kmchiti commited on
Commit
73075ff
1 Parent(s): 93c9bc7

Training in progress, step 45000, checkpoint

Browse files
tmp-spec-checkpoint-45000/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_bias": false,
3
+ "attention_dropout": 0.0,
4
+ "bos_token_id": 2,
5
+ "eos_token_id": 3,
6
+ "fused_bias_fc": false,
7
+ "fused_dropout_add_ln": false,
8
+ "fused_mlp": false,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 512,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 1024,
13
+ "max_position_embeddings": 2048,
14
+ "max_seq_length": 64,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 8,
18
+ "num_hidden_layers": 12,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "residual_in_fp32": true,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "transformers_version": "4.44.2",
27
+ "use_cache": true,
28
+ "use_flash_attn": true,
29
+ "vocab_size": 500
30
+ }
tmp-spec-checkpoint-45000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c7e9a2f8f28433a3ee2f71a32b02bb881b10d099a95ec1c1ae0d5c7707e97c
3
+ size 63988303
tmp-spec-checkpoint-45000/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<bos>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<eos>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tmp-spec-checkpoint-45000/tokenizer.json ADDED
@@ -0,0 +1,1079 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<unk>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<pad>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<bos>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<eos>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": null,
44
+ "pre_tokenizer": null,
45
+ "post_processor": {
46
+ "type": "TemplateProcessing",
47
+ "single": [
48
+ {
49
+ "SpecialToken": {
50
+ "id": "<bos>",
51
+ "type_id": 0
52
+ }
53
+ },
54
+ {
55
+ "Sequence": {
56
+ "id": "A",
57
+ "type_id": 0
58
+ }
59
+ },
60
+ {
61
+ "SpecialToken": {
62
+ "id": "<eos>",
63
+ "type_id": 0
64
+ }
65
+ }
66
+ ],
67
+ "pair": [
68
+ {
69
+ "Sequence": {
70
+ "id": "A",
71
+ "type_id": 0
72
+ }
73
+ },
74
+ {
75
+ "Sequence": {
76
+ "id": "B",
77
+ "type_id": 1
78
+ }
79
+ }
80
+ ],
81
+ "special_tokens": {
82
+ "<bos>": {
83
+ "id": "<bos>",
84
+ "ids": [
85
+ 2
86
+ ],
87
+ "tokens": [
88
+ "<bos>"
89
+ ]
90
+ },
91
+ "<eos>": {
92
+ "id": "<eos>",
93
+ "ids": [
94
+ 3
95
+ ],
96
+ "tokens": [
97
+ "<eos>"
98
+ ]
99
+ }
100
+ }
101
+ },
102
+ "decoder": {
103
+ "type": "BPEDecoder",
104
+ "suffix": "</w>"
105
+ },
106
+ "model": {
107
+ "type": "BPE",
108
+ "dropout": 0.1,
109
+ "unk_token": "<unk>",
110
+ "continuing_subword_prefix": null,
111
+ "end_of_word_suffix": null,
112
+ "fuse_unk": false,
113
+ "byte_fallback": false,
114
+ "ignore_merges": false,
115
+ "vocab": {
116
+ "<unk>": 0,
117
+ "<pad>": 1,
118
+ "<bos>": 2,
119
+ "<eos>": 3,
120
+ "#": 4,
121
+ "(": 5,
122
+ ")": 6,
123
+ "+": 7,
124
+ "-": 8,
125
+ ".": 9,
126
+ "/": 10,
127
+ "1": 11,
128
+ "2": 12,
129
+ "3": 13,
130
+ "4": 14,
131
+ "5": 15,
132
+ "6": 16,
133
+ "7": 17,
134
+ "8": 18,
135
+ "9": 19,
136
+ "=": 20,
137
+ "@": 21,
138
+ "B": 22,
139
+ "C": 23,
140
+ "F": 24,
141
+ "H": 25,
142
+ "I": 26,
143
+ "N": 27,
144
+ "O": 28,
145
+ "P": 29,
146
+ "S": 30,
147
+ "[": 31,
148
+ "]": 32,
149
+ "c": 33,
150
+ "e": 34,
151
+ "i": 35,
152
+ "l": 36,
153
+ "n": 37,
154
+ "o": 38,
155
+ "r": 39,
156
+ "s": 40,
157
+ "CC": 41,
158
+ "O)": 42,
159
+ "(C": 43,
160
+ "=O)": 44,
161
+ "(=O)": 45,
162
+ "[C": 46,
163
+ "[C@": 47,
164
+ "H]": 48,
165
+ "cc": 49,
166
+ ")C": 50,
167
+ "[C@H]": 51,
168
+ "[C@@": 52,
169
+ "c1": 53,
170
+ "C(=O)": 54,
171
+ "[C@@H]": 55,
172
+ "(C)": 56,
173
+ "(=O)N": 57,
174
+ "NC(=O)": 58,
175
+ "CCC": 59,
176
+ "c2": 60,
177
+ "N(C": 61,
178
+ "F)": 62,
179
+ "1CC": 63,
180
+ "c1cc": 64,
181
+ "2)": 65,
182
+ "1C": 66,
183
+ "(C)C": 67,
184
+ "N(C(=O)": 68,
185
+ "(F)": 69,
186
+ "(C(=O)N": 70,
187
+ "cn": 71,
188
+ "2CC": 72,
189
+ "(CC": 73,
190
+ ")C1": 74,
191
+ "2C": 75,
192
+ "c3": 76,
193
+ "CC1": 77,
194
+ "OC": 78,
195
+ "C(=O)N": 79,
196
+ "=C": 80,
197
+ "c2cc": 81,
198
+ "c(": 82,
199
+ "NC(=O)C": 83,
200
+ "n1": 84,
201
+ "[C@H](": 85,
202
+ "[n": 86,
203
+ "[nH]": 87,
204
+ "[C@@H](": 88,
205
+ "2)C1": 89,
206
+ "CC(=O)N": 90,
207
+ "3)": 91,
208
+ "CO": 92,
209
+ "1CCC": 93,
210
+ "c(C": 94,
211
+ "C[C@H]": 95,
212
+ "c1n": 96,
213
+ "C[C@@H]": 97,
214
+ "l)": 98,
215
+ "[C@]": 99,
216
+ "N(C)C": 100,
217
+ "CCCC": 101,
218
+ "[C@@]": 102,
219
+ "(N": 103,
220
+ "Cc1cc": 104,
221
+ "2CCC": 105,
222
+ "cc1": 106,
223
+ "nn": 107,
224
+ "[C@H]1C": 108,
225
+ ")C2)": 109,
226
+ "CC(C)": 110,
227
+ "CCO": 111,
228
+ "O=C": 112,
229
+ "N(C(=O)C": 113,
230
+ "O)C": 114,
231
+ "c3cc": 115,
232
+ "c(C(=O)N": 116,
233
+ "(CNC(=O)": 117,
234
+ "[C@@H]1C": 118,
235
+ "CCN": 119,
236
+ "1)": 120,
237
+ "[C@H]2C": 121,
238
+ "c(C)": 122,
239
+ "ccc1": 123,
240
+ "c1cn": 124,
241
+ "3CC": 125,
242
+ "F)C": 126,
243
+ "[C@H](C)": 127,
244
+ "(C)(C)C": 128,
245
+ "2)C": 129,
246
+ "[C@@H]2C": 130,
247
+ "[C@@H](C)": 131,
248
+ "Br": 132,
249
+ "(F)(F)": 133,
250
+ "[C@H]1": 134,
251
+ "3C": 135,
252
+ "cs": 136,
253
+ "c(Cl)": 137,
254
+ "1)C": 138,
255
+ "N(C)C(=O)": 139,
256
+ "[C@H]1CC": 140,
257
+ "(O)": 141,
258
+ "c(F)": 142,
259
+ "(CC(=O)N": 143,
260
+ ")CC": 144,
261
+ "[C@@H]1CC": 145,
262
+ "c2cccc": 146,
263
+ "1C(=O)": 147,
264
+ "[C@H](C": 148,
265
+ "C=C": 149,
266
+ "=CC": 150,
267
+ "CCC1": 151,
268
+ "C1": 152,
269
+ "ncc": 153,
270
+ "[C@@H]1": 154,
271
+ "[C@@H](C": 155,
272
+ "[C@H]2CC": 156,
273
+ "Br)": 157,
274
+ "(NC(=O)": 158,
275
+ "OCC": 159,
276
+ "CN": 160,
277
+ "[C@H](C)C": 161,
278
+ "3)C": 162,
279
+ "3)C2)": 163,
280
+ "c4": 164,
281
+ "c2cn": 165,
282
+ "Cc1n": 166,
283
+ "(C)CC": 167,
284
+ "2)CC1": 168,
285
+ "S(=O)": 169,
286
+ ")C(=O)N": 170,
287
+ "(Cl)": 171,
288
+ "=N": 172,
289
+ "[C@H](NC(=O)": 173,
290
+ "[C@]1": 174,
291
+ "c1C": 175,
292
+ "[C@@H](C)C": 176,
293
+ "O=C(N": 177,
294
+ "(C)C)": 178,
295
+ "[C@H](C(=O)N": 179,
296
+ "[C@@H](NC(=O)": 180,
297
+ "(N)": 181,
298
+ "c2)": 182,
299
+ "C#": 183,
300
+ "[C@@H]2CC": 184,
301
+ "C(=O)N1CC": 185,
302
+ "c[nH]": 186,
303
+ "[C@H]2": 187,
304
+ "[C@@]1": 188,
305
+ "c1cccc": 189,
306
+ "n1cc": 190,
307
+ "c(O)": 191,
308
+ "OC)": 192,
309
+ "#N": 193,
310
+ "co": 194,
311
+ "nc1": 195,
312
+ "[C@@H](C(=O)N": 196,
313
+ "3CCC": 197,
314
+ "NC": 198,
315
+ "n2": 199,
316
+ "(C)(C)": 200,
317
+ "SC": 201,
318
+ "c1ccccc1": 202,
319
+ "[C@@H]2": 203,
320
+ "c2C": 204,
321
+ "(CCC": 205,
322
+ "c2n": 206,
323
+ "[N": 207,
324
+ "N1C(=O)": 208,
325
+ "(F)F)": 209,
326
+ "COC": 210,
327
+ "NC(=O)c1cc": 211,
328
+ "N(C(=O)c2cc": 212,
329
+ "3)CC": 213,
330
+ "N1CC": 214,
331
+ "S(=O)(=O)": 215,
332
+ "Cc1": 216,
333
+ "(F)(F)F)": 217,
334
+ "2C(=O)": 218,
335
+ "2(CC": 219,
336
+ "(F)C": 220,
337
+ "2(C": 221,
338
+ "=O": 222,
339
+ "cc2": 223,
340
+ "+]": 224,
341
+ "COc1cc": 225,
342
+ "-]": 226,
343
+ "[C@H](O)": 227,
344
+ "F)C1": 228,
345
+ "n(C)": 229,
346
+ "1CC1": 230,
347
+ "[C@@H]1CCC": 231,
348
+ "[N+]": 232,
349
+ "c(N": 233,
350
+ "cn1": 234,
351
+ "c3cccc": 235,
352
+ "[C@H]3": 236,
353
+ "C[C@@H]1C": 237,
354
+ ")C(=O)": 238,
355
+ "(N)=O)": 239,
356
+ "[C@H]1CCC": 240,
357
+ "c1C(=O)N": 241,
358
+ "(C(=O)N2CC": 242,
359
+ "CC(=O)N1CC": 243,
360
+ "CS": 244,
361
+ "c(Br)": 245,
362
+ "[C@@H]3": 246,
363
+ "s1": 247,
364
+ "C[C@H]1C": 248,
365
+ "2CC2)": 249,
366
+ "[C@H](CC": 250,
367
+ "c1ncc": 251,
368
+ "nn1": 252,
369
+ "[C@@H](O)": 253,
370
+ "N(C(=O)CC": 254,
371
+ "[C@H](CNC(=O)": 255,
372
+ "[O": 256,
373
+ "[O-]": 257,
374
+ "N2C(=O)": 258,
375
+ "COC(=O)": 259,
376
+ "[C@](C)": 260,
377
+ "C=": 261,
378
+ "[C@H](O)C": 262,
379
+ "c2)C1": 263,
380
+ "o1": 264,
381
+ "3)C1": 265,
382
+ "NC(=O)C1": 266,
383
+ "CCN1C(=O)": 267,
384
+ "O=C(C": 268,
385
+ "#N)": 269,
386
+ "[C@@](C)": 270,
387
+ "[C@@H](O)C": 271,
388
+ "(CO)": 272,
389
+ "[C@@H](CC": 273,
390
+ "(=O)[O-]": 274,
391
+ "[N+](=O)[O-]": 275,
392
+ "c1)": 276,
393
+ "CCC(=O)N": 277,
394
+ "4)C": 278,
395
+ "[C@]2": 279,
396
+ "(Br)": 280,
397
+ "CC2": 281,
398
+ "(=O)=O)": 282,
399
+ "[nH]1": 283,
400
+ "cc1C": 284,
401
+ "O1": 285,
402
+ "[C@@]2": 286,
403
+ "C=CC": 287,
404
+ "N(": 288,
405
+ "c(-": 289,
406
+ "c3cn": 290,
407
+ "[C@H]3C": 291,
408
+ "CC(C)(C)C": 292,
409
+ "(NC(=O)C": 293,
410
+ "[C@H](NC(=O)C": 294,
411
+ "cc1C(=O)N": 295,
412
+ "2)CC": 296,
413
+ "/C=C": 297,
414
+ "2)c1": 298,
415
+ "(CC)": 299,
416
+ "/C=C/": 300,
417
+ "[C@@H]2CCC": 301,
418
+ "[C@H](C)C(=O)N": 302,
419
+ "c(=N": 303,
420
+ "[C@@H](CNC(=O)": 304,
421
+ "NC(=O)CC": 305,
422
+ "(C(=O)NC": 306,
423
+ "[C@@H](NC(=O)C": 307,
424
+ "[C@H]2CCC": 308,
425
+ "4)": 309,
426
+ "CC(C)(C)": 310,
427
+ "c2ncc": 311,
428
+ "c2ccccc2": 312,
429
+ "(CNC(=O)C": 313,
430
+ "N=": 314,
431
+ "(F)(F)C": 315,
432
+ "N(CC": 316,
433
+ "CC(C)C": 317,
434
+ "OC1": 318,
435
+ "cccc": 319,
436
+ "n3": 320,
437
+ "CCOCC": 321,
438
+ "(-": 322,
439
+ "(F)F": 323,
440
+ ")C2": 324,
441
+ "c3C": 325,
442
+ "C[C@@H]1CC": 326,
443
+ "c(C(=O)N2CC": 327,
444
+ "CC1)": 328,
445
+ "Cc1cn": 329,
446
+ "CCc1cc": 330,
447
+ "[C@H]3CC": 331,
448
+ "c(F)cc": 332,
449
+ "c3n": 333,
450
+ "[C@@H](C)C(=O)N": 334,
451
+ "C[C@H]1CC": 335,
452
+ "[N+](=O)[O-])": 336,
453
+ "n2cc": 337,
454
+ "(C)(C)C)": 338,
455
+ "CCN(C(=O)": 339,
456
+ "[C@@H]3C": 340,
457
+ "(C)CCC": 341,
458
+ "C(=O)NC": 342,
459
+ "ccc2": 343,
460
+ "nc2": 344,
461
+ "=CC(=O)N": 345,
462
+ "3(CC": 346,
463
+ "4CC": 347,
464
+ "1)N": 348,
465
+ "S(=O)(=O)N": 349,
466
+ "N2CC": 350,
467
+ "(O)C": 351,
468
+ "cnc1": 352,
469
+ "S(C)": 353,
470
+ "1)C2": 354,
471
+ "CCNC(=O)": 355,
472
+ "l)C": 356,
473
+ "Cn1": 357,
474
+ "N(C(=O)c3cc": 358,
475
+ "[C@H]1C(=O)N": 359,
476
+ "n2)": 360,
477
+ "NC(=O)c2cc": 361,
478
+ "c3ccccc3": 362,
479
+ "3CC3)": 363,
480
+ "c2nn": 364,
481
+ "2)C1)": 365,
482
+ "[C@@H]1C(=O)N": 366,
483
+ "(F)(F)F": 367,
484
+ "COCC": 368,
485
+ "CC2)": 369,
486
+ "CCCCC": 370,
487
+ "c1cs": 371,
488
+ "C[C@]1": 372,
489
+ "3)C2)C1": 373,
490
+ "n1)": 374,
491
+ "(C)=O)": 375,
492
+ "O=C(": 376,
493
+ "CCN(CC": 377,
494
+ "CCS": 378,
495
+ "cs1": 379,
496
+ "F)C(=O)N": 380,
497
+ "c(C)n": 381,
498
+ "N(C)": 382,
499
+ "[C@@H]3CC": 383,
500
+ "S(C)(=O)=O)": 384,
501
+ "N(C)C)": 385,
502
+ "CC1(C)C": 386,
503
+ "OCC(=O)N": 387,
504
+ "N(C(=O)C2": 388,
505
+ "OC(C)(C)C": 389,
506
+ "CCc1n": 390,
507
+ "c4cc": 391,
508
+ "(C(=O)N2C": 392,
509
+ "N(C(=O)c2": 393,
510
+ "N1CCC": 394,
511
+ "C[C@H]2C": 395,
512
+ "c1ccc(": 396,
513
+ "C1CC": 397,
514
+ "3(C": 398,
515
+ "n1C": 399,
516
+ "c1ccn": 400,
517
+ "CCO1": 401,
518
+ "N1C": 402,
519
+ "Cc1cccc": 403,
520
+ "CCOC": 404,
521
+ "c(Cl)cc": 405,
522
+ "=CCC": 406,
523
+ "c2c(": 407,
524
+ "2)cc1": 408,
525
+ "[C@H](CNC(=O)C": 409,
526
+ "N3": 410,
527
+ "N(C(=O)c2cn": 411,
528
+ "cnc2": 412,
529
+ "1)C(=O)N": 413,
530
+ "c(C(=O)NC": 414,
531
+ "NC(=O)c1cn": 415,
532
+ "Cn1cc": 416,
533
+ "[C@H](CC(=O)N": 417,
534
+ "c1[nH]": 418,
535
+ "OC)C": 419,
536
+ "C[C@@]1": 420,
537
+ "n2)C1": 421,
538
+ "cc2C": 422,
539
+ "O)C1": 423,
540
+ "2)n1": 424,
541
+ "(C)C)C": 425,
542
+ "(C(=O)N2CCC": 426,
543
+ "O=C(CC": 427,
544
+ "C#CC": 428,
545
+ "1)C(=O)": 429,
546
+ "OC)C(=O)N": 430,
547
+ "CN(CC": 431,
548
+ "1CCCC1": 432,
549
+ "c1ccc(F)": 433,
550
+ "c(CC(=O)N": 434,
551
+ "CC(=O)N1C": 435,
552
+ "c3)": 436,
553
+ "4C": 437,
554
+ "c1ccc(C": 438,
555
+ "CCC2": 439,
556
+ "c3ncc": 440,
557
+ "CCOC(=O)": 441,
558
+ "c(N)": 442,
559
+ "CC(=O)": 443,
560
+ "c(=O)": 444,
561
+ "CN1CC": 445,
562
+ "Cc1ncc": 446,
563
+ "c1Cl": 447,
564
+ "CCn1": 448,
565
+ "CC[C@H](C)": 449,
566
+ "C[C@@H]2C": 450,
567
+ "c(CC": 451,
568
+ "c(OC)": 452,
569
+ "(OC)": 453,
570
+ "NC(=O)c1": 454,
571
+ "CC(=O)N1CCC": 455,
572
+ "NC(=O)N": 456,
573
+ "C(=O)N1C": 457,
574
+ "CN(C": 458,
575
+ "C[C@H](C": 459,
576
+ ")CC1": 460,
577
+ "c2ccccc2)": 461,
578
+ "N#": 462,
579
+ "(C)(C)C(=O)N": 463,
580
+ "2CCCC": 464,
581
+ "3)CC1": 465,
582
+ "ncn": 466,
583
+ "3)CC2)": 467,
584
+ "(C#N)": 468,
585
+ "C[C@@H](C": 469,
586
+ "c(=N)": 470,
587
+ "(C)C)C1": 471,
588
+ "(F)cc": 472,
589
+ "[C@@H](CNC(=O)C": 473,
590
+ "[C@H]1CN(C(=O)": 474,
591
+ "c1ccc(Cl)": 475,
592
+ "C[C@H]1": 476,
593
+ "[C@@H]1CN(C(=O)": 477,
594
+ "(F)(": 478,
595
+ "CC1CC": 479,
596
+ "Cc1cc(C(=O)N": 480,
597
+ "C[C@@H]1": 481,
598
+ "c(C)c1": 482,
599
+ "C(=O)N1CCC": 483,
600
+ "c(C(=O)N2C": 484,
601
+ "CCCO": 485,
602
+ "4)CC": 486,
603
+ "(=N": 487,
604
+ "2CC2)C1": 488,
605
+ "(CCNC(=O)": 489,
606
+ "n[nH]": 490,
607
+ "cc3": 491,
608
+ "(O)CC": 492,
609
+ "2(CCC": 493,
610
+ "[S": 494,
611
+ "S(N)": 495,
612
+ "ccc1C": 496,
613
+ "N(C)C(=O)C": 497,
614
+ "F)C2)": 498,
615
+ "(F)F)C": 499
616
+ },
617
+ "merges": [
618
+ "C C",
619
+ "O )",
620
+ "( C",
621
+ "= O)",
622
+ "( =O)",
623
+ "[ C",
624
+ "[C @",
625
+ "H ]",
626
+ "c c",
627
+ ") C",
628
+ "[C@ H]",
629
+ "[C@ @",
630
+ "c 1",
631
+ "C (=O)",
632
+ "[C@@ H]",
633
+ "(C )",
634
+ "(=O) N",
635
+ "N C(=O)",
636
+ "CC C",
637
+ "c 2",
638
+ "N (C",
639
+ "F )",
640
+ "1 CC",
641
+ "c1 cc",
642
+ "2 )",
643
+ "1 C",
644
+ "(C )C",
645
+ "N(C (=O)",
646
+ "( F)",
647
+ "(C (=O)N",
648
+ "c n",
649
+ "2 CC",
650
+ "( CC",
651
+ ")C 1",
652
+ "2 C",
653
+ "c 3",
654
+ "CC 1",
655
+ "O C",
656
+ "C(=O) N",
657
+ "= C",
658
+ "c2 cc",
659
+ "c (",
660
+ "NC(=O) C",
661
+ "n 1",
662
+ "[C@H] (",
663
+ "[ n",
664
+ "[n H]",
665
+ "[C@@H] (",
666
+ "2 )C1",
667
+ "CC (=O)N",
668
+ "3 )",
669
+ "C O",
670
+ "1 CCC",
671
+ "c (C",
672
+ "C [C@H]",
673
+ "c1 n",
674
+ "C [C@@H]",
675
+ "l )",
676
+ "[C@ ]",
677
+ "N(C )C",
678
+ "CC CC",
679
+ "[C@@ ]",
680
+ "( N",
681
+ "C c1cc",
682
+ "2 CCC",
683
+ "cc 1",
684
+ "n n",
685
+ "[C@H] 1C",
686
+ ")C 2)",
687
+ "CC (C)",
688
+ "CC O",
689
+ "O =C",
690
+ "N(C(=O) C",
691
+ "O) C",
692
+ "c3 cc",
693
+ "c (C(=O)N",
694
+ "(C NC(=O)",
695
+ "[C@@H] 1C",
696
+ "CC N",
697
+ "1 )",
698
+ "[C@H] 2C",
699
+ "c (C)",
700
+ "cc c1",
701
+ "c1 cn",
702
+ "3 CC",
703
+ "F )C",
704
+ "[C@H] (C)",
705
+ "(C) (C)C",
706
+ "2 )C",
707
+ "[C@@H] 2C",
708
+ "[C@@H] (C)",
709
+ "B r",
710
+ "(F) (F)",
711
+ "[C@H] 1",
712
+ "3 C",
713
+ "c s",
714
+ "c(C l)",
715
+ "1 )C",
716
+ "N(C)C (=O)",
717
+ "[C@H] 1CC",
718
+ "( O)",
719
+ "c (F)",
720
+ "(CC (=O)N",
721
+ ") CC",
722
+ "[C@@H] 1CC",
723
+ "c2cc cc",
724
+ "1 C(=O)",
725
+ "[C@H] (C",
726
+ "C =C",
727
+ "= CC",
728
+ "CCC 1",
729
+ "C 1",
730
+ "n cc",
731
+ "[C@@H] 1",
732
+ "[C@@H] (C",
733
+ "[C@H] 2CC",
734
+ "Br )",
735
+ "( NC(=O)",
736
+ "O CC",
737
+ "C N",
738
+ "[C@H] (C)C",
739
+ "3 )C",
740
+ "3 )C2)",
741
+ "c 4",
742
+ "c2 cn",
743
+ "C c1n",
744
+ "(C) CC",
745
+ "2) CC1",
746
+ "S (=O)",
747
+ ")C (=O)N",
748
+ "(C l)",
749
+ "= N",
750
+ "[C@H]( NC(=O)",
751
+ "[C@] 1",
752
+ "c1 C",
753
+ "[C@@H] (C)C",
754
+ "O=C (N",
755
+ "(C)C )",
756
+ "[C@H] (C(=O)N",
757
+ "[C@@H]( NC(=O)",
758
+ "(N )",
759
+ "c2 )",
760
+ "C #",
761
+ "[C@@H] 2CC",
762
+ "C(=O)N 1CC",
763
+ "c [nH]",
764
+ "[C@H] 2",
765
+ "[C@@] 1",
766
+ "c1cc cc",
767
+ "n1 cc",
768
+ "c( O)",
769
+ "OC )",
770
+ "# N",
771
+ "c o",
772
+ "n c1",
773
+ "[C@@H] (C(=O)N",
774
+ "3 CCC",
775
+ "N C",
776
+ "n 2",
777
+ "(C) (C)",
778
+ "S C",
779
+ "c1cc ccc1",
780
+ "[C@@H] 2",
781
+ "c2 C",
782
+ "( CCC",
783
+ "c2 n",
784
+ "[ N",
785
+ "N 1C(=O)",
786
+ "(F) F)",
787
+ "C OC",
788
+ "NC(=O) c1cc",
789
+ "N(C(=O) c2cc",
790
+ "3) CC",
791
+ "N 1CC",
792
+ "S(=O) (=O)",
793
+ "C c1",
794
+ "(F)(F) F)",
795
+ "2 C(=O)",
796
+ "2 (CC",
797
+ "( F)C",
798
+ "2 (C",
799
+ "= O",
800
+ "cc 2",
801
+ "+ ]",
802
+ "CO c1cc",
803
+ "- ]",
804
+ "[C@H]( O)",
805
+ "F )C1",
806
+ "n (C)",
807
+ "1CC 1",
808
+ "[C@@H] 1CCC",
809
+ "[N +]",
810
+ "c( N",
811
+ "cn 1",
812
+ "c3cc cc",
813
+ "[C@H] 3",
814
+ "C[C@@H] 1C",
815
+ ")C (=O)",
816
+ "(N) =O)",
817
+ "[C@H] 1CCC",
818
+ "c1 C(=O)N",
819
+ "(C(=O)N 2CC",
820
+ "CC(=O)N 1CC",
821
+ "C S",
822
+ "c( Br)",
823
+ "[C@@H] 3",
824
+ "s 1",
825
+ "C[C@H] 1C",
826
+ "2CC 2)",
827
+ "[C@H] (CC",
828
+ "c1n cc",
829
+ "n n1",
830
+ "[C@@H]( O)",
831
+ "N(C(=O) CC",
832
+ "[C@H] (CNC(=O)",
833
+ "[ O",
834
+ "[O -]",
835
+ "N 2C(=O)",
836
+ "CO C(=O)",
837
+ "[C@] (C)",
838
+ "C =",
839
+ "[C@H]( O)C",
840
+ "c2 )C1",
841
+ "o 1",
842
+ "3 )C1",
843
+ "NC(=O)C 1",
844
+ "CCN 1C(=O)",
845
+ "O=C (C",
846
+ "#N )",
847
+ "[C@@] (C)",
848
+ "[C@@H]( O)C",
849
+ "(C O)",
850
+ "[C@@H] (CC",
851
+ "(=O) [O-]",
852
+ "[N+] (=O)[O-]",
853
+ "c1 )",
854
+ "CC C(=O)N",
855
+ "4 )C",
856
+ "[C@] 2",
857
+ "( Br)",
858
+ "CC 2",
859
+ "(=O) =O)",
860
+ "[nH] 1",
861
+ "cc 1C",
862
+ "O 1",
863
+ "[C@@] 2",
864
+ "C =CC",
865
+ "N (",
866
+ "c( -",
867
+ "c3 cn",
868
+ "[C@H] 3C",
869
+ "CC(C) (C)C",
870
+ "( NC(=O)C",
871
+ "[C@H]( NC(=O)C",
872
+ "cc1 C(=O)N",
873
+ "2) CC",
874
+ "/ C=C",
875
+ "2) c1",
876
+ "(CC )",
877
+ "/C=C /",
878
+ "[C@@H] 2CCC",
879
+ "[C@H](C)C (=O)N",
880
+ "c( =N",
881
+ "[C@@H] (CNC(=O)",
882
+ "NC(=O) CC",
883
+ "(C(=O)N C",
884
+ "[C@@H]( NC(=O)C",
885
+ "[C@H] 2CCC",
886
+ "4 )",
887
+ "CC(C) (C)",
888
+ "c2 ncc",
889
+ "c2cccc c2",
890
+ "(C NC(=O)C",
891
+ "N =",
892
+ "(F) (F)C",
893
+ "N (CC",
894
+ "CC (C)C",
895
+ "OC 1",
896
+ "cc cc",
897
+ "n 3",
898
+ "CCO CC",
899
+ "( -",
900
+ "(F) F",
901
+ ")C 2",
902
+ "c3 C",
903
+ "C[C@@H] 1CC",
904
+ "c(C(=O)N 2CC",
905
+ "CC1 )",
906
+ "C c1cn",
907
+ "CC c1cc",
908
+ "[C@H] 3CC",
909
+ "c(F) cc",
910
+ "c3 n",
911
+ "[C@@H](C)C (=O)N",
912
+ "C[C@H] 1CC",
913
+ "[N+](=O)[O-] )",
914
+ "n2 cc",
915
+ "(C)(C)C )",
916
+ "CC N(C(=O)",
917
+ "[C@@H] 3C",
918
+ "(C) CCC",
919
+ "C(=O)N C",
920
+ "cc c2",
921
+ "n c2",
922
+ "= CC(=O)N",
923
+ "3 (CC",
924
+ "4 CC",
925
+ "1) N",
926
+ "S(=O) (=O)N",
927
+ "N 2CC",
928
+ "( O)C",
929
+ "cn c1",
930
+ "S (C)",
931
+ "1)C 2",
932
+ "CC NC(=O)",
933
+ "l )C",
934
+ "C n1",
935
+ "N(C(=O) c3cc",
936
+ "[C@H]1 C(=O)N",
937
+ "n 2)",
938
+ "NC(=O) c2cc",
939
+ "c3cccc c3",
940
+ "3CC 3)",
941
+ "c2 nn",
942
+ "2)C1 )",
943
+ "[C@@H]1 C(=O)N",
944
+ "(F)(F) F",
945
+ "CO CC",
946
+ "CC 2)",
947
+ "CC CCC",
948
+ "c1 cs",
949
+ "C [C@]1",
950
+ "3)C 2)C1",
951
+ "n1 )",
952
+ "(C) =O)",
953
+ "O=C (",
954
+ "CCN (CC",
955
+ "CC S",
956
+ "cs 1",
957
+ "F)C (=O)N",
958
+ "c(C) n",
959
+ "N (C)",
960
+ "[C@@H] 3CC",
961
+ "S(C) (=O)=O)",
962
+ "N(C)C )",
963
+ "CC1 (C)C",
964
+ "O CC(=O)N",
965
+ "N(C(=O)C 2",
966
+ "OC (C)(C)C",
967
+ "CC c1n",
968
+ "c4 cc",
969
+ "(C(=O)N 2C",
970
+ "N(C(=O) c2",
971
+ "N 1CCC",
972
+ "C[C@H] 2C",
973
+ "c1cc c(",
974
+ "C 1CC",
975
+ "3 (C",
976
+ "n 1C",
977
+ "c1cc n",
978
+ "CCO 1",
979
+ "N 1C",
980
+ "Cc1cc cc",
981
+ "CC OC",
982
+ "c(Cl) cc",
983
+ "= CCC",
984
+ "c2 c(",
985
+ "2) cc1",
986
+ "[C@H](C NC(=O)C",
987
+ "N 3",
988
+ "N(C(=O) c2cn",
989
+ "cn c2",
990
+ "1)C (=O)N",
991
+ "c(C(=O)N C",
992
+ "NC(=O) c1cn",
993
+ "C n1cc",
994
+ "[C@H] (CC(=O)N",
995
+ "c1 [nH]",
996
+ "OC )C",
997
+ "C [C@@]1",
998
+ "n 2)C1",
999
+ "cc 2C",
1000
+ "O)C 1",
1001
+ "2) n1",
1002
+ "(C)C )C",
1003
+ "(C(=O)N 2CCC",
1004
+ "O=C (CC",
1005
+ "C# CC",
1006
+ "1)C (=O)",
1007
+ "OC )C(=O)N",
1008
+ "CN (CC",
1009
+ "1CC CC1",
1010
+ "c1cc c(F)",
1011
+ "c (CC(=O)N",
1012
+ "CC(=O)N 1C",
1013
+ "c3 )",
1014
+ "4 C",
1015
+ "c1cc c(C",
1016
+ "CCC 2",
1017
+ "c3 ncc",
1018
+ "CCO C(=O)",
1019
+ "c(N )",
1020
+ "CC (=O)",
1021
+ "c (=O)",
1022
+ "CN 1CC",
1023
+ "Cc1n cc",
1024
+ "c1C l",
1025
+ "CC n1",
1026
+ "CC [C@H](C)",
1027
+ "C[C@@H] 2C",
1028
+ "c (CC",
1029
+ "c( OC)",
1030
+ "( OC)",
1031
+ "NC(=O) c1",
1032
+ "CC(=O)N 1CCC",
1033
+ "NC(=O) N",
1034
+ "C(=O)N 1C",
1035
+ "C N(C",
1036
+ "C[C@H] (C",
1037
+ ") CC1",
1038
+ "c2cccc c2)",
1039
+ "N #",
1040
+ "(C)(C)C (=O)N",
1041
+ "2CC CC",
1042
+ "3) CC1",
1043
+ "n cn",
1044
+ "3)CC 2)",
1045
+ "(C #N)",
1046
+ "C[C@@H] (C",
1047
+ "c(=N )",
1048
+ "(C)C )C1",
1049
+ "(F) cc",
1050
+ "[C@@H](C NC(=O)C",
1051
+ "[C@H]1C N(C(=O)",
1052
+ "c1cc c(Cl)",
1053
+ "C[C@H] 1",
1054
+ "[C@@H]1C N(C(=O)",
1055
+ "(F) (",
1056
+ "CC 1CC",
1057
+ "Cc1cc (C(=O)N",
1058
+ "C[C@@H] 1",
1059
+ "c(C) c1",
1060
+ "C(=O)N 1CCC",
1061
+ "c(C(=O)N 2C",
1062
+ "CCC O",
1063
+ "4 )CC",
1064
+ "( =N",
1065
+ "2CC 2)C1",
1066
+ "(CC NC(=O)",
1067
+ "n [nH]",
1068
+ "cc 3",
1069
+ "(O) CC",
1070
+ "2 (CCC",
1071
+ "[ S",
1072
+ "S (N)",
1073
+ "ccc1 C",
1074
+ "N(C)C(=O) C",
1075
+ "F )C2)",
1076
+ "(F) F)C"
1077
+ ]
1078
+ }
1079
+ }
tmp-spec-checkpoint-45000/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<bos>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<eos>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<bos>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "eos_token": "<eos>",
39
+ "model_max_length": 1000000000000000019884624838656,
40
+ "pad_token": "<pad>",
41
+ "tokenizer_class": "PreTrainedTokenizerFast",
42
+ "unk_token": "<unk>"
43
+ }
tmp-spec-checkpoint-45000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22cef1f8c8951f4ba462c4b633185d1df1538dc09e6cd62e58b5f9ff257bf5e5
3
+ size 6584