Wenkai Li commited on
Commit
43df8a7
·
1 Parent(s): cd71b8b

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,301 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'bout": 30605,
3
+ "'em": 30538,
4
+ "--Pudd'nhead": 30547,
5
+ "--and": 30595,
6
+ "1.E.1": 30585,
7
+ "1.E.7": 30634,
8
+ "1.E.8": 30586,
9
+ "1.E.9": 30635,
10
+ "1.F.3": 30587,
11
+ "A.": 30576,
12
+ "Abner": 30596,
13
+ "Alas": 30703,
14
+ "Australasia": 30666,
15
+ "B.": 30621,
16
+ "Ballarat": 30720,
17
+ "Ballou": 30748,
18
+ "Benares": 30654,
19
+ "Bixby": 30568,
20
+ "Blucher": 30769,
21
+ "Boers": 30618,
22
+ "Brede": 30799,
23
+ "Buller": 30543,
24
+ "C.": 30636,
25
+ "Camelot": 30721,
26
+ "Canty": 30542,
27
+ "Chamonix": 30749,
28
+ "Dr.": 30555,
29
+ "Ellsworth": 30626,
30
+ "Englishman": 30691,
31
+ "Ephesus": 30770,
32
+ "Fluker": 30667,
33
+ "Frenchman": 30606,
34
+ "Galilee": 30644,
35
+ "Ganges": 30733,
36
+ "Gutenberg": 30523,
37
+ "H.": 30734,
38
+ "Hargraves": 30735,
39
+ "Hendon": 30532,
40
+ "Hertford": 30627,
41
+ "Higbie": 30750,
42
+ "Hindoo": 30607,
43
+ "Horner": 30704,
44
+ "Hotchkiss": 30622,
45
+ "Huck": 30525,
46
+ "Huckleberry": 30668,
47
+ "I.": 30559,
48
+ "Injun": 30549,
49
+ "J.": 30655,
50
+ "Kamp": 30597,
51
+ "Kanaka": 30705,
52
+ "LICENSE": 30800,
53
+ "LIMITED": 30637,
54
+ "Launcelot": 30638,
55
+ "M.": 30611,
56
+ "Marget": 30575,
57
+ "Matterhorn": 30722,
58
+ "Meantime": 30628,
59
+ "Morland": 30645,
60
+ "Mormons": 30771,
61
+ "Mr.": 30522,
62
+ "Mrs.": 30528,
63
+ "Neckar": 30772,
64
+ "Nikolaus": 30656,
65
+ "P.M.": 30736,
66
+ "Podington": 30541,
67
+ "Presently": 30529,
68
+ "Protector": 30801,
69
+ "Q.": 30639,
70
+ "Rev.": 30669,
71
+ "S.": 30773,
72
+ "Saviour": 30577,
73
+ "Says": 30774,
74
+ "Seppi": 30657,
75
+ "Smyrna": 30775,
76
+ "St.": 30524,
77
+ "Taj": 30751,
78
+ "Thou": 30567,
79
+ "Thug": 30670,
80
+ "Thugs": 30671,
81
+ "Tis": 30706,
82
+ "Titbottom": 30623,
83
+ "Twain": 30737,
84
+ "U.S.": 30602,
85
+ "W.": 30723,
86
+ "Watkinson": 30578,
87
+ "What's": 30820,
88
+ "Zermatt": 30612,
89
+ "abide": 30646,
90
+ "abreast": 30629,
91
+ "admirable": 30738,
92
+ "agin": 30658,
93
+ "agreeable": 30776,
94
+ "airy": 30659,
95
+ "alas": 30724,
96
+ "aloft": 30560,
97
+ "and--": 30672,
98
+ "apiece": 30582,
99
+ "assemblage": 30684,
100
+ "astrologer": 30692,
101
+ "beggar": 30660,
102
+ "beggars": 30707,
103
+ "bewildering": 30739,
104
+ "bosom": 30647,
105
+ "boyhood": 30777,
106
+ "breezy": 30752,
107
+ "buggy": 30778,
108
+ "calamity": 30693,
109
+ "chap": 30685,
110
+ "charmed": 30753,
111
+ "chivalry": 30779,
112
+ "coachman": 30780,
113
+ "comely": 30708,
114
+ "contented": 30686,
115
+ "cordial": 30781,
116
+ "countenance": 30551,
117
+ "crags": 30673,
118
+ "dainty": 30588,
119
+ "deceive": 30687,
120
+ "desolate": 30603,
121
+ "desolation": 30613,
122
+ "dey": 30589,
123
+ "didn't": 30819,
124
+ "diligently": 30802,
125
+ "dismal": 30548,
126
+ "doan": 30740,
127
+ "donkeys": 30694,
128
+ "doth": 30608,
129
+ "doubtless": 30569,
130
+ "dreamy": 30661,
131
+ "dreary": 30579,
132
+ "dusky": 30803,
133
+ "eloquent": 30609,
134
+ "enchanting": 30630,
135
+ "enchantment": 30754,
136
+ "errand": 30695,
137
+ "exceedingly": 30557,
138
+ "fanciful": 30674,
139
+ "feeble": 30648,
140
+ "fetched": 30546,
141
+ "fooling": 30782,
142
+ "forlorn": 30615,
143
+ "fortnight": 30725,
144
+ "friendless": 30741,
145
+ "furnish": 30558,
146
+ "gait": 30631,
147
+ "gaudy": 30592,
148
+ "ghastly": 30610,
149
+ "git": 30561,
150
+ "glimpses": 30675,
151
+ "gloomy": 30688,
152
+ "goin'": 30742,
153
+ "graces": 30804,
154
+ "gracious": 30564,
155
+ "grandeur": 30565,
156
+ "gratefully": 30755,
157
+ "gratified": 30709,
158
+ "greatness": 30805,
159
+ "grisly": 30726,
160
+ "gwyne": 30676,
161
+ "hain't": 30550,
162
+ "hast": 30662,
163
+ "hath": 30536,
164
+ "hearty": 30632,
165
+ "heave": 30806,
166
+ "hither": 30590,
167
+ "hogs": 30677,
168
+ "homeward": 30743,
169
+ "hospitable": 30783,
170
+ "idiotic": 30784,
171
+ "indignation": 30744,
172
+ "inquire": 30640,
173
+ "inquiring": 30807,
174
+ "intolerable": 30808,
175
+ "invent": 30745,
176
+ "jest": 30604,
177
+ "knowed": 30537,
178
+ "lain": 30785,
179
+ "lofty": 30539,
180
+ "lonesome": 30678,
181
+ "manifestly": 30809,
182
+ "marvels": 30727,
183
+ "massed": 30593,
184
+ "mellow": 30649,
185
+ "merciful": 30810,
186
+ "misfortune": 30619,
187
+ "monotonous": 30641,
188
+ "mournful": 30679,
189
+ "mules": 30556,
190
+ "multitudes": 30616,
191
+ "natured": 30710,
192
+ "nigger": 30531,
193
+ "niggers": 30598,
194
+ "nigh": 30786,
195
+ "o'clock": 30534,
196
+ "out--": 30787,
197
+ "o’clock": 30572,
198
+ "paddled": 30811,
199
+ "pap": 30580,
200
+ "paragraphs": 30696,
201
+ "particulars": 30697,
202
+ "pathos": 30788,
203
+ "pauper": 30756,
204
+ "peculiarly": 30599,
205
+ "perceptible": 30789,
206
+ "peril": 30624,
207
+ "perilous": 30711,
208
+ "perplexed": 30680,
209
+ "personage": 30757,
210
+ "petrified": 30698,
211
+ "piloting": 30758,
212
+ "pitiful": 30642,
213
+ "pitiless": 30759,
214
+ "placid": 30760,
215
+ "placidly": 30812,
216
+ "pluck": 30813,
217
+ "precipice": 30552,
218
+ "precipices": 30699,
219
+ "prodigious": 30540,
220
+ "profanity": 30663,
221
+ "quaint": 30553,
222
+ "rafts": 30790,
223
+ "raiment": 30728,
224
+ "rascal": 30761,
225
+ "readable": 30791,
226
+ "reckoned": 30544,
227
+ "refund": 30566,
228
+ "repose": 30746,
229
+ "repulsive": 30792,
230
+ "reverence": 30570,
231
+ "reverent": 30793,
232
+ "reverently": 30729,
233
+ "rightly": 30681,
234
+ "roused": 30794,
235
+ "said--": 30530,
236
+ "savages": 30571,
237
+ "says--": 30712,
238
+ "shabby": 30617,
239
+ "shalt": 30713,
240
+ "shapely": 30814,
241
+ "showy": 30650,
242
+ "skiff": 30651,
243
+ "slouch": 30762,
244
+ "smote": 30763,
245
+ "smothered": 30700,
246
+ "sociable": 30614,
247
+ "solemnity": 30682,
248
+ "sorrowful": 30620,
249
+ "spectacles": 30554,
250
+ "splendor": 30594,
251
+ "splendors": 30764,
252
+ "staid": 30714,
253
+ "starve": 30815,
254
+ "stately": 30533,
255
+ "steamboats": 30652,
256
+ "straightway": 30573,
257
+ "stupendous": 30683,
258
+ "suggestive": 30715,
259
+ "summits": 30701,
260
+ "sumptuous": 30643,
261
+ "superstition": 30765,
262
+ "swarmed": 30716,
263
+ "t'other": 30664,
264
+ "tarry": 30730,
265
+ "tedious": 30563,
266
+ "thickly": 30766,
267
+ "thine": 30767,
268
+ "thither": 30562,
269
+ "thyself": 30816,
270
+ "tint": 30717,
271
+ "tiresome": 30600,
272
+ "tm": 30526,
273
+ "tolerably": 30591,
274
+ "torrent": 30718,
275
+ "tramp": 30583,
276
+ "tranquil": 30584,
277
+ "tranquilly": 30817,
278
+ "trifle": 30545,
279
+ "trifles": 30768,
280
+ "trifling": 30574,
281
+ "trot": 30795,
282
+ "troublesome": 30633,
283
+ "twinkling": 30731,
284
+ "unconsciously": 30653,
285
+ "unspeakably": 30719,
286
+ "voice--": 30796,
287
+ "waked": 30797,
288
+ "warn't": 30527,
289
+ "warn’t": 30665,
290
+ "watchman": 30689,
291
+ "wherefore": 30702,
292
+ "wholesome": 30690,
293
+ "whoop": 30798,
294
+ "widest": 30732,
295
+ "withal": 30747,
296
+ "wonderfully": 30601,
297
+ "worldly": 30818,
298
+ "wretched": 30625,
299
+ "yonder": 30535,
300
+ "’em": 30581
301
+ }
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.21.1",
24
+ "vocab_size": 30821
25
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cfac8905a81fc1977fb747b00dd00e13d3d958285a383436b327b1611abb551
3
+ size 268772849
runs/Aug07_06-10-00_61fa7434770c/1659852620.367633/events.out.tfevents.1659852620.61fa7434770c.76.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91bbf185dba6e1288bbf7cb5d9854d3fa64a0f9c5554515df7293ceaeddcc701
3
+ size 5521
runs/Aug07_06-10-00_61fa7434770c/events.out.tfevents.1659852620.61fa7434770c.76.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc18f7d9fa562fc1661b9fff745ec095abd7fe5f54191d5c9b15b77c4bdf6c44
3
+ size 3738
runs/Aug07_06-11-32_61fa7434770c/1659852702.952371/events.out.tfevents.1659852702.61fa7434770c.76.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d8dc5e6c5de12d292bc73932caa0117fa9cd04936f8266bfbe28e2390df1fa7
3
+ size 5521
runs/Aug07_06-11-32_61fa7434770c/events.out.tfevents.1659852702.61fa7434770c.76.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29ad7447de26255885c57f2d972f059a44f4a4da547b729532097f05f4b0c4d5
3
+ size 5003
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 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "distilbert-base-uncased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "DistilBertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aaa732f4f671e83f2998070266824939310364e021d80068cc74ef8d088a8fc
3
+ size 3439
vocab.txt ADDED
The diff for this file is too large to render. See raw diff