Hugging Face's logo

karths
/
low_priority_roberta

Text Classification
Transformers
Safetensors
roberta
Model card Files
xet
 Community
karths commited on
Commit
3aad2a5
·
verified ·
1 Parent(s): 6f5ee32

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. .gitattributes +4 -0
  2. checkpoint-11700/config.json +28 -0
  3. checkpoint-11700/model.safetensors +3 -0
  4. checkpoint-11700/optimizer.pt +3 -0
  5. checkpoint-11700/rng_state.pth +3 -0
  6. checkpoint-11700/scheduler.pt +3 -0
  7. checkpoint-11700/trainer_state.json +157 -0
  8. checkpoint-11700/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-11700/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-11700/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659745c47ab94cb68f23a246881e0e255d61b36983c7774c087e61da11b8aac4
3
+ size 328492280
checkpoint-11700/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e5d7a617a55f8cebb48a93962244c920207b8d254d08d245f2f25bb2721a0e2
3
+ size 657047610
checkpoint-11700/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc308d57d2653dffed65c503a55a8a4f27a634ce64160e76b576a6144426c763
3
+ size 14244
checkpoint-11700/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1ce8fa04d4f40720edb99d59e56185e3d7f009b8ee52b15246ef717d43c2c5d
3
+ size 1064
checkpoint-11700/trainer_state.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 11700,
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": 4.99e-05,
14
+ "loss": 0.0578,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.43,
19
+ "learning_rate": 4.97555074370203e-05,
20
+ "loss": 0.0726,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.64,
25
+ "learning_rate": 4.902487340802553e-05,
26
+ "loss": 0.0771,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.85,
31
+ "learning_rate": 4.782530645265661e-05,
32
+ "loss": 0.0811,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.07,
37
+ "learning_rate": 4.6175563381732146e-05,
38
+ "loss": 0.0805,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 1.28,
43
+ "learning_rate": 4.410997990525693e-05,
44
+ "loss": 0.065,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 1.5,
49
+ "learning_rate": 4.1669119433756176e-05,
50
+ "loss": 0.0679,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 1.71,
55
+ "learning_rate": 3.890091497331169e-05,
56
+ "loss": 0.067,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 1.92,
61
+ "learning_rate": 3.585972782920385e-05,
62
+ "loss": 0.0683,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 2.14,
67
+ "learning_rate": 3.2605280072225486e-05,
68
+ "loss": 0.057,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 2.35,
73
+ "learning_rate": 2.9208394310544068e-05,
74
+ "loss": 0.0529,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 2.56,
79
+ "learning_rate": 2.572218533139099e-05,
80
+ "loss": 0.0474,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 2.78,
85
+ "learning_rate": 2.222179425773234e-05,
86
+ "loss": 0.0479,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 2.99,
91
+ "learning_rate": 1.8775960892019472e-05,
92
+ "loss": 0.0513,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 3.21,
97
+ "learning_rate": 1.545235364611126e-05,
98
+ "loss": 0.0366,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 3.42,
103
+ "learning_rate": 1.2322284121554425e-05,
104
+ "loss": 0.0382,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 3.63,
109
+ "learning_rate": 9.434695081950772e-06,
110
+ "loss": 0.0382,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 3.85,
115
+ "learning_rate": 6.852773598527792e-06,
116
+ "loss": 0.0362,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 4.06,
121
+ "learning_rate": 4.627222798159206e-06,
122
+ "loss": 0.037,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 4.27,
127
+ "learning_rate": 2.804973953863538e-06,
128
+ "loss": 0.0323,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 4.49,
133
+ "learning_rate": 1.414520328716995e-06,
134
+ "loss": 0.0348,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 4.7,
139
+ "learning_rate": 4.872324411147266e-07,
140
+ "loss": 0.0399,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 4.91,
145
+ "learning_rate": 4.132013814752977e-08,
146
+ "loss": 0.043,
147
+ "step": 11500
148
+ }
149
+ ],
150
+ "logging_steps": 500,
151
+ "max_steps": 11700,
152
+ "num_train_epochs": 5,
153
+ "save_steps": 500,
154
+ "total_flos": 9.91816530587136e+16,
155
+ "trial_name": null,
156
+ "trial_params": null
157
+ }
checkpoint-11700/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e42bd909af546dc47efeb558c040128f2148109be043e30fd547a767dbc8784
3
+ size 4664
classification_report.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"0": {"precision": 0.9913057224154284, "recall": 0.9921945045092558, "f1-score": 0.9917499143361712, "support": 18961}, "1": {"precision": 0.9919817965109979, "recall": 0.9910690121786198, "f1-score": 0.9915251942707064, "support": 18475}, "accuracy": 0.9916390640025644, "macro avg": {"precision": 0.9916437594632131, "recall": 0.9916317583439378, "f1-score": 0.9916375543034388, "support": 37436}, "weighted avg": {"precision": 0.9916393710134528, "recall": 0.9916390640025644, "f1-score": 0.991639012978936, "support": 37436}}
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": 0.5364634990692139,
4
+ "eval_precision": 0.7926068170907346,
5
+ "eval_recall": 0.8042325178610089,
6
+ "eval_acc": 0.7995298768597912,
7
+ "eval_mcc": 0.59913045250335,
8
+ "eval_f1": 0.7983773473390109,
9
+ "eval_auc": 0.882308022349952,
10
+ "eval_runtime": 154.6804,
11
+ "eval_samples_per_second": 242.028,
12
+ "eval_steps_per_second": 3.782,
13
+ "epoch": 5.0
14
+ },
15
+ "1": {
16
+ "eval_loss": 0.34983137249946594,
17
+ "eval_precision": 0.8814480124791566,
18
+ "eval_recall": 0.8869824086603518,
19
+ "eval_acc": 0.8853509990383588,
20
+ "eval_mcc": 0.7706966014565018,
21
+ "eval_f1": 0.8842065504775265,
22
+ "eval_auc": 0.9549378008944933,
23
+ "eval_runtime": 157.4738,
24
+ "eval_samples_per_second": 237.728,
25
+ "eval_steps_per_second": 3.715,
26
+ "epoch": 5.0
27
+ },
28
+ "2": {
29
+ "eval_loss": 0.10594335198402405,
30
+ "eval_precision": 0.9667083039157117,
31
+ "eval_recall": 0.9634641407307172,
32
+ "eval_acc": 0.9655946148092744,
33
+ "eval_mcc": 0.9311797808626449,
34
+ "eval_f1": 0.9650834959878551,
35
+ "eval_auc": 0.9947737236299934,
36
+ "eval_runtime": 159.9467,
37
+ "eval_samples_per_second": 234.053,
38
+ "eval_steps_per_second": 3.657,
39
+ "epoch": 5.0
40
+ },
41
+ "3": {
42
+ "eval_loss": 0.041776783764362335,
43
+ "eval_precision": 0.9890743055933032,
44
+ "eval_recall": 0.9848985115020298,
45
+ "eval_acc": 0.9871781173202265,
46
+ "eval_mcc": 0.9743589877725845,
47
+ "eval_f1": 0.9869819917552615,
48
+ "eval_auc": 0.9991941638770101,
49
+ "eval_runtime": 170.6415,
50
+ "eval_samples_per_second": 219.384,
51
+ "eval_steps_per_second": 3.428,
52
+ "epoch": 5.0
53
+ },
54
+ "4": {
55
+ "eval_loss": 0.028623433783650398,
56
+ "eval_precision": 0.9919817965109979,
57
+ "eval_recall": 0.9910690121786198,
58
+ "eval_acc": 0.9916390640025644,
59
+ "eval_mcc": 0.9832755177339126,
60
+ "eval_f1": 0.9915251942707064,
61
+ "eval_auc": 0.9995504938953462,
62
+ "eval_runtime": 171.8544,
63
+ "eval_samples_per_second": 217.836,
64
+ "eval_steps_per_second": 3.404,
65
+ "epoch": 5.0
66
+ }
67
+ }
metrics.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"precision": 0.9919817965109979, "recall": 0.9910690121786198, "acc": 0.9916390640025644, "mcc": 0.9832755177339126, "f1": 0.9915251942707064, "auc": 0.9995504938953462}
metrics_all_fold.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": [
3
+ 0.7926068170907346,
4
+ 0.8814480124791566,
5
+ 0.9667083039157117,
6
+ 0.9890743055933032,
7
+ 0.9919817965109979
8
+ ],
9
+ "recall": [
10
+ 0.8042325178610089,
11
+ 0.8869824086603518,
12
+ 0.9634641407307172,
13
+ 0.9848985115020298,
14
+ 0.9910690121786198
15
+ ],
16
+ "f1": [
17
+ 0.7983773473390109,
18
+ 0.8842065504775265,
19
+ 0.9650834959878551,
20
+ 0.9869819917552615,
21
+ 0.9915251942707064
22
+ ],
23
+ "auc": [
24
+ 0.882308022349952,
25
+ 0.9549378008944933,
26
+ 0.9947737236299934,
27
+ 0.9991941638770101,
28
+ 0.9995504938953462
29
+ ],
30
+ "acc": [
31
+ 0.7995298768597912,
32
+ 0.8853509990383588,
33
+ 0.9655946148092744,
34
+ 0.9871781173202265,
35
+ 0.9916390640025644
36
+ ],
37
+ "mcc": [
38
+ 0.59913045250335,
39
+ 0.7706966014565018,
40
+ 0.9311797808626449,
41
+ 0.9743589877725845,
42
+ 0.9832755177339126
43
+ ]
44
+ }
metrics_ci_bounds.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": {
3
+ "ci_lower": 0.8172737151580437,
4
+ "ci_upper": 1.0314539790779176
5
+ },
6
+ "recall": {
7
+ "ci_lower": 0.82707561384329,
8
+ "ci_upper": 1.0251830225298009
9
+ },
10
+ "f1": {
11
+ "ci_lower": 0.8221484195671952,
12
+ "ci_upper": 1.028321412364949
13
+ },
14
+ "auc": {
15
+ "ci_lower": 0.9035071762663421,
16
+ "ci_upper": 1.0287985055923756
17
+ },
18
+ "acc": {
19
+ "ci_lower": 0.8233443086617191,
20
+ "ci_upper": 1.028372760150367
21
+ },
22
+ "mcc": {
23
+ "ci_lower": 0.6467339955523154,
24
+ "ci_upper": 1.056722540579282
25
+ }
26
+ }
metrics_mean.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.9243638471179807,
3
+ "recall": 0.9261293181865454,
4
+ "f1": 0.9252349159660721,
5
+ "auc": 0.9661528409293589,
6
+ "acc": 0.925858534406043,
7
+ "mcc": 0.8517282680657987
8
+ }
metrics_std.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.08624727149603854,
3
+ "recall": 0.07977496688842549,
4
+ "f1": 0.08302286008775751,
5
+ "auc": 0.050452992720769994,
6
+ "acc": 0.08256196997949888,
7
+ "mcc": 0.16509641320843244
8
+ }
metrics_visualisation.png ADDED
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:659745c47ab94cb68f23a246881e0e255d61b36983c7774c087e61da11b8aac4
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 sha256:00ff5d2231e5a005da2dde0d55d873b72c1a3121613f6eb39d575fe912950e65
3
+ size 710263190
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:d0be65c54fb289f6bd4bda0fe2a3ca1fdb3e3f485f5b821881b5ca8eb1e236a5
3
+ size 130340056
test_top_repo_data.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff8f2bb1e1f529707f5f07475502a9a7d1bd010a121abb15d6399a2645f3d2d5
3
+ size 29456272
top_repo_data.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d5c800ba132bf0d72490b3dc6a04ef17d485e40f9fce8de042f221d46bfe6e2
3
+ size 16876988
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": 0.2898318955236641,
9
+ "cpu_model": "AMD EPYC 7642 48-Core Processor",
10
+ "cpu_power": 14.777823204192094,
11
+ "duration": 23877.541753292084,
12
+ "emissions": 0.13444669435818363,
13
+ "emissions_rate": 5.630675709724054e-06,
14
+ "energy_consumed": 4.88009779884514,
15
+ "gpu_count": 4,
16
+ "gpu_energy": 2.04924088522473,
17
+ "gpu_model": "4 x NVIDIA GeForce RTX 3090",
18
+ "gpu_power": 305.7879058852936,
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": 2.541025018096745,
27
+ "ram_power": 377.6938133239746,
28
+ "ram_total_size": 1007.1835021972656,
29
+ "region": "oslo county",
30
+ "run_id": "2925896d-5f26-46d1-9508-465cca7923cb",
31
+ "timestamp": "2024-03-02T01:56:30",
32
+ "tracking_mode": "machine"
33
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e42bd909af546dc47efeb558c040128f2148109be043e30fd547a767dbc8784
3
+ size 4664