Hugging Face's logo

karths
/
binary_classification_train_infrastructure

Text Classification
Transformers
Safetensors
roberta
Model card Files
xet
Community
karths commited on
Commit
624dc64
·
verified ·
1 Parent(s): 4c0e5e1

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. .gitattributes +4 -0
  2. checkpoint-3090/config.json +28 -0
  3. checkpoint-3090/model.safetensors +3 -0
  4. checkpoint-3090/optimizer.pt +3 -0
  5. checkpoint-3090/rng_state.pth +3 -0
  6. checkpoint-3090/scheduler.pt +3 -0
  7. checkpoint-3090/trainer_state.json +55 -0
  8. checkpoint-3090/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-3090/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-3090/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0db1daf8e333e43f2217a088bfdaf39007fac1a756dede6702d7fe43ad389f
3
+ size 328492280
checkpoint-3090/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b6d3163f37f1ce5fc2d8f0058b0b6cecde30ba1691ca242d06197dc18eeaf0
3
+ size 657047610
checkpoint-3090/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26751333a94ddc5bf1cecea26aecd3d5347c7e24888278572a1de6df4ec908b7
3
+ size 14244
checkpoint-3090/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e58a0065c2413459c421bf7be9777ba14d2b7dffbfaa51878e8a6981f9d303
3
+ size 1064
checkpoint-3090/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.995957962813258,
5
+ "eval_steps": 500,
6
+ "global_step": 3090,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.81,
13
+ "learning_rate": 4.9800000000000004e-05,
14
+ "loss": 0.0634,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.62,
19
+ "learning_rate": 4.557592164542048e-05,
20
+ "loss": 0.0823,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 2.43,
25
+ "learning_rate": 3.381275475633684e-05,
26
+ "loss": 0.072,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 3.23,
31
+ "learning_rate": 1.8906193524453964e-05,
32
+ "loss": 0.0483,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 4.04,
37
+ "learning_rate": 6.193178695564386e-06,
38
+ "loss": 0.0289,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 4.85,
43
+ "learning_rate": 1.5889694102974583e-07,
44
+ "loss": 0.012,
45
+ "step": 3000
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 3090,
50
+ "num_train_epochs": 5,
51
+ "save_steps": 500,
52
+ "total_flos": 2.618615536631808e+16,
53
+ "trial_name": null,
54
+ "trial_params": null
55
+ }
checkpoint-3090/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fad545aa56e39547604a6aec89a48aa9d41070fb3f411ae2857c916de8c0bf55
3
+ size 4664
classification_report.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"0": {"precision": 0.9946598101265823, "recall": 0.9958415841584158, "f1-score": 0.9952503463289136, "support": 5050}, "1": {"precision": 0.9956557716177079, "recall": 0.9944214876033057, "f1-score": 0.9950382468472193, "support": 4840}, "accuracy": 0.9951466127401416, "macro avg": {"precision": 0.9951577908721452, "recall": 0.9951315358808608, "f1-score": 0.9951442965880665, "support": 9890}, "weighted avg": {"precision": 0.9951472169634931, "recall": 0.9951466127401416, "f1-score": 0.9951465484025839, "support": 9890}}
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": 0.5355825424194336,
4
+ "eval_precision": 0.8071514664523906,
5
+ "eval_recall": 0.8299938029332783,
6
+ "eval_acc": 0.8197351127287433,
7
+ "eval_mcc": 0.6397657383445139,
8
+ "eval_f1": 0.8184132803747837,
9
+ "eval_auc": 0.8944352386075212,
10
+ "eval_runtime": 57.1313,
11
+ "eval_samples_per_second": 173.128,
12
+ "eval_steps_per_second": 2.713,
13
+ "epoch": 5.0
14
+ },
15
+ "1": {
16
+ "eval_loss": 0.23044656217098236,
17
+ "eval_precision": 0.9200890147683592,
18
+ "eval_recall": 0.9394753150175583,
19
+ "eval_acc": 0.9304418157921343,
20
+ "eval_mcc": 0.8610653101668877,
21
+ "eval_f1": 0.9296811120196239,
22
+ "eval_auc": 0.9787842295900733,
23
+ "eval_runtime": 57.432,
24
+ "eval_samples_per_second": 172.221,
25
+ "eval_steps_per_second": 2.699,
26
+ "epoch": 5.0
27
+ },
28
+ "2": {
29
+ "eval_loss": 0.06663916260004044,
30
+ "eval_precision": 0.9790080263428689,
31
+ "eval_recall": 0.9826482131790952,
32
+ "eval_acc": 0.981195025781013,
33
+ "eval_mcc": 0.9623825256052116,
34
+ "eval_f1": 0.9808247422680412,
35
+ "eval_auc": 0.9977456993788617,
36
+ "eval_runtime": 48.9974,
37
+ "eval_samples_per_second": 201.868,
38
+ "eval_steps_per_second": 3.163,
39
+ "epoch": 5.0
40
+ },
41
+ "3": {
42
+ "eval_loss": 0.02976991981267929,
43
+ "eval_precision": 0.9913276894486889,
44
+ "eval_recall": 0.9917372443709978,
45
+ "eval_acc": 0.9917096350217369,
46
+ "eval_mcc": 0.9834120858983001,
47
+ "eval_f1": 0.9915324246179266,
48
+ "eval_auc": 0.9996454582454734,
49
+ "eval_runtime": 49.5752,
50
+ "eval_samples_per_second": 199.515,
51
+ "eval_steps_per_second": 3.127,
52
+ "epoch": 5.0
53
+ },
54
+ "4": {
55
+ "eval_loss": 0.02025197632610798,
56
+ "eval_precision": 0.9956557716177079,
57
+ "eval_recall": 0.9944214876033057,
58
+ "eval_acc": 0.9951466127401416,
59
+ "eval_mcc": 0.9902893264049639,
60
+ "eval_f1": 0.9950382468472193,
61
+ "eval_auc": 0.9996905122330415,
62
+ "eval_runtime": 51.1558,
63
+ "eval_samples_per_second": 193.331,
64
+ "eval_steps_per_second": 3.03,
65
+ "epoch": 5.0
66
+ }
67
+ }
metrics.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"precision": 0.9956557716177079, "recall": 0.9944214876033057, "acc": 0.9951466127401416, "mcc": 0.9902893264049639, "f1": 0.9950382468472193, "auc": 0.9996905122330415}
metrics_all_fold.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": [
3
+ 0.8071514664523906,
4
+ 0.9200890147683592,
5
+ 0.9790080263428689,
6
+ 0.9913276894486889,
7
+ 0.9956557716177079
8
+ ],
9
+ "recall": [
10
+ 0.8299938029332783,
11
+ 0.9394753150175583,
12
+ 0.9826482131790952,
13
+ 0.9917372443709978,
14
+ 0.9944214876033057
15
+ ],
16
+ "f1": [
17
+ 0.8184132803747837,
18
+ 0.9296811120196239,
19
+ 0.9808247422680412,
20
+ 0.9915324246179266,
21
+ 0.9950382468472193
22
+ ],
23
+ "auc": [
24
+ 0.8944352386075212,
25
+ 0.9787842295900733,
26
+ 0.9977456993788617,
27
+ 0.9996454582454734,
28
+ 0.9996905122330415
29
+ ],
30
+ "acc": [
31
+ 0.8197351127287433,
32
+ 0.9304418157921343,
33
+ 0.981195025781013,
34
+ 0.9917096350217369,
35
+ 0.9951466127401416
36
+ ],
37
+ "mcc": [
38
+ 0.6397657383445139,
39
+ 0.8610653101668877,
40
+ 0.9623825256052116,
41
+ 0.9834120858983001,
42
+ 0.9902893264049639
43
+ ]
44
+ }
metrics_ci_bounds.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": {
3
+ "ci_lower": 0.8399170409326607,
4
+ "ci_upper": 1.0373757465193452
5
+ },
6
+ "recall": {
7
+ "ci_lower": 0.8614826170958688,
8
+ "ci_upper": 1.0338278081458254
9
+ },
10
+ "f1": {
11
+ "ci_lower": 0.8506100738810776,
12
+ "ci_upper": 1.0355858485699603
13
+ },
14
+ "auc": {
15
+ "ci_lower": 0.9177217430307886,
16
+ "ci_upper": 1.0303987121912
17
+ },
18
+ "acc": {
19
+ "ci_lower": 0.8517696067910826,
20
+ "ci_upper": 1.0355216740344249
21
+ },
22
+ "mcc": {
23
+ "ci_lower": 0.7037980777788673,
24
+ "ci_upper": 1.0709679167890835
25
+ }
26
+ }
metrics_mean.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.938646393726003,
3
+ "recall": 0.9476552126208471,
4
+ "f1": 0.9430979612255189,
5
+ "auc": 0.9740602276109943,
6
+ "acc": 0.9436456404127538,
7
+ "mcc": 0.8873829972839754
8
+ }
metrics_std.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.07951374360226879,
3
+ "recall": 0.0694008972231123,
4
+ "f1": 0.0744870492164043,
5
+ "auc": 0.04537337368378794,
6
+ "acc": 0.07399428005852,
7
+ "mcc": 0.14785394419962916
8
+ }
metrics_visualisation.png ADDED
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0db1daf8e333e43f2217a088bfdaf39007fac1a756dede6702d7fe43ad389f
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 sha256:2a3d625b859cda8eaa62ee6e0c95f11b84b081fc55939975bf2398feb8698248
3
+ size 183865163
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 sha256:5adc72120c0ab5d993faaa58eb13ce09f017f84bfe2c1e3d747e1394ff133a77
3
+ size 34091671
test_top_repo_data.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d1a000058e87e016b85d730ab899fa727a4d1f962f2661400d4930c8494f2ea
3
+ size 20938539
top_repo_data.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7d1e7c1ad91e0f17c3dcf36623fb95662d01597d29f07fcf73845a72bc630c7
3
+ size 16679667
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": 0.21070856568616209,
9
+ "cpu_model": "AMD EPYC 7642 48-Core Processor",
10
+ "cpu_power": 14.93635051899041,
11
+ "duration": 7855.889054298401,
12
+ "emissions": 0.07101383122209443,
13
+ "emissions_rate": 9.039566461702861e-06,
14
+ "energy_consumed": 2.5776345271177648,
15
+ "gpu_count": 4,
16
+ "gpu_energy": 1.5509463718672163,
17
+ "gpu_model": "4 x NVIDIA GeForce RTX 3090",
18
+ "gpu_power": 686.1233491786718,
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": 0.8159795895643854,
27
+ "ram_power": 377.6938190460205,
28
+ "ram_total_size": 1007.1835174560547,
29
+ "region": "oslo county",
30
+ "run_id": "b6c47195-8121-4883-be9b-32ddfd0f197e",
31
+ "timestamp": "2024-04-05T19:08:39",
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:fad545aa56e39547604a6aec89a48aa9d41070fb3f411ae2857c916de8c0bf55
3
+ size 4664