Commit
•
e0b7f9e
1
Parent(s):
9d73213
init commit
Browse files- config.json +49 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- trainer_state.json +183 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
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 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"B-LOC": 5,
|
25 |
+
"B-ORG": 3,
|
26 |
+
"B-PER": 1,
|
27 |
+
"I-LOC": 6,
|
28 |
+
"I-ORG": 4,
|
29 |
+
"I-PER": 2,
|
30 |
+
"O": 0
|
31 |
+
},
|
32 |
+
"layer_norm_eps": 1e-12,
|
33 |
+
"max_position_embeddings": 512,
|
34 |
+
"model_type": "bert",
|
35 |
+
"num_attention_heads": 12,
|
36 |
+
"num_hidden_layers": 12,
|
37 |
+
"pad_token_id": 0,
|
38 |
+
"pooler_fc_size": 768,
|
39 |
+
"pooler_num_attention_heads": 12,
|
40 |
+
"pooler_num_fc_layers": 3,
|
41 |
+
"pooler_size_per_head": 128,
|
42 |
+
"pooler_type": "first_token_transform",
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.40.2",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"use_cache": true,
|
48 |
+
"vocab_size": 119547
|
49 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fdcd4f0f1209395fde7739420c0a1347a36d5348fdd027a046f7cd93258aea6
|
3 |
+
size 709096284
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41fe982724cd3de1137111a0bd53c358162c492f42716dc6f9a17eb91d02159c
|
3 |
+
size 1418312250
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cf20707cfe44b9a2276c69f13c12e7734e37012f02f270f239bb9bfd5745003
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:977b16ce1d671299321ed5cdc5925bcc339f51b69ce7fef2d33400b154276801
|
3 |
+
size 1064
|
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 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": false,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"num_labels": 7,
|
50 |
+
"pad_token": "[PAD]",
|
51 |
+
"sep_token": "[SEP]",
|
52 |
+
"strip_accents": null,
|
53 |
+
"tokenize_chinese_chars": true,
|
54 |
+
"tokenizer_class": "BertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 6250,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.9648939348670451,
|
14 |
+
"eval_f1": 0.8973252804141502,
|
15 |
+
"eval_loss": 0.189955934882164,
|
16 |
+
"eval_precision": 0.8587943848059455,
|
17 |
+
"eval_recall": 0.9394760614272809,
|
18 |
+
"eval_runtime": 2.5262,
|
19 |
+
"eval_samples_per_second": 395.851,
|
20 |
+
"eval_steps_per_second": 24.939,
|
21 |
+
"step": 625
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.6,
|
25 |
+
"grad_norm": 5.951064109802246,
|
26 |
+
"learning_rate": 1.6800000000000002e-05,
|
27 |
+
"loss": 0.0567,
|
28 |
+
"step": 1000
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"eval_accuracy": 0.97169106662683,
|
33 |
+
"eval_f1": 0.9429726088908846,
|
34 |
+
"eval_loss": 0.1852019727230072,
|
35 |
+
"eval_precision": 0.9375,
|
36 |
+
"eval_recall": 0.948509485094851,
|
37 |
+
"eval_runtime": 2.561,
|
38 |
+
"eval_samples_per_second": 390.465,
|
39 |
+
"eval_steps_per_second": 24.599,
|
40 |
+
"step": 1250
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 3.0,
|
44 |
+
"eval_accuracy": 0.9731102479832686,
|
45 |
+
"eval_f1": 0.9533213644524237,
|
46 |
+
"eval_loss": 0.17272309958934784,
|
47 |
+
"eval_precision": 0.9473684210526315,
|
48 |
+
"eval_recall": 0.959349593495935,
|
49 |
+
"eval_runtime": 3.904,
|
50 |
+
"eval_samples_per_second": 256.151,
|
51 |
+
"eval_steps_per_second": 16.137,
|
52 |
+
"step": 1875
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 3.2,
|
56 |
+
"grad_norm": 0.4564518630504608,
|
57 |
+
"learning_rate": 1.3600000000000002e-05,
|
58 |
+
"loss": 0.0338,
|
59 |
+
"step": 2000
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"eval_accuracy": 0.9777412608305945,
|
64 |
+
"eval_f1": 0.9547288211564321,
|
65 |
+
"eval_loss": 0.15044009685516357,
|
66 |
+
"eval_precision": 0.947508896797153,
|
67 |
+
"eval_recall": 0.962059620596206,
|
68 |
+
"eval_runtime": 2.4284,
|
69 |
+
"eval_samples_per_second": 411.796,
|
70 |
+
"eval_steps_per_second": 25.943,
|
71 |
+
"step": 2500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 4.8,
|
75 |
+
"grad_norm": 0.006230680737644434,
|
76 |
+
"learning_rate": 1.04e-05,
|
77 |
+
"loss": 0.0318,
|
78 |
+
"step": 3000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 5.0,
|
82 |
+
"eval_accuracy": 0.9756498356737376,
|
83 |
+
"eval_f1": 0.9563259792886086,
|
84 |
+
"eval_loss": 0.17377431690692902,
|
85 |
+
"eval_precision": 0.9533213644524237,
|
86 |
+
"eval_recall": 0.959349593495935,
|
87 |
+
"eval_runtime": 2.4667,
|
88 |
+
"eval_samples_per_second": 405.403,
|
89 |
+
"eval_steps_per_second": 25.54,
|
90 |
+
"step": 3125
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 6.0,
|
94 |
+
"eval_accuracy": 0.9788616671646251,
|
95 |
+
"eval_f1": 0.9630297565374211,
|
96 |
+
"eval_loss": 0.1647682785987854,
|
97 |
+
"eval_precision": 0.9612961296129613,
|
98 |
+
"eval_recall": 0.964769647696477,
|
99 |
+
"eval_runtime": 3.1374,
|
100 |
+
"eval_samples_per_second": 318.737,
|
101 |
+
"eval_steps_per_second": 20.08,
|
102 |
+
"step": 3750
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 6.4,
|
106 |
+
"grad_norm": 0.0044134571217000484,
|
107 |
+
"learning_rate": 7.2000000000000005e-06,
|
108 |
+
"loss": 0.02,
|
109 |
+
"step": 4000
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 7.0,
|
113 |
+
"eval_accuracy": 0.9770690170301762,
|
114 |
+
"eval_f1": 0.9643340857787811,
|
115 |
+
"eval_loss": 0.17450480163097382,
|
116 |
+
"eval_precision": 0.9638989169675091,
|
117 |
+
"eval_recall": 0.964769647696477,
|
118 |
+
"eval_runtime": 2.53,
|
119 |
+
"eval_samples_per_second": 395.256,
|
120 |
+
"eval_steps_per_second": 24.901,
|
121 |
+
"step": 4375
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 8.0,
|
125 |
+
"grad_norm": 0.0022473218850791454,
|
126 |
+
"learning_rate": 4.000000000000001e-06,
|
127 |
+
"loss": 0.0063,
|
128 |
+
"step": 5000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 8.0,
|
132 |
+
"eval_accuracy": 0.9793845234538393,
|
133 |
+
"eval_f1": 0.9652370203160271,
|
134 |
+
"eval_loss": 0.16244609653949738,
|
135 |
+
"eval_precision": 0.9648014440433214,
|
136 |
+
"eval_recall": 0.9656729900632339,
|
137 |
+
"eval_runtime": 2.5135,
|
138 |
+
"eval_samples_per_second": 397.859,
|
139 |
+
"eval_steps_per_second": 25.065,
|
140 |
+
"step": 5000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 9.0,
|
144 |
+
"eval_accuracy": 0.98125186734389,
|
145 |
+
"eval_f1": 0.9643340857787811,
|
146 |
+
"eval_loss": 0.16350433230400085,
|
147 |
+
"eval_precision": 0.9638989169675091,
|
148 |
+
"eval_recall": 0.964769647696477,
|
149 |
+
"eval_runtime": 2.4878,
|
150 |
+
"eval_samples_per_second": 401.967,
|
151 |
+
"eval_steps_per_second": 25.324,
|
152 |
+
"step": 5625
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 9.6,
|
156 |
+
"grad_norm": 0.0036331522278487682,
|
157 |
+
"learning_rate": 8.000000000000001e-07,
|
158 |
+
"loss": 0.0036,
|
159 |
+
"step": 6000
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 10.0,
|
163 |
+
"eval_accuracy": 0.9799820734986555,
|
164 |
+
"eval_f1": 0.9643662607126748,
|
165 |
+
"eval_loss": 0.16758297383785248,
|
166 |
+
"eval_precision": 0.9630630630630631,
|
167 |
+
"eval_recall": 0.9656729900632339,
|
168 |
+
"eval_runtime": 2.4417,
|
169 |
+
"eval_samples_per_second": 409.55,
|
170 |
+
"eval_steps_per_second": 25.802,
|
171 |
+
"step": 6250
|
172 |
+
}
|
173 |
+
],
|
174 |
+
"logging_steps": 1000,
|
175 |
+
"max_steps": 6250,
|
176 |
+
"num_input_tokens_seen": 0,
|
177 |
+
"num_train_epochs": 10,
|
178 |
+
"save_steps": 500,
|
179 |
+
"total_flos": 1559350717084512.0,
|
180 |
+
"train_batch_size": 16,
|
181 |
+
"trial_name": null,
|
182 |
+
"trial_params": null
|
183 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f1b754cd60aa361668b15b13955195a067f3076165ef6deae96d79c0a157511
|
3 |
+
size 4984
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|