Hugging Face's logo

kaixkhazaki
/
turkish-zeroshot-large

Zero-Shot Classification
Transformers
TensorBoard
Safetensors
Turkish
bert
text-classification
Generated from Trainer
turkush
Model card Files Metrics Community
kaixkhazaki commited on
Commit
a62ca86
·
verified ·
1 Parent(s): 28b9307

Pushing of the best model checkpoint

Browse files
Files changed (9) hide show
  1. README.md +147 -0
  2. config.json +36 -0
  3. model.safetensors +3 -0
  4. runs/Jan09_15-42-55_ip-10-10-13-247.eu-central-1.compute.internal/events.out.tfevents.1736437377.ip-10-10-13-247.eu-central-1.compute.internal.8585.0 +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 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: dbmdz/bert-base-turkish-128k-uncased
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ - precision
11
+ - recall
12
+ model-index:
13
+ - name: turkish-zeroshot-large
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-large
21
+
22
+ This model is a fine-tuned version of [dbmdz/bert-base-turkish-128k-uncased](https://huggingface.co/dbmdz/bert-base-turkish-128k-uncased) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.6957
25
+ - Accuracy: 0.7622
26
+ - F1: 0.7621
27
+ - Precision: 0.7702
28
+ - Recall: 0.7622
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
+ | 1.0339 | 0.0326 | 200 | 1.0342 | 0.4855 | 0.4610 | 0.5453 | 0.4855 |
61
+ | 0.8777 | 0.0652 | 400 | 0.7819 | 0.6631 | 0.6634 | 0.6903 | 0.6631 |
62
+ | 0.8194 | 0.0978 | 600 | 0.7322 | 0.6888 | 0.6891 | 0.6956 | 0.6888 |
63
+ | 0.7745 | 0.1304 | 800 | 0.6895 | 0.7120 | 0.7129 | 0.7217 | 0.7120 |
64
+ | 0.7766 | 0.1630 | 1000 | 0.7042 | 0.7044 | 0.7057 | 0.7180 | 0.7044 |
65
+ | 0.7388 | 0.1956 | 1200 | 0.6933 | 0.7092 | 0.7097 | 0.7310 | 0.7092 |
66
+ | 0.7392 | 0.2282 | 1400 | 0.6812 | 0.7201 | 0.7208 | 0.7384 | 0.7201 |
67
+ | 0.7205 | 0.2608 | 1600 | 0.6892 | 0.7108 | 0.7092 | 0.7326 | 0.7108 |
68
+ | 0.7229 | 0.2934 | 1800 | 0.6762 | 0.7120 | 0.7123 | 0.7265 | 0.7120 |
69
+ | 0.6833 | 0.3259 | 2000 | 0.6374 | 0.7333 | 0.7338 | 0.7404 | 0.7333 |
70
+ | 0.7356 | 0.3585 | 2200 | 0.6803 | 0.7112 | 0.7100 | 0.7294 | 0.7112 |
71
+ | 0.7044 | 0.3911 | 2400 | 0.6894 | 0.7169 | 0.7168 | 0.7430 | 0.7169 |
72
+ | 0.701 | 0.4237 | 2600 | 0.6512 | 0.7209 | 0.7225 | 0.7431 | 0.7209 |
73
+ | 0.7005 | 0.4563 | 2800 | 0.6160 | 0.7442 | 0.7451 | 0.7516 | 0.7442 |
74
+ | 0.7028 | 0.4889 | 3000 | 0.6207 | 0.7349 | 0.7360 | 0.7444 | 0.7349 |
75
+ | 0.7129 | 0.5215 | 3200 | 0.6281 | 0.7341 | 0.7360 | 0.7503 | 0.7341 |
76
+ | 0.6812 | 0.5541 | 3400 | 0.6082 | 0.7438 | 0.7444 | 0.7495 | 0.7438 |
77
+ | 0.6615 | 0.5867 | 3600 | 0.6600 | 0.7293 | 0.7296 | 0.7509 | 0.7293 |
78
+ | 0.6851 | 0.6193 | 3800 | 0.6117 | 0.7466 | 0.7476 | 0.7556 | 0.7466 |
79
+ | 0.69 | 0.6519 | 4000 | 0.6284 | 0.7454 | 0.7461 | 0.7578 | 0.7454 |
80
+ | 0.6591 | 0.6845 | 4200 | 0.6088 | 0.7526 | 0.7536 | 0.7615 | 0.7526 |
81
+ | 0.6858 | 0.7171 | 4400 | 0.6241 | 0.7442 | 0.7459 | 0.7649 | 0.7442 |
82
+ | 0.6562 | 0.7497 | 4600 | 0.5933 | 0.7631 | 0.7638 | 0.7684 | 0.7631 |
83
+ | 0.6584 | 0.7823 | 4800 | 0.6152 | 0.7510 | 0.7523 | 0.7667 | 0.7510 |
84
+ | 0.6288 | 0.8149 | 5000 | 0.5803 | 0.7663 | 0.7670 | 0.7696 | 0.7663 |
85
+ | 0.6456 | 0.8475 | 5200 | 0.6443 | 0.7369 | 0.7376 | 0.7582 | 0.7369 |
86
+ | 0.6751 | 0.8801 | 5400 | 0.5841 | 0.7627 | 0.7639 | 0.7684 | 0.7627 |
87
+ | 0.6296 | 0.9126 | 5600 | 0.5990 | 0.7510 | 0.7528 | 0.7655 | 0.7510 |
88
+ | 0.6536 | 0.9452 | 5800 | 0.6069 | 0.7454 | 0.7471 | 0.7736 | 0.7454 |
89
+ | 0.6541 | 0.9778 | 6000 | 0.5822 | 0.7598 | 0.7612 | 0.7694 | 0.7598 |
90
+ | 0.5352 | 1.0104 | 6200 | 0.6166 | 0.7590 | 0.7589 | 0.7667 | 0.7590 |
91
+ | 0.513 | 1.0430 | 6400 | 0.5883 | 0.7667 | 0.7669 | 0.7719 | 0.7667 |
92
+ | 0.5426 | 1.0756 | 6600 | 0.5802 | 0.7631 | 0.7641 | 0.7709 | 0.7631 |
93
+ | 0.5609 | 1.1082 | 6800 | 0.5901 | 0.7558 | 0.7559 | 0.7602 | 0.7558 |
94
+ | 0.5626 | 1.1408 | 7000 | 0.5967 | 0.7538 | 0.7556 | 0.7727 | 0.7538 |
95
+ | 0.5404 | 1.1734 | 7200 | 0.5973 | 0.7530 | 0.7549 | 0.7668 | 0.7530 |
96
+ | 0.547 | 1.2060 | 7400 | 0.6014 | 0.7538 | 0.7539 | 0.7652 | 0.7538 |
97
+ | 0.5364 | 1.2386 | 7600 | 0.5895 | 0.7647 | 0.7656 | 0.7770 | 0.7647 |
98
+ | 0.5504 | 1.2712 | 7800 | 0.6127 | 0.7494 | 0.7483 | 0.7621 | 0.7494 |
99
+ | 0.5322 | 1.3038 | 8000 | 0.5927 | 0.7639 | 0.7646 | 0.7713 | 0.7639 |
100
+ | 0.5211 | 1.3364 | 8200 | 0.6247 | 0.7494 | 0.7510 | 0.7689 | 0.7494 |
101
+ | 0.561 | 1.3690 | 8400 | 0.5600 | 0.7731 | 0.7739 | 0.7775 | 0.7731 |
102
+ | 0.559 | 1.4016 | 8600 | 0.6107 | 0.7506 | 0.7514 | 0.7647 | 0.7506 |
103
+ | 0.5492 | 1.4342 | 8800 | 0.5770 | 0.7651 | 0.7661 | 0.7721 | 0.7651 |
104
+ | 0.5399 | 1.4668 | 9000 | 0.5827 | 0.7614 | 0.7623 | 0.7697 | 0.7614 |
105
+ | 0.5125 | 1.4993 | 9200 | 0.6080 | 0.7606 | 0.7620 | 0.7732 | 0.7606 |
106
+ | 0.5407 | 1.5319 | 9400 | 0.5651 | 0.7679 | 0.7684 | 0.7707 | 0.7679 |
107
+ | 0.5429 | 1.5645 | 9600 | 0.5778 | 0.7635 | 0.7645 | 0.7695 | 0.7635 |
108
+ | 0.538 | 1.5971 | 9800 | 0.5937 | 0.7526 | 0.7542 | 0.7660 | 0.7526 |
109
+ | 0.5533 | 1.6297 | 10000 | 0.5955 | 0.7715 | 0.7724 | 0.7765 | 0.7715 |
110
+ | 0.5309 | 1.6623 | 10200 | 0.6251 | 0.7538 | 0.7546 | 0.7660 | 0.7538 |
111
+ | 0.5301 | 1.6949 | 10400 | 0.5991 | 0.7627 | 0.7639 | 0.7777 | 0.7627 |
112
+ | 0.5076 | 1.7275 | 10600 | 0.6074 | 0.7578 | 0.7587 | 0.7720 | 0.7578 |
113
+ | 0.5571 | 1.7601 | 10800 | 0.6309 | 0.7534 | 0.7542 | 0.7708 | 0.7534 |
114
+ | 0.5352 | 1.7927 | 11000 | 0.5786 | 0.7739 | 0.7742 | 0.7826 | 0.7739 |
115
+ | 0.5387 | 1.8253 | 11200 | 0.6231 | 0.7526 | 0.7516 | 0.7670 | 0.7526 |
116
+ | 0.5389 | 1.8579 | 11400 | 0.5686 | 0.7671 | 0.7680 | 0.7760 | 0.7671 |
117
+ | 0.5454 | 1.8905 | 11600 | 0.6054 | 0.7546 | 0.7562 | 0.7751 | 0.7546 |
118
+ | 0.5326 | 1.9231 | 11800 | 0.5860 | 0.7715 | 0.7721 | 0.7787 | 0.7715 |
119
+ | 0.5428 | 1.9557 | 12000 | 0.5853 | 0.7655 | 0.7664 | 0.7782 | 0.7655 |
120
+ | 0.5454 | 1.9883 | 12200 | 0.5810 | 0.7651 | 0.7654 | 0.7689 | 0.7651 |
121
+ | 0.3759 | 2.0209 | 12400 | 0.6863 | 0.7679 | 0.7685 | 0.7737 | 0.7679 |
122
+ | 0.3644 | 2.0535 | 12600 | 0.7031 | 0.7586 | 0.7595 | 0.7713 | 0.7586 |
123
+ | 0.3615 | 2.0860 | 12800 | 0.7177 | 0.7582 | 0.7594 | 0.7659 | 0.7582 |
124
+ | 0.383 | 2.1186 | 13000 | 0.6836 | 0.7586 | 0.7594 | 0.7720 | 0.7586 |
125
+ | 0.3818 | 2.1512 | 13200 | 0.6996 | 0.7683 | 0.7693 | 0.7803 | 0.7683 |
126
+ | 0.3917 | 2.1838 | 13400 | 0.6490 | 0.7679 | 0.7693 | 0.7751 | 0.7679 |
127
+ | 0.3527 | 2.2164 | 13600 | 0.7409 | 0.7570 | 0.7580 | 0.7717 | 0.7570 |
128
+ | 0.3785 | 2.2490 | 13800 | 0.6836 | 0.7570 | 0.7571 | 0.7700 | 0.7570 |
129
+ | 0.3732 | 2.2816 | 14000 | 0.6396 | 0.7723 | 0.7732 | 0.7782 | 0.7723 |
130
+ | 0.3616 | 2.3142 | 14200 | 0.6664 | 0.7651 | 0.7663 | 0.7758 | 0.7651 |
131
+ | 0.3705 | 2.3468 | 14400 | 0.6688 | 0.7570 | 0.7582 | 0.7691 | 0.7570 |
132
+ | 0.3668 | 2.3794 | 14600 | 0.7041 | 0.7627 | 0.7631 | 0.7722 | 0.7627 |
133
+ | 0.3697 | 2.4120 | 14800 | 0.6771 | 0.7554 | 0.7558 | 0.7666 | 0.7554 |
134
+ | 0.3767 | 2.4446 | 15000 | 0.6950 | 0.7606 | 0.7613 | 0.7733 | 0.7606 |
135
+ | 0.3999 | 2.4772 | 15200 | 0.6775 | 0.7602 | 0.7608 | 0.7685 | 0.7602 |
136
+ | 0.3758 | 2.5098 | 15400 | 0.6654 | 0.7618 | 0.7622 | 0.7679 | 0.7618 |
137
+ | 0.3851 | 2.5424 | 15600 | 0.7070 | 0.7558 | 0.7568 | 0.7687 | 0.7558 |
138
+ | 0.3716 | 2.5750 | 15800 | 0.7472 | 0.7546 | 0.7555 | 0.7704 | 0.7546 |
139
+ | 0.3633 | 2.6076 | 16000 | 0.6957 | 0.7622 | 0.7621 | 0.7702 | 0.7622 |
140
+
141
+
142
+ ### Framework versions
143
+
144
+ - Transformers 4.48.0.dev0
145
+ - Pytorch 2.4.1+cu121
146
+ - Datasets 3.1.0
147
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dbmdz/bert-base-turkish-128k-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": "entailment",
13
+ "1": "neutral",
14
+ "2": "contradiction"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "contradiction": 2,
20
+ "entailment": 0,
21
+ "neutral": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "problem_type": "single_label_classification",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.48.0.dev0",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 128000
36
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04c895c757933f016e29bbfed6def072f3f548cc34a02b6d4d1bf04b39ec8f00
3
+ size 737414148
runs/Jan09_15-42-55_ip-10-10-13-247.eu-central-1.compute.internal/events.out.tfevents.1736437377.ip-10-10-13-247.eu-central-1.compute.internal.8585.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:520f58c7e58cd9b5b050f3b4e277189ea7312b01a90fc148932b7494f6df5069
3
+ size 110851
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": true,
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 sha256:605fa87e12cf36ec8f2b26bfa7f4f70d7a150e956959f1f2c63280cc223f3616
3
+ size 5432
vocab.txt ADDED
The diff for this file is too large to render. See raw diff