nlztrk commited on
Commit
1535c93
1 Parent(s): 50be355

Upload ./ with huggingface_hub (#1)

Browse files

- Upload ./ with huggingface_hub (ffc8dec0f7cb77f84cb87b1566992ade4970ceea)

.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 250101
3
+ }
config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/mdeberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "O",
12
+ "1": "B-no",
13
+ "2": "I-no",
14
+ "3": "B-mahalle",
15
+ "4": "I-mahalle",
16
+ "5": "B-ad-soyad",
17
+ "6": "I-ad-soyad",
18
+ "7": "B-kat",
19
+ "8": "I-kat",
20
+ "9": "B-ilce",
21
+ "10": "I-ilce",
22
+ "11": "B-sokak",
23
+ "12": "I-sokak",
24
+ "13": "B-dis kapi no",
25
+ "14": "I-dis kapi no",
26
+ "15": "B-Apartman/Site",
27
+ "16": "I-Apartman/Site",
28
+ "17": "B-ic kapi no",
29
+ "18": "I-ic kapi no",
30
+ "19": "B-il",
31
+ "20": "I-il"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "B-Apartman/Site": 15,
37
+ "B-ad-soyad": 5,
38
+ "B-dis kapi no": 13,
39
+ "B-ic kapi no": 17,
40
+ "B-il": 19,
41
+ "B-ilce": 9,
42
+ "B-kat": 7,
43
+ "B-mahalle": 3,
44
+ "B-no": 1,
45
+ "B-sokak": 11,
46
+ "I-Apartman/Site": 16,
47
+ "I-ad-soyad": 6,
48
+ "I-dis kapi no": 14,
49
+ "I-ic kapi no": 18,
50
+ "I-il": 20,
51
+ "I-ilce": 10,
52
+ "I-kat": 8,
53
+ "I-mahalle": 4,
54
+ "I-no": 2,
55
+ "I-sokak": 12,
56
+ "O": 0
57
+ },
58
+ "layer_norm_eps": 1e-07,
59
+ "max_position_embeddings": 512,
60
+ "max_relative_positions": -1,
61
+ "model_type": "deberta-v2",
62
+ "norm_rel_ebd": "layer_norm",
63
+ "num_attention_heads": 12,
64
+ "num_hidden_layers": 12,
65
+ "pad_token_id": 0,
66
+ "pooler_dropout": 0,
67
+ "pooler_hidden_act": "gelu",
68
+ "pooler_hidden_size": 768,
69
+ "pos_att_type": [
70
+ "p2c",
71
+ "c2p"
72
+ ],
73
+ "position_biased_input": false,
74
+ "position_buckets": 256,
75
+ "relative_attention": true,
76
+ "share_att_key": true,
77
+ "torch_dtype": "float32",
78
+ "transformers_version": "4.26.0",
79
+ "type_vocab_size": 0,
80
+ "vocab_size": 251000
81
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:479a1d78063494cd731b178b38316e7d414ea9223c3a1401709db0bc0c88baa5
3
+ size 2225996485
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce63d98d63447ee96d1bad8ffcce9cb618b935ec6dc604eebcbb70cf2c8978e5
3
+ size 1113013041
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61092adc49435c20c2e2c84d24935827b06869e2073ce6f8c8f2c4a1ff701c20
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a5f6f6630041eeb927048a09b193f603b988aa51c276cceb0fd0012ec658de3
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
3
+ size 4305025
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f06fc3bbcbbc8f07be861b9a6a69e177247bc549b2bcbf0483e4dd98c06b6f6
3
+ size 16331301
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "eos_token": "[SEP]",
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "name_or_path": "microsoft/mdeberta-v3-base",
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "special_tokens_map_file": null,
13
+ "split_by_punct": false,
14
+ "tokenizer_class": "DebertaV2Tokenizer",
15
+ "unk_token": "[UNK]",
16
+ "vocab_type": "spm"
17
+ }
trainer_state.json ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.24886493384838104,
3
+ "best_model_checkpoint": "address_detection_model/checkpoint-480",
4
+ "epoch": 13.0,
5
+ "global_step": 1248,
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": 0.90849413168888,
13
+ "eval_f1": 0.59986366734833,
14
+ "eval_loss": 0.4046468734741211,
15
+ "eval_precision": 0.561941251596424,
16
+ "eval_recall": 0.6432748538011696,
17
+ "eval_runtime": 0.333,
18
+ "eval_samples_per_second": 576.556,
19
+ "eval_steps_per_second": 36.035,
20
+ "step": 96
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.9192361249254029,
25
+ "eval_f1": 0.693135935397039,
26
+ "eval_loss": 0.305729478597641,
27
+ "eval_precision": 0.64214463840399,
28
+ "eval_recall": 0.7529239766081871,
29
+ "eval_runtime": 0.3645,
30
+ "eval_samples_per_second": 526.796,
31
+ "eval_steps_per_second": 32.925,
32
+ "step": 192
33
+ },
34
+ {
35
+ "epoch": 3.0,
36
+ "eval_accuracy": 0.9305748955639547,
37
+ "eval_f1": 0.7226428079834825,
38
+ "eval_loss": 0.25665250420570374,
39
+ "eval_precision": 0.682704811443433,
40
+ "eval_recall": 0.7675438596491229,
41
+ "eval_runtime": 0.3364,
42
+ "eval_samples_per_second": 570.696,
43
+ "eval_steps_per_second": 35.669,
44
+ "step": 288
45
+ },
46
+ {
47
+ "epoch": 4.0,
48
+ "eval_accuracy": 0.9289834891585439,
49
+ "eval_f1": 0.7248787248787248,
50
+ "eval_loss": 0.2604641616344452,
51
+ "eval_precision": 0.689064558629776,
52
+ "eval_recall": 0.7646198830409356,
53
+ "eval_runtime": 0.3089,
54
+ "eval_samples_per_second": 621.464,
55
+ "eval_steps_per_second": 38.842,
56
+ "step": 384
57
+ },
58
+ {
59
+ "epoch": 5.0,
60
+ "eval_accuracy": 0.9327630793713945,
61
+ "eval_f1": 0.7221067221067221,
62
+ "eval_loss": 0.24886493384838104,
63
+ "eval_precision": 0.686429512516469,
64
+ "eval_recall": 0.7616959064327485,
65
+ "eval_runtime": 0.3123,
66
+ "eval_samples_per_second": 614.738,
67
+ "eval_steps_per_second": 38.421,
68
+ "step": 480
69
+ },
70
+ {
71
+ "epoch": 5.21,
72
+ "learning_rate": 1.9583333333333333e-05,
73
+ "loss": 0.3477,
74
+ "step": 500
75
+ },
76
+ {
77
+ "epoch": 6.0,
78
+ "eval_accuracy": 0.9341555599761289,
79
+ "eval_f1": 0.7311679336558397,
80
+ "eval_loss": 0.2547823190689087,
81
+ "eval_precision": 0.6933158584534731,
82
+ "eval_recall": 0.7733918128654971,
83
+ "eval_runtime": 0.3117,
84
+ "eval_samples_per_second": 615.908,
85
+ "eval_steps_per_second": 38.494,
86
+ "step": 576
87
+ },
88
+ {
89
+ "epoch": 7.0,
90
+ "eval_accuracy": 0.9307738213646309,
91
+ "eval_f1": 0.7350069735006974,
92
+ "eval_loss": 0.26613351702690125,
93
+ "eval_precision": 0.7026666666666667,
94
+ "eval_recall": 0.77046783625731,
95
+ "eval_runtime": 0.3453,
96
+ "eval_samples_per_second": 555.983,
97
+ "eval_steps_per_second": 34.749,
98
+ "step": 672
99
+ },
100
+ {
101
+ "epoch": 8.0,
102
+ "eval_accuracy": 0.9345534115774816,
103
+ "eval_f1": 0.7416201117318436,
104
+ "eval_loss": 0.25599348545074463,
105
+ "eval_precision": 0.7098930481283422,
106
+ "eval_recall": 0.7763157894736842,
107
+ "eval_runtime": 0.313,
108
+ "eval_samples_per_second": 613.472,
109
+ "eval_steps_per_second": 38.342,
110
+ "step": 768
111
+ },
112
+ {
113
+ "epoch": 9.0,
114
+ "eval_accuracy": 0.9321663019693655,
115
+ "eval_f1": 0.7372764786795049,
116
+ "eval_loss": 0.27552878856658936,
117
+ "eval_precision": 0.6961038961038961,
118
+ "eval_recall": 0.783625730994152,
119
+ "eval_runtime": 0.3343,
120
+ "eval_samples_per_second": 574.283,
121
+ "eval_steps_per_second": 35.893,
122
+ "step": 864
123
+ },
124
+ {
125
+ "epoch": 10.0,
126
+ "eval_accuracy": 0.9299781181619255,
127
+ "eval_f1": 0.7323549965059398,
128
+ "eval_loss": 0.2917962074279785,
129
+ "eval_precision": 0.7014725568942436,
130
+ "eval_recall": 0.7660818713450293,
131
+ "eval_runtime": 0.329,
132
+ "eval_samples_per_second": 583.528,
133
+ "eval_steps_per_second": 36.47,
134
+ "step": 960
135
+ },
136
+ {
137
+ "epoch": 10.42,
138
+ "learning_rate": 9.166666666666668e-06,
139
+ "loss": 0.1205,
140
+ "step": 1000
141
+ },
142
+ {
143
+ "epoch": 11.0,
144
+ "eval_accuracy": 0.9315695245673364,
145
+ "eval_f1": 0.7329624478442281,
146
+ "eval_loss": 0.28479865193367004,
147
+ "eval_precision": 0.6989389920424404,
148
+ "eval_recall": 0.77046783625731,
149
+ "eval_runtime": 0.3325,
150
+ "eval_samples_per_second": 577.484,
151
+ "eval_steps_per_second": 36.093,
152
+ "step": 1056
153
+ },
154
+ {
155
+ "epoch": 12.0,
156
+ "eval_accuracy": 0.9299781181619255,
157
+ "eval_f1": 0.7342995169082126,
158
+ "eval_loss": 0.3070613443851471,
159
+ "eval_precision": 0.6954248366013072,
160
+ "eval_recall": 0.7777777777777778,
161
+ "eval_runtime": 0.3292,
162
+ "eval_samples_per_second": 583.292,
163
+ "eval_steps_per_second": 36.456,
164
+ "step": 1152
165
+ },
166
+ {
167
+ "epoch": 13.0,
168
+ "eval_accuracy": 0.9333598567734235,
169
+ "eval_f1": 0.745998608211552,
170
+ "eval_loss": 0.2998543679714203,
171
+ "eval_precision": 0.7118193891102258,
172
+ "eval_recall": 0.783625730994152,
173
+ "eval_runtime": 0.3372,
174
+ "eval_samples_per_second": 569.432,
175
+ "eval_steps_per_second": 35.589,
176
+ "step": 1248
177
+ }
178
+ ],
179
+ "max_steps": 1440,
180
+ "num_train_epochs": 15,
181
+ "total_flos": 487199638963260.0,
182
+ "trial_name": null,
183
+ "trial_params": null
184
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09bb5d9dbb6337c6490cdbdf41cfe94c785983c80a23b84c6c88312b6c7b52b4
3
+ size 3515