medxiaorudan
commited on
Commit
•
f6de6f2
1
Parent(s):
c9e77c9
Upload 10 files
Browse files- all_results.json +8 -0
- config.json +92 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- train_results.json +8 -0
- trainer_state.json +286 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"total_flos": 1.929975843125117e+16,
|
4 |
+
"train_loss": 0.1132796828881914,
|
5 |
+
"train_runtime": 2485.5568,
|
6 |
+
"train_samples_per_second": 211.269,
|
7 |
+
"train_steps_per_second": 4.401
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "B-PER",
|
15 |
+
"2": "I-PER",
|
16 |
+
"3": "B-ORG",
|
17 |
+
"4": "I-ORG",
|
18 |
+
"5": "B-LOC",
|
19 |
+
"6": "I-LOC",
|
20 |
+
"7": "B-ANIM",
|
21 |
+
"8": "I-ANIM",
|
22 |
+
"9": "B-BIO",
|
23 |
+
"10": "I-BIO",
|
24 |
+
"11": "B-CEL",
|
25 |
+
"12": "I-CEL",
|
26 |
+
"13": "B-DIS",
|
27 |
+
"14": "I-DIS",
|
28 |
+
"15": "B-EVE",
|
29 |
+
"16": "I-EVE",
|
30 |
+
"17": "B-FOOD",
|
31 |
+
"18": "I-FOOD",
|
32 |
+
"19": "B-INST",
|
33 |
+
"20": "I-INST",
|
34 |
+
"21": "B-MEDIA",
|
35 |
+
"22": "I-MEDIA",
|
36 |
+
"23": "B-MYTH",
|
37 |
+
"24": "I-MYTH",
|
38 |
+
"25": "B-PLANT",
|
39 |
+
"26": "I-PLANT",
|
40 |
+
"27": "B-TIME",
|
41 |
+
"28": "I-TIME",
|
42 |
+
"29": "B-VEHI",
|
43 |
+
"30": "I-VEHI"
|
44 |
+
},
|
45 |
+
"initializer_range": 0.02,
|
46 |
+
"intermediate_size": 3072,
|
47 |
+
"label2id": {
|
48 |
+
"B-ANIM": 7,
|
49 |
+
"B-BIO": 9,
|
50 |
+
"B-CEL": 11,
|
51 |
+
"B-DIS": 13,
|
52 |
+
"B-EVE": 15,
|
53 |
+
"B-FOOD": 17,
|
54 |
+
"B-INST": 19,
|
55 |
+
"B-LOC": 5,
|
56 |
+
"B-MEDIA": 21,
|
57 |
+
"B-MYTH": 23,
|
58 |
+
"B-ORG": 3,
|
59 |
+
"B-PER": 1,
|
60 |
+
"B-PLANT": 25,
|
61 |
+
"B-TIME": 27,
|
62 |
+
"B-VEHI": 29,
|
63 |
+
"I-ANIM": 8,
|
64 |
+
"I-BIO": 10,
|
65 |
+
"I-CEL": 12,
|
66 |
+
"I-DIS": 14,
|
67 |
+
"I-EVE": 16,
|
68 |
+
"I-FOOD": 18,
|
69 |
+
"I-INST": 20,
|
70 |
+
"I-LOC": 6,
|
71 |
+
"I-MEDIA": 22,
|
72 |
+
"I-MYTH": 24,
|
73 |
+
"I-ORG": 4,
|
74 |
+
"I-PER": 2,
|
75 |
+
"I-PLANT": 26,
|
76 |
+
"I-TIME": 28,
|
77 |
+
"I-VEHI": 30,
|
78 |
+
"O": 0
|
79 |
+
},
|
80 |
+
"layer_norm_eps": 1e-12,
|
81 |
+
"max_position_embeddings": 512,
|
82 |
+
"model_type": "bert",
|
83 |
+
"num_attention_heads": 12,
|
84 |
+
"num_hidden_layers": 12,
|
85 |
+
"pad_token_id": 0,
|
86 |
+
"position_embedding_type": "absolute",
|
87 |
+
"torch_dtype": "float32",
|
88 |
+
"transformers_version": "4.33.0.dev0",
|
89 |
+
"type_vocab_size": 2,
|
90 |
+
"use_cache": true,
|
91 |
+
"vocab_size": 28996
|
92 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8ae503b7cc85256bdd8d206cb41cb5e51c49dcf386f4d730d63b6b183b9d0e4
|
3 |
+
size 431040051
|
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": false,
|
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": "BertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"total_flos": 1.929975843125117e+16,
|
4 |
+
"train_loss": 0.1132796828881914,
|
5 |
+
"train_runtime": 2485.5568,
|
6 |
+
"train_samples_per_second": 211.269,
|
7 |
+
"train_steps_per_second": 4.401
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,286 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 10940,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 1.9998171846435103e-05,
|
14 |
+
"loss": 3.4748,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.23,
|
19 |
+
"learning_rate": 1.7714808043875687e-05,
|
20 |
+
"loss": 0.3223,
|
21 |
+
"step": 1250
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.46,
|
25 |
+
"learning_rate": 1.5429616087751372e-05,
|
26 |
+
"loss": 0.1466,
|
27 |
+
"step": 2500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.69,
|
31 |
+
"learning_rate": 1.3144424131627058e-05,
|
32 |
+
"loss": 0.1219,
|
33 |
+
"step": 3750
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.91,
|
37 |
+
"learning_rate": 1.0859232175502743e-05,
|
38 |
+
"loss": 0.1025,
|
39 |
+
"step": 5000
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.0,
|
43 |
+
"eval_ANIM": {
|
44 |
+
"f1": 0.6988922457200403,
|
45 |
+
"number": 3208,
|
46 |
+
"precision": 0.5861486486486487,
|
47 |
+
"recall": 0.8653366583541147
|
48 |
+
},
|
49 |
+
"eval_BIO": {
|
50 |
+
"f1": 0.5263157894736842,
|
51 |
+
"number": 16,
|
52 |
+
"precision": 0.45454545454545453,
|
53 |
+
"recall": 0.625
|
54 |
+
},
|
55 |
+
"eval_CEL": {
|
56 |
+
"f1": 0.7659574468085106,
|
57 |
+
"number": 82,
|
58 |
+
"precision": 0.6792452830188679,
|
59 |
+
"recall": 0.8780487804878049
|
60 |
+
},
|
61 |
+
"eval_DIS": {
|
62 |
+
"f1": 0.6575342465753424,
|
63 |
+
"number": 1518,
|
64 |
+
"precision": 0.5229571984435798,
|
65 |
+
"recall": 0.8853754940711462
|
66 |
+
},
|
67 |
+
"eval_EVE": {
|
68 |
+
"f1": 0.958100558659218,
|
69 |
+
"number": 704,
|
70 |
+
"precision": 0.9423076923076923,
|
71 |
+
"recall": 0.9744318181818182
|
72 |
+
},
|
73 |
+
"eval_FOOD": {
|
74 |
+
"f1": 0.53125,
|
75 |
+
"number": 1132,
|
76 |
+
"precision": 0.38825448613376834,
|
77 |
+
"recall": 0.8409893992932862
|
78 |
+
},
|
79 |
+
"eval_INST": {
|
80 |
+
"f1": 0.5454545454545454,
|
81 |
+
"number": 24,
|
82 |
+
"precision": 0.42857142857142855,
|
83 |
+
"recall": 0.75
|
84 |
+
},
|
85 |
+
"eval_LOC": {
|
86 |
+
"f1": 0.9938849369774116,
|
87 |
+
"number": 24048,
|
88 |
+
"precision": 0.9942571785268415,
|
89 |
+
"recall": 0.9935129740518962
|
90 |
+
},
|
91 |
+
"eval_MEDIA": {
|
92 |
+
"f1": 0.9480381760339343,
|
93 |
+
"number": 916,
|
94 |
+
"precision": 0.9216494845360824,
|
95 |
+
"recall": 0.9759825327510917
|
96 |
+
},
|
97 |
+
"eval_MYTH": {
|
98 |
+
"f1": 0.6987951807228915,
|
99 |
+
"number": 64,
|
100 |
+
"precision": 0.5686274509803921,
|
101 |
+
"recall": 0.90625
|
102 |
+
},
|
103 |
+
"eval_ORG": {
|
104 |
+
"f1": 0.9804511278195489,
|
105 |
+
"number": 6618,
|
106 |
+
"precision": 0.9757557617479796,
|
107 |
+
"recall": 0.9851919008763977
|
108 |
+
},
|
109 |
+
"eval_PER": {
|
110 |
+
"f1": 0.9935385784872672,
|
111 |
+
"number": 10530,
|
112 |
+
"precision": 0.9941053432211447,
|
113 |
+
"recall": 0.9929724596391263
|
114 |
+
},
|
115 |
+
"eval_PLANT": {
|
116 |
+
"f1": 0.56656346749226,
|
117 |
+
"number": 1788,
|
118 |
+
"precision": 0.4331360946745562,
|
119 |
+
"recall": 0.8187919463087249
|
120 |
+
},
|
121 |
+
"eval_TIME": {
|
122 |
+
"f1": 0.7452830188679245,
|
123 |
+
"number": 578,
|
124 |
+
"precision": 0.6829971181556196,
|
125 |
+
"recall": 0.8200692041522492
|
126 |
+
},
|
127 |
+
"eval_VEHI": {
|
128 |
+
"f1": 0.8571428571428572,
|
129 |
+
"number": 64,
|
130 |
+
"precision": 0.7894736842105263,
|
131 |
+
"recall": 0.9375
|
132 |
+
},
|
133 |
+
"eval_loss": 0.09848607331514359,
|
134 |
+
"eval_overall_accuracy": 0.9839002953677689,
|
135 |
+
"eval_overall_f1": 0.9165482757984463,
|
136 |
+
"eval_overall_precision": 0.8698606149751348,
|
137 |
+
"eval_overall_recall": 0.9685318775589784,
|
138 |
+
"eval_runtime": 95.1985,
|
139 |
+
"eval_samples_per_second": 345.678,
|
140 |
+
"eval_steps_per_second": 7.206,
|
141 |
+
"step": 5470
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 1.14,
|
145 |
+
"learning_rate": 8.574040219378429e-06,
|
146 |
+
"loss": 0.0791,
|
147 |
+
"step": 6250
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 1.37,
|
151 |
+
"learning_rate": 6.288848263254113e-06,
|
152 |
+
"loss": 0.0668,
|
153 |
+
"step": 7500
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 1.6,
|
157 |
+
"learning_rate": 4.003656307129799e-06,
|
158 |
+
"loss": 0.0584,
|
159 |
+
"step": 8750
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 1.83,
|
163 |
+
"learning_rate": 1.7184643510054846e-06,
|
164 |
+
"loss": 0.0526,
|
165 |
+
"step": 10000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 2.0,
|
169 |
+
"eval_ANIM": {
|
170 |
+
"f1": 0.7314670813893208,
|
171 |
+
"number": 3208,
|
172 |
+
"precision": 0.6259982253771074,
|
173 |
+
"recall": 0.8796758104738155
|
174 |
+
},
|
175 |
+
"eval_BIO": {
|
176 |
+
"f1": 0.6363636363636364,
|
177 |
+
"number": 16,
|
178 |
+
"precision": 0.5,
|
179 |
+
"recall": 0.875
|
180 |
+
},
|
181 |
+
"eval_CEL": {
|
182 |
+
"f1": 0.7835051546391752,
|
183 |
+
"number": 82,
|
184 |
+
"precision": 0.6785714285714286,
|
185 |
+
"recall": 0.926829268292683
|
186 |
+
},
|
187 |
+
"eval_DIS": {
|
188 |
+
"f1": 0.6950578338590956,
|
189 |
+
"number": 1518,
|
190 |
+
"precision": 0.5783027121609798,
|
191 |
+
"recall": 0.8708827404479579
|
192 |
+
},
|
193 |
+
"eval_EVE": {
|
194 |
+
"f1": 0.9678321678321677,
|
195 |
+
"number": 704,
|
196 |
+
"precision": 0.953168044077135,
|
197 |
+
"recall": 0.9829545454545454
|
198 |
+
},
|
199 |
+
"eval_FOOD": {
|
200 |
+
"f1": 0.5880893300248139,
|
201 |
+
"number": 1132,
|
202 |
+
"precision": 0.45315487571701724,
|
203 |
+
"recall": 0.8374558303886925
|
204 |
+
},
|
205 |
+
"eval_INST": {
|
206 |
+
"f1": 0.5625000000000001,
|
207 |
+
"number": 24,
|
208 |
+
"precision": 0.45,
|
209 |
+
"recall": 0.75
|
210 |
+
},
|
211 |
+
"eval_LOC": {
|
212 |
+
"f1": 0.9941398944349777,
|
213 |
+
"number": 24048,
|
214 |
+
"precision": 0.9936030572401762,
|
215 |
+
"recall": 0.9946773120425815
|
216 |
+
},
|
217 |
+
"eval_MEDIA": {
|
218 |
+
"f1": 0.9540106951871657,
|
219 |
+
"number": 916,
|
220 |
+
"precision": 0.9350104821802935,
|
221 |
+
"recall": 0.9737991266375546
|
222 |
+
},
|
223 |
+
"eval_MYTH": {
|
224 |
+
"f1": 0.8055555555555555,
|
225 |
+
"number": 64,
|
226 |
+
"precision": 0.725,
|
227 |
+
"recall": 0.90625
|
228 |
+
},
|
229 |
+
"eval_ORG": {
|
230 |
+
"f1": 0.9806938159879336,
|
231 |
+
"number": 6618,
|
232 |
+
"precision": 0.9789220114423366,
|
233 |
+
"recall": 0.9824720459353279
|
234 |
+
},
|
235 |
+
"eval_PER": {
|
236 |
+
"f1": 0.9945915172217479,
|
237 |
+
"number": 10530,
|
238 |
+
"precision": 0.9937428896473265,
|
239 |
+
"recall": 0.9954415954415955
|
240 |
+
},
|
241 |
+
"eval_PLANT": {
|
242 |
+
"f1": 0.6153232242617718,
|
243 |
+
"number": 1788,
|
244 |
+
"precision": 0.478287841191067,
|
245 |
+
"recall": 0.8624161073825504
|
246 |
+
},
|
247 |
+
"eval_TIME": {
|
248 |
+
"f1": 0.7310030395136778,
|
249 |
+
"number": 578,
|
250 |
+
"precision": 0.6517615176151762,
|
251 |
+
"recall": 0.8321799307958477
|
252 |
+
},
|
253 |
+
"eval_VEHI": {
|
254 |
+
"f1": 0.8571428571428572,
|
255 |
+
"number": 64,
|
256 |
+
"precision": 0.7894736842105263,
|
257 |
+
"recall": 0.9375
|
258 |
+
},
|
259 |
+
"eval_loss": 0.11049605160951614,
|
260 |
+
"eval_overall_accuracy": 0.9861263597723507,
|
261 |
+
"eval_overall_f1": 0.9277588486101026,
|
262 |
+
"eval_overall_precision": 0.8877743728620296,
|
263 |
+
"eval_overall_recall": 0.9715149151881458,
|
264 |
+
"eval_runtime": 94.1134,
|
265 |
+
"eval_samples_per_second": 349.663,
|
266 |
+
"eval_steps_per_second": 7.289,
|
267 |
+
"step": 10940
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 2.0,
|
271 |
+
"step": 10940,
|
272 |
+
"total_flos": 1.929975843125117e+16,
|
273 |
+
"train_loss": 0.1132796828881914,
|
274 |
+
"train_runtime": 2485.5568,
|
275 |
+
"train_samples_per_second": 211.269,
|
276 |
+
"train_steps_per_second": 4.401
|
277 |
+
}
|
278 |
+
],
|
279 |
+
"logging_steps": 1250,
|
280 |
+
"max_steps": 10940,
|
281 |
+
"num_train_epochs": 2,
|
282 |
+
"save_steps": 500,
|
283 |
+
"total_flos": 1.929975843125117e+16,
|
284 |
+
"trial_name": null,
|
285 |
+
"trial_params": null
|
286 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c703d30f4b92af3adbd1285ac8dc67f3529f8939696ac473deb440cfcb72f8de
|
3 |
+
size 4207
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|