hjctty commited on
Commit
307d807
1 Parent(s): b27b5ee

Model save

Browse files
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: sentence-transformers/all-distilroberta-v1
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ model-index:
10
+ - name: all-distilroberta-finetuned-on-agent
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # all-distilroberta-finetuned-on-agent
18
+
19
+ This model is a fine-tuned version of [sentence-transformers/all-distilroberta-v1](https://huggingface.co/sentence-transformers/all-distilroberta-v1) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.0505
22
+ - Accuracy: 1.0
23
+ - F1: 1.0
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 2e-05
43
+ - train_batch_size: 6
44
+ - eval_batch_size: 6
45
+ - seed: 42
46
+ - distributed_type: tpu
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 10
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
+ | 4.8137 | 1.0 | 30 | 4.2195 | 0.5 | 0.4046 |
56
+ | 3.8117 | 2.0 | 60 | 3.3029 | 0.7667 | 0.7270 |
57
+ | 3.0598 | 3.0 | 90 | 2.6420 | 0.8333 | 0.8137 |
58
+ | 2.4888 | 4.0 | 120 | 2.1405 | 0.8667 | 0.8470 |
59
+ | 2.0583 | 5.0 | 150 | 1.7464 | 0.9 | 0.8825 |
60
+ | 1.6867 | 6.0 | 180 | 1.4774 | 0.9667 | 0.9644 |
61
+ | 1.4817 | 7.0 | 210 | 1.2812 | 0.9667 | 0.9644 |
62
+ | 1.2876 | 8.0 | 240 | 1.1481 | 1.0 | 1.0 |
63
+ | 1.1833 | 9.0 | 270 | 1.0764 | 1.0 | 1.0 |
64
+ | 1.1549 | 10.0 | 300 | 1.0505 | 1.0 | 1.0 |
65
+
66
+
67
+ ### Framework versions
68
+
69
+ - Transformers 4.38.2
70
+ - Pytorch 2.2.0+cu121
71
+ - Datasets 2.18.0
72
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,391 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-distilroberta-v1",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3",
19
+ "4": "LABEL_4",
20
+ "5": "LABEL_5",
21
+ "6": "LABEL_6",
22
+ "7": "LABEL_7",
23
+ "8": "LABEL_8",
24
+ "9": "LABEL_9",
25
+ "10": "LABEL_10",
26
+ "11": "LABEL_11",
27
+ "12": "LABEL_12",
28
+ "13": "LABEL_13",
29
+ "14": "LABEL_14",
30
+ "15": "LABEL_15",
31
+ "16": "LABEL_16",
32
+ "17": "LABEL_17",
33
+ "18": "LABEL_18",
34
+ "19": "LABEL_19",
35
+ "20": "LABEL_20",
36
+ "21": "LABEL_21",
37
+ "22": "LABEL_22",
38
+ "23": "LABEL_23",
39
+ "24": "LABEL_24",
40
+ "25": "LABEL_25",
41
+ "26": "LABEL_26",
42
+ "27": "LABEL_27",
43
+ "28": "LABEL_28",
44
+ "29": "LABEL_29",
45
+ "30": "LABEL_30",
46
+ "31": "LABEL_31",
47
+ "32": "LABEL_32",
48
+ "33": "LABEL_33",
49
+ "34": "LABEL_34",
50
+ "35": "LABEL_35",
51
+ "36": "LABEL_36",
52
+ "37": "LABEL_37",
53
+ "38": "LABEL_38",
54
+ "39": "LABEL_39",
55
+ "40": "LABEL_40",
56
+ "41": "LABEL_41",
57
+ "42": "LABEL_42",
58
+ "43": "LABEL_43",
59
+ "44": "LABEL_44",
60
+ "45": "LABEL_45",
61
+ "46": "LABEL_46",
62
+ "47": "LABEL_47",
63
+ "48": "LABEL_48",
64
+ "49": "LABEL_49",
65
+ "50": "LABEL_50",
66
+ "51": "LABEL_51",
67
+ "52": "LABEL_52",
68
+ "53": "LABEL_53",
69
+ "54": "LABEL_54",
70
+ "55": "LABEL_55",
71
+ "56": "LABEL_56",
72
+ "57": "LABEL_57",
73
+ "58": "LABEL_58",
74
+ "59": "LABEL_59",
75
+ "60": "LABEL_60",
76
+ "61": "LABEL_61",
77
+ "62": "LABEL_62",
78
+ "63": "LABEL_63",
79
+ "64": "LABEL_64",
80
+ "65": "LABEL_65",
81
+ "66": "LABEL_66",
82
+ "67": "LABEL_67",
83
+ "68": "LABEL_68",
84
+ "69": "LABEL_69",
85
+ "70": "LABEL_70",
86
+ "71": "LABEL_71",
87
+ "72": "LABEL_72",
88
+ "73": "LABEL_73",
89
+ "74": "LABEL_74",
90
+ "75": "LABEL_75",
91
+ "76": "LABEL_76",
92
+ "77": "LABEL_77",
93
+ "78": "LABEL_78",
94
+ "79": "LABEL_79",
95
+ "80": "LABEL_80",
96
+ "81": "LABEL_81",
97
+ "82": "LABEL_82",
98
+ "83": "LABEL_83",
99
+ "84": "LABEL_84",
100
+ "85": "LABEL_85",
101
+ "86": "LABEL_86",
102
+ "87": "LABEL_87",
103
+ "88": "LABEL_88",
104
+ "89": "LABEL_89",
105
+ "90": "LABEL_90",
106
+ "91": "LABEL_91",
107
+ "92": "LABEL_92",
108
+ "93": "LABEL_93",
109
+ "94": "LABEL_94",
110
+ "95": "LABEL_95",
111
+ "96": "LABEL_96",
112
+ "97": "LABEL_97",
113
+ "98": "LABEL_98",
114
+ "99": "LABEL_99",
115
+ "100": "LABEL_100",
116
+ "101": "LABEL_101",
117
+ "102": "LABEL_102",
118
+ "103": "LABEL_103",
119
+ "104": "LABEL_104",
120
+ "105": "LABEL_105",
121
+ "106": "LABEL_106",
122
+ "107": "LABEL_107",
123
+ "108": "LABEL_108",
124
+ "109": "LABEL_109",
125
+ "110": "LABEL_110",
126
+ "111": "LABEL_111",
127
+ "112": "LABEL_112",
128
+ "113": "LABEL_113",
129
+ "114": "LABEL_114",
130
+ "115": "LABEL_115",
131
+ "116": "LABEL_116",
132
+ "117": "LABEL_117",
133
+ "118": "LABEL_118",
134
+ "119": "LABEL_119",
135
+ "120": "LABEL_120",
136
+ "121": "LABEL_121",
137
+ "122": "LABEL_122",
138
+ "123": "LABEL_123",
139
+ "124": "LABEL_124",
140
+ "125": "LABEL_125",
141
+ "126": "LABEL_126",
142
+ "127": "LABEL_127",
143
+ "128": "LABEL_128",
144
+ "129": "LABEL_129",
145
+ "130": "LABEL_130",
146
+ "131": "LABEL_131",
147
+ "132": "LABEL_132",
148
+ "133": "LABEL_133",
149
+ "134": "LABEL_134",
150
+ "135": "LABEL_135",
151
+ "136": "LABEL_136",
152
+ "137": "LABEL_137",
153
+ "138": "LABEL_138",
154
+ "139": "LABEL_139",
155
+ "140": "LABEL_140",
156
+ "141": "LABEL_141",
157
+ "142": "LABEL_142",
158
+ "143": "LABEL_143",
159
+ "144": "LABEL_144",
160
+ "145": "LABEL_145",
161
+ "146": "LABEL_146",
162
+ "147": "LABEL_147",
163
+ "148": "LABEL_148",
164
+ "149": "LABEL_149",
165
+ "150": "LABEL_150",
166
+ "151": "LABEL_151",
167
+ "152": "LABEL_152",
168
+ "153": "LABEL_153",
169
+ "154": "LABEL_154",
170
+ "155": "LABEL_155",
171
+ "156": "LABEL_156",
172
+ "157": "LABEL_157",
173
+ "158": "LABEL_158",
174
+ "159": "LABEL_159",
175
+ "160": "LABEL_160",
176
+ "161": "LABEL_161",
177
+ "162": "LABEL_162",
178
+ "163": "LABEL_163",
179
+ "164": "LABEL_164",
180
+ "165": "LABEL_165",
181
+ "166": "LABEL_166",
182
+ "167": "LABEL_167",
183
+ "168": "LABEL_168",
184
+ "169": "LABEL_169",
185
+ "170": "LABEL_170",
186
+ "171": "LABEL_171",
187
+ "172": "LABEL_172",
188
+ "173": "LABEL_173",
189
+ "174": "LABEL_174",
190
+ "175": "LABEL_175",
191
+ "176": "LABEL_176",
192
+ "177": "LABEL_177",
193
+ "178": "LABEL_178"
194
+ },
195
+ "initializer_range": 0.02,
196
+ "intermediate_size": 3072,
197
+ "label2id": {
198
+ "LABEL_0": 0,
199
+ "LABEL_1": 1,
200
+ "LABEL_10": 10,
201
+ "LABEL_100": 100,
202
+ "LABEL_101": 101,
203
+ "LABEL_102": 102,
204
+ "LABEL_103": 103,
205
+ "LABEL_104": 104,
206
+ "LABEL_105": 105,
207
+ "LABEL_106": 106,
208
+ "LABEL_107": 107,
209
+ "LABEL_108": 108,
210
+ "LABEL_109": 109,
211
+ "LABEL_11": 11,
212
+ "LABEL_110": 110,
213
+ "LABEL_111": 111,
214
+ "LABEL_112": 112,
215
+ "LABEL_113": 113,
216
+ "LABEL_114": 114,
217
+ "LABEL_115": 115,
218
+ "LABEL_116": 116,
219
+ "LABEL_117": 117,
220
+ "LABEL_118": 118,
221
+ "LABEL_119": 119,
222
+ "LABEL_12": 12,
223
+ "LABEL_120": 120,
224
+ "LABEL_121": 121,
225
+ "LABEL_122": 122,
226
+ "LABEL_123": 123,
227
+ "LABEL_124": 124,
228
+ "LABEL_125": 125,
229
+ "LABEL_126": 126,
230
+ "LABEL_127": 127,
231
+ "LABEL_128": 128,
232
+ "LABEL_129": 129,
233
+ "LABEL_13": 13,
234
+ "LABEL_130": 130,
235
+ "LABEL_131": 131,
236
+ "LABEL_132": 132,
237
+ "LABEL_133": 133,
238
+ "LABEL_134": 134,
239
+ "LABEL_135": 135,
240
+ "LABEL_136": 136,
241
+ "LABEL_137": 137,
242
+ "LABEL_138": 138,
243
+ "LABEL_139": 139,
244
+ "LABEL_14": 14,
245
+ "LABEL_140": 140,
246
+ "LABEL_141": 141,
247
+ "LABEL_142": 142,
248
+ "LABEL_143": 143,
249
+ "LABEL_144": 144,
250
+ "LABEL_145": 145,
251
+ "LABEL_146": 146,
252
+ "LABEL_147": 147,
253
+ "LABEL_148": 148,
254
+ "LABEL_149": 149,
255
+ "LABEL_15": 15,
256
+ "LABEL_150": 150,
257
+ "LABEL_151": 151,
258
+ "LABEL_152": 152,
259
+ "LABEL_153": 153,
260
+ "LABEL_154": 154,
261
+ "LABEL_155": 155,
262
+ "LABEL_156": 156,
263
+ "LABEL_157": 157,
264
+ "LABEL_158": 158,
265
+ "LABEL_159": 159,
266
+ "LABEL_16": 16,
267
+ "LABEL_160": 160,
268
+ "LABEL_161": 161,
269
+ "LABEL_162": 162,
270
+ "LABEL_163": 163,
271
+ "LABEL_164": 164,
272
+ "LABEL_165": 165,
273
+ "LABEL_166": 166,
274
+ "LABEL_167": 167,
275
+ "LABEL_168": 168,
276
+ "LABEL_169": 169,
277
+ "LABEL_17": 17,
278
+ "LABEL_170": 170,
279
+ "LABEL_171": 171,
280
+ "LABEL_172": 172,
281
+ "LABEL_173": 173,
282
+ "LABEL_174": 174,
283
+ "LABEL_175": 175,
284
+ "LABEL_176": 176,
285
+ "LABEL_177": 177,
286
+ "LABEL_178": 178,
287
+ "LABEL_18": 18,
288
+ "LABEL_19": 19,
289
+ "LABEL_2": 2,
290
+ "LABEL_20": 20,
291
+ "LABEL_21": 21,
292
+ "LABEL_22": 22,
293
+ "LABEL_23": 23,
294
+ "LABEL_24": 24,
295
+ "LABEL_25": 25,
296
+ "LABEL_26": 26,
297
+ "LABEL_27": 27,
298
+ "LABEL_28": 28,
299
+ "LABEL_29": 29,
300
+ "LABEL_3": 3,
301
+ "LABEL_30": 30,
302
+ "LABEL_31": 31,
303
+ "LABEL_32": 32,
304
+ "LABEL_33": 33,
305
+ "LABEL_34": 34,
306
+ "LABEL_35": 35,
307
+ "LABEL_36": 36,
308
+ "LABEL_37": 37,
309
+ "LABEL_38": 38,
310
+ "LABEL_39": 39,
311
+ "LABEL_4": 4,
312
+ "LABEL_40": 40,
313
+ "LABEL_41": 41,
314
+ "LABEL_42": 42,
315
+ "LABEL_43": 43,
316
+ "LABEL_44": 44,
317
+ "LABEL_45": 45,
318
+ "LABEL_46": 46,
319
+ "LABEL_47": 47,
320
+ "LABEL_48": 48,
321
+ "LABEL_49": 49,
322
+ "LABEL_5": 5,
323
+ "LABEL_50": 50,
324
+ "LABEL_51": 51,
325
+ "LABEL_52": 52,
326
+ "LABEL_53": 53,
327
+ "LABEL_54": 54,
328
+ "LABEL_55": 55,
329
+ "LABEL_56": 56,
330
+ "LABEL_57": 57,
331
+ "LABEL_58": 58,
332
+ "LABEL_59": 59,
333
+ "LABEL_6": 6,
334
+ "LABEL_60": 60,
335
+ "LABEL_61": 61,
336
+ "LABEL_62": 62,
337
+ "LABEL_63": 63,
338
+ "LABEL_64": 64,
339
+ "LABEL_65": 65,
340
+ "LABEL_66": 66,
341
+ "LABEL_67": 67,
342
+ "LABEL_68": 68,
343
+ "LABEL_69": 69,
344
+ "LABEL_7": 7,
345
+ "LABEL_70": 70,
346
+ "LABEL_71": 71,
347
+ "LABEL_72": 72,
348
+ "LABEL_73": 73,
349
+ "LABEL_74": 74,
350
+ "LABEL_75": 75,
351
+ "LABEL_76": 76,
352
+ "LABEL_77": 77,
353
+ "LABEL_78": 78,
354
+ "LABEL_79": 79,
355
+ "LABEL_8": 8,
356
+ "LABEL_80": 80,
357
+ "LABEL_81": 81,
358
+ "LABEL_82": 82,
359
+ "LABEL_83": 83,
360
+ "LABEL_84": 84,
361
+ "LABEL_85": 85,
362
+ "LABEL_86": 86,
363
+ "LABEL_87": 87,
364
+ "LABEL_88": 88,
365
+ "LABEL_89": 89,
366
+ "LABEL_9": 9,
367
+ "LABEL_90": 90,
368
+ "LABEL_91": 91,
369
+ "LABEL_92": 92,
370
+ "LABEL_93": 93,
371
+ "LABEL_94": 94,
372
+ "LABEL_95": 95,
373
+ "LABEL_96": 96,
374
+ "LABEL_97": 97,
375
+ "LABEL_98": 98,
376
+ "LABEL_99": 99
377
+ },
378
+ "layer_norm_eps": 1e-05,
379
+ "max_position_embeddings": 514,
380
+ "model_type": "roberta",
381
+ "num_attention_heads": 12,
382
+ "num_hidden_layers": 6,
383
+ "pad_token_id": 1,
384
+ "position_embedding_type": "absolute",
385
+ "problem_type": "single_label_classification",
386
+ "torch_dtype": "float32",
387
+ "transformers_version": "4.38.2",
388
+ "type_vocab_size": 1,
389
+ "use_cache": true,
390
+ "vocab_size": 50265
391
+ }
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 sha256:013b51ccecd39c3bd3cb3db7449762b4555b0be35d3b51cf4f5b69c0e0b7dec2
3
+ size 329036732
runs/Mar22_22-11-24_fsm-hjason-text-test-t4/events.out.tfevents.1711145500.fsm-hjason-text-test-t4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d8096b599bf99fb3a12c140dca231f58c69d9eb6b36826f053fbf759037a012
3
+ size 14829
runs/Mar22_22-14-49_fsm-hjason-text-test-t4/events.out.tfevents.1711145694.fsm-hjason-text-test-t4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e53af537a9e842f358c1014fe764ee80a3c7dd1548ce2c30a908bda967b0fa0
3
+ size 14829
runs/Mar25_19-52-17_fsm-hjason-text-test-t4/events.out.tfevents.1711396348.fsm-hjason-text-test-t4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863617d6fb2c528f8f9d0f18693ae9ac97ebc88fd16cd3d22181e8880b157e09
3
+ size 12483
runs/Mar25_19-52-17_fsm-hjason-text-test-t4/events.out.tfevents.1711396405.fsm-hjason-text-test-t4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d412f8e486922fa26955150635c7dd1e0d8aa8985a84f0ecc884618d60e425ec
3
+ size 14176
runs/Mar25_19-56-18_fsm-hjason-text-test-t4/events.out.tfevents.1711396581.fsm-hjason-text-test-t4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e17b60d715a69af8d8fac718fc2296ca6d012fa14be42febc31fd841b12e7c3f
3
+ size 18593
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
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": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_length": 128,
52
+ "model_max_length": 512,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "<pad>",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "</s>",
58
+ "stride": 0,
59
+ "tokenizer_class": "RobertaTokenizer",
60
+ "trim_offsets": true,
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "<unk>"
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6329be7baaaeefee665abe38784efabd4feb0b0fc7bffa9aab85fb58e0631d15
3
+ size 4920
vocab.json ADDED
The diff for this file is too large to render. See raw diff