Hugging Face's logo

karths
/
binary_classification_train_usab

Text Classification
Transformers
Safetensors
roberta
text-embeddings-inference
Model card Files
xet
Community
karths commited on
Commit
bf73d26
·
verified ·
1 Parent(s): 37c4dff

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. .gitattributes +2 -0
  2. checkpoint-2180/config.json +28 -0
  3. checkpoint-2180/model.safetensors +3 -0
  4. checkpoint-2180/optimizer.pt +3 -0
  5. checkpoint-2180/rng_state.pth +3 -0
  6. checkpoint-2180/scheduler.pt +3 -0
  7. checkpoint-2180/trainer_state.json +43 -0
  8. checkpoint-2180/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 +0 -0
  26. top_repo_data.csv +0 -0
  27. tracker_carbon_statistics.json +33 -0
  28. 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
checkpoint-2180/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-2180/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beadc08a56f100fde4c91910066cb811227f3ed59602afeddc2f31ca16e578af
3
+ size 328492280
checkpoint-2180/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0b729adc73eab4e69aa52805a32463cfb3e59b90ecd11d27be9e3c3856c5290
3
+ size 657047610
checkpoint-2180/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f0a513ba2b8a63d0694020aced6b663d62f3b7742f53af9eaee9f4c899e3246
3
+ size 14244
checkpoint-2180/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75ffbc9149f0e8bcac3899424e9f8c5c6b2927e37340236a29a8bac5b5e36d54
3
+ size 1064
checkpoint-2180/trainer_state.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2180,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.15,
13
+ "learning_rate": 4.9800000000000004e-05,
14
+ "loss": 0.0354,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 2.29,
19
+ "learning_rate": 3.992063035456259e-05,
20
+ "loss": 0.0576,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 3.44,
25
+ "learning_rate": 1.7720517816018433e-05,
26
+ "loss": 0.0357,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 4.59,
31
+ "learning_rate": 1.4339627226955392e-06,
32
+ "loss": 0.017,
33
+ "step": 2000
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 2180,
38
+ "num_train_epochs": 5,
39
+ "save_steps": 500,
40
+ "total_flos": 1.84692670576128e+16,
41
+ "trial_name": null,
42
+ "trial_params": null
43
+ }
checkpoint-2180/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a6905c365b426a1e0a4d3d61f224c7b790939e60a4343b9346c925f1e81fb59
3
+ size 4664
classification_report.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"0": {"precision": 0.9952986725663717, "recall": 0.9952986725663717, "f1-score": 0.9952986725663717, "support": 3616}, "1": {"precision": 0.9949329359165425, "recall": 0.9949329359165425, "f1-score": 0.9949329359165425, "support": 3355}, "accuracy": 0.9951226509826424, "macro avg": {"precision": 0.9951158042414572, "recall": 0.9951158042414572, "f1-score": 0.9951158042414572, "support": 6971}, "weighted avg": {"precision": 0.9951226509826424, "recall": 0.9951226509826424, "f1-score": 0.9951226509826424, "support": 6971}}
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": 0.5698052644729614,
4
+ "eval_precision": 0.7999409855414576,
5
+ "eval_recall": 0.8080476900149032,
6
+ "eval_acc": 0.8103843947217442,
7
+ "eval_mcc": 0.6204014004148342,
8
+ "eval_f1": 0.8039739027283511,
9
+ "eval_auc": 0.895946777244565,
10
+ "eval_runtime": 45.6798,
11
+ "eval_samples_per_second": 152.628,
12
+ "eval_steps_per_second": 2.386,
13
+ "epoch": 5.0
14
+ },
15
+ "1": {
16
+ "eval_loss": 0.20604972541332245,
17
+ "eval_precision": 0.9361384661295136,
18
+ "eval_recall": 0.9353011329755516,
19
+ "eval_acc": 0.9381724286329077,
20
+ "eval_mcc": 0.8761648964319617,
21
+ "eval_f1": 0.9357196122296794,
22
+ "eval_auc": 0.9853056749013183,
23
+ "eval_runtime": 43.4125,
24
+ "eval_samples_per_second": 160.576,
25
+ "eval_steps_per_second": 2.511,
26
+ "epoch": 5.0
27
+ },
28
+ "2": {
29
+ "eval_loss": 0.03554569557309151,
30
+ "eval_precision": 0.9904676794757223,
31
+ "eval_recall": 0.9910581222056631,
32
+ "eval_acc": 0.9911060106154067,
33
+ "eval_mcc": 0.9821875961225488,
34
+ "eval_f1": 0.9907628128724671,
35
+ "eval_auc": 0.9991500764939397,
36
+ "eval_runtime": 47.6856,
37
+ "eval_samples_per_second": 146.187,
38
+ "eval_steps_per_second": 2.286,
39
+ "epoch": 5.0
40
+ },
41
+ "3": {
42
+ "eval_loss": 0.020433001220226288,
43
+ "eval_precision": 0.99375,
44
+ "eval_recall": 0.995230998509687,
45
+ "eval_acc": 0.9946922966575814,
46
+ "eval_mcc": 0.9893712840331538,
47
+ "eval_f1": 0.9944899478778852,
48
+ "eval_auc": 0.999496236300331,
49
+ "eval_runtime": 45.3682,
50
+ "eval_samples_per_second": 153.654,
51
+ "eval_steps_per_second": 2.403,
52
+ "epoch": 5.0
53
+ },
54
+ "4": {
55
+ "eval_loss": 0.020634396001696587,
56
+ "eval_precision": 0.9949329359165425,
57
+ "eval_recall": 0.9949329359165425,
58
+ "eval_acc": 0.9951226509826424,
59
+ "eval_mcc": 0.9902316084829141,
60
+ "eval_f1": 0.9949329359165425,
61
+ "eval_auc": 0.999638096290044,
62
+ "eval_runtime": 44.1628,
63
+ "eval_samples_per_second": 157.848,
64
+ "eval_steps_per_second": 2.468,
65
+ "epoch": 5.0
66
+ }
67
+ }
metrics.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"precision": 0.9949329359165425, "recall": 0.9949329359165425, "acc": 0.9951226509826424, "mcc": 0.9902316084829141, "f1": 0.9949329359165425, "auc": 0.999638096290044}
metrics_all_fold.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": [
3
+ 0.7999409855414576,
4
+ 0.9361384661295136,
5
+ 0.9904676794757223,
6
+ 0.99375,
7
+ 0.9949329359165425
8
+ ],
9
+ "recall": [
10
+ 0.8080476900149032,
11
+ 0.9353011329755516,
12
+ 0.9910581222056631,
13
+ 0.995230998509687,
14
+ 0.9949329359165425
15
+ ],
16
+ "f1": [
17
+ 0.8039739027283511,
18
+ 0.9357196122296794,
19
+ 0.9907628128724671,
20
+ 0.9944899478778852,
21
+ 0.9949329359165425
22
+ ],
23
+ "auc": [
24
+ 0.895946777244565,
25
+ 0.9853056749013183,
26
+ 0.9991500764939397,
27
+ 0.999496236300331,
28
+ 0.999638096290044
29
+ ],
30
+ "acc": [
31
+ 0.8103843947217442,
32
+ 0.9381724286329077,
33
+ 0.9911060106154067,
34
+ 0.9946922966575814,
35
+ 0.9951226509826424
36
+ ],
37
+ "mcc": [
38
+ 0.6204014004148342,
39
+ 0.8761648964319617,
40
+ 0.9821875961225488,
41
+ 0.9893712840331538,
42
+ 0.9902316084829141
43
+ ]
44
+ }
metrics_ci_bounds.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": {
3
+ "ci_lower": 0.8390891372190341,
4
+ "ci_upper": 1.0470028896062602
5
+ },
6
+ "recall": {
7
+ "ci_lower": 0.8448315742138132,
8
+ "ci_upper": 1.0449967776351259
9
+ },
10
+ "f1": {
11
+ "ci_lower": 0.8419513457466477,
12
+ "ci_upper": 1.0460003389033226
13
+ },
14
+ "auc": {
15
+ "ci_lower": 0.9198884039380292,
16
+ "ci_upper": 1.0319263405540502
17
+ },
18
+ "acc": {
19
+ "ci_lower": 0.84720213826446,
20
+ "ci_upper": 1.044588974379653
21
+ },
22
+ "mcc": {
23
+ "ci_lower": 0.6940941429275611,
24
+ "ci_upper": 1.089248571266604
25
+ }
26
+ }
metrics_mean.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.9430460134126472,
3
+ "recall": 0.9449141759244695,
4
+ "f1": 0.9439758423249851,
5
+ "auc": 0.9759073722460396,
6
+ "acc": 0.9458955563220565,
7
+ "mcc": 0.8916713570970826
8
+ }
metrics_std.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.08372383861012372,
3
+ "recall": 0.08060361084435021,
4
+ "f1": 0.08216755638073554,
5
+ "auc": 0.04511604458939733,
6
+ "acc": 0.0794848028132971,
7
+ "mcc": 0.15912293056361734
8
+ }
metrics_visualisation.png ADDED
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beadc08a56f100fde4c91910066cb811227f3ed59602afeddc2f31ca16e578af
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 sha256:7a0aa8468dc3b829458b19a4d2b922757d25a8b949c08163a991a9bcd364283c
3
+ size 128609100
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:d948c7b913ba958ed74e4df221b8a100aa14047259b95fc947dc0caf4e938bd7
3
+ size 23815390
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": 192,
8
+ "cpu_energy": 0.19162993172382276,
9
+ "cpu_model": "AMD EPYC 7642 48-Core Processor",
10
+ "cpu_power": 84.33826915787697,
11
+ "duration": 4968.924512147903,
12
+ "emissions": 0.056606367882956206,
13
+ "emissions_rate": 1.13920764432155e-05,
14
+ "energy_consumed": 2.0546776001073033,
15
+ "gpu_count": 4,
16
+ "gpu_energy": 1.3415015084781259,
17
+ "gpu_model": "4 x NVIDIA GeForce RTX 3090",
18
+ "gpu_power": 955.5160699119477,
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": 0.5215461599053545,
27
+ "ram_power": 377.6938190460205,
28
+ "ram_total_size": 1007.1835174560547,
29
+ "region": "oslo county",
30
+ "run_id": "a23befb1-5b69-4b03-acc7-576c8c23bb1a",
31
+ "timestamp": "2024-04-05T14:02:11",
32
+ "tracking_mode": "machine"
33
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a6905c365b426a1e0a4d3d61f224c7b790939e60a4343b9346c925f1e81fb59
3
+ size 4664