Hugging Face's logo

karths
/
medium_priority_roberta

Text Classification
Transformers
Safetensors
roberta
Model card Files
xet
 Community
karths commited on
Commit
444c870
·
verified ·
1 Parent(s): 6fe10f7

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. .gitattributes +3 -0
  2. .ipynb_checkpoints/detailed_confusion_matrix-checkpoint.png +0 -0
  3. checkpoint-11820/config.json +28 -0
  4. checkpoint-11820/model.safetensors +3 -0
  5. checkpoint-11820/optimizer.pt +3 -0
  6. checkpoint-11820/rng_state.pth +3 -0
  7. checkpoint-11820/scheduler.pt +3 -0
  8. checkpoint-11820/trainer_state.json +157 -0
  9. checkpoint-11820/training_args.bin +3 -0
  10. classification_report.json +1 -0
  11. config.json +28 -0
  12. confusion_matrix.png +0 -0
  13. detailed_confusion_matrix.png +0 -0
  14. fold_results.json +67 -0
  15. metrics.json +1 -0
  16. metrics_all_fold.json +44 -0
  17. metrics_ci_bounds.json +26 -0
  18. metrics_mean.json +8 -0
  19. metrics_std.json +8 -0
  20. metrics_visualisation.png +0 -0
  21. model.safetensors +3 -0
  22. precision_recall_curve.png +0 -0
  23. reduced_main_data.csv +3 -0
  24. roc_curve.png +0 -0
  25. test_data_for_future_evaluation.csv +3 -0
  26. test_top_repo_data.csv +3 -0
  27. top_repo_data.csv +0 -0
  28. tracker_carbon_statistics.json +33 -0
  29. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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
.ipynb_checkpoints/detailed_confusion_matrix-checkpoint.png ADDED
checkpoint-11820/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-11820/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a95ee069d4168c7d3365ca440c2f16dfcdc7efb7878bce98630282f3270c1705
3
+ size 328492280
checkpoint-11820/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89498c10c03f1e59d20960ce7c236a3eeac91ee106d5a75011e577bb8e8d619b
3
+ size 657047610
checkpoint-11820/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a857b2650ab34daa84fc2c4f4b26d82e60286eaaac7fa6aea552c562bc7d21
3
+ size 14244
checkpoint-11820/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad0ea4cfce17d6a2282b50064bfecae906fddcc08a2ba9a7d833a963696e368
3
+ size 1064
checkpoint-11820/trainer_state.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.998942694015648,
5
+ "eval_steps": 500,
6
+ "global_step": 11820,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.21,
13
+ "learning_rate": 4.9800000000000004e-05,
14
+ "loss": 0.0466,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.42,
19
+ "learning_rate": 4.976161211704926e-05,
20
+ "loss": 0.0691,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.63,
25
+ "learning_rate": 4.9047204098004095e-05,
26
+ "loss": 0.0741,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.85,
31
+ "learning_rate": 4.7870506066506904e-05,
32
+ "loss": 0.0763,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.06,
37
+ "learning_rate": 4.62541391865573e-05,
38
+ "loss": 0.0716,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 1.27,
43
+ "learning_rate": 4.422917693605373e-05,
44
+ "loss": 0.0591,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 1.48,
49
+ "learning_rate": 4.183454774177651e-05,
50
+ "loss": 0.0632,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 1.69,
55
+ "learning_rate": 3.91162866086904e-05,
56
+ "loss": 0.0608,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 1.9,
61
+ "learning_rate": 3.613286279641655e-05,
62
+ "loss": 0.0622,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 2.11,
67
+ "learning_rate": 3.292969207944561e-05,
68
+ "loss": 0.0533,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 2.33,
73
+ "learning_rate": 2.9574078798457334e-05,
74
+ "loss": 0.0498,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 2.54,
79
+ "learning_rate": 2.613053217868765e-05,
80
+ "loss": 0.0479,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 2.75,
85
+ "learning_rate": 2.2672159813612203e-05,
86
+ "loss": 0.0445,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 2.96,
91
+ "learning_rate": 1.925835994414427e-05,
92
+ "loss": 0.0429,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 3.17,
97
+ "learning_rate": 1.5948030836583748e-05,
98
+ "loss": 0.0348,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 3.38,
103
+ "learning_rate": 1.2811719253897084e-05,
104
+ "loss": 0.032,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 3.59,
109
+ "learning_rate": 9.909718505639284e-06,
110
+ "loss": 0.0335,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 3.81,
115
+ "learning_rate": 7.302717325477024e-06,
116
+ "loss": 0.0334,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 4.02,
121
+ "learning_rate": 5.030401317985792e-06,
122
+ "loss": 0.0309,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 4.23,
127
+ "learning_rate": 3.141986323924076e-06,
128
+ "loss": 0.0269,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 4.44,
133
+ "learning_rate": 1.6737757483597487e-06,
134
+ "loss": 0.0311,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 4.65,
139
+ "learning_rate": 6.539948719738204e-07,
140
+ "loss": 0.0303,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 4.86,
145
+ "learning_rate": 1.0287606124971538e-07,
146
+ "loss": 0.0325,
147
+ "step": 11500
148
+ }
149
+ ],
150
+ "logging_steps": 500,
151
+ "max_steps": 11820,
152
+ "num_train_epochs": 5,
153
+ "save_steps": 500,
154
+ "total_flos": 1.0019728060420915e+17,
155
+ "trial_name": null,
156
+ "trial_params": null
157
+ }
checkpoint-11820/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b446cc14a4826cf3da183f238854503e14c55fce6c9fd91ae844a33bde459d0
3
+ size 4664
classification_report.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"0": {"precision": 0.9958119568631557, "recall": 0.9931084890884411, "f1-score": 0.9944583856127144, "support": 19154}, "1": {"precision": 0.9929502243110446, "recall": 0.9957155098543273, "f1-score": 0.9943309444860413, "support": 18672}, "accuracy": 0.9943953894146883, "macro avg": {"precision": 0.9943810905871002, "recall": 0.9944119994713843, "f1-score": 0.9943946650493778, "support": 37826}, "weighted avg": {"precision": 0.9943993234836543, "recall": 0.9943953894146883, "f1-score": 0.9943954770123538, "support": 37826}}
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": 0.4894842505455017,
4
+ "eval_precision": 0.797077839433895,
5
+ "eval_recall": 0.8385282776349614,
6
+ "eval_acc": 0.8149205593887964,
7
+ "eval_mcc": 0.6308544272382445,
8
+ "eval_f1": 0.8172778285266865,
9
+ "eval_auc": 0.9029118022996898,
10
+ "eval_runtime": 140.306,
11
+ "eval_samples_per_second": 269.604,
12
+ "eval_steps_per_second": 4.219,
13
+ "epoch": 5.0
14
+ },
15
+ "1": {
16
+ "eval_loss": 0.30189815163612366,
17
+ "eval_precision": 0.8898150560041678,
18
+ "eval_recall": 0.914738646101114,
19
+ "eval_acc": 0.9020012160626008,
20
+ "eval_mcc": 0.8043471347208236,
21
+ "eval_f1": 0.90210473499353,
22
+ "eval_auc": 0.9664702229053249,
23
+ "eval_runtime": 145.1802,
24
+ "eval_samples_per_second": 260.552,
25
+ "eval_steps_per_second": 4.078,
26
+ "epoch": 5.0
27
+ },
28
+ "2": {
29
+ "eval_loss": 0.13572567701339722,
30
+ "eval_precision": 0.9530286256523802,
31
+ "eval_recall": 0.9682395158266831,
32
+ "eval_acc": 0.9607677259028181,
33
+ "eval_mcc": 0.9216528289238667,
34
+ "eval_f1": 0.9605738575982997,
35
+ "eval_auc": 0.9932413748732483,
36
+ "eval_runtime": 146.7514,
37
+ "eval_samples_per_second": 257.756,
38
+ "eval_steps_per_second": 4.034,
39
+ "epoch": 5.0
40
+ },
41
+ "3": {
42
+ "eval_loss": 0.03292611241340637,
43
+ "eval_precision": 0.9882822902796272,
44
+ "eval_recall": 0.9937339331619537,
45
+ "eval_acc": 0.9910907841167451,
46
+ "eval_mcc": 0.9821944795487312,
47
+ "eval_f1": 0.9910006142014046,
48
+ "eval_auc": 0.9993099888344676,
49
+ "eval_runtime": 149.3977,
50
+ "eval_samples_per_second": 253.19,
51
+ "eval_steps_per_second": 3.963,
52
+ "epoch": 5.0
53
+ },
54
+ "4": {
55
+ "eval_loss": 0.021255388855934143,
56
+ "eval_precision": 0.9929502243110446,
57
+ "eval_recall": 0.9957155098543273,
58
+ "eval_acc": 0.9943953894146883,
59
+ "eval_mcc": 0.9887930895753908,
60
+ "eval_f1": 0.9943309444860413,
61
+ "eval_auc": 0.9996470227915908,
62
+ "eval_runtime": 152.3623,
63
+ "eval_samples_per_second": 248.264,
64
+ "eval_steps_per_second": 3.885,
65
+ "epoch": 5.0
66
+ }
67
+ }
metrics.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"precision": 0.9929502243110446, "recall": 0.9957155098543273, "acc": 0.9943953894146883, "mcc": 0.9887930895753908, "f1": 0.9943309444860413, "auc": 0.9996470227915908}
metrics_all_fold.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": [
3
+ 0.797077839433895,
4
+ 0.8898150560041678,
5
+ 0.9530286256523802,
6
+ 0.9882822902796272,
7
+ 0.9929502243110446
8
+ ],
9
+ "recall": [
10
+ 0.8385282776349614,
11
+ 0.914738646101114,
12
+ 0.9682395158266831,
13
+ 0.9937339331619537,
14
+ 0.9957155098543273
15
+ ],
16
+ "f1": [
17
+ 0.8172778285266865,
18
+ 0.90210473499353,
19
+ 0.9605738575982997,
20
+ 0.9910006142014046,
21
+ 0.9943309444860413
22
+ ],
23
+ "auc": [
24
+ 0.9029118022996898,
25
+ 0.9664702229053249,
26
+ 0.9932413748732483,
27
+ 0.9993099888344676,
28
+ 0.9996470227915908
29
+ ],
30
+ "acc": [
31
+ 0.8149205593887964,
32
+ 0.9020012160626008,
33
+ 0.9607677259028181,
34
+ 0.9910907841167451,
35
+ 0.9943953894146883
36
+ ],
37
+ "mcc": [
38
+ 0.6308544272382445,
39
+ 0.8043471347208236,
40
+ 0.9216528289238667,
41
+ 0.9821944795487312,
42
+ 0.9887930895753908
43
+ ]
44
+ }
metrics_ci_bounds.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": {
3
+ "ci_lower": 0.8222052584794745,
4
+ "ci_upper": 1.0262563557929716
5
+ },
6
+ "recall": {
7
+ "ci_lower": 0.8595956350124584,
8
+ "ci_upper": 1.0247867180191574
9
+ },
10
+ "f1": {
11
+ "ci_lower": 0.8404890769938336,
12
+ "ci_upper": 1.0256261149285513
13
+ },
14
+ "auc": {
15
+ "ci_lower": 0.9212542173438407,
16
+ "ci_upper": 1.0233779473378881
17
+ },
18
+ "acc": {
19
+ "ci_lower": 0.8388545766959804,
20
+ "ci_upper": 1.0264156932582789
21
+ },
22
+ "mcc": {
23
+ "ci_lower": 0.6785236289948702,
24
+ "ci_upper": 1.0526131550079523
25
+ }
26
+ }
metrics_mean.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.924230807136223,
3
+ "recall": 0.9421911765158079,
4
+ "f1": 0.9330575959611924,
5
+ "auc": 0.9723160823408644,
6
+ "acc": 0.9326351349771297,
7
+ "mcc": 0.8655683920014112
8
+ }
metrics_std.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.08216840369402846,
3
+ "recall": 0.06652004215539391,
4
+ "f1": 0.07455198757576255,
5
+ "auc": 0.041123738040960776,
6
+ "acc": 0.07552812871824857,
7
+ "mcc": 0.15064040133009118
8
+ }
metrics_visualisation.png ADDED
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a95ee069d4168c7d3365ca440c2f16dfcdc7efb7878bce98630282f3270c1705
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 sha256:974465e69f61aeeb0bd35a58984cda3aa19211c1d4048e18c400c381a4787843
3
+ size 739635171
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 sha256:4329d38bcb602d54b1a5649f5c20dd5ddd5db16790961c4d2f1a0f9a8e3595cc
3
+ size 132511279
test_top_repo_data.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:934908191818388b67cd9e863630ee44be092075423ce9047fb3b8f25395ccd4
3
+ size 18864191
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": 0.2805582379736331,
9
+ "cpu_model": "AMD EPYC 7642 48-Core Processor",
10
+ "cpu_power": 13.170642692663874,
11
+ "duration": 23640.817118406296,
12
+ "emissions": 0.13423884939187516,
13
+ "emissions_rate": 5.678266056521343e-06,
14
+ "energy_consumed": 4.872553516946467,
15
+ "gpu_count": 4,
16
+ "gpu_energy": 2.0628040124641123,
17
+ "gpu_model": "4 x NVIDIA GeForce RTX 3090",
18
+ "gpu_power": 311.66423576058344,
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": 2.5291912665087213,
27
+ "ram_power": 377.6938133239746,
28
+ "ram_total_size": 1007.1835021972656,
29
+ "region": "oslo county",
30
+ "run_id": "296b5fc3-192f-42d9-81b1-6fca1ee69702",
31
+ "timestamp": "2024-03-01T19:13:31",
32
+ "tracking_mode": "machine"
33
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b446cc14a4826cf3da183f238854503e14c55fce6c9fd91ae844a33bde459d0
3
+ size 4664