lxyuan commited on
Commit
a6bc588
1 Parent(s): 4c70cd0

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<end>": 105880,
3
+ "<start>": 105879
4
+ }
config.json ADDED
@@ -0,0 +1,231 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SpanMarkerModel"
4
+ ],
5
+ "encoder": {
6
+ "_name_or_path": "bert-base-multilingual-uncased",
7
+ "add_cross_attention": false,
8
+ "architectures": [
9
+ "BertForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": null,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "directionality": "bidi",
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": null,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "hidden_act": "gelu",
30
+ "hidden_dropout_prob": 0.1,
31
+ "hidden_size": 768,
32
+ "id2label": {
33
+ "0": "O",
34
+ "1": "B-PER",
35
+ "2": "I-PER",
36
+ "3": "B-ORG",
37
+ "4": "I-ORG",
38
+ "5": "B-LOC",
39
+ "6": "I-LOC",
40
+ "7": "B-ANIM",
41
+ "8": "I-ANIM",
42
+ "9": "B-BIO",
43
+ "10": "I-BIO",
44
+ "11": "B-CEL",
45
+ "12": "I-CEL",
46
+ "13": "B-DIS",
47
+ "14": "I-DIS",
48
+ "15": "B-EVE",
49
+ "16": "I-EVE",
50
+ "17": "B-FOOD",
51
+ "18": "I-FOOD",
52
+ "19": "B-INST",
53
+ "20": "I-INST",
54
+ "21": "B-MEDIA",
55
+ "22": "I-MEDIA",
56
+ "23": "B-MYTH",
57
+ "24": "I-MYTH",
58
+ "25": "B-PLANT",
59
+ "26": "I-PLANT",
60
+ "27": "B-TIME",
61
+ "28": "I-TIME",
62
+ "29": "B-VEHI",
63
+ "30": "I-VEHI"
64
+ },
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 3072,
67
+ "is_decoder": false,
68
+ "is_encoder_decoder": false,
69
+ "label2id": {
70
+ "B-ANIM": 7,
71
+ "B-BIO": 9,
72
+ "B-CEL": 11,
73
+ "B-DIS": 13,
74
+ "B-EVE": 15,
75
+ "B-FOOD": 17,
76
+ "B-INST": 19,
77
+ "B-LOC": 5,
78
+ "B-MEDIA": 21,
79
+ "B-MYTH": 23,
80
+ "B-ORG": 3,
81
+ "B-PER": 1,
82
+ "B-PLANT": 25,
83
+ "B-TIME": 27,
84
+ "B-VEHI": 29,
85
+ "I-ANIM": 8,
86
+ "I-BIO": 10,
87
+ "I-CEL": 12,
88
+ "I-DIS": 14,
89
+ "I-EVE": 16,
90
+ "I-FOOD": 18,
91
+ "I-INST": 20,
92
+ "I-LOC": 6,
93
+ "I-MEDIA": 22,
94
+ "I-MYTH": 24,
95
+ "I-ORG": 4,
96
+ "I-PER": 2,
97
+ "I-PLANT": 26,
98
+ "I-TIME": 28,
99
+ "I-VEHI": 30,
100
+ "O": 0
101
+ },
102
+ "layer_norm_eps": 1e-12,
103
+ "length_penalty": 1.0,
104
+ "max_length": 20,
105
+ "max_position_embeddings": 512,
106
+ "min_length": 0,
107
+ "model_type": "bert",
108
+ "no_repeat_ngram_size": 0,
109
+ "num_attention_heads": 12,
110
+ "num_beam_groups": 1,
111
+ "num_beams": 1,
112
+ "num_hidden_layers": 12,
113
+ "num_return_sequences": 1,
114
+ "output_attentions": false,
115
+ "output_hidden_states": false,
116
+ "output_scores": false,
117
+ "pad_token_id": 0,
118
+ "pooler_fc_size": 768,
119
+ "pooler_num_attention_heads": 12,
120
+ "pooler_num_fc_layers": 3,
121
+ "pooler_size_per_head": 128,
122
+ "pooler_type": "first_token_transform",
123
+ "position_embedding_type": "absolute",
124
+ "prefix": null,
125
+ "problem_type": null,
126
+ "pruned_heads": {},
127
+ "remove_invalid_values": false,
128
+ "repetition_penalty": 1.0,
129
+ "return_dict": true,
130
+ "return_dict_in_generate": false,
131
+ "sep_token_id": null,
132
+ "suppress_tokens": null,
133
+ "task_specific_params": null,
134
+ "temperature": 1.0,
135
+ "tf_legacy_loss": false,
136
+ "tie_encoder_decoder": false,
137
+ "tie_word_embeddings": true,
138
+ "tokenizer_class": null,
139
+ "top_k": 50,
140
+ "top_p": 1.0,
141
+ "torch_dtype": null,
142
+ "torchscript": false,
143
+ "transformers_version": "4.30.2",
144
+ "type_vocab_size": 2,
145
+ "typical_p": 1.0,
146
+ "use_bfloat16": false,
147
+ "use_cache": true,
148
+ "vocab_size": 105881
149
+ },
150
+ "entity_max_length": 8,
151
+ "id2label": {
152
+ "0": "O",
153
+ "1": "ANIM",
154
+ "2": "BIO",
155
+ "3": "CEL",
156
+ "4": "DIS",
157
+ "5": "EVE",
158
+ "6": "FOOD",
159
+ "7": "INST",
160
+ "8": "LOC",
161
+ "9": "MEDIA",
162
+ "10": "MYTH",
163
+ "11": "ORG",
164
+ "12": "PER",
165
+ "13": "PLANT",
166
+ "14": "TIME",
167
+ "15": "VEHI"
168
+ },
169
+ "id2reduced_id": {
170
+ "0": 0,
171
+ "1": 12,
172
+ "2": 12,
173
+ "3": 11,
174
+ "4": 11,
175
+ "5": 8,
176
+ "6": 8,
177
+ "7": 1,
178
+ "8": 1,
179
+ "9": 2,
180
+ "10": 2,
181
+ "11": 3,
182
+ "12": 3,
183
+ "13": 4,
184
+ "14": 4,
185
+ "15": 5,
186
+ "16": 5,
187
+ "17": 6,
188
+ "18": 6,
189
+ "19": 7,
190
+ "20": 7,
191
+ "21": 9,
192
+ "22": 9,
193
+ "23": 10,
194
+ "24": 10,
195
+ "25": 13,
196
+ "26": 13,
197
+ "27": 14,
198
+ "28": 14,
199
+ "29": 15,
200
+ "30": 15
201
+ },
202
+ "label2id": {
203
+ "ANIM": 1,
204
+ "BIO": 2,
205
+ "CEL": 3,
206
+ "DIS": 4,
207
+ "EVE": 5,
208
+ "FOOD": 6,
209
+ "INST": 7,
210
+ "LOC": 8,
211
+ "MEDIA": 9,
212
+ "MYTH": 10,
213
+ "O": 0,
214
+ "ORG": 11,
215
+ "PER": 12,
216
+ "PLANT": 13,
217
+ "TIME": 14,
218
+ "VEHI": 15
219
+ },
220
+ "marker_max_length": 128,
221
+ "max_next_context": null,
222
+ "max_prev_context": null,
223
+ "model_max_length": 256,
224
+ "model_max_length_default": 512,
225
+ "model_type": "span-marker",
226
+ "span_marker_version": "1.2.4",
227
+ "torch_dtype": "float32",
228
+ "trained_with_document_context": false,
229
+ "transformers_version": "4.30.2",
230
+ "vocab_size": 105881
231
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa3b076d6d8ab937f591c118a99f8c501947bb3369b7f30a2a7a55e32d9c1fba
3
+ size 669603573
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": true,
6
+ "entity_max_length": 8,
7
+ "marker_max_length": 128,
8
+ "mask_token": "[MASK]",
9
+ "model_max_length": 256,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79219cb5c3f8eae0260ac62e6ae343bc69b0454cb6713912b70b5c1571958d99
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff