Simon Clematide
commited on
Commit
·
6f47768
1
Parent(s):
a5847e1
Initial model upload
Browse files- config.json +71 -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 +59 -0
- trainer_state.json +143 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "deepset/gbert-base",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "B-BERUF",
|
14 |
+
"2": "I-BERUF",
|
15 |
+
"3": "B-REGISTER",
|
16 |
+
"4": "I-REGISTER",
|
17 |
+
"5": "B-ZEIT",
|
18 |
+
"6": "I-ZEIT",
|
19 |
+
"7": "B-FIRMA",
|
20 |
+
"8": "I-FIRMA",
|
21 |
+
"9": "B-HAUS",
|
22 |
+
"10": "I-HAUS",
|
23 |
+
"11": "B-ORT",
|
24 |
+
"12": "I-ORT",
|
25 |
+
"13": "B-STRASSE",
|
26 |
+
"14": "I-STRASSE",
|
27 |
+
"15": "B-POI",
|
28 |
+
"16": "I-POI",
|
29 |
+
"17": "B-QUELLE",
|
30 |
+
"18": "I-QUELLE",
|
31 |
+
"19": "B-PERS",
|
32 |
+
"20": "I-PERS"
|
33 |
+
},
|
34 |
+
"initializer_range": 0.02,
|
35 |
+
"intermediate_size": 3072,
|
36 |
+
"label2id": {
|
37 |
+
"B-BERUF": 1,
|
38 |
+
"B-FIRMA": 7,
|
39 |
+
"B-HAUS": 9,
|
40 |
+
"B-ORT": 11,
|
41 |
+
"B-PERS": 19,
|
42 |
+
"B-POI": 15,
|
43 |
+
"B-QUELLE": 17,
|
44 |
+
"B-REGISTER": 3,
|
45 |
+
"B-STRASSE": 13,
|
46 |
+
"B-ZEIT": 5,
|
47 |
+
"I-BERUF": 2,
|
48 |
+
"I-FIRMA": 8,
|
49 |
+
"I-HAUS": 10,
|
50 |
+
"I-ORT": 12,
|
51 |
+
"I-PERS": 20,
|
52 |
+
"I-POI": 16,
|
53 |
+
"I-QUELLE": 18,
|
54 |
+
"I-REGISTER": 4,
|
55 |
+
"I-STRASSE": 14,
|
56 |
+
"I-ZEIT": 6,
|
57 |
+
"O": 0
|
58 |
+
},
|
59 |
+
"layer_norm_eps": 1e-12,
|
60 |
+
"max_position_embeddings": 512,
|
61 |
+
"model_type": "bert",
|
62 |
+
"num_attention_heads": 12,
|
63 |
+
"num_hidden_layers": 12,
|
64 |
+
"pad_token_id": 0,
|
65 |
+
"position_embedding_type": "absolute",
|
66 |
+
"torch_dtype": "float32",
|
67 |
+
"transformers_version": "4.48.2",
|
68 |
+
"type_vocab_size": 2,
|
69 |
+
"use_cache": true,
|
70 |
+
"vocab_size": 31102
|
71 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9540c958937287073de970630ee42a155aa1bdcb4efe5cf025a28131f0d2744c
|
3 |
+
size 437436292
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efcfadfeadb81168630bbbc82e86cf499a6ece1117d14e70352974a1d68d3b82
|
3 |
+
size 874986810
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4caff9e1b1eb83b6120a061cb8148c2bd6e9fb70502e1e76ee58be07951c580d
|
3 |
+
size 13990
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3a415493a2d9a886432683884ce416a80be33c13d4737d245662735e16cbade
|
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 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"101": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"102": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"103": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"104": {
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"max_len": 512,
|
51 |
+
"model_max_length": 512,
|
52 |
+
"never_split": null,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"sep_token": "[SEP]",
|
55 |
+
"strip_accents": false,
|
56 |
+
"tokenize_chinese_chars": true,
|
57 |
+
"tokenizer_class": "BertTokenizer",
|
58 |
+
"unk_token": "[UNK]"
|
59 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,143 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3051736056804657,
|
3 |
+
"best_model_checkpoint": "hf-ner-sample_004-gbert-base.model/checkpoint-230",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 230,
|
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_f1": 0.0979020979020979,
|
14 |
+
"eval_loss": 1.2133915424346924,
|
15 |
+
"eval_precision": 0.1590909090909091,
|
16 |
+
"eval_recall": 0.0707070707070707,
|
17 |
+
"eval_runtime": 0.4132,
|
18 |
+
"eval_samples_per_second": 142.792,
|
19 |
+
"eval_steps_per_second": 7.261,
|
20 |
+
"step": 23
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.0,
|
24 |
+
"eval_f1": 0.4466338259441708,
|
25 |
+
"eval_loss": 0.741108775138855,
|
26 |
+
"eval_precision": 0.4358974358974359,
|
27 |
+
"eval_recall": 0.45791245791245794,
|
28 |
+
"eval_runtime": 0.3079,
|
29 |
+
"eval_samples_per_second": 191.613,
|
30 |
+
"eval_steps_per_second": 9.743,
|
31 |
+
"step": 46
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 3.0,
|
35 |
+
"eval_f1": 0.637873754152824,
|
36 |
+
"eval_loss": 0.5308826565742493,
|
37 |
+
"eval_precision": 0.6295081967213115,
|
38 |
+
"eval_recall": 0.6464646464646465,
|
39 |
+
"eval_runtime": 0.3155,
|
40 |
+
"eval_samples_per_second": 187.003,
|
41 |
+
"eval_steps_per_second": 9.509,
|
42 |
+
"step": 69
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 4.0,
|
46 |
+
"eval_f1": 0.6928327645051194,
|
47 |
+
"eval_loss": 0.4319136440753937,
|
48 |
+
"eval_precision": 0.7024221453287197,
|
49 |
+
"eval_recall": 0.6835016835016835,
|
50 |
+
"eval_runtime": 0.3102,
|
51 |
+
"eval_samples_per_second": 190.21,
|
52 |
+
"eval_steps_per_second": 9.672,
|
53 |
+
"step": 92
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 5.0,
|
57 |
+
"eval_f1": 0.7133550488599348,
|
58 |
+
"eval_loss": 0.3702440857887268,
|
59 |
+
"eval_precision": 0.6908517350157729,
|
60 |
+
"eval_recall": 0.7373737373737373,
|
61 |
+
"eval_runtime": 0.3081,
|
62 |
+
"eval_samples_per_second": 191.509,
|
63 |
+
"eval_steps_per_second": 9.738,
|
64 |
+
"step": 115
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 6.0,
|
68 |
+
"eval_f1": 0.7408637873754154,
|
69 |
+
"eval_loss": 0.33849552273750305,
|
70 |
+
"eval_precision": 0.7311475409836066,
|
71 |
+
"eval_recall": 0.7508417508417509,
|
72 |
+
"eval_runtime": 0.306,
|
73 |
+
"eval_samples_per_second": 192.832,
|
74 |
+
"eval_steps_per_second": 9.805,
|
75 |
+
"step": 138
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 7.0,
|
79 |
+
"eval_f1": 0.7397708674304418,
|
80 |
+
"eval_loss": 0.3240445554256439,
|
81 |
+
"eval_precision": 0.7197452229299363,
|
82 |
+
"eval_recall": 0.7609427609427609,
|
83 |
+
"eval_runtime": 0.309,
|
84 |
+
"eval_samples_per_second": 190.938,
|
85 |
+
"eval_steps_per_second": 9.709,
|
86 |
+
"step": 161
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 8.0,
|
90 |
+
"eval_f1": 0.763157894736842,
|
91 |
+
"eval_loss": 0.31296223402023315,
|
92 |
+
"eval_precision": 0.7459807073954984,
|
93 |
+
"eval_recall": 0.7811447811447811,
|
94 |
+
"eval_runtime": 0.3151,
|
95 |
+
"eval_samples_per_second": 187.228,
|
96 |
+
"eval_steps_per_second": 9.52,
|
97 |
+
"step": 184
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 9.0,
|
101 |
+
"eval_f1": 0.7560581583198708,
|
102 |
+
"eval_loss": 0.30645591020584106,
|
103 |
+
"eval_precision": 0.7267080745341615,
|
104 |
+
"eval_recall": 0.7878787878787878,
|
105 |
+
"eval_runtime": 0.3136,
|
106 |
+
"eval_samples_per_second": 188.12,
|
107 |
+
"eval_steps_per_second": 9.565,
|
108 |
+
"step": 207
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 10.0,
|
112 |
+
"eval_f1": 0.7585089141004862,
|
113 |
+
"eval_loss": 0.3051736056804657,
|
114 |
+
"eval_precision": 0.73125,
|
115 |
+
"eval_recall": 0.7878787878787878,
|
116 |
+
"eval_runtime": 0.4257,
|
117 |
+
"eval_samples_per_second": 138.601,
|
118 |
+
"eval_steps_per_second": 7.048,
|
119 |
+
"step": 230
|
120 |
+
}
|
121 |
+
],
|
122 |
+
"logging_steps": 500,
|
123 |
+
"max_steps": 230,
|
124 |
+
"num_input_tokens_seen": 0,
|
125 |
+
"num_train_epochs": 10,
|
126 |
+
"save_steps": 500,
|
127 |
+
"stateful_callbacks": {
|
128 |
+
"TrainerControl": {
|
129 |
+
"args": {
|
130 |
+
"should_epoch_stop": false,
|
131 |
+
"should_evaluate": false,
|
132 |
+
"should_log": false,
|
133 |
+
"should_save": true,
|
134 |
+
"should_training_stop": true
|
135 |
+
},
|
136 |
+
"attributes": {}
|
137 |
+
}
|
138 |
+
},
|
139 |
+
"total_flos": 312424744893732.0,
|
140 |
+
"train_batch_size": 24,
|
141 |
+
"trial_name": null,
|
142 |
+
"trial_params": null
|
143 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9be1a344932cc442bd5bfd4212bd88c9470cf41de8a91825932e4fc34f4b427
|
3 |
+
size 5304
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|