Hugging Face's logo

kaixkhazaki
/
turkish-zeroshot-distilbert

Zero-Shot Classification
Transformers
TensorBoard
Safetensors
distilbert
text-classification
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
kaixkhazaki commited on
Commit
38468fb
·
verified ·
1 Parent(s): 632ee50

Pushing of the best model checkpoint

Browse files
Files changed (9) hide show
  1. README.md +138 -0
  2. config.json +36 -0
  3. model.safetensors +3 -0
  4. runs/Jan09_08-47-26_ip-10-10-15-55.eu-central-1.compute.internal/events.out.tfevents.1736412446.ip-10-10-15-55.eu-central-1.compute.internal.23155.4 +3 -0
  5. special_tokens_map.json +7 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +59 -0
  8. training_args.bin +3 -0
  9. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: dbmdz/distilbert-base-turkish-cased
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ - precision
11
+ - recall
12
+ model-index:
13
+ - name: turkish-zeroshot-distilbert
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # turkish-zeroshot-distilbert
21
+
22
+ This model is a fine-tuned version of [dbmdz/distilbert-base-turkish-cased](https://huggingface.co/dbmdz/distilbert-base-turkish-cased) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.6942
25
+ - Accuracy: 0.7137
26
+ - F1: 0.7148
27
+ - Precision: 0.7188
28
+ - Recall: 0.7137
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 5e-05
48
+ - train_batch_size: 64
49
+ - eval_batch_size: 32
50
+ - seed: 42
51
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: cosine
53
+ - lr_scheduler_warmup_steps: 500
54
+ - num_epochs: 5
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
59
+ |:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
60
+ | 1.0977 | 0.0326 | 200 | 1.0947 | 0.3546 | 0.2595 | 0.3604 | 0.3546 |
61
+ | 0.986 | 0.0652 | 400 | 0.9576 | 0.5482 | 0.5453 | 0.5749 | 0.5482 |
62
+ | 0.9344 | 0.0978 | 600 | 0.8824 | 0.6044 | 0.6044 | 0.6050 | 0.6044 |
63
+ | 0.8965 | 0.1304 | 800 | 0.8571 | 0.6040 | 0.6042 | 0.6059 | 0.6040 |
64
+ | 0.9036 | 0.1630 | 1000 | 0.8388 | 0.6273 | 0.6278 | 0.6289 | 0.6273 |
65
+ | 0.8795 | 0.1956 | 1200 | 0.8158 | 0.6329 | 0.6334 | 0.6476 | 0.6329 |
66
+ | 0.8891 | 0.2282 | 1400 | 0.8250 | 0.6217 | 0.6212 | 0.6360 | 0.6217 |
67
+ | 0.8661 | 0.2608 | 1600 | 0.8230 | 0.6257 | 0.6259 | 0.6262 | 0.6257 |
68
+ | 0.8444 | 0.2934 | 1800 | 0.8146 | 0.6169 | 0.6162 | 0.6434 | 0.6169 |
69
+ | 0.8163 | 0.3259 | 2000 | 0.8073 | 0.6337 | 0.6331 | 0.6398 | 0.6337 |
70
+ | 0.855 | 0.3585 | 2200 | 0.8061 | 0.6446 | 0.6426 | 0.6591 | 0.6446 |
71
+ | 0.8418 | 0.3911 | 2400 | 0.8080 | 0.6430 | 0.6419 | 0.6632 | 0.6430 |
72
+ | 0.8141 | 0.4237 | 2600 | 0.7773 | 0.6526 | 0.6517 | 0.6631 | 0.6526 |
73
+ | 0.8159 | 0.4563 | 2800 | 0.7642 | 0.6715 | 0.6702 | 0.6739 | 0.6715 |
74
+ | 0.8247 | 0.4889 | 3000 | 0.7589 | 0.6578 | 0.6585 | 0.6653 | 0.6578 |
75
+ | 0.8224 | 0.5215 | 3200 | 0.7727 | 0.6635 | 0.6631 | 0.6859 | 0.6635 |
76
+ | 0.8163 | 0.5541 | 3400 | 0.7443 | 0.6819 | 0.6822 | 0.6841 | 0.6819 |
77
+ | 0.792 | 0.5867 | 3600 | 0.7537 | 0.6663 | 0.6669 | 0.6741 | 0.6663 |
78
+ | 0.7892 | 0.6193 | 3800 | 0.7494 | 0.6711 | 0.6711 | 0.6791 | 0.6711 |
79
+ | 0.8136 | 0.6519 | 4000 | 0.7463 | 0.6739 | 0.6740 | 0.6855 | 0.6739 |
80
+ | 0.7988 | 0.6845 | 4200 | 0.7367 | 0.6811 | 0.6818 | 0.6868 | 0.6811 |
81
+ | 0.7905 | 0.7171 | 4400 | 0.7454 | 0.6767 | 0.6767 | 0.6812 | 0.6767 |
82
+ | 0.7746 | 0.7497 | 4600 | 0.7533 | 0.6779 | 0.6774 | 0.6831 | 0.6779 |
83
+ | 0.7778 | 0.7823 | 4800 | 0.7317 | 0.6791 | 0.6792 | 0.6879 | 0.6791 |
84
+ | 0.7709 | 0.8149 | 5000 | 0.7304 | 0.6831 | 0.6834 | 0.6987 | 0.6831 |
85
+ | 0.7479 | 0.8475 | 5200 | 0.7320 | 0.6759 | 0.6768 | 0.6889 | 0.6759 |
86
+ | 0.7907 | 0.8801 | 5400 | 0.7156 | 0.6924 | 0.6931 | 0.6958 | 0.6924 |
87
+ | 0.7587 | 0.9126 | 5600 | 0.7175 | 0.6952 | 0.6952 | 0.6983 | 0.6952 |
88
+ | 0.7635 | 0.9452 | 5800 | 0.7206 | 0.6763 | 0.6767 | 0.6944 | 0.6763 |
89
+ | 0.7437 | 0.9778 | 6000 | 0.7220 | 0.6843 | 0.6849 | 0.6999 | 0.6843 |
90
+ | 0.7029 | 1.0104 | 6200 | 0.7448 | 0.6803 | 0.6792 | 0.6961 | 0.6803 |
91
+ | 0.6853 | 1.0430 | 6400 | 0.7167 | 0.6896 | 0.6895 | 0.6963 | 0.6896 |
92
+ | 0.7019 | 1.0756 | 6600 | 0.7333 | 0.6928 | 0.6931 | 0.7095 | 0.6928 |
93
+ | 0.7006 | 1.1082 | 6800 | 0.7178 | 0.6960 | 0.6963 | 0.7043 | 0.6960 |
94
+ | 0.7054 | 1.1408 | 7000 | 0.7078 | 0.6980 | 0.6986 | 0.7059 | 0.6980 |
95
+ | 0.7125 | 1.1734 | 7200 | 0.7094 | 0.7016 | 0.7021 | 0.7114 | 0.7016 |
96
+ | 0.6992 | 1.2060 | 7400 | 0.7339 | 0.6936 | 0.6924 | 0.7077 | 0.6936 |
97
+ | 0.6989 | 1.2386 | 7600 | 0.7008 | 0.6980 | 0.6993 | 0.7065 | 0.6980 |
98
+ | 0.7084 | 1.2712 | 7800 | 0.7040 | 0.7064 | 0.7066 | 0.7123 | 0.7064 |
99
+ | 0.6951 | 1.3038 | 8000 | 0.7038 | 0.7064 | 0.7070 | 0.7154 | 0.7064 |
100
+ | 0.6809 | 1.3364 | 8200 | 0.7146 | 0.7040 | 0.7043 | 0.7186 | 0.7040 |
101
+ | 0.7038 | 1.3690 | 8400 | 0.6909 | 0.7120 | 0.7129 | 0.7194 | 0.7120 |
102
+ | 0.7045 | 1.4016 | 8600 | 0.7248 | 0.6863 | 0.6852 | 0.7051 | 0.6863 |
103
+ | 0.693 | 1.4342 | 8800 | 0.7133 | 0.6952 | 0.6952 | 0.7104 | 0.6952 |
104
+ | 0.6912 | 1.4668 | 9000 | 0.7002 | 0.7024 | 0.7036 | 0.7145 | 0.7024 |
105
+ | 0.6622 | 1.4993 | 9200 | 0.6899 | 0.7068 | 0.7079 | 0.7128 | 0.7068 |
106
+ | 0.6986 | 1.5319 | 9400 | 0.6816 | 0.7129 | 0.7128 | 0.7137 | 0.7129 |
107
+ | 0.6812 | 1.5645 | 9600 | 0.6879 | 0.7036 | 0.7041 | 0.7067 | 0.7036 |
108
+ | 0.7011 | 1.5971 | 9800 | 0.6907 | 0.7032 | 0.7037 | 0.7098 | 0.7032 |
109
+ | 0.6957 | 1.6297 | 10000 | 0.7047 | 0.7032 | 0.7040 | 0.7105 | 0.7032 |
110
+ | 0.6978 | 1.6623 | 10200 | 0.6784 | 0.7137 | 0.7144 | 0.7169 | 0.7137 |
111
+ | 0.6804 | 1.6949 | 10400 | 0.6965 | 0.7028 | 0.7036 | 0.7164 | 0.7028 |
112
+ | 0.6673 | 1.7275 | 10600 | 0.7054 | 0.7036 | 0.7047 | 0.7162 | 0.7036 |
113
+ | 0.6929 | 1.7601 | 10800 | 0.6933 | 0.7040 | 0.7050 | 0.7130 | 0.7040 |
114
+ | 0.6714 | 1.7927 | 11000 | 0.6960 | 0.7020 | 0.7022 | 0.7113 | 0.7020 |
115
+ | 0.6887 | 1.8253 | 11200 | 0.7028 | 0.7020 | 0.7023 | 0.7145 | 0.7020 |
116
+ | 0.6894 | 1.8579 | 11400 | 0.7022 | 0.6996 | 0.6998 | 0.7154 | 0.6996 |
117
+ | 0.6793 | 1.8905 | 11600 | 0.6930 | 0.7092 | 0.7100 | 0.7195 | 0.7092 |
118
+ | 0.6767 | 1.9231 | 11800 | 0.6863 | 0.7173 | 0.7177 | 0.7245 | 0.7173 |
119
+ | 0.695 | 1.9557 | 12000 | 0.6748 | 0.7161 | 0.7165 | 0.7241 | 0.7161 |
120
+ | 0.6951 | 1.9883 | 12200 | 0.6874 | 0.7028 | 0.7034 | 0.7131 | 0.7028 |
121
+ | 0.5979 | 2.0209 | 12400 | 0.6976 | 0.7116 | 0.7111 | 0.7122 | 0.7116 |
122
+ | 0.5878 | 2.0535 | 12600 | 0.7078 | 0.7064 | 0.7070 | 0.7100 | 0.7064 |
123
+ | 0.5826 | 2.0860 | 12800 | 0.7238 | 0.7036 | 0.7050 | 0.7155 | 0.7036 |
124
+ | 0.5927 | 2.1186 | 13000 | 0.7100 | 0.7068 | 0.7075 | 0.7141 | 0.7068 |
125
+ | 0.5976 | 2.1512 | 13200 | 0.7132 | 0.7056 | 0.7066 | 0.7175 | 0.7056 |
126
+ | 0.5995 | 2.1838 | 13400 | 0.7001 | 0.7129 | 0.7137 | 0.7174 | 0.7129 |
127
+ | 0.5898 | 2.2164 | 13600 | 0.7011 | 0.7145 | 0.7155 | 0.7202 | 0.7145 |
128
+ | 0.5952 | 2.2490 | 13800 | 0.7345 | 0.7024 | 0.7028 | 0.7147 | 0.7024 |
129
+ | 0.5886 | 2.2816 | 14000 | 0.7008 | 0.7088 | 0.7088 | 0.7144 | 0.7088 |
130
+ | 0.5761 | 2.3142 | 14200 | 0.6942 | 0.7137 | 0.7148 | 0.7188 | 0.7137 |
131
+
132
+
133
+ ### Framework versions
134
+
135
+ - Transformers 4.48.0.dev0
136
+ - Pytorch 2.4.1+cu121
137
+ - Datasets 3.1.0
138
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dbmdz/distilbert-base-turkish-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "entailment",
13
+ "1": "neutral",
14
+ "2": "contradiction"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "contradiction": 2,
19
+ "entailment": 0,
20
+ "neutral": 1
21
+ },
22
+ "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "problem_type": "single_label_classification",
29
+ "qa_dropout": 0.1,
30
+ "seq_classif_dropout": 0.2,
31
+ "sinusoidal_pos_embds": true,
32
+ "tie_weights_": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.48.0.dev0",
35
+ "vocab_size": 32000
36
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c42acc21560f6428cf0b4d6690bff6ffa6d3024493fdb5e282940ce5283fa50
3
+ size 272376060
runs/Jan09_08-47-26_ip-10-10-15-55.eu-central-1.compute.internal/events.out.tfevents.1736412446.ip-10-10-15-55.eu-central-1.compute.internal.23155.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a3595a10cb7adcebc4b2a23535664e5455c67886328fe3479840014d02e6e6c
3
+ size 98957
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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": 128,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb587b6d0985c9eb36410d5434694ae9287d8bb24ff222cba48f3027a6c411f6
3
+ size 5432
vocab.txt ADDED
The diff for this file is too large to render. See raw diff