taeuk1 commited on
Commit
da74a91
·
verified ·
1 Parent(s): eaa2d6a

Upload folder using huggingface_hub

Browse files
Files changed (45) hide show
  1. checkpoint-2875/config.json +36 -0
  2. checkpoint-2875/merges.txt +0 -0
  3. checkpoint-2875/model.safetensors +3 -0
  4. checkpoint-2875/optimizer.pt +3 -0
  5. checkpoint-2875/rng_state.pth +3 -0
  6. checkpoint-2875/scheduler.pt +3 -0
  7. checkpoint-2875/special_tokens_map.json +51 -0
  8. checkpoint-2875/tokenizer.json +0 -0
  9. checkpoint-2875/tokenizer_config.json +57 -0
  10. checkpoint-2875/trainer_state.json +428 -0
  11. checkpoint-2875/training_args.bin +3 -0
  12. checkpoint-2875/vocab.json +0 -0
  13. checkpoint-5750/config.json +36 -0
  14. checkpoint-5750/merges.txt +0 -0
  15. checkpoint-5750/model.safetensors +3 -0
  16. checkpoint-5750/optimizer.pt +3 -0
  17. checkpoint-5750/rng_state.pth +3 -0
  18. checkpoint-5750/scheduler.pt +3 -0
  19. checkpoint-5750/special_tokens_map.json +51 -0
  20. checkpoint-5750/tokenizer.json +0 -0
  21. checkpoint-5750/tokenizer_config.json +57 -0
  22. checkpoint-5750/trainer_state.json +842 -0
  23. checkpoint-5750/training_args.bin +3 -0
  24. checkpoint-5750/vocab.json +0 -0
  25. checkpoint-8625/config.json +36 -0
  26. checkpoint-8625/merges.txt +0 -0
  27. checkpoint-8625/model.safetensors +3 -0
  28. checkpoint-8625/optimizer.pt +3 -0
  29. checkpoint-8625/rng_state.pth +3 -0
  30. checkpoint-8625/scheduler.pt +3 -0
  31. checkpoint-8625/special_tokens_map.json +51 -0
  32. checkpoint-8625/tokenizer.json +0 -0
  33. checkpoint-8625/tokenizer_config.json +57 -0
  34. checkpoint-8625/trainer_state.json +1249 -0
  35. checkpoint-8625/training_args.bin +3 -0
  36. checkpoint-8625/vocab.json +0 -0
  37. config.json +36 -0
  38. merges.txt +0 -0
  39. model.safetensors +3 -0
  40. runs/May10_06-12-27_3c19404100c4/events.out.tfevents.1746857552.3c19404100c4.7029.0 +3 -0
  41. special_tokens_map.json +51 -0
  42. tokenizer.json +0 -0
  43. tokenizer_config.json +57 -0
  44. training_args.bin +3 -0
  45. vocab.json +0 -0
checkpoint-2875/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/codebert-base",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
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
+ "id2label": {
14
+ "0": "SAFE",
15
+ "1": "VULN"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "SAFE": 0,
21
+ "VULN": 1
22
+ },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "roberta",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "output_past": true,
29
+ "pad_token_id": 1,
30
+ "position_embedding_type": "absolute",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.40.1",
33
+ "type_vocab_size": 1,
34
+ "use_cache": true,
35
+ "vocab_size": 50265
36
+ }
checkpoint-2875/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2875/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e62061bc8d0e2181901522c6f63f52bb9d66165a0622a5f58fd41612b28b3a9b
3
+ size 496250232
checkpoint-2875/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1016e63951fdaa0089716b34f217a60e526d7819ae130fd8fba8e2b69b8a6702
3
+ size 992619066
checkpoint-2875/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:934870fc06199734c1c496aa714dd9dff19364c06641d126bff1e727f940aa3e
3
+ size 14244
checkpoint-2875/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4e2ac2d6f8f2a1efb6d5bd5d7bd8de2a5d4f4b882932f4a5ef65d2a21d7e763
3
+ size 1064
checkpoint-2875/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
+ }
checkpoint-2875/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2875/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
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
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
checkpoint-2875/trainer_state.json ADDED
@@ -0,0 +1,428 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0025361417792737484,
3
+ "best_model_checkpoint": "./codebert-vuln-tokcls/checkpoint-2875",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2875,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017391304347826087,
13
+ "grad_norm": 0.41397327184677124,
14
+ "learning_rate": 4.9710144927536237e-05,
15
+ "loss": 0.1154,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.034782608695652174,
20
+ "grad_norm": 0.555982768535614,
21
+ "learning_rate": 4.9420289855072464e-05,
22
+ "loss": 0.0386,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.05217391304347826,
27
+ "grad_norm": 0.3676406145095825,
28
+ "learning_rate": 4.91304347826087e-05,
29
+ "loss": 0.0315,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.06956521739130435,
34
+ "grad_norm": 0.574974536895752,
35
+ "learning_rate": 4.884057971014493e-05,
36
+ "loss": 0.028,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.08695652173913043,
41
+ "grad_norm": 0.41208797693252563,
42
+ "learning_rate": 4.855072463768116e-05,
43
+ "loss": 0.0252,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.10434782608695652,
48
+ "grad_norm": 0.34254035353660583,
49
+ "learning_rate": 4.8260869565217394e-05,
50
+ "loss": 0.0231,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.12173913043478261,
55
+ "grad_norm": 0.17080576717853546,
56
+ "learning_rate": 4.797101449275362e-05,
57
+ "loss": 0.0232,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.1391304347826087,
62
+ "grad_norm": 0.1468990445137024,
63
+ "learning_rate": 4.7681159420289855e-05,
64
+ "loss": 0.0194,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.1565217391304348,
69
+ "grad_norm": 0.20004335045814514,
70
+ "learning_rate": 4.739130434782609e-05,
71
+ "loss": 0.0198,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.17391304347826086,
76
+ "grad_norm": 0.6127797961235046,
77
+ "learning_rate": 4.710144927536232e-05,
78
+ "loss": 0.0167,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.19130434782608696,
83
+ "grad_norm": 0.2098260074853897,
84
+ "learning_rate": 4.681159420289855e-05,
85
+ "loss": 0.0195,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.20869565217391303,
90
+ "grad_norm": 0.26583606004714966,
91
+ "learning_rate": 4.6521739130434785e-05,
92
+ "loss": 0.0158,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.22608695652173913,
97
+ "grad_norm": 0.30250421166419983,
98
+ "learning_rate": 4.623188405797101e-05,
99
+ "loss": 0.0163,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.24347826086956523,
104
+ "grad_norm": 0.2696796655654907,
105
+ "learning_rate": 4.594202898550725e-05,
106
+ "loss": 0.0131,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.2608695652173913,
111
+ "grad_norm": 0.4439266324043274,
112
+ "learning_rate": 4.565217391304348e-05,
113
+ "loss": 0.0136,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.2782608695652174,
118
+ "grad_norm": 0.4392126798629761,
119
+ "learning_rate": 4.5362318840579715e-05,
120
+ "loss": 0.0137,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.2956521739130435,
125
+ "grad_norm": 0.36367908120155334,
126
+ "learning_rate": 4.507246376811595e-05,
127
+ "loss": 0.0116,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.3130434782608696,
132
+ "grad_norm": 0.3119848072528839,
133
+ "learning_rate": 4.478260869565218e-05,
134
+ "loss": 0.0129,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.33043478260869563,
139
+ "grad_norm": 0.3177811801433563,
140
+ "learning_rate": 4.449275362318841e-05,
141
+ "loss": 0.0095,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.34782608695652173,
146
+ "grad_norm": 0.9409816265106201,
147
+ "learning_rate": 4.4202898550724645e-05,
148
+ "loss": 0.0087,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.3652173913043478,
153
+ "grad_norm": 0.19778360426425934,
154
+ "learning_rate": 4.391304347826087e-05,
155
+ "loss": 0.011,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.3826086956521739,
160
+ "grad_norm": 0.21794016659259796,
161
+ "learning_rate": 4.362318840579711e-05,
162
+ "loss": 0.009,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.4,
167
+ "grad_norm": 0.3412404954433441,
168
+ "learning_rate": 4.3333333333333334e-05,
169
+ "loss": 0.0096,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.41739130434782606,
174
+ "grad_norm": 0.27317434549331665,
175
+ "learning_rate": 4.304347826086957e-05,
176
+ "loss": 0.0081,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.43478260869565216,
181
+ "grad_norm": 0.0843023881316185,
182
+ "learning_rate": 4.27536231884058e-05,
183
+ "loss": 0.0082,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.45217391304347826,
188
+ "grad_norm": 0.17682024836540222,
189
+ "learning_rate": 4.246376811594203e-05,
190
+ "loss": 0.0077,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.46956521739130436,
195
+ "grad_norm": 0.41122502088546753,
196
+ "learning_rate": 4.2173913043478264e-05,
197
+ "loss": 0.0059,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.48695652173913045,
202
+ "grad_norm": 0.2303285449743271,
203
+ "learning_rate": 4.18840579710145e-05,
204
+ "loss": 0.0075,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.5043478260869565,
209
+ "grad_norm": 0.1975090056657791,
210
+ "learning_rate": 4.1594202898550726e-05,
211
+ "loss": 0.0068,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.5217391304347826,
216
+ "grad_norm": 0.30486345291137695,
217
+ "learning_rate": 4.130434782608696e-05,
218
+ "loss": 0.0056,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.5391304347826087,
223
+ "grad_norm": 0.08862517029047012,
224
+ "learning_rate": 4.101449275362319e-05,
225
+ "loss": 0.0054,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 0.5565217391304348,
230
+ "grad_norm": 0.3306777775287628,
231
+ "learning_rate": 4.072463768115942e-05,
232
+ "loss": 0.0055,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 0.5739130434782609,
237
+ "grad_norm": 0.15247593820095062,
238
+ "learning_rate": 4.0434782608695655e-05,
239
+ "loss": 0.0045,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 0.591304347826087,
244
+ "grad_norm": 0.2155187875032425,
245
+ "learning_rate": 4.014492753623188e-05,
246
+ "loss": 0.0074,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 0.6086956521739131,
251
+ "grad_norm": 0.14913377165794373,
252
+ "learning_rate": 3.985507246376812e-05,
253
+ "loss": 0.0051,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 0.6260869565217392,
258
+ "grad_norm": 0.10386908054351807,
259
+ "learning_rate": 3.956521739130435e-05,
260
+ "loss": 0.0058,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 0.6434782608695652,
265
+ "grad_norm": 0.25304195284843445,
266
+ "learning_rate": 3.927536231884058e-05,
267
+ "loss": 0.0063,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 0.6608695652173913,
272
+ "grad_norm": 0.18636035919189453,
273
+ "learning_rate": 3.898550724637681e-05,
274
+ "loss": 0.0054,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 0.6782608695652174,
279
+ "grad_norm": 0.26325523853302,
280
+ "learning_rate": 3.869565217391305e-05,
281
+ "loss": 0.004,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 0.6956521739130435,
286
+ "grad_norm": 0.21789908409118652,
287
+ "learning_rate": 3.8405797101449274e-05,
288
+ "loss": 0.0045,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 0.7130434782608696,
293
+ "grad_norm": 0.3563387393951416,
294
+ "learning_rate": 3.811594202898551e-05,
295
+ "loss": 0.0048,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 0.7304347826086957,
300
+ "grad_norm": 0.09919373691082001,
301
+ "learning_rate": 3.7826086956521736e-05,
302
+ "loss": 0.0049,
303
+ "step": 2100
304
+ },
305
+ {
306
+ "epoch": 0.7478260869565218,
307
+ "grad_norm": 0.7440153360366821,
308
+ "learning_rate": 3.753623188405797e-05,
309
+ "loss": 0.0054,
310
+ "step": 2150
311
+ },
312
+ {
313
+ "epoch": 0.7652173913043478,
314
+ "grad_norm": 0.14773143827915192,
315
+ "learning_rate": 3.7246376811594204e-05,
316
+ "loss": 0.0039,
317
+ "step": 2200
318
+ },
319
+ {
320
+ "epoch": 0.782608695652174,
321
+ "grad_norm": 0.09251661598682404,
322
+ "learning_rate": 3.695652173913043e-05,
323
+ "loss": 0.0039,
324
+ "step": 2250
325
+ },
326
+ {
327
+ "epoch": 0.8,
328
+ "grad_norm": 0.02156330831348896,
329
+ "learning_rate": 3.6666666666666666e-05,
330
+ "loss": 0.004,
331
+ "step": 2300
332
+ },
333
+ {
334
+ "epoch": 0.8173913043478261,
335
+ "grad_norm": 0.30019891262054443,
336
+ "learning_rate": 3.63768115942029e-05,
337
+ "loss": 0.0038,
338
+ "step": 2350
339
+ },
340
+ {
341
+ "epoch": 0.8347826086956521,
342
+ "grad_norm": 0.08380095660686493,
343
+ "learning_rate": 3.6086956521739134e-05,
344
+ "loss": 0.0047,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 0.8521739130434782,
349
+ "grad_norm": 0.17295339703559875,
350
+ "learning_rate": 3.579710144927537e-05,
351
+ "loss": 0.0037,
352
+ "step": 2450
353
+ },
354
+ {
355
+ "epoch": 0.8695652173913043,
356
+ "grad_norm": 0.02843887358903885,
357
+ "learning_rate": 3.5507246376811596e-05,
358
+ "loss": 0.0033,
359
+ "step": 2500
360
+ },
361
+ {
362
+ "epoch": 0.8869565217391304,
363
+ "grad_norm": 0.35363340377807617,
364
+ "learning_rate": 3.521739130434783e-05,
365
+ "loss": 0.0042,
366
+ "step": 2550
367
+ },
368
+ {
369
+ "epoch": 0.9043478260869565,
370
+ "grad_norm": 0.6101410984992981,
371
+ "learning_rate": 3.4927536231884064e-05,
372
+ "loss": 0.0035,
373
+ "step": 2600
374
+ },
375
+ {
376
+ "epoch": 0.9217391304347826,
377
+ "grad_norm": 0.043613508343696594,
378
+ "learning_rate": 3.463768115942029e-05,
379
+ "loss": 0.0041,
380
+ "step": 2650
381
+ },
382
+ {
383
+ "epoch": 0.9391304347826087,
384
+ "grad_norm": 0.12494798004627228,
385
+ "learning_rate": 3.4347826086956526e-05,
386
+ "loss": 0.0038,
387
+ "step": 2700
388
+ },
389
+ {
390
+ "epoch": 0.9565217391304348,
391
+ "grad_norm": 0.03580565005540848,
392
+ "learning_rate": 3.405797101449276e-05,
393
+ "loss": 0.0044,
394
+ "step": 2750
395
+ },
396
+ {
397
+ "epoch": 0.9739130434782609,
398
+ "grad_norm": 0.12163197249174118,
399
+ "learning_rate": 3.376811594202899e-05,
400
+ "loss": 0.0029,
401
+ "step": 2800
402
+ },
403
+ {
404
+ "epoch": 0.991304347826087,
405
+ "grad_norm": 0.09125994145870209,
406
+ "learning_rate": 3.347826086956522e-05,
407
+ "loss": 0.0035,
408
+ "step": 2850
409
+ },
410
+ {
411
+ "epoch": 1.0,
412
+ "eval_loss": 0.0025361417792737484,
413
+ "eval_runtime": 96.0353,
414
+ "eval_samples_per_second": 29.937,
415
+ "eval_steps_per_second": 3.749,
416
+ "step": 2875
417
+ }
418
+ ],
419
+ "logging_steps": 50,
420
+ "max_steps": 8625,
421
+ "num_input_tokens_seen": 0,
422
+ "num_train_epochs": 3,
423
+ "save_steps": 500,
424
+ "total_flos": 6009564108171264.0,
425
+ "train_batch_size": 8,
426
+ "trial_name": null,
427
+ "trial_params": null
428
+ }
checkpoint-2875/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee1502bb3f8db9acd55a79b31f914b1fc26b999623288aaacdcb1ae8b8de2b9
3
+ size 5048
checkpoint-2875/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-5750/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/codebert-base",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
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
+ "id2label": {
14
+ "0": "SAFE",
15
+ "1": "VULN"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "SAFE": 0,
21
+ "VULN": 1
22
+ },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "roberta",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "output_past": true,
29
+ "pad_token_id": 1,
30
+ "position_embedding_type": "absolute",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.40.1",
33
+ "type_vocab_size": 1,
34
+ "use_cache": true,
35
+ "vocab_size": 50265
36
+ }
checkpoint-5750/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-5750/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fe047cf09f3a0df02881580dccdb45c9ccb7da79d9dcb1dd8451822f8165c2f
3
+ size 496250232
checkpoint-5750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c913061275a733fa3e321009beac4745c2cdaa519a54eaafd688db5b3eca9a3b
3
+ size 992619066
checkpoint-5750/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04139d4f5a631eb86dd99b5941b000ffb330d8b0855bde405c423829051ae447
3
+ size 14244
checkpoint-5750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fa2b4c8b8704e3d983d73a9fba54566d5c0ff67d7373291b8b0b452ecea86af
3
+ size 1064
checkpoint-5750/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
+ }
checkpoint-5750/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-5750/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
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
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
checkpoint-5750/trainer_state.json ADDED
@@ -0,0 +1,842 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0012920453445985913,
3
+ "best_model_checkpoint": "./codebert-vuln-tokcls/checkpoint-5750",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5750,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017391304347826087,
13
+ "grad_norm": 0.41397327184677124,
14
+ "learning_rate": 4.9710144927536237e-05,
15
+ "loss": 0.1154,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.034782608695652174,
20
+ "grad_norm": 0.555982768535614,
21
+ "learning_rate": 4.9420289855072464e-05,
22
+ "loss": 0.0386,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.05217391304347826,
27
+ "grad_norm": 0.3676406145095825,
28
+ "learning_rate": 4.91304347826087e-05,
29
+ "loss": 0.0315,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.06956521739130435,
34
+ "grad_norm": 0.574974536895752,
35
+ "learning_rate": 4.884057971014493e-05,
36
+ "loss": 0.028,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.08695652173913043,
41
+ "grad_norm": 0.41208797693252563,
42
+ "learning_rate": 4.855072463768116e-05,
43
+ "loss": 0.0252,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.10434782608695652,
48
+ "grad_norm": 0.34254035353660583,
49
+ "learning_rate": 4.8260869565217394e-05,
50
+ "loss": 0.0231,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.12173913043478261,
55
+ "grad_norm": 0.17080576717853546,
56
+ "learning_rate": 4.797101449275362e-05,
57
+ "loss": 0.0232,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.1391304347826087,
62
+ "grad_norm": 0.1468990445137024,
63
+ "learning_rate": 4.7681159420289855e-05,
64
+ "loss": 0.0194,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.1565217391304348,
69
+ "grad_norm": 0.20004335045814514,
70
+ "learning_rate": 4.739130434782609e-05,
71
+ "loss": 0.0198,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.17391304347826086,
76
+ "grad_norm": 0.6127797961235046,
77
+ "learning_rate": 4.710144927536232e-05,
78
+ "loss": 0.0167,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.19130434782608696,
83
+ "grad_norm": 0.2098260074853897,
84
+ "learning_rate": 4.681159420289855e-05,
85
+ "loss": 0.0195,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.20869565217391303,
90
+ "grad_norm": 0.26583606004714966,
91
+ "learning_rate": 4.6521739130434785e-05,
92
+ "loss": 0.0158,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.22608695652173913,
97
+ "grad_norm": 0.30250421166419983,
98
+ "learning_rate": 4.623188405797101e-05,
99
+ "loss": 0.0163,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.24347826086956523,
104
+ "grad_norm": 0.2696796655654907,
105
+ "learning_rate": 4.594202898550725e-05,
106
+ "loss": 0.0131,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.2608695652173913,
111
+ "grad_norm": 0.4439266324043274,
112
+ "learning_rate": 4.565217391304348e-05,
113
+ "loss": 0.0136,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.2782608695652174,
118
+ "grad_norm": 0.4392126798629761,
119
+ "learning_rate": 4.5362318840579715e-05,
120
+ "loss": 0.0137,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.2956521739130435,
125
+ "grad_norm": 0.36367908120155334,
126
+ "learning_rate": 4.507246376811595e-05,
127
+ "loss": 0.0116,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.3130434782608696,
132
+ "grad_norm": 0.3119848072528839,
133
+ "learning_rate": 4.478260869565218e-05,
134
+ "loss": 0.0129,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.33043478260869563,
139
+ "grad_norm": 0.3177811801433563,
140
+ "learning_rate": 4.449275362318841e-05,
141
+ "loss": 0.0095,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.34782608695652173,
146
+ "grad_norm": 0.9409816265106201,
147
+ "learning_rate": 4.4202898550724645e-05,
148
+ "loss": 0.0087,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.3652173913043478,
153
+ "grad_norm": 0.19778360426425934,
154
+ "learning_rate": 4.391304347826087e-05,
155
+ "loss": 0.011,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.3826086956521739,
160
+ "grad_norm": 0.21794016659259796,
161
+ "learning_rate": 4.362318840579711e-05,
162
+ "loss": 0.009,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.4,
167
+ "grad_norm": 0.3412404954433441,
168
+ "learning_rate": 4.3333333333333334e-05,
169
+ "loss": 0.0096,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.41739130434782606,
174
+ "grad_norm": 0.27317434549331665,
175
+ "learning_rate": 4.304347826086957e-05,
176
+ "loss": 0.0081,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.43478260869565216,
181
+ "grad_norm": 0.0843023881316185,
182
+ "learning_rate": 4.27536231884058e-05,
183
+ "loss": 0.0082,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.45217391304347826,
188
+ "grad_norm": 0.17682024836540222,
189
+ "learning_rate": 4.246376811594203e-05,
190
+ "loss": 0.0077,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.46956521739130436,
195
+ "grad_norm": 0.41122502088546753,
196
+ "learning_rate": 4.2173913043478264e-05,
197
+ "loss": 0.0059,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.48695652173913045,
202
+ "grad_norm": 0.2303285449743271,
203
+ "learning_rate": 4.18840579710145e-05,
204
+ "loss": 0.0075,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.5043478260869565,
209
+ "grad_norm": 0.1975090056657791,
210
+ "learning_rate": 4.1594202898550726e-05,
211
+ "loss": 0.0068,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.5217391304347826,
216
+ "grad_norm": 0.30486345291137695,
217
+ "learning_rate": 4.130434782608696e-05,
218
+ "loss": 0.0056,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.5391304347826087,
223
+ "grad_norm": 0.08862517029047012,
224
+ "learning_rate": 4.101449275362319e-05,
225
+ "loss": 0.0054,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 0.5565217391304348,
230
+ "grad_norm": 0.3306777775287628,
231
+ "learning_rate": 4.072463768115942e-05,
232
+ "loss": 0.0055,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 0.5739130434782609,
237
+ "grad_norm": 0.15247593820095062,
238
+ "learning_rate": 4.0434782608695655e-05,
239
+ "loss": 0.0045,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 0.591304347826087,
244
+ "grad_norm": 0.2155187875032425,
245
+ "learning_rate": 4.014492753623188e-05,
246
+ "loss": 0.0074,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 0.6086956521739131,
251
+ "grad_norm": 0.14913377165794373,
252
+ "learning_rate": 3.985507246376812e-05,
253
+ "loss": 0.0051,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 0.6260869565217392,
258
+ "grad_norm": 0.10386908054351807,
259
+ "learning_rate": 3.956521739130435e-05,
260
+ "loss": 0.0058,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 0.6434782608695652,
265
+ "grad_norm": 0.25304195284843445,
266
+ "learning_rate": 3.927536231884058e-05,
267
+ "loss": 0.0063,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 0.6608695652173913,
272
+ "grad_norm": 0.18636035919189453,
273
+ "learning_rate": 3.898550724637681e-05,
274
+ "loss": 0.0054,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 0.6782608695652174,
279
+ "grad_norm": 0.26325523853302,
280
+ "learning_rate": 3.869565217391305e-05,
281
+ "loss": 0.004,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 0.6956521739130435,
286
+ "grad_norm": 0.21789908409118652,
287
+ "learning_rate": 3.8405797101449274e-05,
288
+ "loss": 0.0045,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 0.7130434782608696,
293
+ "grad_norm": 0.3563387393951416,
294
+ "learning_rate": 3.811594202898551e-05,
295
+ "loss": 0.0048,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 0.7304347826086957,
300
+ "grad_norm": 0.09919373691082001,
301
+ "learning_rate": 3.7826086956521736e-05,
302
+ "loss": 0.0049,
303
+ "step": 2100
304
+ },
305
+ {
306
+ "epoch": 0.7478260869565218,
307
+ "grad_norm": 0.7440153360366821,
308
+ "learning_rate": 3.753623188405797e-05,
309
+ "loss": 0.0054,
310
+ "step": 2150
311
+ },
312
+ {
313
+ "epoch": 0.7652173913043478,
314
+ "grad_norm": 0.14773143827915192,
315
+ "learning_rate": 3.7246376811594204e-05,
316
+ "loss": 0.0039,
317
+ "step": 2200
318
+ },
319
+ {
320
+ "epoch": 0.782608695652174,
321
+ "grad_norm": 0.09251661598682404,
322
+ "learning_rate": 3.695652173913043e-05,
323
+ "loss": 0.0039,
324
+ "step": 2250
325
+ },
326
+ {
327
+ "epoch": 0.8,
328
+ "grad_norm": 0.02156330831348896,
329
+ "learning_rate": 3.6666666666666666e-05,
330
+ "loss": 0.004,
331
+ "step": 2300
332
+ },
333
+ {
334
+ "epoch": 0.8173913043478261,
335
+ "grad_norm": 0.30019891262054443,
336
+ "learning_rate": 3.63768115942029e-05,
337
+ "loss": 0.0038,
338
+ "step": 2350
339
+ },
340
+ {
341
+ "epoch": 0.8347826086956521,
342
+ "grad_norm": 0.08380095660686493,
343
+ "learning_rate": 3.6086956521739134e-05,
344
+ "loss": 0.0047,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 0.8521739130434782,
349
+ "grad_norm": 0.17295339703559875,
350
+ "learning_rate": 3.579710144927537e-05,
351
+ "loss": 0.0037,
352
+ "step": 2450
353
+ },
354
+ {
355
+ "epoch": 0.8695652173913043,
356
+ "grad_norm": 0.02843887358903885,
357
+ "learning_rate": 3.5507246376811596e-05,
358
+ "loss": 0.0033,
359
+ "step": 2500
360
+ },
361
+ {
362
+ "epoch": 0.8869565217391304,
363
+ "grad_norm": 0.35363340377807617,
364
+ "learning_rate": 3.521739130434783e-05,
365
+ "loss": 0.0042,
366
+ "step": 2550
367
+ },
368
+ {
369
+ "epoch": 0.9043478260869565,
370
+ "grad_norm": 0.6101410984992981,
371
+ "learning_rate": 3.4927536231884064e-05,
372
+ "loss": 0.0035,
373
+ "step": 2600
374
+ },
375
+ {
376
+ "epoch": 0.9217391304347826,
377
+ "grad_norm": 0.043613508343696594,
378
+ "learning_rate": 3.463768115942029e-05,
379
+ "loss": 0.0041,
380
+ "step": 2650
381
+ },
382
+ {
383
+ "epoch": 0.9391304347826087,
384
+ "grad_norm": 0.12494798004627228,
385
+ "learning_rate": 3.4347826086956526e-05,
386
+ "loss": 0.0038,
387
+ "step": 2700
388
+ },
389
+ {
390
+ "epoch": 0.9565217391304348,
391
+ "grad_norm": 0.03580565005540848,
392
+ "learning_rate": 3.405797101449276e-05,
393
+ "loss": 0.0044,
394
+ "step": 2750
395
+ },
396
+ {
397
+ "epoch": 0.9739130434782609,
398
+ "grad_norm": 0.12163197249174118,
399
+ "learning_rate": 3.376811594202899e-05,
400
+ "loss": 0.0029,
401
+ "step": 2800
402
+ },
403
+ {
404
+ "epoch": 0.991304347826087,
405
+ "grad_norm": 0.09125994145870209,
406
+ "learning_rate": 3.347826086956522e-05,
407
+ "loss": 0.0035,
408
+ "step": 2850
409
+ },
410
+ {
411
+ "epoch": 1.0,
412
+ "eval_loss": 0.0025361417792737484,
413
+ "eval_runtime": 96.0353,
414
+ "eval_samples_per_second": 29.937,
415
+ "eval_steps_per_second": 3.749,
416
+ "step": 2875
417
+ },
418
+ {
419
+ "epoch": 1.008695652173913,
420
+ "grad_norm": 0.08735060691833496,
421
+ "learning_rate": 3.318840579710145e-05,
422
+ "loss": 0.0026,
423
+ "step": 2900
424
+ },
425
+ {
426
+ "epoch": 1.0260869565217392,
427
+ "grad_norm": 0.0311286523938179,
428
+ "learning_rate": 3.289855072463768e-05,
429
+ "loss": 0.0029,
430
+ "step": 2950
431
+ },
432
+ {
433
+ "epoch": 1.0434782608695652,
434
+ "grad_norm": 0.1523689180612564,
435
+ "learning_rate": 3.260869565217392e-05,
436
+ "loss": 0.0044,
437
+ "step": 3000
438
+ },
439
+ {
440
+ "epoch": 1.0608695652173914,
441
+ "grad_norm": 0.09883025288581848,
442
+ "learning_rate": 3.2318840579710144e-05,
443
+ "loss": 0.0029,
444
+ "step": 3050
445
+ },
446
+ {
447
+ "epoch": 1.0782608695652174,
448
+ "grad_norm": 0.20815688371658325,
449
+ "learning_rate": 3.202898550724638e-05,
450
+ "loss": 0.0029,
451
+ "step": 3100
452
+ },
453
+ {
454
+ "epoch": 1.0956521739130434,
455
+ "grad_norm": 0.2510022819042206,
456
+ "learning_rate": 3.173913043478261e-05,
457
+ "loss": 0.0033,
458
+ "step": 3150
459
+ },
460
+ {
461
+ "epoch": 1.1130434782608696,
462
+ "grad_norm": 0.06902216374874115,
463
+ "learning_rate": 3.144927536231884e-05,
464
+ "loss": 0.0031,
465
+ "step": 3200
466
+ },
467
+ {
468
+ "epoch": 1.1304347826086956,
469
+ "grad_norm": 0.5787861347198486,
470
+ "learning_rate": 3.1159420289855074e-05,
471
+ "loss": 0.004,
472
+ "step": 3250
473
+ },
474
+ {
475
+ "epoch": 1.1478260869565218,
476
+ "grad_norm": 0.1607126146554947,
477
+ "learning_rate": 3.086956521739131e-05,
478
+ "loss": 0.0027,
479
+ "step": 3300
480
+ },
481
+ {
482
+ "epoch": 1.1652173913043478,
483
+ "grad_norm": 0.27043744921684265,
484
+ "learning_rate": 3.0579710144927536e-05,
485
+ "loss": 0.0032,
486
+ "step": 3350
487
+ },
488
+ {
489
+ "epoch": 1.182608695652174,
490
+ "grad_norm": 0.040458448231220245,
491
+ "learning_rate": 3.028985507246377e-05,
492
+ "loss": 0.0025,
493
+ "step": 3400
494
+ },
495
+ {
496
+ "epoch": 1.2,
497
+ "grad_norm": 0.070162333548069,
498
+ "learning_rate": 3e-05,
499
+ "loss": 0.0036,
500
+ "step": 3450
501
+ },
502
+ {
503
+ "epoch": 1.2173913043478262,
504
+ "grad_norm": 0.01620602235198021,
505
+ "learning_rate": 2.971014492753623e-05,
506
+ "loss": 0.0023,
507
+ "step": 3500
508
+ },
509
+ {
510
+ "epoch": 1.2347826086956522,
511
+ "grad_norm": 1.2112153768539429,
512
+ "learning_rate": 2.9420289855072462e-05,
513
+ "loss": 0.0024,
514
+ "step": 3550
515
+ },
516
+ {
517
+ "epoch": 1.2521739130434781,
518
+ "grad_norm": 0.009653642773628235,
519
+ "learning_rate": 2.9130434782608696e-05,
520
+ "loss": 0.0021,
521
+ "step": 3600
522
+ },
523
+ {
524
+ "epoch": 1.2695652173913043,
525
+ "grad_norm": 0.14598160982131958,
526
+ "learning_rate": 2.8840579710144927e-05,
527
+ "loss": 0.0028,
528
+ "step": 3650
529
+ },
530
+ {
531
+ "epoch": 1.2869565217391306,
532
+ "grad_norm": 0.07699096202850342,
533
+ "learning_rate": 2.8550724637681158e-05,
534
+ "loss": 0.0021,
535
+ "step": 3700
536
+ },
537
+ {
538
+ "epoch": 1.3043478260869565,
539
+ "grad_norm": 0.27755749225616455,
540
+ "learning_rate": 2.826086956521739e-05,
541
+ "loss": 0.0025,
542
+ "step": 3750
543
+ },
544
+ {
545
+ "epoch": 1.3217391304347825,
546
+ "grad_norm": 0.22564417123794556,
547
+ "learning_rate": 2.7971014492753623e-05,
548
+ "loss": 0.0022,
549
+ "step": 3800
550
+ },
551
+ {
552
+ "epoch": 1.3391304347826087,
553
+ "grad_norm": 0.655219554901123,
554
+ "learning_rate": 2.7681159420289854e-05,
555
+ "loss": 0.0025,
556
+ "step": 3850
557
+ },
558
+ {
559
+ "epoch": 1.3565217391304347,
560
+ "grad_norm": 0.02139280177652836,
561
+ "learning_rate": 2.7391304347826085e-05,
562
+ "loss": 0.0027,
563
+ "step": 3900
564
+ },
565
+ {
566
+ "epoch": 1.373913043478261,
567
+ "grad_norm": 0.0938597247004509,
568
+ "learning_rate": 2.7101449275362322e-05,
569
+ "loss": 0.0029,
570
+ "step": 3950
571
+ },
572
+ {
573
+ "epoch": 1.391304347826087,
574
+ "grad_norm": 0.010128723457455635,
575
+ "learning_rate": 2.6811594202898553e-05,
576
+ "loss": 0.0031,
577
+ "step": 4000
578
+ },
579
+ {
580
+ "epoch": 1.4086956521739131,
581
+ "grad_norm": 0.15920484066009521,
582
+ "learning_rate": 2.6521739130434787e-05,
583
+ "loss": 0.0022,
584
+ "step": 4050
585
+ },
586
+ {
587
+ "epoch": 1.4260869565217391,
588
+ "grad_norm": 0.10766106098890305,
589
+ "learning_rate": 2.6231884057971018e-05,
590
+ "loss": 0.0015,
591
+ "step": 4100
592
+ },
593
+ {
594
+ "epoch": 1.4434782608695653,
595
+ "grad_norm": 0.12829457223415375,
596
+ "learning_rate": 2.594202898550725e-05,
597
+ "loss": 0.0027,
598
+ "step": 4150
599
+ },
600
+ {
601
+ "epoch": 1.4608695652173913,
602
+ "grad_norm": 0.042468324303627014,
603
+ "learning_rate": 2.5652173913043483e-05,
604
+ "loss": 0.0028,
605
+ "step": 4200
606
+ },
607
+ {
608
+ "epoch": 1.4782608695652173,
609
+ "grad_norm": 0.018434317782521248,
610
+ "learning_rate": 2.5362318840579714e-05,
611
+ "loss": 0.0021,
612
+ "step": 4250
613
+ },
614
+ {
615
+ "epoch": 1.4956521739130435,
616
+ "grad_norm": 0.0739726796746254,
617
+ "learning_rate": 2.5072463768115944e-05,
618
+ "loss": 0.0022,
619
+ "step": 4300
620
+ },
621
+ {
622
+ "epoch": 1.5130434782608697,
623
+ "grad_norm": 0.07464097440242767,
624
+ "learning_rate": 2.4782608695652175e-05,
625
+ "loss": 0.0022,
626
+ "step": 4350
627
+ },
628
+ {
629
+ "epoch": 1.5304347826086957,
630
+ "grad_norm": 0.07711721211671829,
631
+ "learning_rate": 2.449275362318841e-05,
632
+ "loss": 0.0024,
633
+ "step": 4400
634
+ },
635
+ {
636
+ "epoch": 1.5478260869565217,
637
+ "grad_norm": 0.5523372888565063,
638
+ "learning_rate": 2.420289855072464e-05,
639
+ "loss": 0.0023,
640
+ "step": 4450
641
+ },
642
+ {
643
+ "epoch": 1.5652173913043477,
644
+ "grad_norm": 0.0014616675907745957,
645
+ "learning_rate": 2.391304347826087e-05,
646
+ "loss": 0.0021,
647
+ "step": 4500
648
+ },
649
+ {
650
+ "epoch": 1.5826086956521739,
651
+ "grad_norm": 0.033656634390354156,
652
+ "learning_rate": 2.36231884057971e-05,
653
+ "loss": 0.0022,
654
+ "step": 4550
655
+ },
656
+ {
657
+ "epoch": 1.6,
658
+ "grad_norm": 0.17268861830234528,
659
+ "learning_rate": 2.3333333333333336e-05,
660
+ "loss": 0.0017,
661
+ "step": 4600
662
+ },
663
+ {
664
+ "epoch": 1.617391304347826,
665
+ "grad_norm": 0.14583924412727356,
666
+ "learning_rate": 2.3043478260869567e-05,
667
+ "loss": 0.0019,
668
+ "step": 4650
669
+ },
670
+ {
671
+ "epoch": 1.634782608695652,
672
+ "grad_norm": 0.020815925672650337,
673
+ "learning_rate": 2.2753623188405797e-05,
674
+ "loss": 0.0026,
675
+ "step": 4700
676
+ },
677
+ {
678
+ "epoch": 1.6521739130434783,
679
+ "grad_norm": 0.1761491745710373,
680
+ "learning_rate": 2.246376811594203e-05,
681
+ "loss": 0.0019,
682
+ "step": 4750
683
+ },
684
+ {
685
+ "epoch": 1.6695652173913045,
686
+ "grad_norm": 0.15895789861679077,
687
+ "learning_rate": 2.2173913043478262e-05,
688
+ "loss": 0.0015,
689
+ "step": 4800
690
+ },
691
+ {
692
+ "epoch": 1.6869565217391305,
693
+ "grad_norm": 0.217234268784523,
694
+ "learning_rate": 2.1884057971014493e-05,
695
+ "loss": 0.0013,
696
+ "step": 4850
697
+ },
698
+ {
699
+ "epoch": 1.7043478260869565,
700
+ "grad_norm": 0.058053504675626755,
701
+ "learning_rate": 2.1594202898550724e-05,
702
+ "loss": 0.0025,
703
+ "step": 4900
704
+ },
705
+ {
706
+ "epoch": 1.7217391304347827,
707
+ "grad_norm": 0.03019527532160282,
708
+ "learning_rate": 2.1304347826086958e-05,
709
+ "loss": 0.0025,
710
+ "step": 4950
711
+ },
712
+ {
713
+ "epoch": 1.7391304347826086,
714
+ "grad_norm": 0.19927392899990082,
715
+ "learning_rate": 2.101449275362319e-05,
716
+ "loss": 0.0026,
717
+ "step": 5000
718
+ },
719
+ {
720
+ "epoch": 1.7565217391304349,
721
+ "grad_norm": 0.046536799520254135,
722
+ "learning_rate": 2.072463768115942e-05,
723
+ "loss": 0.002,
724
+ "step": 5050
725
+ },
726
+ {
727
+ "epoch": 1.7739130434782608,
728
+ "grad_norm": 0.3650865852832794,
729
+ "learning_rate": 2.0434782608695654e-05,
730
+ "loss": 0.0021,
731
+ "step": 5100
732
+ },
733
+ {
734
+ "epoch": 1.7913043478260868,
735
+ "grad_norm": 0.12650315463542938,
736
+ "learning_rate": 2.0144927536231885e-05,
737
+ "loss": 0.0015,
738
+ "step": 5150
739
+ },
740
+ {
741
+ "epoch": 1.808695652173913,
742
+ "grad_norm": 0.01490619033575058,
743
+ "learning_rate": 1.985507246376812e-05,
744
+ "loss": 0.0016,
745
+ "step": 5200
746
+ },
747
+ {
748
+ "epoch": 1.8260869565217392,
749
+ "grad_norm": 0.09603610634803772,
750
+ "learning_rate": 1.956521739130435e-05,
751
+ "loss": 0.002,
752
+ "step": 5250
753
+ },
754
+ {
755
+ "epoch": 1.8434782608695652,
756
+ "grad_norm": 0.02328038401901722,
757
+ "learning_rate": 1.927536231884058e-05,
758
+ "loss": 0.0016,
759
+ "step": 5300
760
+ },
761
+ {
762
+ "epoch": 1.8608695652173912,
763
+ "grad_norm": 0.011464759707450867,
764
+ "learning_rate": 1.8985507246376814e-05,
765
+ "loss": 0.0017,
766
+ "step": 5350
767
+ },
768
+ {
769
+ "epoch": 1.8782608695652174,
770
+ "grad_norm": 0.08598850667476654,
771
+ "learning_rate": 1.8695652173913045e-05,
772
+ "loss": 0.0014,
773
+ "step": 5400
774
+ },
775
+ {
776
+ "epoch": 1.8956521739130436,
777
+ "grad_norm": 0.07689868658781052,
778
+ "learning_rate": 1.8405797101449276e-05,
779
+ "loss": 0.0016,
780
+ "step": 5450
781
+ },
782
+ {
783
+ "epoch": 1.9130434782608696,
784
+ "grad_norm": 0.1737821102142334,
785
+ "learning_rate": 1.8115942028985507e-05,
786
+ "loss": 0.0014,
787
+ "step": 5500
788
+ },
789
+ {
790
+ "epoch": 1.9304347826086956,
791
+ "grad_norm": 0.02161916345357895,
792
+ "learning_rate": 1.782608695652174e-05,
793
+ "loss": 0.0011,
794
+ "step": 5550
795
+ },
796
+ {
797
+ "epoch": 1.9478260869565216,
798
+ "grad_norm": 0.499637633562088,
799
+ "learning_rate": 1.7536231884057972e-05,
800
+ "loss": 0.0019,
801
+ "step": 5600
802
+ },
803
+ {
804
+ "epoch": 1.9652173913043478,
805
+ "grad_norm": 0.1786130666732788,
806
+ "learning_rate": 1.7246376811594203e-05,
807
+ "loss": 0.0012,
808
+ "step": 5650
809
+ },
810
+ {
811
+ "epoch": 1.982608695652174,
812
+ "grad_norm": 0.0513494610786438,
813
+ "learning_rate": 1.6956521739130433e-05,
814
+ "loss": 0.0016,
815
+ "step": 5700
816
+ },
817
+ {
818
+ "epoch": 2.0,
819
+ "grad_norm": 0.06775401532649994,
820
+ "learning_rate": 1.6666666666666667e-05,
821
+ "loss": 0.0013,
822
+ "step": 5750
823
+ },
824
+ {
825
+ "epoch": 2.0,
826
+ "eval_loss": 0.0012920453445985913,
827
+ "eval_runtime": 96.4408,
828
+ "eval_samples_per_second": 29.811,
829
+ "eval_steps_per_second": 3.733,
830
+ "step": 5750
831
+ }
832
+ ],
833
+ "logging_steps": 50,
834
+ "max_steps": 8625,
835
+ "num_input_tokens_seen": 0,
836
+ "num_train_epochs": 3,
837
+ "save_steps": 500,
838
+ "total_flos": 1.2019128216342528e+16,
839
+ "train_batch_size": 8,
840
+ "trial_name": null,
841
+ "trial_params": null
842
+ }
checkpoint-5750/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee1502bb3f8db9acd55a79b31f914b1fc26b999623288aaacdcb1ae8b8de2b9
3
+ size 5048
checkpoint-5750/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8625/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/codebert-base",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
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
+ "id2label": {
14
+ "0": "SAFE",
15
+ "1": "VULN"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "SAFE": 0,
21
+ "VULN": 1
22
+ },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "roberta",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "output_past": true,
29
+ "pad_token_id": 1,
30
+ "position_embedding_type": "absolute",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.40.1",
33
+ "type_vocab_size": 1,
34
+ "use_cache": true,
35
+ "vocab_size": 50265
36
+ }
checkpoint-8625/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8625/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:764d780f015cce8f139f809a3674e87207e82baa9337207bffc204b2ecb44f7e
3
+ size 496250232
checkpoint-8625/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1044a776e591b00bb20b05c07062482d7c66c38ffd779da55048ece12b627c7
3
+ size 992619066
checkpoint-8625/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c3af4ce09881020a03700c4c97fb71333dababfa947938a499db09b5246f604
3
+ size 14244
checkpoint-8625/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:595e155e3ac1b002d56273b536e3b911c797a979b0eade71e7242dd22b0f06e3
3
+ size 1064
checkpoint-8625/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
+ }
checkpoint-8625/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8625/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
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
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
checkpoint-8625/trainer_state.json ADDED
@@ -0,0 +1,1249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0009732216713018715,
3
+ "best_model_checkpoint": "./codebert-vuln-tokcls/checkpoint-8625",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 8625,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017391304347826087,
13
+ "grad_norm": 0.41397327184677124,
14
+ "learning_rate": 4.9710144927536237e-05,
15
+ "loss": 0.1154,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.034782608695652174,
20
+ "grad_norm": 0.555982768535614,
21
+ "learning_rate": 4.9420289855072464e-05,
22
+ "loss": 0.0386,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.05217391304347826,
27
+ "grad_norm": 0.3676406145095825,
28
+ "learning_rate": 4.91304347826087e-05,
29
+ "loss": 0.0315,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.06956521739130435,
34
+ "grad_norm": 0.574974536895752,
35
+ "learning_rate": 4.884057971014493e-05,
36
+ "loss": 0.028,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.08695652173913043,
41
+ "grad_norm": 0.41208797693252563,
42
+ "learning_rate": 4.855072463768116e-05,
43
+ "loss": 0.0252,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.10434782608695652,
48
+ "grad_norm": 0.34254035353660583,
49
+ "learning_rate": 4.8260869565217394e-05,
50
+ "loss": 0.0231,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.12173913043478261,
55
+ "grad_norm": 0.17080576717853546,
56
+ "learning_rate": 4.797101449275362e-05,
57
+ "loss": 0.0232,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.1391304347826087,
62
+ "grad_norm": 0.1468990445137024,
63
+ "learning_rate": 4.7681159420289855e-05,
64
+ "loss": 0.0194,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.1565217391304348,
69
+ "grad_norm": 0.20004335045814514,
70
+ "learning_rate": 4.739130434782609e-05,
71
+ "loss": 0.0198,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.17391304347826086,
76
+ "grad_norm": 0.6127797961235046,
77
+ "learning_rate": 4.710144927536232e-05,
78
+ "loss": 0.0167,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.19130434782608696,
83
+ "grad_norm": 0.2098260074853897,
84
+ "learning_rate": 4.681159420289855e-05,
85
+ "loss": 0.0195,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.20869565217391303,
90
+ "grad_norm": 0.26583606004714966,
91
+ "learning_rate": 4.6521739130434785e-05,
92
+ "loss": 0.0158,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.22608695652173913,
97
+ "grad_norm": 0.30250421166419983,
98
+ "learning_rate": 4.623188405797101e-05,
99
+ "loss": 0.0163,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.24347826086956523,
104
+ "grad_norm": 0.2696796655654907,
105
+ "learning_rate": 4.594202898550725e-05,
106
+ "loss": 0.0131,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.2608695652173913,
111
+ "grad_norm": 0.4439266324043274,
112
+ "learning_rate": 4.565217391304348e-05,
113
+ "loss": 0.0136,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.2782608695652174,
118
+ "grad_norm": 0.4392126798629761,
119
+ "learning_rate": 4.5362318840579715e-05,
120
+ "loss": 0.0137,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.2956521739130435,
125
+ "grad_norm": 0.36367908120155334,
126
+ "learning_rate": 4.507246376811595e-05,
127
+ "loss": 0.0116,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.3130434782608696,
132
+ "grad_norm": 0.3119848072528839,
133
+ "learning_rate": 4.478260869565218e-05,
134
+ "loss": 0.0129,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.33043478260869563,
139
+ "grad_norm": 0.3177811801433563,
140
+ "learning_rate": 4.449275362318841e-05,
141
+ "loss": 0.0095,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.34782608695652173,
146
+ "grad_norm": 0.9409816265106201,
147
+ "learning_rate": 4.4202898550724645e-05,
148
+ "loss": 0.0087,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.3652173913043478,
153
+ "grad_norm": 0.19778360426425934,
154
+ "learning_rate": 4.391304347826087e-05,
155
+ "loss": 0.011,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.3826086956521739,
160
+ "grad_norm": 0.21794016659259796,
161
+ "learning_rate": 4.362318840579711e-05,
162
+ "loss": 0.009,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.4,
167
+ "grad_norm": 0.3412404954433441,
168
+ "learning_rate": 4.3333333333333334e-05,
169
+ "loss": 0.0096,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.41739130434782606,
174
+ "grad_norm": 0.27317434549331665,
175
+ "learning_rate": 4.304347826086957e-05,
176
+ "loss": 0.0081,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.43478260869565216,
181
+ "grad_norm": 0.0843023881316185,
182
+ "learning_rate": 4.27536231884058e-05,
183
+ "loss": 0.0082,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.45217391304347826,
188
+ "grad_norm": 0.17682024836540222,
189
+ "learning_rate": 4.246376811594203e-05,
190
+ "loss": 0.0077,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.46956521739130436,
195
+ "grad_norm": 0.41122502088546753,
196
+ "learning_rate": 4.2173913043478264e-05,
197
+ "loss": 0.0059,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.48695652173913045,
202
+ "grad_norm": 0.2303285449743271,
203
+ "learning_rate": 4.18840579710145e-05,
204
+ "loss": 0.0075,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.5043478260869565,
209
+ "grad_norm": 0.1975090056657791,
210
+ "learning_rate": 4.1594202898550726e-05,
211
+ "loss": 0.0068,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.5217391304347826,
216
+ "grad_norm": 0.30486345291137695,
217
+ "learning_rate": 4.130434782608696e-05,
218
+ "loss": 0.0056,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.5391304347826087,
223
+ "grad_norm": 0.08862517029047012,
224
+ "learning_rate": 4.101449275362319e-05,
225
+ "loss": 0.0054,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 0.5565217391304348,
230
+ "grad_norm": 0.3306777775287628,
231
+ "learning_rate": 4.072463768115942e-05,
232
+ "loss": 0.0055,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 0.5739130434782609,
237
+ "grad_norm": 0.15247593820095062,
238
+ "learning_rate": 4.0434782608695655e-05,
239
+ "loss": 0.0045,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 0.591304347826087,
244
+ "grad_norm": 0.2155187875032425,
245
+ "learning_rate": 4.014492753623188e-05,
246
+ "loss": 0.0074,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 0.6086956521739131,
251
+ "grad_norm": 0.14913377165794373,
252
+ "learning_rate": 3.985507246376812e-05,
253
+ "loss": 0.0051,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 0.6260869565217392,
258
+ "grad_norm": 0.10386908054351807,
259
+ "learning_rate": 3.956521739130435e-05,
260
+ "loss": 0.0058,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 0.6434782608695652,
265
+ "grad_norm": 0.25304195284843445,
266
+ "learning_rate": 3.927536231884058e-05,
267
+ "loss": 0.0063,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 0.6608695652173913,
272
+ "grad_norm": 0.18636035919189453,
273
+ "learning_rate": 3.898550724637681e-05,
274
+ "loss": 0.0054,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 0.6782608695652174,
279
+ "grad_norm": 0.26325523853302,
280
+ "learning_rate": 3.869565217391305e-05,
281
+ "loss": 0.004,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 0.6956521739130435,
286
+ "grad_norm": 0.21789908409118652,
287
+ "learning_rate": 3.8405797101449274e-05,
288
+ "loss": 0.0045,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 0.7130434782608696,
293
+ "grad_norm": 0.3563387393951416,
294
+ "learning_rate": 3.811594202898551e-05,
295
+ "loss": 0.0048,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 0.7304347826086957,
300
+ "grad_norm": 0.09919373691082001,
301
+ "learning_rate": 3.7826086956521736e-05,
302
+ "loss": 0.0049,
303
+ "step": 2100
304
+ },
305
+ {
306
+ "epoch": 0.7478260869565218,
307
+ "grad_norm": 0.7440153360366821,
308
+ "learning_rate": 3.753623188405797e-05,
309
+ "loss": 0.0054,
310
+ "step": 2150
311
+ },
312
+ {
313
+ "epoch": 0.7652173913043478,
314
+ "grad_norm": 0.14773143827915192,
315
+ "learning_rate": 3.7246376811594204e-05,
316
+ "loss": 0.0039,
317
+ "step": 2200
318
+ },
319
+ {
320
+ "epoch": 0.782608695652174,
321
+ "grad_norm": 0.09251661598682404,
322
+ "learning_rate": 3.695652173913043e-05,
323
+ "loss": 0.0039,
324
+ "step": 2250
325
+ },
326
+ {
327
+ "epoch": 0.8,
328
+ "grad_norm": 0.02156330831348896,
329
+ "learning_rate": 3.6666666666666666e-05,
330
+ "loss": 0.004,
331
+ "step": 2300
332
+ },
333
+ {
334
+ "epoch": 0.8173913043478261,
335
+ "grad_norm": 0.30019891262054443,
336
+ "learning_rate": 3.63768115942029e-05,
337
+ "loss": 0.0038,
338
+ "step": 2350
339
+ },
340
+ {
341
+ "epoch": 0.8347826086956521,
342
+ "grad_norm": 0.08380095660686493,
343
+ "learning_rate": 3.6086956521739134e-05,
344
+ "loss": 0.0047,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 0.8521739130434782,
349
+ "grad_norm": 0.17295339703559875,
350
+ "learning_rate": 3.579710144927537e-05,
351
+ "loss": 0.0037,
352
+ "step": 2450
353
+ },
354
+ {
355
+ "epoch": 0.8695652173913043,
356
+ "grad_norm": 0.02843887358903885,
357
+ "learning_rate": 3.5507246376811596e-05,
358
+ "loss": 0.0033,
359
+ "step": 2500
360
+ },
361
+ {
362
+ "epoch": 0.8869565217391304,
363
+ "grad_norm": 0.35363340377807617,
364
+ "learning_rate": 3.521739130434783e-05,
365
+ "loss": 0.0042,
366
+ "step": 2550
367
+ },
368
+ {
369
+ "epoch": 0.9043478260869565,
370
+ "grad_norm": 0.6101410984992981,
371
+ "learning_rate": 3.4927536231884064e-05,
372
+ "loss": 0.0035,
373
+ "step": 2600
374
+ },
375
+ {
376
+ "epoch": 0.9217391304347826,
377
+ "grad_norm": 0.043613508343696594,
378
+ "learning_rate": 3.463768115942029e-05,
379
+ "loss": 0.0041,
380
+ "step": 2650
381
+ },
382
+ {
383
+ "epoch": 0.9391304347826087,
384
+ "grad_norm": 0.12494798004627228,
385
+ "learning_rate": 3.4347826086956526e-05,
386
+ "loss": 0.0038,
387
+ "step": 2700
388
+ },
389
+ {
390
+ "epoch": 0.9565217391304348,
391
+ "grad_norm": 0.03580565005540848,
392
+ "learning_rate": 3.405797101449276e-05,
393
+ "loss": 0.0044,
394
+ "step": 2750
395
+ },
396
+ {
397
+ "epoch": 0.9739130434782609,
398
+ "grad_norm": 0.12163197249174118,
399
+ "learning_rate": 3.376811594202899e-05,
400
+ "loss": 0.0029,
401
+ "step": 2800
402
+ },
403
+ {
404
+ "epoch": 0.991304347826087,
405
+ "grad_norm": 0.09125994145870209,
406
+ "learning_rate": 3.347826086956522e-05,
407
+ "loss": 0.0035,
408
+ "step": 2850
409
+ },
410
+ {
411
+ "epoch": 1.0,
412
+ "eval_loss": 0.0025361417792737484,
413
+ "eval_runtime": 96.0353,
414
+ "eval_samples_per_second": 29.937,
415
+ "eval_steps_per_second": 3.749,
416
+ "step": 2875
417
+ },
418
+ {
419
+ "epoch": 1.008695652173913,
420
+ "grad_norm": 0.08735060691833496,
421
+ "learning_rate": 3.318840579710145e-05,
422
+ "loss": 0.0026,
423
+ "step": 2900
424
+ },
425
+ {
426
+ "epoch": 1.0260869565217392,
427
+ "grad_norm": 0.0311286523938179,
428
+ "learning_rate": 3.289855072463768e-05,
429
+ "loss": 0.0029,
430
+ "step": 2950
431
+ },
432
+ {
433
+ "epoch": 1.0434782608695652,
434
+ "grad_norm": 0.1523689180612564,
435
+ "learning_rate": 3.260869565217392e-05,
436
+ "loss": 0.0044,
437
+ "step": 3000
438
+ },
439
+ {
440
+ "epoch": 1.0608695652173914,
441
+ "grad_norm": 0.09883025288581848,
442
+ "learning_rate": 3.2318840579710144e-05,
443
+ "loss": 0.0029,
444
+ "step": 3050
445
+ },
446
+ {
447
+ "epoch": 1.0782608695652174,
448
+ "grad_norm": 0.20815688371658325,
449
+ "learning_rate": 3.202898550724638e-05,
450
+ "loss": 0.0029,
451
+ "step": 3100
452
+ },
453
+ {
454
+ "epoch": 1.0956521739130434,
455
+ "grad_norm": 0.2510022819042206,
456
+ "learning_rate": 3.173913043478261e-05,
457
+ "loss": 0.0033,
458
+ "step": 3150
459
+ },
460
+ {
461
+ "epoch": 1.1130434782608696,
462
+ "grad_norm": 0.06902216374874115,
463
+ "learning_rate": 3.144927536231884e-05,
464
+ "loss": 0.0031,
465
+ "step": 3200
466
+ },
467
+ {
468
+ "epoch": 1.1304347826086956,
469
+ "grad_norm": 0.5787861347198486,
470
+ "learning_rate": 3.1159420289855074e-05,
471
+ "loss": 0.004,
472
+ "step": 3250
473
+ },
474
+ {
475
+ "epoch": 1.1478260869565218,
476
+ "grad_norm": 0.1607126146554947,
477
+ "learning_rate": 3.086956521739131e-05,
478
+ "loss": 0.0027,
479
+ "step": 3300
480
+ },
481
+ {
482
+ "epoch": 1.1652173913043478,
483
+ "grad_norm": 0.27043744921684265,
484
+ "learning_rate": 3.0579710144927536e-05,
485
+ "loss": 0.0032,
486
+ "step": 3350
487
+ },
488
+ {
489
+ "epoch": 1.182608695652174,
490
+ "grad_norm": 0.040458448231220245,
491
+ "learning_rate": 3.028985507246377e-05,
492
+ "loss": 0.0025,
493
+ "step": 3400
494
+ },
495
+ {
496
+ "epoch": 1.2,
497
+ "grad_norm": 0.070162333548069,
498
+ "learning_rate": 3e-05,
499
+ "loss": 0.0036,
500
+ "step": 3450
501
+ },
502
+ {
503
+ "epoch": 1.2173913043478262,
504
+ "grad_norm": 0.01620602235198021,
505
+ "learning_rate": 2.971014492753623e-05,
506
+ "loss": 0.0023,
507
+ "step": 3500
508
+ },
509
+ {
510
+ "epoch": 1.2347826086956522,
511
+ "grad_norm": 1.2112153768539429,
512
+ "learning_rate": 2.9420289855072462e-05,
513
+ "loss": 0.0024,
514
+ "step": 3550
515
+ },
516
+ {
517
+ "epoch": 1.2521739130434781,
518
+ "grad_norm": 0.009653642773628235,
519
+ "learning_rate": 2.9130434782608696e-05,
520
+ "loss": 0.0021,
521
+ "step": 3600
522
+ },
523
+ {
524
+ "epoch": 1.2695652173913043,
525
+ "grad_norm": 0.14598160982131958,
526
+ "learning_rate": 2.8840579710144927e-05,
527
+ "loss": 0.0028,
528
+ "step": 3650
529
+ },
530
+ {
531
+ "epoch": 1.2869565217391306,
532
+ "grad_norm": 0.07699096202850342,
533
+ "learning_rate": 2.8550724637681158e-05,
534
+ "loss": 0.0021,
535
+ "step": 3700
536
+ },
537
+ {
538
+ "epoch": 1.3043478260869565,
539
+ "grad_norm": 0.27755749225616455,
540
+ "learning_rate": 2.826086956521739e-05,
541
+ "loss": 0.0025,
542
+ "step": 3750
543
+ },
544
+ {
545
+ "epoch": 1.3217391304347825,
546
+ "grad_norm": 0.22564417123794556,
547
+ "learning_rate": 2.7971014492753623e-05,
548
+ "loss": 0.0022,
549
+ "step": 3800
550
+ },
551
+ {
552
+ "epoch": 1.3391304347826087,
553
+ "grad_norm": 0.655219554901123,
554
+ "learning_rate": 2.7681159420289854e-05,
555
+ "loss": 0.0025,
556
+ "step": 3850
557
+ },
558
+ {
559
+ "epoch": 1.3565217391304347,
560
+ "grad_norm": 0.02139280177652836,
561
+ "learning_rate": 2.7391304347826085e-05,
562
+ "loss": 0.0027,
563
+ "step": 3900
564
+ },
565
+ {
566
+ "epoch": 1.373913043478261,
567
+ "grad_norm": 0.0938597247004509,
568
+ "learning_rate": 2.7101449275362322e-05,
569
+ "loss": 0.0029,
570
+ "step": 3950
571
+ },
572
+ {
573
+ "epoch": 1.391304347826087,
574
+ "grad_norm": 0.010128723457455635,
575
+ "learning_rate": 2.6811594202898553e-05,
576
+ "loss": 0.0031,
577
+ "step": 4000
578
+ },
579
+ {
580
+ "epoch": 1.4086956521739131,
581
+ "grad_norm": 0.15920484066009521,
582
+ "learning_rate": 2.6521739130434787e-05,
583
+ "loss": 0.0022,
584
+ "step": 4050
585
+ },
586
+ {
587
+ "epoch": 1.4260869565217391,
588
+ "grad_norm": 0.10766106098890305,
589
+ "learning_rate": 2.6231884057971018e-05,
590
+ "loss": 0.0015,
591
+ "step": 4100
592
+ },
593
+ {
594
+ "epoch": 1.4434782608695653,
595
+ "grad_norm": 0.12829457223415375,
596
+ "learning_rate": 2.594202898550725e-05,
597
+ "loss": 0.0027,
598
+ "step": 4150
599
+ },
600
+ {
601
+ "epoch": 1.4608695652173913,
602
+ "grad_norm": 0.042468324303627014,
603
+ "learning_rate": 2.5652173913043483e-05,
604
+ "loss": 0.0028,
605
+ "step": 4200
606
+ },
607
+ {
608
+ "epoch": 1.4782608695652173,
609
+ "grad_norm": 0.018434317782521248,
610
+ "learning_rate": 2.5362318840579714e-05,
611
+ "loss": 0.0021,
612
+ "step": 4250
613
+ },
614
+ {
615
+ "epoch": 1.4956521739130435,
616
+ "grad_norm": 0.0739726796746254,
617
+ "learning_rate": 2.5072463768115944e-05,
618
+ "loss": 0.0022,
619
+ "step": 4300
620
+ },
621
+ {
622
+ "epoch": 1.5130434782608697,
623
+ "grad_norm": 0.07464097440242767,
624
+ "learning_rate": 2.4782608695652175e-05,
625
+ "loss": 0.0022,
626
+ "step": 4350
627
+ },
628
+ {
629
+ "epoch": 1.5304347826086957,
630
+ "grad_norm": 0.07711721211671829,
631
+ "learning_rate": 2.449275362318841e-05,
632
+ "loss": 0.0024,
633
+ "step": 4400
634
+ },
635
+ {
636
+ "epoch": 1.5478260869565217,
637
+ "grad_norm": 0.5523372888565063,
638
+ "learning_rate": 2.420289855072464e-05,
639
+ "loss": 0.0023,
640
+ "step": 4450
641
+ },
642
+ {
643
+ "epoch": 1.5652173913043477,
644
+ "grad_norm": 0.0014616675907745957,
645
+ "learning_rate": 2.391304347826087e-05,
646
+ "loss": 0.0021,
647
+ "step": 4500
648
+ },
649
+ {
650
+ "epoch": 1.5826086956521739,
651
+ "grad_norm": 0.033656634390354156,
652
+ "learning_rate": 2.36231884057971e-05,
653
+ "loss": 0.0022,
654
+ "step": 4550
655
+ },
656
+ {
657
+ "epoch": 1.6,
658
+ "grad_norm": 0.17268861830234528,
659
+ "learning_rate": 2.3333333333333336e-05,
660
+ "loss": 0.0017,
661
+ "step": 4600
662
+ },
663
+ {
664
+ "epoch": 1.617391304347826,
665
+ "grad_norm": 0.14583924412727356,
666
+ "learning_rate": 2.3043478260869567e-05,
667
+ "loss": 0.0019,
668
+ "step": 4650
669
+ },
670
+ {
671
+ "epoch": 1.634782608695652,
672
+ "grad_norm": 0.020815925672650337,
673
+ "learning_rate": 2.2753623188405797e-05,
674
+ "loss": 0.0026,
675
+ "step": 4700
676
+ },
677
+ {
678
+ "epoch": 1.6521739130434783,
679
+ "grad_norm": 0.1761491745710373,
680
+ "learning_rate": 2.246376811594203e-05,
681
+ "loss": 0.0019,
682
+ "step": 4750
683
+ },
684
+ {
685
+ "epoch": 1.6695652173913045,
686
+ "grad_norm": 0.15895789861679077,
687
+ "learning_rate": 2.2173913043478262e-05,
688
+ "loss": 0.0015,
689
+ "step": 4800
690
+ },
691
+ {
692
+ "epoch": 1.6869565217391305,
693
+ "grad_norm": 0.217234268784523,
694
+ "learning_rate": 2.1884057971014493e-05,
695
+ "loss": 0.0013,
696
+ "step": 4850
697
+ },
698
+ {
699
+ "epoch": 1.7043478260869565,
700
+ "grad_norm": 0.058053504675626755,
701
+ "learning_rate": 2.1594202898550724e-05,
702
+ "loss": 0.0025,
703
+ "step": 4900
704
+ },
705
+ {
706
+ "epoch": 1.7217391304347827,
707
+ "grad_norm": 0.03019527532160282,
708
+ "learning_rate": 2.1304347826086958e-05,
709
+ "loss": 0.0025,
710
+ "step": 4950
711
+ },
712
+ {
713
+ "epoch": 1.7391304347826086,
714
+ "grad_norm": 0.19927392899990082,
715
+ "learning_rate": 2.101449275362319e-05,
716
+ "loss": 0.0026,
717
+ "step": 5000
718
+ },
719
+ {
720
+ "epoch": 1.7565217391304349,
721
+ "grad_norm": 0.046536799520254135,
722
+ "learning_rate": 2.072463768115942e-05,
723
+ "loss": 0.002,
724
+ "step": 5050
725
+ },
726
+ {
727
+ "epoch": 1.7739130434782608,
728
+ "grad_norm": 0.3650865852832794,
729
+ "learning_rate": 2.0434782608695654e-05,
730
+ "loss": 0.0021,
731
+ "step": 5100
732
+ },
733
+ {
734
+ "epoch": 1.7913043478260868,
735
+ "grad_norm": 0.12650315463542938,
736
+ "learning_rate": 2.0144927536231885e-05,
737
+ "loss": 0.0015,
738
+ "step": 5150
739
+ },
740
+ {
741
+ "epoch": 1.808695652173913,
742
+ "grad_norm": 0.01490619033575058,
743
+ "learning_rate": 1.985507246376812e-05,
744
+ "loss": 0.0016,
745
+ "step": 5200
746
+ },
747
+ {
748
+ "epoch": 1.8260869565217392,
749
+ "grad_norm": 0.09603610634803772,
750
+ "learning_rate": 1.956521739130435e-05,
751
+ "loss": 0.002,
752
+ "step": 5250
753
+ },
754
+ {
755
+ "epoch": 1.8434782608695652,
756
+ "grad_norm": 0.02328038401901722,
757
+ "learning_rate": 1.927536231884058e-05,
758
+ "loss": 0.0016,
759
+ "step": 5300
760
+ },
761
+ {
762
+ "epoch": 1.8608695652173912,
763
+ "grad_norm": 0.011464759707450867,
764
+ "learning_rate": 1.8985507246376814e-05,
765
+ "loss": 0.0017,
766
+ "step": 5350
767
+ },
768
+ {
769
+ "epoch": 1.8782608695652174,
770
+ "grad_norm": 0.08598850667476654,
771
+ "learning_rate": 1.8695652173913045e-05,
772
+ "loss": 0.0014,
773
+ "step": 5400
774
+ },
775
+ {
776
+ "epoch": 1.8956521739130436,
777
+ "grad_norm": 0.07689868658781052,
778
+ "learning_rate": 1.8405797101449276e-05,
779
+ "loss": 0.0016,
780
+ "step": 5450
781
+ },
782
+ {
783
+ "epoch": 1.9130434782608696,
784
+ "grad_norm": 0.1737821102142334,
785
+ "learning_rate": 1.8115942028985507e-05,
786
+ "loss": 0.0014,
787
+ "step": 5500
788
+ },
789
+ {
790
+ "epoch": 1.9304347826086956,
791
+ "grad_norm": 0.02161916345357895,
792
+ "learning_rate": 1.782608695652174e-05,
793
+ "loss": 0.0011,
794
+ "step": 5550
795
+ },
796
+ {
797
+ "epoch": 1.9478260869565216,
798
+ "grad_norm": 0.499637633562088,
799
+ "learning_rate": 1.7536231884057972e-05,
800
+ "loss": 0.0019,
801
+ "step": 5600
802
+ },
803
+ {
804
+ "epoch": 1.9652173913043478,
805
+ "grad_norm": 0.1786130666732788,
806
+ "learning_rate": 1.7246376811594203e-05,
807
+ "loss": 0.0012,
808
+ "step": 5650
809
+ },
810
+ {
811
+ "epoch": 1.982608695652174,
812
+ "grad_norm": 0.0513494610786438,
813
+ "learning_rate": 1.6956521739130433e-05,
814
+ "loss": 0.0016,
815
+ "step": 5700
816
+ },
817
+ {
818
+ "epoch": 2.0,
819
+ "grad_norm": 0.06775401532649994,
820
+ "learning_rate": 1.6666666666666667e-05,
821
+ "loss": 0.0013,
822
+ "step": 5750
823
+ },
824
+ {
825
+ "epoch": 2.0,
826
+ "eval_loss": 0.0012920453445985913,
827
+ "eval_runtime": 96.4408,
828
+ "eval_samples_per_second": 29.811,
829
+ "eval_steps_per_second": 3.733,
830
+ "step": 5750
831
+ },
832
+ {
833
+ "epoch": 2.017391304347826,
834
+ "grad_norm": 0.03558877110481262,
835
+ "learning_rate": 1.6376811594202898e-05,
836
+ "loss": 0.001,
837
+ "step": 5800
838
+ },
839
+ {
840
+ "epoch": 2.034782608695652,
841
+ "grad_norm": 0.020766105502843857,
842
+ "learning_rate": 1.608695652173913e-05,
843
+ "loss": 0.0012,
844
+ "step": 5850
845
+ },
846
+ {
847
+ "epoch": 2.0521739130434784,
848
+ "grad_norm": 0.00028670133906416595,
849
+ "learning_rate": 1.5797101449275363e-05,
850
+ "loss": 0.0015,
851
+ "step": 5900
852
+ },
853
+ {
854
+ "epoch": 2.0695652173913044,
855
+ "grad_norm": 0.10913717746734619,
856
+ "learning_rate": 1.5507246376811597e-05,
857
+ "loss": 0.0017,
858
+ "step": 5950
859
+ },
860
+ {
861
+ "epoch": 2.0869565217391304,
862
+ "grad_norm": 0.006257515866309404,
863
+ "learning_rate": 1.5217391304347828e-05,
864
+ "loss": 0.001,
865
+ "step": 6000
866
+ },
867
+ {
868
+ "epoch": 2.1043478260869564,
869
+ "grad_norm": 0.0009001060971058905,
870
+ "learning_rate": 1.4927536231884059e-05,
871
+ "loss": 0.0009,
872
+ "step": 6050
873
+ },
874
+ {
875
+ "epoch": 2.121739130434783,
876
+ "grad_norm": 0.04532545059919357,
877
+ "learning_rate": 1.4637681159420291e-05,
878
+ "loss": 0.0011,
879
+ "step": 6100
880
+ },
881
+ {
882
+ "epoch": 2.139130434782609,
883
+ "grad_norm": 0.055269885808229446,
884
+ "learning_rate": 1.4347826086956522e-05,
885
+ "loss": 0.001,
886
+ "step": 6150
887
+ },
888
+ {
889
+ "epoch": 2.1565217391304348,
890
+ "grad_norm": 0.5711213946342468,
891
+ "learning_rate": 1.4057971014492755e-05,
892
+ "loss": 0.0018,
893
+ "step": 6200
894
+ },
895
+ {
896
+ "epoch": 2.1739130434782608,
897
+ "grad_norm": 0.029410233721137047,
898
+ "learning_rate": 1.3768115942028985e-05,
899
+ "loss": 0.0012,
900
+ "step": 6250
901
+ },
902
+ {
903
+ "epoch": 2.1913043478260867,
904
+ "grad_norm": 0.022352011874318123,
905
+ "learning_rate": 1.3478260869565218e-05,
906
+ "loss": 0.001,
907
+ "step": 6300
908
+ },
909
+ {
910
+ "epoch": 2.208695652173913,
911
+ "grad_norm": 0.04188627377152443,
912
+ "learning_rate": 1.318840579710145e-05,
913
+ "loss": 0.0016,
914
+ "step": 6350
915
+ },
916
+ {
917
+ "epoch": 2.226086956521739,
918
+ "grad_norm": 0.11063901335000992,
919
+ "learning_rate": 1.2898550724637681e-05,
920
+ "loss": 0.0011,
921
+ "step": 6400
922
+ },
923
+ {
924
+ "epoch": 2.243478260869565,
925
+ "grad_norm": 0.01330894511193037,
926
+ "learning_rate": 1.2608695652173914e-05,
927
+ "loss": 0.0013,
928
+ "step": 6450
929
+ },
930
+ {
931
+ "epoch": 2.260869565217391,
932
+ "grad_norm": 0.05966261401772499,
933
+ "learning_rate": 1.2318840579710146e-05,
934
+ "loss": 0.0011,
935
+ "step": 6500
936
+ },
937
+ {
938
+ "epoch": 2.2782608695652176,
939
+ "grad_norm": 0.14330358803272247,
940
+ "learning_rate": 1.2028985507246379e-05,
941
+ "loss": 0.0007,
942
+ "step": 6550
943
+ },
944
+ {
945
+ "epoch": 2.2956521739130435,
946
+ "grad_norm": 0.0212959386408329,
947
+ "learning_rate": 1.173913043478261e-05,
948
+ "loss": 0.0011,
949
+ "step": 6600
950
+ },
951
+ {
952
+ "epoch": 2.3130434782608695,
953
+ "grad_norm": 0.20731711387634277,
954
+ "learning_rate": 1.1449275362318842e-05,
955
+ "loss": 0.0013,
956
+ "step": 6650
957
+ },
958
+ {
959
+ "epoch": 2.3304347826086955,
960
+ "grad_norm": 0.08254529535770416,
961
+ "learning_rate": 1.1159420289855073e-05,
962
+ "loss": 0.0012,
963
+ "step": 6700
964
+ },
965
+ {
966
+ "epoch": 2.3478260869565215,
967
+ "grad_norm": 0.020656369626522064,
968
+ "learning_rate": 1.0869565217391305e-05,
969
+ "loss": 0.0012,
970
+ "step": 6750
971
+ },
972
+ {
973
+ "epoch": 2.365217391304348,
974
+ "grad_norm": 0.036002080887556076,
975
+ "learning_rate": 1.0579710144927536e-05,
976
+ "loss": 0.0018,
977
+ "step": 6800
978
+ },
979
+ {
980
+ "epoch": 2.382608695652174,
981
+ "grad_norm": 0.041759081184864044,
982
+ "learning_rate": 1.0289855072463768e-05,
983
+ "loss": 0.0013,
984
+ "step": 6850
985
+ },
986
+ {
987
+ "epoch": 2.4,
988
+ "grad_norm": 0.11052204668521881,
989
+ "learning_rate": 1e-05,
990
+ "loss": 0.0011,
991
+ "step": 6900
992
+ },
993
+ {
994
+ "epoch": 2.417391304347826,
995
+ "grad_norm": 0.058441516011953354,
996
+ "learning_rate": 9.710144927536233e-06,
997
+ "loss": 0.0017,
998
+ "step": 6950
999
+ },
1000
+ {
1001
+ "epoch": 2.4347826086956523,
1002
+ "grad_norm": 0.05065017566084862,
1003
+ "learning_rate": 9.420289855072464e-06,
1004
+ "loss": 0.001,
1005
+ "step": 7000
1006
+ },
1007
+ {
1008
+ "epoch": 2.4521739130434783,
1009
+ "grad_norm": 0.32241326570510864,
1010
+ "learning_rate": 9.130434782608697e-06,
1011
+ "loss": 0.0014,
1012
+ "step": 7050
1013
+ },
1014
+ {
1015
+ "epoch": 2.4695652173913043,
1016
+ "grad_norm": 0.0022826960776001215,
1017
+ "learning_rate": 8.840579710144927e-06,
1018
+ "loss": 0.0014,
1019
+ "step": 7100
1020
+ },
1021
+ {
1022
+ "epoch": 2.4869565217391303,
1023
+ "grad_norm": 0.07568530738353729,
1024
+ "learning_rate": 8.55072463768116e-06,
1025
+ "loss": 0.0012,
1026
+ "step": 7150
1027
+ },
1028
+ {
1029
+ "epoch": 2.5043478260869563,
1030
+ "grad_norm": 0.0877290740609169,
1031
+ "learning_rate": 8.26086956521739e-06,
1032
+ "loss": 0.001,
1033
+ "step": 7200
1034
+ },
1035
+ {
1036
+ "epoch": 2.5217391304347827,
1037
+ "grad_norm": 0.015493788756430149,
1038
+ "learning_rate": 7.971014492753623e-06,
1039
+ "loss": 0.0011,
1040
+ "step": 7250
1041
+ },
1042
+ {
1043
+ "epoch": 2.5391304347826087,
1044
+ "grad_norm": 0.060608845204114914,
1045
+ "learning_rate": 7.681159420289856e-06,
1046
+ "loss": 0.0013,
1047
+ "step": 7300
1048
+ },
1049
+ {
1050
+ "epoch": 2.5565217391304347,
1051
+ "grad_norm": 0.014519167132675648,
1052
+ "learning_rate": 7.391304347826088e-06,
1053
+ "loss": 0.0007,
1054
+ "step": 7350
1055
+ },
1056
+ {
1057
+ "epoch": 2.573913043478261,
1058
+ "grad_norm": 0.09587720036506653,
1059
+ "learning_rate": 7.10144927536232e-06,
1060
+ "loss": 0.0013,
1061
+ "step": 7400
1062
+ },
1063
+ {
1064
+ "epoch": 2.591304347826087,
1065
+ "grad_norm": 0.29099398851394653,
1066
+ "learning_rate": 6.811594202898551e-06,
1067
+ "loss": 0.0013,
1068
+ "step": 7450
1069
+ },
1070
+ {
1071
+ "epoch": 2.608695652173913,
1072
+ "grad_norm": 0.0012901765294373035,
1073
+ "learning_rate": 6.521739130434783e-06,
1074
+ "loss": 0.0009,
1075
+ "step": 7500
1076
+ },
1077
+ {
1078
+ "epoch": 2.626086956521739,
1079
+ "grad_norm": 0.013467655517160892,
1080
+ "learning_rate": 6.231884057971015e-06,
1081
+ "loss": 0.0015,
1082
+ "step": 7550
1083
+ },
1084
+ {
1085
+ "epoch": 2.643478260869565,
1086
+ "grad_norm": 0.023615246638655663,
1087
+ "learning_rate": 5.942028985507247e-06,
1088
+ "loss": 0.0012,
1089
+ "step": 7600
1090
+ },
1091
+ {
1092
+ "epoch": 2.660869565217391,
1093
+ "grad_norm": 0.0002624622720759362,
1094
+ "learning_rate": 5.652173913043479e-06,
1095
+ "loss": 0.0011,
1096
+ "step": 7650
1097
+ },
1098
+ {
1099
+ "epoch": 2.6782608695652175,
1100
+ "grad_norm": 0.019460059702396393,
1101
+ "learning_rate": 5.36231884057971e-06,
1102
+ "loss": 0.0008,
1103
+ "step": 7700
1104
+ },
1105
+ {
1106
+ "epoch": 2.6956521739130435,
1107
+ "grad_norm": 0.13803550601005554,
1108
+ "learning_rate": 5.072463768115943e-06,
1109
+ "loss": 0.0012,
1110
+ "step": 7750
1111
+ },
1112
+ {
1113
+ "epoch": 2.7130434782608694,
1114
+ "grad_norm": 0.05893932282924652,
1115
+ "learning_rate": 4.782608695652174e-06,
1116
+ "loss": 0.0008,
1117
+ "step": 7800
1118
+ },
1119
+ {
1120
+ "epoch": 2.730434782608696,
1121
+ "grad_norm": 0.05466777831315994,
1122
+ "learning_rate": 4.492753623188406e-06,
1123
+ "loss": 0.0012,
1124
+ "step": 7850
1125
+ },
1126
+ {
1127
+ "epoch": 2.747826086956522,
1128
+ "grad_norm": 0.12380136549472809,
1129
+ "learning_rate": 4.202898550724638e-06,
1130
+ "loss": 0.0012,
1131
+ "step": 7900
1132
+ },
1133
+ {
1134
+ "epoch": 2.765217391304348,
1135
+ "grad_norm": 0.0890166386961937,
1136
+ "learning_rate": 3.91304347826087e-06,
1137
+ "loss": 0.0009,
1138
+ "step": 7950
1139
+ },
1140
+ {
1141
+ "epoch": 2.782608695652174,
1142
+ "grad_norm": 0.008756608702242374,
1143
+ "learning_rate": 3.6231884057971017e-06,
1144
+ "loss": 0.0011,
1145
+ "step": 8000
1146
+ },
1147
+ {
1148
+ "epoch": 2.8,
1149
+ "grad_norm": 0.0008163052843883634,
1150
+ "learning_rate": 3.3333333333333333e-06,
1151
+ "loss": 0.0007,
1152
+ "step": 8050
1153
+ },
1154
+ {
1155
+ "epoch": 2.8173913043478263,
1156
+ "grad_norm": 0.004910512827336788,
1157
+ "learning_rate": 3.0434782608695654e-06,
1158
+ "loss": 0.0011,
1159
+ "step": 8100
1160
+ },
1161
+ {
1162
+ "epoch": 2.8347826086956522,
1163
+ "grad_norm": 0.11592869460582733,
1164
+ "learning_rate": 2.753623188405797e-06,
1165
+ "loss": 0.0007,
1166
+ "step": 8150
1167
+ },
1168
+ {
1169
+ "epoch": 2.8521739130434782,
1170
+ "grad_norm": 0.0014929580502212048,
1171
+ "learning_rate": 2.463768115942029e-06,
1172
+ "loss": 0.0013,
1173
+ "step": 8200
1174
+ },
1175
+ {
1176
+ "epoch": 2.869565217391304,
1177
+ "grad_norm": 0.22627107799053192,
1178
+ "learning_rate": 2.173913043478261e-06,
1179
+ "loss": 0.0006,
1180
+ "step": 8250
1181
+ },
1182
+ {
1183
+ "epoch": 2.8869565217391306,
1184
+ "grad_norm": 0.0002495117951184511,
1185
+ "learning_rate": 1.884057971014493e-06,
1186
+ "loss": 0.0007,
1187
+ "step": 8300
1188
+ },
1189
+ {
1190
+ "epoch": 2.9043478260869566,
1191
+ "grad_norm": 0.01157305110245943,
1192
+ "learning_rate": 1.5942028985507246e-06,
1193
+ "loss": 0.0008,
1194
+ "step": 8350
1195
+ },
1196
+ {
1197
+ "epoch": 2.9217391304347826,
1198
+ "grad_norm": 0.03670734167098999,
1199
+ "learning_rate": 1.3043478260869564e-06,
1200
+ "loss": 0.0011,
1201
+ "step": 8400
1202
+ },
1203
+ {
1204
+ "epoch": 2.9391304347826086,
1205
+ "grad_norm": 0.03576314449310303,
1206
+ "learning_rate": 1.0144927536231885e-06,
1207
+ "loss": 0.0008,
1208
+ "step": 8450
1209
+ },
1210
+ {
1211
+ "epoch": 2.9565217391304346,
1212
+ "grad_norm": 0.03780396282672882,
1213
+ "learning_rate": 7.246376811594203e-07,
1214
+ "loss": 0.0008,
1215
+ "step": 8500
1216
+ },
1217
+ {
1218
+ "epoch": 2.973913043478261,
1219
+ "grad_norm": 0.015078218653798103,
1220
+ "learning_rate": 4.347826086956522e-07,
1221
+ "loss": 0.0008,
1222
+ "step": 8550
1223
+ },
1224
+ {
1225
+ "epoch": 2.991304347826087,
1226
+ "grad_norm": 0.0382976308465004,
1227
+ "learning_rate": 1.4492753623188405e-07,
1228
+ "loss": 0.0012,
1229
+ "step": 8600
1230
+ },
1231
+ {
1232
+ "epoch": 3.0,
1233
+ "eval_loss": 0.0009732216713018715,
1234
+ "eval_runtime": 96.1116,
1235
+ "eval_samples_per_second": 29.913,
1236
+ "eval_steps_per_second": 3.746,
1237
+ "step": 8625
1238
+ }
1239
+ ],
1240
+ "logging_steps": 50,
1241
+ "max_steps": 8625,
1242
+ "num_input_tokens_seen": 0,
1243
+ "num_train_epochs": 3,
1244
+ "save_steps": 500,
1245
+ "total_flos": 1.802869232451379e+16,
1246
+ "train_batch_size": 8,
1247
+ "trial_name": null,
1248
+ "trial_params": null
1249
+ }
checkpoint-8625/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee1502bb3f8db9acd55a79b31f914b1fc26b999623288aaacdcb1ae8b8de2b9
3
+ size 5048
checkpoint-8625/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/codebert-base",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
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
+ "id2label": {
14
+ "0": "SAFE",
15
+ "1": "VULN"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "SAFE": 0,
21
+ "VULN": 1
22
+ },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "roberta",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "output_past": true,
29
+ "pad_token_id": 1,
30
+ "position_embedding_type": "absolute",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.40.1",
33
+ "type_vocab_size": 1,
34
+ "use_cache": true,
35
+ "vocab_size": 50265
36
+ }
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 sha256:764d780f015cce8f139f809a3674e87207e82baa9337207bffc204b2ecb44f7e
3
+ size 496250232
runs/May10_06-12-27_3c19404100c4/events.out.tfevents.1746857552.3c19404100c4.7029.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24d35a6d0c926d21be3579993d403f44947f54b2d1e5c57a21b9fcf57ba436d8
3
+ size 42289
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
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
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee1502bb3f8db9acd55a79b31f914b1fc26b999623288aaacdcb1ae8b8de2b9
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff