nikitakapitan commited on
Commit
413294c
1 Parent(s): b53909e

End of training

Browse files
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - clinc_oos
8
+ model-index:
9
+ - name: distilbert-base-uncased-finetuned-clinc_oos
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # distilbert-base-uncased-finetuned-clinc_oos
17
+
18
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 3
44
+
45
+ ### Framework versions
46
+
47
+ - Transformers 4.33.1
48
+ - Pytorch 2.0.1+cu118
49
+ - Datasets 2.13.1
50
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31",
44
+ "32": "LABEL_32",
45
+ "33": "LABEL_33",
46
+ "34": "LABEL_34",
47
+ "35": "LABEL_35",
48
+ "36": "LABEL_36",
49
+ "37": "LABEL_37",
50
+ "38": "LABEL_38",
51
+ "39": "LABEL_39",
52
+ "40": "LABEL_40",
53
+ "41": "LABEL_41",
54
+ "42": "LABEL_42",
55
+ "43": "LABEL_43",
56
+ "44": "LABEL_44",
57
+ "45": "LABEL_45",
58
+ "46": "LABEL_46",
59
+ "47": "LABEL_47",
60
+ "48": "LABEL_48",
61
+ "49": "LABEL_49",
62
+ "50": "LABEL_50",
63
+ "51": "LABEL_51",
64
+ "52": "LABEL_52",
65
+ "53": "LABEL_53",
66
+ "54": "LABEL_54",
67
+ "55": "LABEL_55",
68
+ "56": "LABEL_56",
69
+ "57": "LABEL_57",
70
+ "58": "LABEL_58",
71
+ "59": "LABEL_59",
72
+ "60": "LABEL_60",
73
+ "61": "LABEL_61",
74
+ "62": "LABEL_62",
75
+ "63": "LABEL_63",
76
+ "64": "LABEL_64",
77
+ "65": "LABEL_65",
78
+ "66": "LABEL_66",
79
+ "67": "LABEL_67",
80
+ "68": "LABEL_68",
81
+ "69": "LABEL_69",
82
+ "70": "LABEL_70",
83
+ "71": "LABEL_71",
84
+ "72": "LABEL_72",
85
+ "73": "LABEL_73",
86
+ "74": "LABEL_74",
87
+ "75": "LABEL_75",
88
+ "76": "LABEL_76",
89
+ "77": "LABEL_77",
90
+ "78": "LABEL_78",
91
+ "79": "LABEL_79",
92
+ "80": "LABEL_80",
93
+ "81": "LABEL_81",
94
+ "82": "LABEL_82",
95
+ "83": "LABEL_83",
96
+ "84": "LABEL_84",
97
+ "85": "LABEL_85",
98
+ "86": "LABEL_86",
99
+ "87": "LABEL_87",
100
+ "88": "LABEL_88",
101
+ "89": "LABEL_89",
102
+ "90": "LABEL_90",
103
+ "91": "LABEL_91",
104
+ "92": "LABEL_92",
105
+ "93": "LABEL_93",
106
+ "94": "LABEL_94",
107
+ "95": "LABEL_95",
108
+ "96": "LABEL_96",
109
+ "97": "LABEL_97",
110
+ "98": "LABEL_98",
111
+ "99": "LABEL_99",
112
+ "100": "LABEL_100",
113
+ "101": "LABEL_101",
114
+ "102": "LABEL_102",
115
+ "103": "LABEL_103",
116
+ "104": "LABEL_104",
117
+ "105": "LABEL_105",
118
+ "106": "LABEL_106",
119
+ "107": "LABEL_107",
120
+ "108": "LABEL_108",
121
+ "109": "LABEL_109",
122
+ "110": "LABEL_110",
123
+ "111": "LABEL_111",
124
+ "112": "LABEL_112",
125
+ "113": "LABEL_113",
126
+ "114": "LABEL_114",
127
+ "115": "LABEL_115",
128
+ "116": "LABEL_116",
129
+ "117": "LABEL_117",
130
+ "118": "LABEL_118",
131
+ "119": "LABEL_119",
132
+ "120": "LABEL_120",
133
+ "121": "LABEL_121",
134
+ "122": "LABEL_122",
135
+ "123": "LABEL_123",
136
+ "124": "LABEL_124",
137
+ "125": "LABEL_125",
138
+ "126": "LABEL_126",
139
+ "127": "LABEL_127",
140
+ "128": "LABEL_128",
141
+ "129": "LABEL_129",
142
+ "130": "LABEL_130",
143
+ "131": "LABEL_131",
144
+ "132": "LABEL_132",
145
+ "133": "LABEL_133",
146
+ "134": "LABEL_134",
147
+ "135": "LABEL_135",
148
+ "136": "LABEL_136",
149
+ "137": "LABEL_137",
150
+ "138": "LABEL_138",
151
+ "139": "LABEL_139",
152
+ "140": "LABEL_140",
153
+ "141": "LABEL_141",
154
+ "142": "LABEL_142",
155
+ "143": "LABEL_143",
156
+ "144": "LABEL_144",
157
+ "145": "LABEL_145",
158
+ "146": "LABEL_146",
159
+ "147": "LABEL_147",
160
+ "148": "LABEL_148",
161
+ "149": "LABEL_149",
162
+ "150": "LABEL_150"
163
+ },
164
+ "initializer_range": 0.02,
165
+ "label2id": {
166
+ "LABEL_0": 0,
167
+ "LABEL_1": 1,
168
+ "LABEL_10": 10,
169
+ "LABEL_100": 100,
170
+ "LABEL_101": 101,
171
+ "LABEL_102": 102,
172
+ "LABEL_103": 103,
173
+ "LABEL_104": 104,
174
+ "LABEL_105": 105,
175
+ "LABEL_106": 106,
176
+ "LABEL_107": 107,
177
+ "LABEL_108": 108,
178
+ "LABEL_109": 109,
179
+ "LABEL_11": 11,
180
+ "LABEL_110": 110,
181
+ "LABEL_111": 111,
182
+ "LABEL_112": 112,
183
+ "LABEL_113": 113,
184
+ "LABEL_114": 114,
185
+ "LABEL_115": 115,
186
+ "LABEL_116": 116,
187
+ "LABEL_117": 117,
188
+ "LABEL_118": 118,
189
+ "LABEL_119": 119,
190
+ "LABEL_12": 12,
191
+ "LABEL_120": 120,
192
+ "LABEL_121": 121,
193
+ "LABEL_122": 122,
194
+ "LABEL_123": 123,
195
+ "LABEL_124": 124,
196
+ "LABEL_125": 125,
197
+ "LABEL_126": 126,
198
+ "LABEL_127": 127,
199
+ "LABEL_128": 128,
200
+ "LABEL_129": 129,
201
+ "LABEL_13": 13,
202
+ "LABEL_130": 130,
203
+ "LABEL_131": 131,
204
+ "LABEL_132": 132,
205
+ "LABEL_133": 133,
206
+ "LABEL_134": 134,
207
+ "LABEL_135": 135,
208
+ "LABEL_136": 136,
209
+ "LABEL_137": 137,
210
+ "LABEL_138": 138,
211
+ "LABEL_139": 139,
212
+ "LABEL_14": 14,
213
+ "LABEL_140": 140,
214
+ "LABEL_141": 141,
215
+ "LABEL_142": 142,
216
+ "LABEL_143": 143,
217
+ "LABEL_144": 144,
218
+ "LABEL_145": 145,
219
+ "LABEL_146": 146,
220
+ "LABEL_147": 147,
221
+ "LABEL_148": 148,
222
+ "LABEL_149": 149,
223
+ "LABEL_15": 15,
224
+ "LABEL_150": 150,
225
+ "LABEL_16": 16,
226
+ "LABEL_17": 17,
227
+ "LABEL_18": 18,
228
+ "LABEL_19": 19,
229
+ "LABEL_2": 2,
230
+ "LABEL_20": 20,
231
+ "LABEL_21": 21,
232
+ "LABEL_22": 22,
233
+ "LABEL_23": 23,
234
+ "LABEL_24": 24,
235
+ "LABEL_25": 25,
236
+ "LABEL_26": 26,
237
+ "LABEL_27": 27,
238
+ "LABEL_28": 28,
239
+ "LABEL_29": 29,
240
+ "LABEL_3": 3,
241
+ "LABEL_30": 30,
242
+ "LABEL_31": 31,
243
+ "LABEL_32": 32,
244
+ "LABEL_33": 33,
245
+ "LABEL_34": 34,
246
+ "LABEL_35": 35,
247
+ "LABEL_36": 36,
248
+ "LABEL_37": 37,
249
+ "LABEL_38": 38,
250
+ "LABEL_39": 39,
251
+ "LABEL_4": 4,
252
+ "LABEL_40": 40,
253
+ "LABEL_41": 41,
254
+ "LABEL_42": 42,
255
+ "LABEL_43": 43,
256
+ "LABEL_44": 44,
257
+ "LABEL_45": 45,
258
+ "LABEL_46": 46,
259
+ "LABEL_47": 47,
260
+ "LABEL_48": 48,
261
+ "LABEL_49": 49,
262
+ "LABEL_5": 5,
263
+ "LABEL_50": 50,
264
+ "LABEL_51": 51,
265
+ "LABEL_52": 52,
266
+ "LABEL_53": 53,
267
+ "LABEL_54": 54,
268
+ "LABEL_55": 55,
269
+ "LABEL_56": 56,
270
+ "LABEL_57": 57,
271
+ "LABEL_58": 58,
272
+ "LABEL_59": 59,
273
+ "LABEL_6": 6,
274
+ "LABEL_60": 60,
275
+ "LABEL_61": 61,
276
+ "LABEL_62": 62,
277
+ "LABEL_63": 63,
278
+ "LABEL_64": 64,
279
+ "LABEL_65": 65,
280
+ "LABEL_66": 66,
281
+ "LABEL_67": 67,
282
+ "LABEL_68": 68,
283
+ "LABEL_69": 69,
284
+ "LABEL_7": 7,
285
+ "LABEL_70": 70,
286
+ "LABEL_71": 71,
287
+ "LABEL_72": 72,
288
+ "LABEL_73": 73,
289
+ "LABEL_74": 74,
290
+ "LABEL_75": 75,
291
+ "LABEL_76": 76,
292
+ "LABEL_77": 77,
293
+ "LABEL_78": 78,
294
+ "LABEL_79": 79,
295
+ "LABEL_8": 8,
296
+ "LABEL_80": 80,
297
+ "LABEL_81": 81,
298
+ "LABEL_82": 82,
299
+ "LABEL_83": 83,
300
+ "LABEL_84": 84,
301
+ "LABEL_85": 85,
302
+ "LABEL_86": 86,
303
+ "LABEL_87": 87,
304
+ "LABEL_88": 88,
305
+ "LABEL_89": 89,
306
+ "LABEL_9": 9,
307
+ "LABEL_90": 90,
308
+ "LABEL_91": 91,
309
+ "LABEL_92": 92,
310
+ "LABEL_93": 93,
311
+ "LABEL_94": 94,
312
+ "LABEL_95": 95,
313
+ "LABEL_96": 96,
314
+ "LABEL_97": 97,
315
+ "LABEL_98": 98,
316
+ "LABEL_99": 99
317
+ },
318
+ "max_position_embeddings": 512,
319
+ "model_type": "distilbert",
320
+ "n_heads": 12,
321
+ "n_layers": 6,
322
+ "pad_token_id": 0,
323
+ "qa_dropout": 0.1,
324
+ "seq_classif_dropout": 0.2,
325
+ "sinusoidal_pos_embds": false,
326
+ "tie_weights_": true,
327
+ "torch_dtype": "float32",
328
+ "transformers_version": "4.33.1",
329
+ "vocab_size": 30522
330
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36e67ea0fce3b2deb936ce32c1b428689f4c494885111823401e6bc20d0994d9
3
+ size 268313837
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22b6203c286cbadd540981e600922de9cd9c6c4006beabc38b10f1da262c8d82
3
+ size 4027
vocab.txt ADDED
The diff for this file is too large to render. See raw diff