Hugging Face's logo

Lazyhope
/
python-clone-detection

Feature Extraction
Transformers
PyTorch
roberta
custom_code
text-embeddings-inference
Model card Files
xet
Community
1
Lazyhope commited on
Commit
8e667e7
·
1 Parent(s): 45d76c8

Init commit, upload model to the hub

Browse files
Files changed (13) hide show
  1. config.json +32 -0
  2. merges.txt +0 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scaler.pt +3 -0
  7. scheduler.pt +3 -0
  8. special_tokens_map.json +51 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +65 -0
  11. trainer_state.json +247 -0
  12. training_args.bin +3 -0
  13. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/graphcodebert-base",
3
+ "architectures": [
4
+ "RobertaRBERT"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dropout_rate": 0.1,
10
+ "eos_token_id": 2,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "layer_norm_eps": 1e-05,
18
+ "max_position_embeddings": 514,
19
+ "model_type": "roberta",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "output_past": true,
23
+ "pad_token_id": 1,
24
+ "position_embedding_type": "absolute",
25
+ "tokenizer_cls_token_id": 0,
26
+ "tokenizer_sep_token_id": 2,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.24.0",
29
+ "type_vocab_size": 1,
30
+ "use_cache": true,
31
+ "vocab_size": 50265
32
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1cdaa6c7d17e585d431feca386edd3809e0d6c6164910c9f4c34334f479ebc8
3
+ size 997332101
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee6809a890981926df5d49e47747fc9912290459d9d678e7f89a49ceb133200d
3
+ size 498680501
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f31d9cd8b9343686ce0ba7b5b8826fe4a034f78096c334829d5e6067b62029
3
+ size 14575
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2878f1a10791fec98059fdd9bb225a422c5a74c51a5aff2629a047b0538b27cf
3
+ size 557
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65f5abd7ad625893f59c14b4a3405aff0c32b287798adf7ea962303aaf2dd62c
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": true,
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 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 512,
37
+ "name_or_path": "microsoft/graphcodebert-base",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": "/root/autodl-tmp/.cache/models--microsoft--graphcodebert-base/snapshots/2b0488a7bb0eefc7041f1bb2cad1ab26b0da269d/special_tokens_map.json",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
trainer_state.json ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9843817398562538,
3
+ "best_model_checkpoint": "./exps/1_fold_RobertaRBERT/checkpoint-22000",
4
+ "epoch": 1.1827271994194017,
5
+ "global_step": 22000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 1.0693175711982806e-05,
13
+ "loss": 0.3694,
14
+ "step": 1000
15
+ },
16
+ {
17
+ "epoch": 0.11,
18
+ "learning_rate": 1.9924167397640137e-05,
19
+ "loss": 0.1227,
20
+ "step": 2000
21
+ },
22
+ {
23
+ "epoch": 0.11,
24
+ "eval_accuracy": 0.9525065963060686,
25
+ "eval_loss": 0.12871456146240234,
26
+ "eval_runtime": 1262.9688,
27
+ "eval_samples_per_second": 141.341,
28
+ "eval_steps_per_second": 4.417,
29
+ "step": 2000
30
+ },
31
+ {
32
+ "epoch": 0.16,
33
+ "learning_rate": 1.9358252454656067e-05,
34
+ "loss": 0.077,
35
+ "step": 3000
36
+ },
37
+ {
38
+ "epoch": 0.22,
39
+ "learning_rate": 1.8792337511671998e-05,
40
+ "loss": 0.0597,
41
+ "step": 4000
42
+ },
43
+ {
44
+ "epoch": 0.22,
45
+ "eval_accuracy": 0.977625777971979,
46
+ "eval_loss": 0.07220922410488129,
47
+ "eval_runtime": 1261.8214,
48
+ "eval_samples_per_second": 141.469,
49
+ "eval_steps_per_second": 4.421,
50
+ "step": 4000
51
+ },
52
+ {
53
+ "epoch": 0.27,
54
+ "learning_rate": 1.8226422568687928e-05,
55
+ "loss": 0.0492,
56
+ "step": 5000
57
+ },
58
+ {
59
+ "epoch": 0.32,
60
+ "learning_rate": 1.766050762570386e-05,
61
+ "loss": 0.0429,
62
+ "step": 6000
63
+ },
64
+ {
65
+ "epoch": 0.32,
66
+ "eval_accuracy": 0.9803035141085323,
67
+ "eval_loss": 0.07511359453201294,
68
+ "eval_runtime": 1262.1321,
69
+ "eval_samples_per_second": 141.434,
70
+ "eval_steps_per_second": 4.42,
71
+ "step": 6000
72
+ },
73
+ {
74
+ "epoch": 0.38,
75
+ "learning_rate": 1.709459268271979e-05,
76
+ "loss": 0.0385,
77
+ "step": 7000
78
+ },
79
+ {
80
+ "epoch": 0.43,
81
+ "learning_rate": 1.652867773973572e-05,
82
+ "loss": 0.0356,
83
+ "step": 8000
84
+ },
85
+ {
86
+ "epoch": 0.43,
87
+ "eval_accuracy": 0.9810037589141164,
88
+ "eval_loss": 0.07426761090755463,
89
+ "eval_runtime": 1264.8606,
90
+ "eval_samples_per_second": 141.129,
91
+ "eval_steps_per_second": 4.411,
92
+ "step": 8000
93
+ },
94
+ {
95
+ "epoch": 0.48,
96
+ "learning_rate": 1.5963328711694633e-05,
97
+ "loss": 0.0326,
98
+ "step": 9000
99
+ },
100
+ {
101
+ "epoch": 0.54,
102
+ "learning_rate": 1.5397413768710567e-05,
103
+ "loss": 0.0288,
104
+ "step": 10000
105
+ },
106
+ {
107
+ "epoch": 0.54,
108
+ "eval_accuracy": 0.9811886235427906,
109
+ "eval_loss": 0.0728357657790184,
110
+ "eval_runtime": 1260.8301,
111
+ "eval_samples_per_second": 141.581,
112
+ "eval_steps_per_second": 4.425,
113
+ "step": 10000
114
+ },
115
+ {
116
+ "epoch": 0.59,
117
+ "learning_rate": 1.4831498825726494e-05,
118
+ "loss": 0.0281,
119
+ "step": 11000
120
+ },
121
+ {
122
+ "epoch": 0.65,
123
+ "learning_rate": 1.4265583882742424e-05,
124
+ "loss": 0.0266,
125
+ "step": 12000
126
+ },
127
+ {
128
+ "epoch": 0.65,
129
+ "eval_accuracy": 0.9783652364866757,
130
+ "eval_loss": 0.08940344303846359,
131
+ "eval_runtime": 1265.0154,
132
+ "eval_samples_per_second": 141.112,
133
+ "eval_steps_per_second": 4.41,
134
+ "step": 12000
135
+ },
136
+ {
137
+ "epoch": 0.7,
138
+ "learning_rate": 1.370023485470134e-05,
139
+ "loss": 0.0244,
140
+ "step": 13000
141
+ },
142
+ {
143
+ "epoch": 0.75,
144
+ "learning_rate": 1.313431991171727e-05,
145
+ "loss": 0.0225,
146
+ "step": 14000
147
+ },
148
+ {
149
+ "epoch": 0.75,
150
+ "eval_accuracy": 0.9823538308992824,
151
+ "eval_loss": 0.06773301213979721,
152
+ "eval_runtime": 1260.1554,
153
+ "eval_samples_per_second": 141.656,
154
+ "eval_steps_per_second": 4.427,
155
+ "step": 14000
156
+ },
157
+ {
158
+ "epoch": 0.81,
159
+ "learning_rate": 1.2568970883676185e-05,
160
+ "loss": 0.0206,
161
+ "step": 15000
162
+ },
163
+ {
164
+ "epoch": 0.86,
165
+ "learning_rate": 1.2003055940692115e-05,
166
+ "loss": 0.0208,
167
+ "step": 16000
168
+ },
169
+ {
170
+ "epoch": 0.86,
171
+ "eval_accuracy": 0.9828524052008583,
172
+ "eval_loss": 0.08000749349594116,
173
+ "eval_runtime": 1262.4987,
174
+ "eval_samples_per_second": 141.393,
175
+ "eval_steps_per_second": 4.419,
176
+ "step": 16000
177
+ },
178
+ {
179
+ "epoch": 0.91,
180
+ "learning_rate": 1.1437140997708046e-05,
181
+ "loss": 0.0199,
182
+ "step": 17000
183
+ },
184
+ {
185
+ "epoch": 0.97,
186
+ "learning_rate": 1.087179196966696e-05,
187
+ "loss": 0.0182,
188
+ "step": 18000
189
+ },
190
+ {
191
+ "epoch": 0.97,
192
+ "eval_accuracy": 0.9813734881714647,
193
+ "eval_loss": 0.08186674118041992,
194
+ "eval_runtime": 1260.8606,
195
+ "eval_samples_per_second": 141.577,
196
+ "eval_steps_per_second": 4.425,
197
+ "step": 18000
198
+ },
199
+ {
200
+ "epoch": 1.02,
201
+ "learning_rate": 1.030587702668289e-05,
202
+ "loss": 0.0159,
203
+ "step": 19000
204
+ },
205
+ {
206
+ "epoch": 1.08,
207
+ "learning_rate": 9.739962083698821e-06,
208
+ "loss": 0.0137,
209
+ "step": 20000
210
+ },
211
+ {
212
+ "epoch": 1.08,
213
+ "eval_accuracy": 0.9839727968897927,
214
+ "eval_loss": 0.062463145703077316,
215
+ "eval_runtime": 1261.7007,
216
+ "eval_samples_per_second": 141.483,
217
+ "eval_steps_per_second": 4.422,
218
+ "step": 20000
219
+ },
220
+ {
221
+ "epoch": 1.13,
222
+ "learning_rate": 9.174047140714752e-06,
223
+ "loss": 0.0123,
224
+ "step": 21000
225
+ },
226
+ {
227
+ "epoch": 1.18,
228
+ "learning_rate": 8.60926402761665e-06,
229
+ "loss": 0.0138,
230
+ "step": 22000
231
+ },
232
+ {
233
+ "epoch": 1.18,
234
+ "eval_accuracy": 0.9843817398562538,
235
+ "eval_loss": 0.07732487469911575,
236
+ "eval_runtime": 1262.988,
237
+ "eval_samples_per_second": 141.339,
238
+ "eval_steps_per_second": 4.417,
239
+ "step": 22000
240
+ }
241
+ ],
242
+ "max_steps": 37202,
243
+ "num_train_epochs": 2,
244
+ "total_flos": 2.7232075889551824e+17,
245
+ "trial_name": null,
246
+ "trial_params": null
247
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eba9bd3d5b296eb72fa1c40a806659725b53e91d1cdd61324cf4601eb2f38df0
3
+ size 3451
vocab.json ADDED
The diff for this file is too large to render. See raw diff