oguuzhansahin
commited on
Commit
•
47bd8ba
1
Parent(s):
c16c7f2
Upload ./ with huggingface_hub
Browse files- config.json +71 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- trainer_state.json +76 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dbmdz/bert-base-turkish-cased",
|
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-no",
|
14 |
+
"2": "I-no",
|
15 |
+
"3": "B-mahalle",
|
16 |
+
"4": "I-mahalle",
|
17 |
+
"5": "B-ad-soyad",
|
18 |
+
"6": "I-ad-soyad",
|
19 |
+
"7": "B-kat",
|
20 |
+
"8": "I-kat",
|
21 |
+
"9": "B-ilce",
|
22 |
+
"10": "I-ilce",
|
23 |
+
"11": "B-sokak",
|
24 |
+
"12": "I-sokak",
|
25 |
+
"13": "B-dis kapi no",
|
26 |
+
"14": "I-dis kapi no",
|
27 |
+
"15": "B-Apartman/Site",
|
28 |
+
"16": "I-Apartman/Site",
|
29 |
+
"17": "B-ic kapi no",
|
30 |
+
"18": "I-ic kapi no",
|
31 |
+
"19": "B-il",
|
32 |
+
"20": "I-il"
|
33 |
+
},
|
34 |
+
"initializer_range": 0.02,
|
35 |
+
"intermediate_size": 3072,
|
36 |
+
"label2id": {
|
37 |
+
"B-Apartman/Site": 15,
|
38 |
+
"B-ad-soyad": 5,
|
39 |
+
"B-dis kapi no": 13,
|
40 |
+
"B-ic kapi no": 17,
|
41 |
+
"B-il": 19,
|
42 |
+
"B-ilce": 9,
|
43 |
+
"B-kat": 7,
|
44 |
+
"B-mahalle": 3,
|
45 |
+
"B-no": 1,
|
46 |
+
"B-sokak": 11,
|
47 |
+
"I-Apartman/Site": 16,
|
48 |
+
"I-ad-soyad": 6,
|
49 |
+
"I-dis kapi no": 14,
|
50 |
+
"I-ic kapi no": 18,
|
51 |
+
"I-il": 20,
|
52 |
+
"I-ilce": 10,
|
53 |
+
"I-kat": 8,
|
54 |
+
"I-mahalle": 4,
|
55 |
+
"I-no": 2,
|
56 |
+
"I-sokak": 12,
|
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": "4.26.0",
|
68 |
+
"type_vocab_size": 2,
|
69 |
+
"use_cache": true,
|
70 |
+
"vocab_size": 32000
|
71 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33a25b72c7fe7d98472edde90c27c723e24d5a35e049ff3c4c9d844bc1900623
|
3 |
+
size 880454149
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf391d9593e46a28c72c354fddec4bf0c32ff3b82d906b7e304ac5434e56ee76
|
3 |
+
size 440240941
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eac24378e997ab22750b8358348a530a7f4bf8bb32d223518d36949b7ee3c384
|
3 |
+
size 13553
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e3b8f60b042b392ad355e090a5de17a747f9b059d9c9d85983e3b19120b529f
|
3 |
+
size 627
|
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 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"max_len": 512,
|
7 |
+
"model_max_length": 512,
|
8 |
+
"name_or_path": "dbmdz/bert-base-turkish-cased",
|
9 |
+
"never_split": null,
|
10 |
+
"pad_token": "[PAD]",
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": true,
|
15 |
+
"tokenizer_class": "BertTokenizer",
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.23053854703903198,
|
3 |
+
"best_model_checkpoint": "address_detection_model/checkpoint-240",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 240,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_accuracy": 0.8829663962920047,
|
13 |
+
"eval_f1": 0.4565916398713826,
|
14 |
+
"eval_loss": 0.41948696970939636,
|
15 |
+
"eval_precision": 0.4152046783625731,
|
16 |
+
"eval_recall": 0.5071428571428571,
|
17 |
+
"eval_runtime": 62.0598,
|
18 |
+
"eval_samples_per_second": 3.094,
|
19 |
+
"eval_steps_per_second": 0.193,
|
20 |
+
"step": 48
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.0,
|
24 |
+
"eval_accuracy": 0.9248744689069138,
|
25 |
+
"eval_f1": 0.66,
|
26 |
+
"eval_loss": 0.2642114460468292,
|
27 |
+
"eval_precision": 0.61875,
|
28 |
+
"eval_recall": 0.7071428571428572,
|
29 |
+
"eval_runtime": 65.1672,
|
30 |
+
"eval_samples_per_second": 2.946,
|
31 |
+
"eval_steps_per_second": 0.184,
|
32 |
+
"step": 96
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 3.0,
|
36 |
+
"eval_accuracy": 0.9341444573194283,
|
37 |
+
"eval_f1": 0.729036729036729,
|
38 |
+
"eval_loss": 0.23378442227840424,
|
39 |
+
"eval_precision": 0.7079407806191117,
|
40 |
+
"eval_recall": 0.7514285714285714,
|
41 |
+
"eval_runtime": 61.439,
|
42 |
+
"eval_samples_per_second": 3.125,
|
43 |
+
"eval_steps_per_second": 0.195,
|
44 |
+
"step": 144
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 4.0,
|
48 |
+
"eval_accuracy": 0.9351100811123986,
|
49 |
+
"eval_f1": 0.729036729036729,
|
50 |
+
"eval_loss": 0.2325739860534668,
|
51 |
+
"eval_precision": 0.7079407806191117,
|
52 |
+
"eval_recall": 0.7514285714285714,
|
53 |
+
"eval_runtime": 63.6313,
|
54 |
+
"eval_samples_per_second": 3.017,
|
55 |
+
"eval_steps_per_second": 0.189,
|
56 |
+
"step": 192
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 5.0,
|
60 |
+
"eval_accuracy": 0.9351100811123986,
|
61 |
+
"eval_f1": 0.7285318559556787,
|
62 |
+
"eval_loss": 0.23053854703903198,
|
63 |
+
"eval_precision": 0.706989247311828,
|
64 |
+
"eval_recall": 0.7514285714285714,
|
65 |
+
"eval_runtime": 61.6163,
|
66 |
+
"eval_samples_per_second": 3.116,
|
67 |
+
"eval_steps_per_second": 0.195,
|
68 |
+
"step": 240
|
69 |
+
}
|
70 |
+
],
|
71 |
+
"max_steps": 240,
|
72 |
+
"num_train_epochs": 5,
|
73 |
+
"total_flos": 180264480845040.0,
|
74 |
+
"trial_name": null,
|
75 |
+
"trial_params": null
|
76 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ddf6899b7a894e80bcf4bec04a3e161773f940e7c3de5b36d8e7471570b4220
|
3 |
+
size 3515
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|