb58c77b569b8dc45c9077c0e38fcdf78cced12936b315424d7747ed52ac
3
+ size 18227032
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": 192,
8
+ "cpu_energy": 0.2798610622300596,
9
+ "cpu_model": "AMD EPYC 7642 48-Core Processor",
10
+ "cpu_power": 21.15110919787667,
11
+ "duration": 13353.504374742508,
12
+ "emissions": 0.10568660371825737,
13
+ "emissions_rate": 7.914521967593641e-06,
14
+ "energy_consumed": 3.836174363639106,
15
+ "gpu_count": 4,
16
+ "gpu_energy": 2.1608095708684965,
17
+ "gpu_model": "4 x NVIDIA GeForce RTX 3090",
18
+ "gpu_power": 603.4907196778789,
19
+ "latitude": 59.9016,
20
+ "longitude": 10.7343,
21
+ "on_cloud": "N",
22
+ "os": "Linux-4.18.0-513.18.1.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": 1.3955037305405495,
27
+ "ram_power": 377.6938190460205,
28
+ "ram_total_size": 1007.1835174560547,
29
+ "region": "oslo county",
30
+ "run_id": "0b753632-0f2e-4b54-b6e2-257b8a4ff34c",
31
+ "timestamp": "2024-04-06T01:33:24",
32
+ "tracking_mode": "machine"
33
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11a910665f03a5670d07d42e1c885d102e5a538067baed6a273eeba3fedf173a
3
+ size 4664