Hugging Face's logo

dzungpham
/
graphcodebert-code-classification

Transformers
Safetensors
detection
AI-generated
bert
Model card Files
xet
 Community
dzungpham commited on
Commit
9f5da22
·
verified ·
1 Parent(s): 9c7b3d3

Upload training checkpoints and best model

Browse files
Files changed (12) hide show
  1. checkpoint-500/config.json +29 -0
  2. checkpoint-500/merges.txt +0 -0
  3. checkpoint-500/model.safetensors +3 -0
  4. checkpoint-500/optimizer.pt +3 -0
  5. checkpoint-500/rng_state.pth +3 -0
  6. checkpoint-500/scheduler.pt +3 -0
  7. checkpoint-500/special_tokens_map.json +51 -0
  8. checkpoint-500/tokenizer.json +0 -0
  9. checkpoint-500/tokenizer_config.json +58 -0
  10. checkpoint-500/trainer_state.json +406 -0
  11. checkpoint-500/training_args.bin +3 -0
  12. checkpoint-500/vocab.json +0 -0
checkpoint-500/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 1026,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "absolute",
24
+ "problem_type": "single_label_classification",
25
+ "transformers_version": "4.56.0",
26
+ "type_vocab_size": 10,
27
+ "use_cache": true,
28
+ "vocab_size": 51416
29
+ }
checkpoint-500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4ef92bc96bd8e16e5672edc0626f0d2844af2b2f0171a6e52ec38d93964fa9f
3
+ size 503749208
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d4ef5b08e045fc8d0e273d93a6504ca621663aabe70342e6b7477337a51dea
3
+ size 1007621899
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1319a6a84eb040363f0531831368126a08d22a17798adaa3582049afe5059f05
3
+ size 14645
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36fc1bf4cec216a4c63e97e36749c2b39b07e1b61c9e31043ed26f2355ccb8a3
3
+ size 1977
checkpoint-500/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
+ }
checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 500,
3
+ "best_metric": 0.8730387325792941,
4
+ "best_model_checkpoint": "taskA-unixcoder-focal/checkpoint-500",
5
+ "epoch": 0.030588523186100575,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0006117704637220115,
14
+ "grad_norm": 5.2196149826049805,
15
+ "learning_rate": 9.178990311065784e-08,
16
+ "loss": 0.2114,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.001223540927444023,
21
+ "grad_norm": 2.4952661991119385,
22
+ "learning_rate": 1.937786843447221e-07,
23
+ "loss": 0.179,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0018353113911660345,
28
+ "grad_norm": 3.8488683700561523,
29
+ "learning_rate": 2.9576746557878637e-07,
30
+ "loss": 0.1949,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.002447081854888046,
35
+ "grad_norm": 3.7437973022460938,
36
+ "learning_rate": 3.9775624681285064e-07,
37
+ "loss": 0.2007,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.0030588523186100575,
42
+ "grad_norm": 3.8342156410217285,
43
+ "learning_rate": 4.997450280469149e-07,
44
+ "loss": 0.1828,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.003670622782332069,
49
+ "grad_norm": 3.510793685913086,
50
+ "learning_rate": 6.017338092809792e-07,
51
+ "loss": 0.1875,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0042823932460540805,
56
+ "grad_norm": 3.223860740661621,
57
+ "learning_rate": 7.037225905150434e-07,
58
+ "loss": 0.1661,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.004894163709776092,
63
+ "grad_norm": 3.791808605194092,
64
+ "learning_rate": 8.057113717491076e-07,
65
+ "loss": 0.1762,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.0055059341734981036,
70
+ "grad_norm": 3.8649113178253174,
71
+ "learning_rate": 9.077001529831719e-07,
72
+ "loss": 0.1774,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.006117704637220115,
77
+ "grad_norm": 2.9645302295684814,
78
+ "learning_rate": 1.0096889342172361e-06,
79
+ "loss": 0.1741,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.006729475100942127,
84
+ "grad_norm": 2.9103174209594727,
85
+ "learning_rate": 1.1116777154513005e-06,
86
+ "loss": 0.1808,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.007341245564664138,
91
+ "grad_norm": 2.3954272270202637,
92
+ "learning_rate": 1.2136664966853646e-06,
93
+ "loss": 0.161,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.00795301602838615,
98
+ "grad_norm": 3.030513048171997,
99
+ "learning_rate": 1.3156552779194289e-06,
100
+ "loss": 0.1689,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.008564786492108161,
105
+ "grad_norm": 1.7593587636947632,
106
+ "learning_rate": 1.4176440591534932e-06,
107
+ "loss": 0.1595,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.009176556955830173,
112
+ "grad_norm": 1.9787609577178955,
113
+ "learning_rate": 1.5196328403875573e-06,
114
+ "loss": 0.1429,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.009788327419552184,
119
+ "grad_norm": 2.549748659133911,
120
+ "learning_rate": 1.6216216216216219e-06,
121
+ "loss": 0.154,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.010400097883274196,
126
+ "grad_norm": 2.4056687355041504,
127
+ "learning_rate": 1.723610402855686e-06,
128
+ "loss": 0.1582,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.011011868346996207,
133
+ "grad_norm": 3.3082435131073,
134
+ "learning_rate": 1.8255991840897503e-06,
135
+ "loss": 0.1502,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.011623638810718219,
140
+ "grad_norm": 3.446185350418091,
141
+ "learning_rate": 1.9275879653238146e-06,
142
+ "loss": 0.1452,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.01223540927444023,
147
+ "grad_norm": 2.6021993160247803,
148
+ "learning_rate": 2.029576746557879e-06,
149
+ "loss": 0.1404,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.012847179738162242,
154
+ "grad_norm": 2.1967263221740723,
155
+ "learning_rate": 2.1315655277919432e-06,
156
+ "loss": 0.1421,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.013458950201884253,
161
+ "grad_norm": 1.9831513166427612,
162
+ "learning_rate": 2.233554309026007e-06,
163
+ "loss": 0.1431,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.014070720665606265,
168
+ "grad_norm": 1.7445921897888184,
169
+ "learning_rate": 2.3355430902600715e-06,
170
+ "loss": 0.1242,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.014682491129328276,
175
+ "grad_norm": 2.7725071907043457,
176
+ "learning_rate": 2.4375318714941358e-06,
177
+ "loss": 0.1346,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.015294261593050288,
182
+ "grad_norm": 1.7258802652359009,
183
+ "learning_rate": 2.5395206527282e-06,
184
+ "loss": 0.1371,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.0159060320567723,
189
+ "grad_norm": 2.1158506870269775,
190
+ "learning_rate": 2.6415094339622644e-06,
191
+ "loss": 0.1271,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.01651780252049431,
196
+ "grad_norm": 2.0771985054016113,
197
+ "learning_rate": 2.7434982151963283e-06,
198
+ "loss": 0.1214,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.017129572984216322,
203
+ "grad_norm": 2.924894332885742,
204
+ "learning_rate": 2.8454869964303926e-06,
205
+ "loss": 0.1281,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.017741343447938332,
210
+ "grad_norm": 2.122687578201294,
211
+ "learning_rate": 2.947475777664457e-06,
212
+ "loss": 0.132,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.018353113911660345,
217
+ "grad_norm": 3.2565481662750244,
218
+ "learning_rate": 3.0494645588985217e-06,
219
+ "loss": 0.1336,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.018964884375382355,
224
+ "grad_norm": 1.2805263996124268,
225
+ "learning_rate": 3.151453340132586e-06,
226
+ "loss": 0.1183,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.019576654839104368,
231
+ "grad_norm": 2.420628786087036,
232
+ "learning_rate": 3.25344212136665e-06,
233
+ "loss": 0.1125,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.020188425302826378,
238
+ "grad_norm": 2.887117862701416,
239
+ "learning_rate": 3.3554309026007142e-06,
240
+ "loss": 0.1041,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.02080019576654839,
245
+ "grad_norm": 1.6021567583084106,
246
+ "learning_rate": 3.4574196838347786e-06,
247
+ "loss": 0.1221,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.0214119662302704,
252
+ "grad_norm": 2.9132304191589355,
253
+ "learning_rate": 3.5594084650688425e-06,
254
+ "loss": 0.1094,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.022023736693992414,
259
+ "grad_norm": 2.5460691452026367,
260
+ "learning_rate": 3.6613972463029068e-06,
261
+ "loss": 0.1096,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.022635507157714424,
266
+ "grad_norm": 2.2170896530151367,
267
+ "learning_rate": 3.763386027536971e-06,
268
+ "loss": 0.0933,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.023247277621436437,
273
+ "grad_norm": 3.799591541290283,
274
+ "learning_rate": 3.865374808771036e-06,
275
+ "loss": 0.1142,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.023859048085158447,
280
+ "grad_norm": 4.609161376953125,
281
+ "learning_rate": 3.9673635900051e-06,
282
+ "loss": 0.0948,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.02447081854888046,
287
+ "grad_norm": 3.329650402069092,
288
+ "learning_rate": 4.0693523712391645e-06,
289
+ "loss": 0.0944,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.02508258901260247,
294
+ "grad_norm": 2.135805368423462,
295
+ "learning_rate": 4.171341152473228e-06,
296
+ "loss": 0.0847,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.025694359476324483,
301
+ "grad_norm": 2.006049156188965,
302
+ "learning_rate": 4.273329933707292e-06,
303
+ "loss": 0.1077,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.026306129940046493,
308
+ "grad_norm": 5.709030628204346,
309
+ "learning_rate": 4.375318714941357e-06,
310
+ "loss": 0.099,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.026917900403768506,
315
+ "grad_norm": 2.466867446899414,
316
+ "learning_rate": 4.477307496175421e-06,
317
+ "loss": 0.0771,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.027529670867490516,
322
+ "grad_norm": 2.3829548358917236,
323
+ "learning_rate": 4.579296277409485e-06,
324
+ "loss": 0.0802,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.02814144133121253,
329
+ "grad_norm": 2.990241050720215,
330
+ "learning_rate": 4.6812850586435496e-06,
331
+ "loss": 0.1048,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.02875321179493454,
336
+ "grad_norm": 3.7126529216766357,
337
+ "learning_rate": 4.783273839877614e-06,
338
+ "loss": 0.0879,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.029364982258656552,
343
+ "grad_norm": 2.6238865852355957,
344
+ "learning_rate": 4.885262621111678e-06,
345
+ "loss": 0.0825,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.029976752722378562,
350
+ "grad_norm": 2.1882681846618652,
351
+ "learning_rate": 4.987251402345742e-06,
352
+ "loss": 0.0821,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.030588523186100575,
357
+ "grad_norm": 2.1399929523468018,
358
+ "learning_rate": 5.089240183579807e-06,
359
+ "loss": 0.0926,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.030588523186100575,
364
+ "eval_accuracy": 0.8732,
365
+ "eval_f1_weighted": 0.8728301347090768,
366
+ "eval_loss": 0.08081420511007309,
367
+ "eval_macro_f1": 0.8730387325792941,
368
+ "eval_precision": 0.8842823474890878,
369
+ "eval_recall": 0.8732,
370
+ "eval_runtime": 1731.362,
371
+ "eval_samples_per_second": 57.758,
372
+ "eval_steps_per_second": 0.903,
373
+ "step": 500
374
+ }
375
+ ],
376
+ "logging_steps": 10,
377
+ "max_steps": 16346,
378
+ "num_input_tokens_seen": 0,
379
+ "num_train_epochs": 1,
380
+ "save_steps": 500,
381
+ "stateful_callbacks": {
382
+ "EarlyStoppingCallback": {
383
+ "args": {
384
+ "early_stopping_patience": 3,
385
+ "early_stopping_threshold": 0.0
386
+ },
387
+ "attributes": {
388
+ "early_stopping_patience_counter": 0
389
+ }
390
+ },
391
+ "TrainerControl": {
392
+ "args": {
393
+ "should_epoch_stop": false,
394
+ "should_evaluate": false,
395
+ "should_log": false,
396
+ "should_save": true,
397
+ "should_training_stop": false
398
+ },
399
+ "attributes": {}
400
+ }
401
+ },
402
+ "total_flos": 4207556886230400.0,
403
+ "train_batch_size": 32,
404
+ "trial_name": null,
405
+ "trial_params": null
406
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e47ae34a1d4d2519557fa72058151dfc9e94761396fa45ac68af2b6afed4e551
3
+ size 5777
checkpoint-500/vocab.json ADDED
The diff for this file is too large to render. See raw diff