File size: 20,766 Bytes
4436f0d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
2022-07-03 13:02:00,483 - __main__ - INFO - Label List:['O', 'B-PERSON', 'I-PERSON', 'B-NORP', 'I-NORP', 'B-FAC', 'I-FAC', 'B-ORG', 'I-ORG', 'B-GPE', 'I-GPE', 'B-LOC', 'I-LOC', 'B-PRODUCT', 'I-PRODUCT', 'B-DATE', 'I-DATE', 'B-TIME', 'I-TIME', 'B-PERCENT', 'I-PERCENT', 'B-MONEY', 'I-MONEY', 'B-QUANTITY', 'I-QUANTITY', 'B-ORDINAL', 'I-ORDINAL', 'B-CARDINAL', 'I-CARDINAL', 'B-EVENT', 'I-EVENT', 'B-WORK_OF_ART', 'I-WORK_OF_ART', 'B-LAW', 'I-LAW', 'B-LANGUAGE', 'I-LANGUAGE']
2022-07-03 13:02:08,987 - __main__ - INFO - Dataset({
    features: ['id', 'words', 'ner_tags'],
    num_rows: 75187
})
2022-07-03 13:02:09,752 - __main__ - INFO - Dataset({
    features: ['id', 'words', 'ner_tags'],
    num_rows: 9479
})
2022-07-03 13:02:09,755 - transformers.tokenization_utils_base - INFO - Didn't find file models/distilbert-base-uncased_1656660721.137864/checkpoint-14100/added_tokens.json. We won't load it.
2022-07-03 13:02:09,756 - transformers.tokenization_utils_base - INFO - loading file models/distilbert-base-uncased_1656660721.137864/checkpoint-14100/vocab.txt
2022-07-03 13:02:09,756 - transformers.tokenization_utils_base - INFO - loading file models/distilbert-base-uncased_1656660721.137864/checkpoint-14100/tokenizer.json
2022-07-03 13:02:09,756 - transformers.tokenization_utils_base - INFO - loading file None
2022-07-03 13:02:09,757 - transformers.tokenization_utils_base - INFO - loading file models/distilbert-base-uncased_1656660721.137864/checkpoint-14100/special_tokens_map.json
2022-07-03 13:02:09,757 - transformers.tokenization_utils_base - INFO - loading file models/distilbert-base-uncased_1656660721.137864/checkpoint-14100/tokenizer_config.json
2022-07-03 13:02:09,775 - __main__ - INFO - {'input_ids': [[101, 2054, 2785, 1997, 3638, 1029, 102, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [101, 2057, 26438, 2135, 13260, 2017, 2000, 3422, 1037, 2569, 3179, 1997, 2408, 2859, 1012, 102, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [101, 1059, 2860, 2462, 16209, 2006, 1996, 2307, 3011, 1997, 2859, 1024, 10721, 5758, 1997, 13843, 18003, 3137, 102, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [101, 3061, 4206, 2006, 13843, 18003, 3137, 2003, 1996, 6104, 2000, 1996, 3634, 10435, 5805, 1012, 102, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [101, 2009, 2003, 3605, 1997, 1037, 3078, 26261, 2571, 1010, 3905, 26261, 4244, 1010, 1037, 4121, 2461, 6743, 1998, 14400, 3578, 1010, 1998, 1996, 2307, 2813, 1010, 2426, 2060, 2477, 1012, 102]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]}
2022-07-03 13:02:09,776 - __main__ - INFO - ['[CLS]', 'what', 'kind', 'of', 'memory', '?', '[SEP]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]']
2022-07-03 13:02:09,776 - __main__ - INFO - ['[CLS]', 'we', 'respectful', '##ly', 'invite', 'you', 'to', 'watch', 'a', 'special', 'edition', 'of', 'across', 'china', '.', '[SEP]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]']
2022-07-03 13:02:09,777 - __main__ - INFO - ['[CLS]', 'w', '##w', 'ii', 'landmarks', 'on', 'the', 'great', 'earth', 'of', 'china', ':', 'eternal', 'memories', 'of', 'tai', '##hang', 'mountain', '[SEP]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]']
2022-07-03 13:02:09,777 - __main__ - INFO - ['[CLS]', 'standing', 'tall', 'on', 'tai', '##hang', 'mountain', 'is', 'the', 'monument', 'to', 'the', 'hundred', 'regiments', 'offensive', '.', '[SEP]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]']
2022-07-03 13:02:09,778 - __main__ - INFO - ['[CLS]', 'it', 'is', 'composed', 'of', 'a', 'primary', 'ste', '##le', ',', 'secondary', 'ste', '##les', ',', 'a', 'huge', 'round', 'sculpture', 'and', 'beacon', 'tower', ',', 'and', 'the', 'great', 'wall', ',', 'among', 'other', 'things', '.', '[SEP]']
2022-07-03 13:02:09,778 - __main__ - INFO - -------------
2022-07-03 13:02:09,778 - __main__ - INFO - ['[CLS]', 'we', 'respectful', '##ly', 'invite', 'you', 'to', 'watch', 'a', 'special', 'edition', 'of', 'across', 'china', '.', '[SEP]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]', '[PAD]']
2022-07-03 13:02:09,779 - __main__ - INFO - [None, 0, 1, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None]
2022-07-03 13:02:09,785 - datasets.fingerprint - WARNING - Parameter 'function'=<function tokenize_and_align_labels at 0x7f675dfb45e0> of the transform datasets.arrow_dataset.Dataset._map_single couldn't be hashed properly, a random hash was used instead. Make sure your transforms and parameters are serializable with pickle or dill for the dataset fingerprinting and caching to work. If you reuse this transform, the caching mechanism will consider it to be different from the previous calls and recompute everything. This warning is only showed once. Subsequent hashing failures won't be showed.
2022-07-03 13:02:14,916 - __main__ - INFO - {'id': [0, 1, 2, 3, 4], 'words': [['What', 'kind', 'of', 'memory', '?'], ['We', 'respectfully', 'invite', 'you', 'to', 'watch', 'a', 'special', 'edition', 'of', 'Across', 'China', '.'], ['WW', 'II', 'Landmarks', 'on', 'the', 'Great', 'Earth', 'of', 'China', ':', 'Eternal', 'Memories', 'of', 'Taihang', 'Mountain'], ['Standing', 'tall', 'on', 'Taihang', 'Mountain', 'is', 'the', 'Monument', 'to', 'the', 'Hundred', 'Regiments', 'Offensive', '.'], ['It', 'is', 'composed', 'of', 'a', 'primary', 'stele', ',', 'secondary', 'steles', ',', 'a', 'huge', 'round', 'sculpture', 'and', 'beacon', 'tower', ',', 'and', 'the', 'Great', 'Wall', ',', 'among', 'other', 'things', '.']], 'ner_tags': [[0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 8, 0], [31, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32], [0, 0, 0, 11, 12, 0, 31, 32, 32, 32, 32, 32, 32, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 31, 32, 32, 0, 0, 0, 0, 0]], 'input_ids': [[101, 2054, 2785, 1997, 3638, 1029, 102], [101, 2057, 26438, 2135, 13260, 2017, 2000, 3422, 1037, 2569, 3179, 1997, 2408, 2859, 1012, 102], [101, 1059, 2860, 2462, 16209, 2006, 1996, 2307, 3011, 1997, 2859, 1024, 10721, 5758, 1997, 13843, 18003, 3137, 102], [101, 3061, 4206, 2006, 13843, 18003, 3137, 2003, 1996, 6104, 2000, 1996, 3634, 10435, 5805, 1012, 102], [101, 2009, 2003, 3605, 1997, 1037, 3078, 26261, 2571, 1010, 3905, 26261, 4244, 1010, 1037, 4121, 2461, 6743, 1998, 14400, 3578, 1010, 1998, 1996, 2307, 2813, 1010, 2426, 2060, 2477, 1012, 102]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]], 'labels': [[-100, 0, 0, 0, 0, 0, -100], [-100, 0, 0, -100, 0, 0, 0, 0, 0, 0, 0, 0, 7, 8, 0, -100], [-100, 31, -100, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, -100, 32, -100], [-100, 0, 0, 0, 11, -100, 12, 0, 31, 32, 32, 32, 32, 32, 32, 0, -100], [-100, 0, 0, 0, 0, 0, 0, 0, -100, 0, 0, 0, -100, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 31, 32, 32, 0, 0, 0, 0, 0, -100]]}
2022-07-03 13:02:16,871 - transformers.configuration_utils - INFO - loading configuration file models/distilbert-base-uncased_1656660721.137864/checkpoint-14100/config.json
2022-07-03 13:02:16,873 - transformers.configuration_utils - INFO - Model config DistilBertConfig {
  "_name_or_path": "models/distilbert-base-uncased_1656660721.137864/checkpoint-14100",
  "activation": "gelu",
  "architectures": [
    "DistilBertForTokenClassification"
  ],
  "attention_dropout": 0.1,
  "dim": 768,
  "dropout": 0.1,
  "hidden_dim": 3072,
  "id2label": {
    "0": "O",
    "1": "B-PERSON",
    "2": "I-PERSON",
    "3": "B-NORP",
    "4": "I-NORP",
    "5": "B-FAC",
    "6": "I-FAC",
    "7": "B-ORG",
    "8": "I-ORG",
    "9": "B-GPE",
    "10": "I-GPE",
    "11": "B-LOC",
    "12": "I-LOC",
    "13": "B-PRODUCT",
    "14": "I-PRODUCT",
    "15": "B-DATE",
    "16": "I-DATE",
    "17": "B-TIME",
    "18": "I-TIME",
    "19": "B-PERCENT",
    "20": "I-PERCENT",
    "21": "B-MONEY",
    "22": "I-MONEY",
    "23": "B-QUANTITY",
    "24": "I-QUANTITY",
    "25": "B-ORDINAL",
    "26": "I-ORDINAL",
    "27": "B-CARDINAL",
    "28": "I-CARDINAL",
    "29": "B-EVENT",
    "30": "I-EVENT",
    "31": "B-WORK_OF_ART",
    "32": "I-WORK_OF_ART",
    "33": "B-LAW",
    "34": "I-LAW",
    "35": "B-LANGUAGE",
    "36": "I-LANGUAGE"
  },
  "initializer_range": 0.02,
  "label2id": {
    "B-CARDINAL": 27,
    "B-DATE": 15,
    "B-EVENT": 29,
    "B-FAC": 5,
    "B-GPE": 9,
    "B-LANGUAGE": 35,
    "B-LAW": 33,
    "B-LOC": 11,
    "B-MONEY": 21,
    "B-NORP": 3,
    "B-ORDINAL": 25,
    "B-ORG": 7,
    "B-PERCENT": 19,
    "B-PERSON": 1,
    "B-PRODUCT": 13,
    "B-QUANTITY": 23,
    "B-TIME": 17,
    "B-WORK_OF_ART": 31,
    "I-CARDINAL": 28,
    "I-DATE": 16,
    "I-EVENT": 30,
    "I-FAC": 6,
    "I-GPE": 10,
    "I-LANGUAGE": 36,
    "I-LAW": 34,
    "I-LOC": 12,
    "I-MONEY": 22,
    "I-NORP": 4,
    "I-ORDINAL": 26,
    "I-ORG": 8,
    "I-PERCENT": 20,
    "I-PERSON": 2,
    "I-PRODUCT": 14,
    "I-QUANTITY": 24,
    "I-TIME": 18,
    "I-WORK_OF_ART": 32,
    "O": 0
  },
  "max_position_embeddings": 512,
  "model_type": "distilbert",
  "n_heads": 12,
  "n_layers": 6,
  "pad_token_id": 0,
  "qa_dropout": 0.1,
  "seq_classif_dropout": 0.2,
  "sinusoidal_pos_embds": false,
  "tie_weights_": true,
  "torch_dtype": "float32",
  "transformers_version": "4.20.0",
  "vocab_size": 30522
}

2022-07-03 13:02:17,083 - transformers.modeling_utils - INFO - loading weights file models/distilbert-base-uncased_1656660721.137864/checkpoint-14100/pytorch_model.bin
2022-07-03 13:02:18,221 - transformers.modeling_utils - INFO - All model checkpoint weights were used when initializing DistilBertForTokenClassification.

2022-07-03 13:02:18,223 - transformers.modeling_utils - INFO - All the weights of DistilBertForTokenClassification were initialized from the model checkpoint at models/distilbert-base-uncased_1656660721.137864/checkpoint-14100.
If your task is similar to the task the model of the checkpoint was trained on, you can already use DistilBertForTokenClassification for predictions without further training.
2022-07-03 13:02:18,226 - __main__ - INFO - DistilBertForTokenClassification(
  (distilbert): DistilBertModel(
    (embeddings): Embeddings(
      (word_embeddings): Embedding(30522, 768, padding_idx=0)
      (position_embeddings): Embedding(512, 768)
      (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
      (dropout): Dropout(p=0.1, inplace=False)
    )
    (transformer): Transformer(
      (layer): ModuleList(
        (0): TransformerBlock(
          (attention): MultiHeadSelfAttention(
            (dropout): Dropout(p=0.1, inplace=False)
            (q_lin): Linear(in_features=768, out_features=768, bias=True)
            (k_lin): Linear(in_features=768, out_features=768, bias=True)
            (v_lin): Linear(in_features=768, out_features=768, bias=True)
            (out_lin): Linear(in_features=768, out_features=768, bias=True)
          )
          (sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
          (ffn): FFN(
            (dropout): Dropout(p=0.1, inplace=False)
            (lin1): Linear(in_features=768, out_features=3072, bias=True)
            (lin2): Linear(in_features=3072, out_features=768, bias=True)
            (activation): GELUActivation()
          )
          (output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
        )
        (1): TransformerBlock(
          (attention): MultiHeadSelfAttention(
            (dropout): Dropout(p=0.1, inplace=False)
            (q_lin): Linear(in_features=768, out_features=768, bias=True)
            (k_lin): Linear(in_features=768, out_features=768, bias=True)
            (v_lin): Linear(in_features=768, out_features=768, bias=True)
            (out_lin): Linear(in_features=768, out_features=768, bias=True)
          )
          (sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
          (ffn): FFN(
            (dropout): Dropout(p=0.1, inplace=False)
            (lin1): Linear(in_features=768, out_features=3072, bias=True)
            (lin2): Linear(in_features=3072, out_features=768, bias=True)
            (activation): GELUActivation()
          )
          (output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
        )
        (2): TransformerBlock(
          (attention): MultiHeadSelfAttention(
            (dropout): Dropout(p=0.1, inplace=False)
            (q_lin): Linear(in_features=768, out_features=768, bias=True)
            (k_lin): Linear(in_features=768, out_features=768, bias=True)
            (v_lin): Linear(in_features=768, out_features=768, bias=True)
            (out_lin): Linear(in_features=768, out_features=768, bias=True)
          )
          (sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
          (ffn): FFN(
            (dropout): Dropout(p=0.1, inplace=False)
            (lin1): Linear(in_features=768, out_features=3072, bias=True)
            (lin2): Linear(in_features=3072, out_features=768, bias=True)
            (activation): GELUActivation()
          )
          (output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
        )
        (3): TransformerBlock(
          (attention): MultiHeadSelfAttention(
            (dropout): Dropout(p=0.1, inplace=False)
            (q_lin): Linear(in_features=768, out_features=768, bias=True)
            (k_lin): Linear(in_features=768, out_features=768, bias=True)
            (v_lin): Linear(in_features=768, out_features=768, bias=True)
            (out_lin): Linear(in_features=768, out_features=768, bias=True)
          )
          (sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
          (ffn): FFN(
            (dropout): Dropout(p=0.1, inplace=False)
            (lin1): Linear(in_features=768, out_features=3072, bias=True)
            (lin2): Linear(in_features=3072, out_features=768, bias=True)
            (activation): GELUActivation()
          )
          (output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
        )
        (4): TransformerBlock(
          (attention): MultiHeadSelfAttention(
            (dropout): Dropout(p=0.1, inplace=False)
            (q_lin): Linear(in_features=768, out_features=768, bias=True)
            (k_lin): Linear(in_features=768, out_features=768, bias=True)
            (v_lin): Linear(in_features=768, out_features=768, bias=True)
            (out_lin): Linear(in_features=768, out_features=768, bias=True)
          )
          (sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
          (ffn): FFN(
            (dropout): Dropout(p=0.1, inplace=False)
            (lin1): Linear(in_features=768, out_features=3072, bias=True)
            (lin2): Linear(in_features=3072, out_features=768, bias=True)
            (activation): GELUActivation()
          )
          (output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
        )
        (5): TransformerBlock(
          (attention): MultiHeadSelfAttention(
            (dropout): Dropout(p=0.1, inplace=False)
            (q_lin): Linear(in_features=768, out_features=768, bias=True)
            (k_lin): Linear(in_features=768, out_features=768, bias=True)
            (v_lin): Linear(in_features=768, out_features=768, bias=True)
            (out_lin): Linear(in_features=768, out_features=768, bias=True)
          )
          (sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
          (ffn): FFN(
            (dropout): Dropout(p=0.1, inplace=False)
            (lin1): Linear(in_features=768, out_features=3072, bias=True)
            (lin2): Linear(in_features=3072, out_features=768, bias=True)
            (activation): GELUActivation()
          )
          (output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
        )
      )
    )
  )
  (dropout): Dropout(p=0.1, inplace=False)
  (classifier): Linear(in_features=768, out_features=37, bias=True)
)
2022-07-03 13:02:18,228 - __main__ - INFO - CONFIGS:{
    "output_dir": "./models/distilbert-base-uncased_1656833520.4812543",
    "per_device_train_batch_size": 16,
    "per_device_eval_batch_size": 16,
    "save_total_limit": 2,
    "num_train_epochs": 3,
    "seed": 1,
    "load_best_model_at_end": true,
    "evaluation_strategy": "epoch",
    "save_strategy": "epoch",
    "learning_rate": 2e-05,
    "weight_decay": 0.01,
    "logging_steps": 469.0
}
2022-07-03 13:02:18,228 - transformers.training_args - INFO - PyTorch: setting up devices
2022-07-03 13:02:18,318 - transformers.training_args - INFO - The default value for the training argument `--report_to` will change in v5 (from all installed integrations to none). In v5, you will need to use `--report_to all` to get the same behavior as now. You should start updating your code and make this info disappear :-).
2022-07-03 13:02:23,736 - __main__ - INFO - [[ MODEL EVALUATION ]]
2022-07-03 13:02:23,736 - transformers.trainer - INFO - The following columns in the evaluation set don't have a corresponding argument in `DistilBertForTokenClassification.forward` and have been ignored: id, ner_tags, words. If id, ner_tags, words are not expected by `DistilBertForTokenClassification.forward`,  you can safely ignore this message.
2022-07-03 13:02:23,752 - transformers.trainer - INFO - ***** Running Evaluation *****
2022-07-03 13:02:23,752 - transformers.trainer - INFO -   Num examples = 9479
2022-07-03 13:02:23,752 - transformers.trainer - INFO -   Batch size = 16
2022-07-03 13:03:05,412 - __main__ - INFO - {'eval_loss': 0.08268037438392639, 'eval_precision': 0.8460803059273423, 'eval_recall': 0.8647952385182553, 'eval_f1': 0.8553354127311866, 'eval_accuracy': 0.9779158976052459, 'eval_runtime': 41.6535, 'eval_samples_per_second': 227.568, 'eval_steps_per_second': 14.236, 'step': 0}
2022-07-03 13:03:05,413 - transformers.trainer - INFO - The following columns in the test set don't have a corresponding argument in `DistilBertForTokenClassification.forward` and have been ignored: id, ner_tags, words. If id, ner_tags, words are not expected by `DistilBertForTokenClassification.forward`,  you can safely ignore this message.
2022-07-03 13:03:05,415 - transformers.trainer - INFO - ***** Running Prediction *****
2022-07-03 13:03:05,415 - transformers.trainer - INFO -   Num examples = 9479
2022-07-03 13:03:05,415 - transformers.trainer - INFO -   Batch size = 16
2022-07-03 13:03:49,560 - __main__ - INFO -               precision    recall  f1-score   support

    CARDINAL       0.84      0.86      0.85       935
        DATE       0.83      0.88      0.85      1602
       EVENT       0.57      0.57      0.57        63
         FAC       0.55      0.62      0.58       135
         GPE       0.95      0.92      0.94      2240
    LANGUAGE       0.82      0.64      0.72        22
         LAW       0.50      0.50      0.50        40
         LOC       0.55      0.72      0.62       179
       MONEY       0.87      0.89      0.88       314
        NORP       0.85      0.89      0.87       841
     ORDINAL       0.81      0.88      0.84       195
         ORG       0.81      0.83      0.82      1795
     PERCENT       0.87      0.89      0.88       349
      PERSON       0.93      0.93      0.93      1988
     PRODUCT       0.55      0.55      0.55        76
    QUANTITY       0.71      0.80      0.75       105
        TIME       0.59      0.66      0.62       212
 WORK_OF_ART       0.42      0.44      0.43       166

   micro avg       0.85      0.86      0.86     11257
   macro avg       0.72      0.75      0.73     11257
weighted avg       0.85      0.86      0.86     11257