Hugging Face's logo

karths
/
binary_classification_train_code

Text Classification
Transformers
Safetensors
roberta
Model card Files
xet
Community
karths commited on
Commit
6cc4b2d
·
verified ·
1 Parent(s): 17e67f1

Upload folder using huggingface_hub

Browse files
Files changed (28) hide show
  1. .gitattributes +4 -0
  2. checkpoint-12885/config.json +28 -0
  3. checkpoint-12885/model.safetensors +3 -0
  4. checkpoint-12885/optimizer.pt +3 -0
  5. checkpoint-12885/rng_state.pth +3 -0
  6. checkpoint-12885/scheduler.pt +3 -0
  7. checkpoint-12885/trainer_state.json +169 -0
  8. checkpoint-12885/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-12885/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-12885/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddf8cae4165bf8c4ce39f9a029b7910466c5a2651b3a41a86f29e7176e98ca7e
3
+ size 328492280
checkpoint-12885/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df67bf6b83ac2642dbe50cbf5fb9c059aec32985697b7ada2fde6c21337cb5ed
3
+ size 657047610
checkpoint-12885/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b776737e1e6d31f9e734e4f1e3f4d7f487d6e54fa570b12ee6db23810f2bfc6
3
+ size 14244
checkpoint-12885/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20298cb29c82eeb24d41e1c40e2c637cad3f42fad4f63868541abcc66bd3c92f
3
+ size 1064
checkpoint-12885/trainer_state.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.999030067895247,
5
+ "eval_steps": 500,
6
+ "global_step": 12885,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.19,
13
+ "learning_rate": 4.99e-05,
14
+ "loss": 0.0599,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.39,
19
+ "learning_rate": 4.97999958968678e-05,
20
+ "loss": 0.0763,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.58,
25
+ "learning_rate": 4.920159465099463e-05,
26
+ "loss": 0.0765,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.78,
31
+ "learning_rate": 4.8214408436601485e-05,
32
+ "loss": 0.0868,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.97,
37
+ "learning_rate": 4.685737469208415e-05,
38
+ "loss": 0.0843,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 1.16,
43
+ "learning_rate": 4.514686169369878e-05,
44
+ "loss": 0.0716,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 1.36,
49
+ "learning_rate": 4.311270072490833e-05,
50
+ "loss": 0.0691,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 1.55,
55
+ "learning_rate": 4.0787569434422325e-05,
56
+ "loss": 0.0677,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 1.75,
61
+ "learning_rate": 3.82142034348649e-05,
62
+ "loss": 0.0695,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 1.94,
67
+ "learning_rate": 3.5423642164834494e-05,
68
+ "loss": 0.0666,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 2.13,
73
+ "learning_rate": 3.24656309622951e-05,
74
+ "loss": 0.0555,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 2.33,
79
+ "learning_rate": 2.9387688608915686e-05,
80
+ "loss": 0.0526,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 2.52,
85
+ "learning_rate": 2.6245594204007562e-05,
86
+ "loss": 0.0478,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 2.72,
91
+ "learning_rate": 2.30772470772302e-05,
92
+ "loss": 0.0545,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 2.91,
97
+ "learning_rate": 1.9939787891736486e-05,
98
+ "loss": 0.0511,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 3.1,
103
+ "learning_rate": 1.6883618159833997e-05,
104
+ "loss": 0.0414,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 3.3,
109
+ "learning_rate": 1.3963523303957105e-05,
110
+ "loss": 0.0355,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 3.49,
115
+ "learning_rate": 1.1214724938519077e-05,
116
+ "loss": 0.0387,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 3.69,
121
+ "learning_rate": 8.692185278441231e-06,
122
+ "loss": 0.0376,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 3.88,
127
+ "learning_rate": 6.426330704931902e-06,
128
+ "loss": 0.0387,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 4.07,
133
+ "learning_rate": 4.458851653214341e-06,
134
+ "loss": 0.0339,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 4.27,
139
+ "learning_rate": 2.821354564608486e-06,
140
+ "loss": 0.0337,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 4.46,
145
+ "learning_rate": 1.542337081476908e-06,
146
+ "loss": 0.0363,
147
+ "step": 11500
148
+ },
149
+ {
150
+ "epoch": 4.66,
151
+ "learning_rate": 6.372264631526293e-07,
152
+ "loss": 0.0355,
153
+ "step": 12000
154
+ },
155
+ {
156
+ "epoch": 4.85,
157
+ "learning_rate": 1.2349006124565966e-07,
158
+ "loss": 0.0398,
159
+ "step": 12500
160
+ }
161
+ ],
162
+ "logging_steps": 500,
163
+ "max_steps": 12885,
164
+ "num_train_epochs": 5,
165
+ "save_steps": 500,
166
+ "total_flos": 1.0922943771416986e+17,
167
+ "trial_name": null,
168
+ "trial_params": null
169
+ }
checkpoint-12885/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:336b64d3e439ccf1f56b003354c997a02fc1f403faa604c0c892f3a88b71156d
3
+ size 4664
classification_report.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"0": {"precision": 0.9909803551190026, "recall": 0.9878548227651461, "f1-score": 0.9894151205827577, "support": 21243}, "1": {"precision": 0.9871385842472582, "recall": 0.9904466563297154, "f1-score": 0.9887898534441865, "support": 19993}, "accuracy": 0.9891114560093123, "macro avg": {"precision": 0.9890594696831304, "recall": 0.9891507395474308, "f1-score": 0.9891024870134721, "support": 41236}, "weighted avg": {"precision": 0.9891176980950724, "recall": 0.9891114560093123, "f1-score": 0.989111963974419, "support": 41236}}
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": 0.5052816867828369,
4
+ "eval_precision": 0.7948368241597662,
5
+ "eval_recall": 0.8162264905962385,
6
+ "eval_acc": 0.8087593365020855,
7
+ "eval_mcc": 0.6176794752614307,
8
+ "eval_f1": 0.8053896648734021,
9
+ "eval_auc": 0.8967781438031812,
10
+ "eval_runtime": 166.2932,
11
+ "eval_samples_per_second": 247.972,
12
+ "eval_steps_per_second": 3.879,
13
+ "epoch": 5.0
14
+ },
15
+ "1": {
16
+ "eval_loss": 0.3054937422275543,
17
+ "eval_precision": 0.8913420127716449,
18
+ "eval_recall": 0.9006602641056423,
19
+ "eval_acc": 0.8986080124163353,
20
+ "eval_mcc": 0.7971324306691953,
21
+ "eval_f1": 0.895976911402483,
22
+ "eval_auc": 0.9648091302045201,
23
+ "eval_runtime": 169.3736,
24
+ "eval_samples_per_second": 243.462,
25
+ "eval_steps_per_second": 3.808,
26
+ "epoch": 5.0
27
+ },
28
+ "2": {
29
+ "eval_loss": 0.11079292744398117,
30
+ "eval_precision": 0.9627800229506561,
31
+ "eval_recall": 0.9652360944377751,
32
+ "eval_acc": 0.9650548064797749,
33
+ "eval_mcc": 0.9300532340632585,
34
+ "eval_f1": 0.9640064943174721,
35
+ "eval_auc": 0.9943482547415502,
36
+ "eval_runtime": 173.7033,
37
+ "eval_samples_per_second": 237.393,
38
+ "eval_steps_per_second": 3.713,
39
+ "epoch": 5.0
40
+ },
41
+ "3": {
42
+ "eval_loss": 0.0527581162750721,
43
+ "eval_precision": 0.9798957557706627,
44
+ "eval_recall": 0.9873455709498324,
45
+ "eval_acc": 0.9840430691628674,
46
+ "eval_mcc": 0.9680902738066289,
47
+ "eval_f1": 0.9836065573770492,
48
+ "eval_auc": 0.998707724514765,
49
+ "eval_runtime": 178.1729,
50
+ "eval_samples_per_second": 231.438,
51
+ "eval_steps_per_second": 3.62,
52
+ "epoch": 5.0
53
+ },
54
+ "4": {
55
+ "eval_loss": 0.04064163565635681,
56
+ "eval_precision": 0.9871385842472582,
57
+ "eval_recall": 0.9904466563297154,
58
+ "eval_acc": 0.9891114560093123,
59
+ "eval_mcc": 0.978210204972689,
60
+ "eval_f1": 0.9887898534441865,
61
+ "eval_auc": 0.9990561329520928,
62
+ "eval_runtime": 198.2012,
63
+ "eval_samples_per_second": 208.051,
64
+ "eval_steps_per_second": 3.254,
65
+ "epoch": 5.0
66
+ }
67
+ }
metrics.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"precision": 0.9871385842472582, "recall": 0.9904466563297154, "acc": 0.9891114560093123, "mcc": 0.978210204972689, "f1": 0.9887898534441865, "auc": 0.9990561329520928}
metrics_all_fold.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": [
3
+ 0.7948368241597662,
4
+ 0.8913420127716449,
5
+ 0.9627800229506561,
6
+ 0.9798957557706627,
7
+ 0.9871385842472582
8
+ ],
9
+ "recall": [
10
+ 0.8162264905962385,
11
+ 0.9006602641056423,
12
+ 0.9652360944377751,
13
+ 0.9873455709498324,
14
+ 0.9904466563297154
15
+ ],
16
+ "f1": [
17
+ 0.8053896648734021,
18
+ 0.895976911402483,
19
+ 0.9640064943174721,
20
+ 0.9836065573770492,
21
+ 0.9887898534441865
22
+ ],
23
+ "auc": [
24
+ 0.8967781438031812,
25
+ 0.9648091302045201,
26
+ 0.9943482547415502,
27
+ 0.998707724514765,
28
+ 0.9990561329520928
29
+ ],
30
+ "acc": [
31
+ 0.8087593365020855,
32
+ 0.8986080124163353,
33
+ 0.9650548064797749,
34
+ 0.9840430691628674,
35
+ 0.9891114560093123
36
+ ],
37
+ "mcc": [
38
+ 0.6176794752614307,
39
+ 0.7971324306691953,
40
+ 0.9300532340632585,
41
+ 0.9680902738066289,
42
+ 0.978210204972689
43
+ ]
44
+ }
metrics_ci_bounds.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": {
3
+ "ci_lower": 0.8223995992144444,
4
+ "ci_upper": 1.023997680745551
5
+ },
6
+ "recall": {
7
+ "ci_lower": 0.8399626753867347,
8
+ "ci_upper": 1.024003355180947
9
+ },
10
+ "f1": {
11
+ "ci_lower": 0.8310914252699197,
12
+ "ci_upper": 1.024016367295917
13
+ },
14
+ "auc": {
15
+ "ci_lower": 0.9164503354317686,
16
+ "ci_upper": 1.0250294190546752
17
+ },
18
+ "acc": {
19
+ "ci_lower": 0.8342996357051065,
20
+ "ci_upper": 1.0239310365230436
21
+ },
22
+ "mcc": {
23
+ "ci_lower": 0.668680421474075,
24
+ "ci_upper": 1.0477858260352062
25
+ }
26
+ }
metrics_mean.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.9231986399799977,
3
+ "recall": 0.9319830152838409,
4
+ "f1": 0.9275538962829184,
5
+ "auc": 0.9707398772432219,
6
+ "acc": 0.929115336114075,
7
+ "mcc": 0.8582331237546406
8
+ }
metrics_std.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "precision": 0.08118060998093907,
3
+ "recall": 0.07411050012743055,
4
+ "f1": 0.07768806307708406,
5
+ "auc": 0.04372321488743366,
6
+ "acc": 0.07636180202223163,
7
+ "mcc": 0.15266022253587036
8
+ }
metrics_visualisation.png ADDED
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddf8cae4165bf8c4ce39f9a029b7910466c5a2651b3a41a86f29e7176e98ca7e
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 sha256:249242a2142aed25a05f8187532ab2b63c5e65e7e05846dcceddd4f4987e77bb
3
+ size 856936819
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 sha256:163ad0b1a9e526b779763b9777029650fb104c8660e8aee2bc2a7f1f75912c93
3
+ size 155760170
test_top_repo_data.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049a972f9efdbea10e21ab37ab596677a68d5fc1e21e6f4a6dba47fc4ca5a87d
3
+ size 47900099
top_repo_data.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12ce5731fa5f0e41302b90457275226e68c949125df13ece28540cb9caf948a7
3
+ size 19462080
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": 0.6414879479552255,
9
+ "cpu_model": "AMD EPYC 7282 16-Core Processor",
10
+ "cpu_power": 6.456417917773275,
11
+ "duration": 46774.495191812515,
12
+ "emissions": 0.49034117249362397,
13
+ "emissions_rate": 1.0483088496900639e-05,
14
+ "energy_consumed": 17.798227676719563,
15
+ "gpu_count": 8,
16
+ "gpu_energy": 15.934865315382055,
17
+ "gpu_model": "8 x NVIDIA GeForce RTX 2080 Ti",
18
+ "gpu_power": 1313.0591675764938,
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": 1.221874413382281,
27
+ "ram_power": 94.20606708526611,
28
+ "ram_total_size": 251.21617889404297,
29
+ "region": "oslo county",
30
+ "run_id": "6bfbcf00-2384-4f98-a040-2eceaed1cceb",
31
+ "timestamp": "2024-03-16T07:50:06",
32
+ "tracking_mode": "machine"
33
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:336b64d3e439ccf1f56b003354c997a02fc1f403faa604c0c892f3a88b71156d
3
+ size 4664