Hugging Face's logo

Fsoft-AIC
/
dopamin-java-expand

Text Classification
Transformers
Safetensors
roberta
Model card Files
xet
Community
NamCyan commited on
Commit
7bcd184
·
1 Parent(s): 8f4c117

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. config.json +43 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +51 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +64 -0
  10. trainer_state.json +262 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/codebert-base",
3
+ "architectures": [
4
+ "CodeBERTHSUMForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "count": 4,
10
+ "eos_token_id": 2,
11
+ "finetuning_task": "text-classification",
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "0",
17
+ "1": "1"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "0": 0,
23
+ "1": 1
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "max_query_length": 128,
28
+ "max_seq_length": -68,
29
+ "mix_type": "HSUM",
30
+ "model_type": "roberta",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "output_past": true,
34
+ "pad_token_id": 1,
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "sc_comment": false,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.35.2",
40
+ "type_vocab_size": 1,
41
+ "use_cache": true,
42
+ "vocab_size": 50265
43
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5907dda1d22b56a15df1e7aed1e9bb4148aaaae203a4abc3fb7455a14c16620
3
+ size 612026240
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a41c0b36a4b696b220e61fc3230216d72b61fb91d527a0774ed09f090f00be1
3
+ size 1224210309
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f94d34191f7ce0c7043252be48cd8024faf022dea480be54f73ecb68829e474
3
+ size 14511
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f062dac82b1cab37ee9f8c1560f56b5e6c70e9975963ce7f156ced1bdc58f3
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_length": 64,
52
+ "model_max_length": 512,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "<pad>",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "</s>",
58
+ "stride": 0,
59
+ "tokenizer_class": "RobertaTokenizer",
60
+ "trim_offsets": true,
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "<unk>"
64
+ }
trainer_state.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5863192182410424,
3
+ "best_model_checkpoint": "/cm/archive/namlh35/code-comment-classification/results/selection_wo_valid/Verification/codebert-postpretrained-HSUM-4layers-datav2-class-comment/java_expand/checkpoint-500",
4
+ "epoch": 7.954545454545455,
5
+ "eval_steps": 50,
6
+ "global_step": 1050,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.38,
13
+ "eval_f1": 0.14423076923076925,
14
+ "eval_loss": 0.19940590858459473,
15
+ "eval_precision": 0.35714285714285715,
16
+ "eval_recall": 0.09036144578313253,
17
+ "eval_runtime": 15.6593,
18
+ "eval_samples_per_second": 135.0,
19
+ "eval_steps_per_second": 8.493,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.76,
24
+ "eval_f1": 0.4090909090909091,
25
+ "eval_loss": 0.21339909732341766,
26
+ "eval_precision": 0.3870967741935484,
27
+ "eval_recall": 0.43373493975903615,
28
+ "eval_runtime": 7.5755,
29
+ "eval_samples_per_second": 279.059,
30
+ "eval_steps_per_second": 17.557,
31
+ "step": 100
32
+ },
33
+ {
34
+ "epoch": 1.14,
35
+ "eval_f1": 0.5236907730673317,
36
+ "eval_loss": 0.2083684802055359,
37
+ "eval_precision": 0.44680851063829785,
38
+ "eval_recall": 0.6325301204819277,
39
+ "eval_runtime": 7.801,
40
+ "eval_samples_per_second": 270.99,
41
+ "eval_steps_per_second": 17.049,
42
+ "step": 150
43
+ },
44
+ {
45
+ "epoch": 1.52,
46
+ "eval_f1": 0.510385756676558,
47
+ "eval_loss": 0.2234768122434616,
48
+ "eval_precision": 0.5029239766081871,
49
+ "eval_recall": 0.5180722891566265,
50
+ "eval_runtime": 7.6406,
51
+ "eval_samples_per_second": 276.682,
52
+ "eval_steps_per_second": 17.407,
53
+ "step": 200
54
+ },
55
+ {
56
+ "epoch": 1.89,
57
+ "eval_f1": 0.5125628140703518,
58
+ "eval_loss": 0.20452718436717987,
59
+ "eval_precision": 0.4396551724137931,
60
+ "eval_recall": 0.6144578313253012,
61
+ "eval_runtime": 7.5874,
62
+ "eval_samples_per_second": 278.618,
63
+ "eval_steps_per_second": 17.529,
64
+ "step": 250
65
+ },
66
+ {
67
+ "epoch": 2.27,
68
+ "eval_f1": 0.5590062111801242,
69
+ "eval_loss": 0.22217300534248352,
70
+ "eval_precision": 0.5769230769230769,
71
+ "eval_recall": 0.5421686746987951,
72
+ "eval_runtime": 7.4841,
73
+ "eval_samples_per_second": 282.467,
74
+ "eval_steps_per_second": 17.771,
75
+ "step": 300
76
+ },
77
+ {
78
+ "epoch": 2.65,
79
+ "eval_f1": 0.5478547854785478,
80
+ "eval_loss": 0.23551225662231445,
81
+ "eval_precision": 0.6058394160583942,
82
+ "eval_recall": 0.5,
83
+ "eval_runtime": 7.5637,
84
+ "eval_samples_per_second": 279.493,
85
+ "eval_steps_per_second": 17.584,
86
+ "step": 350
87
+ },
88
+ {
89
+ "epoch": 3.03,
90
+ "eval_f1": 0.5739130434782609,
91
+ "eval_loss": 0.22371679544448853,
92
+ "eval_precision": 0.553072625698324,
93
+ "eval_recall": 0.5963855421686747,
94
+ "eval_runtime": 7.9409,
95
+ "eval_samples_per_second": 266.215,
96
+ "eval_steps_per_second": 16.749,
97
+ "step": 400
98
+ },
99
+ {
100
+ "epoch": 3.41,
101
+ "eval_f1": 0.5586206896551725,
102
+ "eval_loss": 0.24752120673656464,
103
+ "eval_precision": 0.6532258064516129,
104
+ "eval_recall": 0.4879518072289157,
105
+ "eval_runtime": 7.5417,
106
+ "eval_samples_per_second": 280.309,
107
+ "eval_steps_per_second": 17.635,
108
+ "step": 450
109
+ },
110
+ {
111
+ "epoch": 3.79,
112
+ "learning_rate": 6.212121212121213e-06,
113
+ "loss": 0.102,
114
+ "step": 500
115
+ },
116
+ {
117
+ "epoch": 3.79,
118
+ "eval_f1": 0.5863192182410424,
119
+ "eval_loss": 0.25533562898635864,
120
+ "eval_precision": 0.6382978723404256,
121
+ "eval_recall": 0.5421686746987951,
122
+ "eval_runtime": 7.9722,
123
+ "eval_samples_per_second": 265.172,
124
+ "eval_steps_per_second": 16.683,
125
+ "step": 500
126
+ },
127
+ {
128
+ "epoch": 4.17,
129
+ "eval_f1": 0.5714285714285715,
130
+ "eval_loss": 0.26097801327705383,
131
+ "eval_precision": 0.6370370370370371,
132
+ "eval_recall": 0.5180722891566265,
133
+ "eval_runtime": 8.3006,
134
+ "eval_samples_per_second": 254.679,
135
+ "eval_steps_per_second": 16.023,
136
+ "step": 550
137
+ },
138
+ {
139
+ "epoch": 4.55,
140
+ "eval_f1": 0.5602409638554217,
141
+ "eval_loss": 0.2843839228153229,
142
+ "eval_precision": 0.5602409638554217,
143
+ "eval_recall": 0.5602409638554217,
144
+ "eval_runtime": 7.9699,
145
+ "eval_samples_per_second": 265.247,
146
+ "eval_steps_per_second": 16.688,
147
+ "step": 600
148
+ },
149
+ {
150
+ "epoch": 4.92,
151
+ "eval_f1": 0.5687500000000001,
152
+ "eval_loss": 0.29494354128837585,
153
+ "eval_precision": 0.5909090909090909,
154
+ "eval_recall": 0.5481927710843374,
155
+ "eval_runtime": 8.3531,
156
+ "eval_samples_per_second": 253.08,
157
+ "eval_steps_per_second": 15.922,
158
+ "step": 650
159
+ },
160
+ {
161
+ "epoch": 5.3,
162
+ "eval_f1": 0.5578231292517006,
163
+ "eval_loss": 0.3040340840816498,
164
+ "eval_precision": 0.640625,
165
+ "eval_recall": 0.4939759036144578,
166
+ "eval_runtime": 7.1333,
167
+ "eval_samples_per_second": 296.358,
168
+ "eval_steps_per_second": 18.645,
169
+ "step": 700
170
+ },
171
+ {
172
+ "epoch": 5.68,
173
+ "eval_f1": 0.559748427672956,
174
+ "eval_loss": 0.3211788833141327,
175
+ "eval_precision": 0.5855263157894737,
176
+ "eval_recall": 0.536144578313253,
177
+ "eval_runtime": 7.2776,
178
+ "eval_samples_per_second": 290.482,
179
+ "eval_steps_per_second": 18.275,
180
+ "step": 750
181
+ },
182
+ {
183
+ "epoch": 6.06,
184
+ "eval_f1": 0.5714285714285714,
185
+ "eval_loss": 0.3221454620361328,
186
+ "eval_precision": 0.6040268456375839,
187
+ "eval_recall": 0.5421686746987951,
188
+ "eval_runtime": 9.612,
189
+ "eval_samples_per_second": 219.932,
190
+ "eval_steps_per_second": 13.837,
191
+ "step": 800
192
+ },
193
+ {
194
+ "epoch": 6.44,
195
+ "eval_f1": 0.5741324921135648,
196
+ "eval_loss": 0.32895684242248535,
197
+ "eval_precision": 0.6026490066225165,
198
+ "eval_recall": 0.5481927710843374,
199
+ "eval_runtime": 9.3112,
200
+ "eval_samples_per_second": 227.038,
201
+ "eval_steps_per_second": 14.284,
202
+ "step": 850
203
+ },
204
+ {
205
+ "epoch": 6.82,
206
+ "eval_f1": 0.5704697986577182,
207
+ "eval_loss": 0.3368590474128723,
208
+ "eval_precision": 0.6439393939393939,
209
+ "eval_recall": 0.5120481927710844,
210
+ "eval_runtime": 10.5803,
211
+ "eval_samples_per_second": 199.805,
212
+ "eval_steps_per_second": 12.571,
213
+ "step": 900
214
+ },
215
+ {
216
+ "epoch": 7.2,
217
+ "eval_f1": 0.5759493670886077,
218
+ "eval_loss": 0.3474346697330475,
219
+ "eval_precision": 0.6066666666666667,
220
+ "eval_recall": 0.5481927710843374,
221
+ "eval_runtime": 9.0583,
222
+ "eval_samples_per_second": 233.377,
223
+ "eval_steps_per_second": 14.683,
224
+ "step": 950
225
+ },
226
+ {
227
+ "epoch": 7.58,
228
+ "learning_rate": 2.4242424242424244e-06,
229
+ "loss": 0.0299,
230
+ "step": 1000
231
+ },
232
+ {
233
+ "epoch": 7.58,
234
+ "eval_f1": 0.5666666666666668,
235
+ "eval_loss": 0.3469344675540924,
236
+ "eval_precision": 0.6343283582089553,
237
+ "eval_recall": 0.5120481927710844,
238
+ "eval_runtime": 8.3925,
239
+ "eval_samples_per_second": 251.892,
240
+ "eval_steps_per_second": 15.847,
241
+ "step": 1000
242
+ },
243
+ {
244
+ "epoch": 7.95,
245
+ "eval_f1": 0.5749235474006117,
246
+ "eval_loss": 0.3440389037132263,
247
+ "eval_precision": 0.5838509316770186,
248
+ "eval_recall": 0.5662650602409639,
249
+ "eval_runtime": 8.5858,
250
+ "eval_samples_per_second": 246.22,
251
+ "eval_steps_per_second": 15.491,
252
+ "step": 1050
253
+ }
254
+ ],
255
+ "logging_steps": 500,
256
+ "max_steps": 1320,
257
+ "num_train_epochs": 10,
258
+ "save_steps": 50,
259
+ "total_flos": 2939592325754112.0,
260
+ "trial_name": null,
261
+ "trial_params": null
262
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa389d4d719facd6db12fab8587445850c7ecaa3c2b7c1fde46d5e6e7ed59e0
3
+ size 4539
vocab.json ADDED
The diff for this file is too large to render. See raw diff