Hugging Face's logo

karths
/
binary_classification_train_architecture

Text Classification
Transformers
Safetensors
roberta
Model card Files
xet
Community
karths commited on
Commit
762a58d
·
verified ·
1 Parent(s): 4e86df3

Upload folder using huggingface_hub

Browse files
Files changed (30) hide show
  1. .gitattributes +2 -0
  2. .ipynb_checkpoints/fold_results-checkpoint.json +67 -0
  3. .ipynb_checkpoints/tracker_carbon_statistics-checkpoint.json +33 -0
  4. checkpoint-1040/config.json +28 -0
  5. checkpoint-1040/model.safetensors +3 -0
  6. checkpoint-1040/optimizer.pt +3 -0
  7. checkpoint-1040/rng_state.pth +3 -0
  8. checkpoint-1040/scheduler.pt +3 -0
  9. checkpoint-1040/trainer_state.json +31 -0
  10. checkpoint-1040/training_args.bin +3 -0
  11. classification_report.json +1 -0
  12. config.json +28 -0
  13. confusion_matrix.png +0 -0
  14. detailed_confusion_matrix.png +0 -0
  15. fold_results.json +67 -0
  16. metrics.json +1 -0
  17. metrics_all_fold.json +44 -0
  18. metrics_ci_bounds.json +26 -0
  19. metrics_mean.json +8 -0
  20. metrics_std.json +8 -0
  21. metrics_visualisation.png +0 -0
  22. model.safetensors +3 -0
  23. precision_recall_curve.png +0 -0
  24. reduced_main_data.csv +3 -0
  25. roc_curve.png +0 -0
  26. test_data_for_future_evaluation.csv +3 -0
  27. test_top_repo_data.csv +0 -0
  28. top_repo_data.csv +0 -0
  29. tracker_carbon_statistics.json +33 -0
  30. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
.ipynb_checkpoints/fold_results-checkpoint.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": {
3
+ "eval_loss": 0.5267969369888306,
4
+ "eval_precision": 0.8185985592665357,
5
+ "eval_recall": 0.7841907151819323,
6
+ "eval_acc": 0.8136813681368137,
7
+ "eval_mcc": 0.6265110018485912,
8
+ "eval_f1": 0.8010253123998718,
9
+ "eval_auc": 0.9007949592455319,
10
+ "eval_runtime": 16.9181,
11
+ "eval_samples_per_second": 197.008,
12
+ "eval_steps_per_second": 3.133,
13
+ "epoch": 4.99
14
+ },
15
+ "1": {
16
+ "eval_loss": 0.15515397489070892,
17
+ "eval_precision": 0.9459962756052142,
18
+ "eval_recall": 0.9566854990583804,
19
+ "eval_acc": 0.9531953195319532,
20
+ "eval_mcc": 0.9063059646905545,
21
+ "eval_f1": 0.951310861423221,
22
+ "eval_auc": 0.9885553535222344,
23
+ "eval_runtime": 14.8662,
24
+ "eval_samples_per_second": 224.2,
25
+ "eval_steps_per_second": 3.565,
26
+ "epoch": 4.99
27
+ },
28
+ "2": {
29
+ "eval_loss": 0.03554769232869148,
30
+ "eval_precision": 0.9862585883822611,
31
+ "eval_recall": 0.9912115505335845,
32
+ "eval_acc": 0.9891989198919892,
33
+ "eval_mcc": 0.9783716402634621,
34
+ "eval_f1": 0.9887288666249218,
35
+ "eval_auc": 0.999065595890065,
36
+ "eval_runtime": 15.6423,
37
+ "eval_samples_per_second": 213.076,
38
+ "eval_steps_per_second": 3.388,
39
+ "epoch": 4.99
40
+ },
41
+ "3": {
42
+ "eval_loss": 0.024563202634453773,
43
+ "eval_precision": 0.9912225705329154,
44
+ "eval_recall": 0.992467043314501,
45
+ "eval_acc": 0.9921992199219922,
46
+ "eval_mcc": 0.9843695731126325,
47
+ "eval_f1": 0.9918444165621079,
48
+ "eval_auc": 0.9998024763512783,
49
+ "eval_runtime": 24.352,
50
+ "eval_samples_per_second": 136.868,
51
+ "eval_steps_per_second": 2.176,
52
+ "epoch": 4.99
53
+ },
54
+ "4": {
55
+ "eval_loss": 0.016317054629325867,
56
+ "eval_precision": 0.9943502824858758,
57
+ "eval_recall": 0.9943502824858758,
58
+ "eval_acc": 0.9945994599459946,
59
+ "eval_mcc": 0.9891778686927722,
60
+ "eval_f1": 0.9943502824858758,
61
+ "eval_auc": 0.999885273935537,
62
+ "eval_runtime": 20.6999,
63
+ "eval_samples_per_second": 161.015,
64
+ "eval_steps_per_second": 2.56,
65
+ "epoch": 4.99
66
+ }
67
+ }
.ipynb_checkpoints/tracker_carbon_statistics-checkpoint.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": 0.09686212190880218,
9
+ "cpu_model": "AMD EPYC 7282 16-Core Processor",
10
+ "cpu_power": 19.17079533382436,
11
+ "duration": 3117.374103307724,
12
+ "emissions": 0.02323189242211557,
13
+ "emissions_rate": 7.452391548856813e-06,
14
+ "energy_consumed": 0.8432628828354108,
15
+ "gpu_count": 8,
16
+ "gpu_energy": 0.6649034747001394,
17
+ "gpu_model": "8 x NVIDIA GeForce RTX 2080 Ti",
18
+ "gpu_power": 731.791919414086,
19
+ "latitude": 59.955,
20
+ "longitude": 10.859,
21
+ "on_cloud": "N",
22
+ "os": "Linux-4.18.0-513.9.1.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": 0.08149728622646912,
27
+ "ram_power": 94.2059955596924,
28
+ "ram_total_size": 251.2159881591797,
29
+ "region": "oslo county",
30
+ "run_id": "3a744030-f267-4edb-8457-e6ae2610343d",
31
+ "timestamp": "2024-03-04T12:53:59",
32
+ "tracking_mode": "machine"
33
+ }
checkpoint-1040/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-1040/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ee2fe2c9bf2796b9cb010ba17e83cbc0967d8b797898781ba11430ac79b7eb
3
+ size 328492280
checkpoint-1040/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92c81ea5bb425b97c225a8b0f86a3c40904e7207260e5e7e146556eefb2e9f1f
3
+ size 657047610
checkpoint-1040/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b7dbf4e842fbd6c941a1fa6f7a96d3da6442d16448a3666e009a04fffaf02aa
3
+ size 14244
checkpoint-1040/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09dde82fa5aa982ebf825cebbdcf3e7be747180673e30dda860695e4a7537f19
3
+ size 1064
checkpoint-1040/trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.988009592326139,
5
+ "eval_steps": 500,
6
+ "global_step": 1040,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 2.4,
13
+ "learning_rate": 4.9800000000000004e-05,
14
+ "loss": 0.04,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 4.8,
19
+ "learning_rate": 7.426068431000882e-07,
20
+ "loss": 0.0369,
21
+ "step": 1000
22
+ }
23
+ ],
24
+ "logging_steps": 500,
25
+ "max_steps": 1040,
26
+ "num_train_epochs": 5,
27
+ "save_steps": 500,
28
+ "total_flos": 8810671619407872.0,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
checkpoint-1040/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eaf06d5345ffe465dd8018ae971057d4233655e8d37542173575dacd209a4c0
3
+ size 4664
classification_report.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"0": {"precision": 0.9948275862068966, "recall": 0.9948275862068966, "f1-score": 0.9948275862068966, "support": 1740}, "1": {"precision": 0.9943502824858758, "recall": 0.9943502824858758, "f1-score": 0.9943502824858758, "support": 1593}, "accuracy": 0.9945994599459946, "macro avg": {"precision": 0.9945889343463862, "recall": 0.9945889343463862, "f1-score": 0.9945889343463862, "support": 3333}, "weighted avg": {"precision": 0.9945994599459946, "recall": 0.9945994599459946, "f1-score": 0.9945994599459946, "support": 3333}}
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": 0.5267969369888306,
4
+ "eval_precision": 0.8185985592665357,
5
+ "eval_recall": 0.7841907151819323,
6
+ "eval_acc": 0.8136813681368137,
7
+ "eval_mcc": 0.6265110018485912,
8
+ "eval_f1": 0.8010253123998718,
9
+ "eval_auc": 0.9007949592455319,
10
+ "eval_runtime": 16.9181,
11
+ "eval_samples_per_second": 197.008,
12
+ "eval_steps_per_second": 3.133,
13
+ "epoch": 4.99
14
+ },
15
+ "1": {
16
+ "eval_loss": 0.15515397489070892,
17
+ "eval_precision": 0.9459962756052142,
18
+ "eval_recall": 0.9566854990583804,
19
+ "eval_acc": 0.9531953195319532,
20
+ "eval_mcc": 0.9063059646905545,
21
+ "eval_f1": 0.951310861423221,
22
+ "eval_auc": 0.9885553535222344,
23
+ "eval_runtime": 14.8662,
24
+ "eval_samples_per_second": 224.2,
25
+ "eval_steps_per_second": 3.565,
26
+ "epoch": 4.99
27
+ },
28
+ "2": {
29
+ "eval_loss": 0.03554769232869148,
30
+ "eval_precision": 0.9862585883822611,
31
+ "eval_recall": 0.9912115505335845,
32
+ "eval_acc": 0.9891989198919892,
33
+ "eval_mcc": 0.9783716402634621,
34
+ "eval_f1": 0.9887288666249218,
35
+ "eval_auc": 0.999065595890065,
36
+ "eval_runtime": 15.6423,
37
+ "eval_samples_per_second": 213.076,
38
+ "eval_steps_per_second": 3.388,
39
+ "epoch": 4.99
40
+ },
41
+ "3": {
42
+ "eval_loss": 0.024563202634453773,
43
+ "eval_precision": 0.9912225705329154,
44
+ "eval_recall": 0.992467043314501,
45
+ "eval_acc": 0.9921992199219922,
46
+ "eval_mcc": 0.9843695731126325,
47
+ "eval_f1": 0.9918444165621079,
48
+ "eval_auc": 0.9998024763512783,
49
+ "eval_runtime": 24.352,
50
+ "eval_samples_per_second": 136.868,
51
+ "eval_steps_per_second": 2.176,
52
+ "epoch": 4.99
53
+ },
54
+ "4": {
55
+ "eval_loss": 0.016317054629325867,
56
+ "eval_precision": 0.9943502824858758,
57
+ "eval_recall": 0.9943502824858758,
58
+ "eval_acc": 0.9945994599459946,
59
+ "eval_mcc": 0.9891778686927722,
60
+ "eval_f1": 0.9943502824858758,
61
+ "eval_auc": 0.999885273935537,
62
+ "eval_runtime": 20.6999,
63
+ "eval_samples_per_second": 161.015,
64
+ "eval_steps_per_second": 2.56,
65
+ "epoch": 4.99
66
+ }
67
+ }
metrics.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"precision": 0.9943502824858758, "recall": 0.9943502824858758, "acc": 0.9945994599459946, "mcc": 0.9891778686927722, "f1": 0.9943502824858758, "auc": 0.999885273935537}
metrics_all_fold.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": [
3
+ 0.8185985592665357,
4
+ 0.9459962756052142,
5
+ 0.9862585883822611,
6
+ 0.9912225705329154,
7
+ 0.9943502824858758
8
+ ],
9
+ "recall": [
10
+ 0.7841907151819323,
11
+ 0.9566854990583804,
12
+ 0.9912115505335845,
13
+ 0.992467043314501,
14
+ 0.9943502824858758
15
+ ],
16
+ "f1": [
17
+ 0.8010253123998718,
18
+ 0.951310861423221,
19
+ 0.9887288666249218,
20
+ 0.9918444165621079,
21
+ 0.9943502824858758
22
+ ],
23
+ "auc": [
24
+ 0.9007949592455319,
25
+ 0.9885553535222344,
26
+ 0.999065595890065,
27
+ 0.9998024763512783,
28
+ 0.999885273935537
29
+ ],
30
+ "acc": [
31
+ 0.8136813681368137,
32
+ 0.9531953195319532,
33
+ 0.9891989198919892,
34
+ 0.9921992199219922,
35
+ 0.9945994599459946
36
+ ],
37
+ "mcc": [
38
+ 0.6265110018485912,
39
+ 0.9063059646905545,
40
+ 0.9783716402634621,
41
+ 0.9843695731126325,
42
+ 0.9891778686927722
43
+ ]
44
+ }
metrics_ci_bounds.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": {
3
+ "ci_lower": 0.8547282769620951,
4
+ "ci_upper": 1.0398422335470257
5
+ },
6
+ "recall": {
7
+ "ci_lower": 0.8313215805994973,
8
+ "ci_upper": 1.056240455630212
9
+ },
10
+ "f1": {
11
+ "ci_lower": 0.8428556705483334,
12
+ "ci_upper": 1.0480482252500658
13
+ },
14
+ "auc": {
15
+ "ci_lower": 0.9239649438214508,
16
+ "ci_upper": 1.0312765197564078
17
+ },
18
+ "acc": {
19
+ "ci_lower": 0.8526181157229019,
20
+ "ci_upper": 1.0445315992485953
21
+ },
22
+ "mcc": {
23
+ "ci_lower": 0.7045870149550184,
24
+ "ci_upper": 1.0893074044881865
25
+ }
26
+ }
metrics_mean.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.9472852552545603,
3
+ "recall": 0.9437810181148547,
4
+ "f1": 0.9454519478991996,
5
+ "auc": 0.9776207317889293,
6
+ "acc": 0.9485748574857485,
7
+ "mcc": 0.8969472097216025
8
+ }
metrics_std.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.0745426930525177,
3
+ "recall": 0.0905715537198832,
4
+ "f1": 0.08262805195228776,
5
+ "auc": 0.043212808010137035,
6
+ "acc": 0.07728076347680288,
7
+ "mcc": 0.15492129516911088
8
+ }
metrics_visualisation.png ADDED
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ee2fe2c9bf2796b9cb010ba17e83cbc0967d8b797898781ba11430ac79b7eb
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:e19993baf5dc66ee5ae047af369db08fcf807b03f191f45eb478f65143746c29
3
+ size 70379087
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:bdd8bbf6549006912fa4008b8e48069e1254f69c7524fb5cdbd26a9a8a4a4f94
3
+ size 13356638
test_top_repo_data.csv ADDED
The diff for this file is too large to render. See raw diff
 
top_repo_data.csv ADDED
The diff for this file is too large to render. See raw diff
 
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": 0.09686212190880218,
9
+ "cpu_model": "AMD EPYC 7282 16-Core Processor",
10
+ "cpu_power": 19.17079533382436,
11
+ "duration": 3117.374103307724,
12
+ "emissions": 0.02323189242211557,
13
+ "emissions_rate": 7.452391548856813e-06,
14
+ "energy_consumed": 0.8432628828354108,
15
+ "gpu_count": 8,
16
+ "gpu_energy": 0.6649034747001394,
17
+ "gpu_model": "8 x NVIDIA GeForce RTX 2080 Ti",
18
+ "gpu_power": 731.791919414086,
19
+ "latitude": 59.955,
20
+ "longitude": 10.859,
21
+ "on_cloud": "N",
22
+ "os": "Linux-4.18.0-513.9.1.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": 0.08149728622646912,
27
+ "ram_power": 94.2059955596924,
28
+ "ram_total_size": 251.2159881591797,
29
+ "region": "oslo county",
30
+ "run_id": "3a744030-f267-4edb-8457-e6ae2610343d",
31
+ "timestamp": "2024-03-04T12:53:59",
32
+ "tracking_mode": "machine"
33
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eaf06d5345ffe465dd8018ae971057d4233655e8d37542173575dacd209a4c0
3
+ size 4664