yeniguno commited on
Commit
c4b155e
·
verified ·
1 Parent(s): 1fd9a7c

End of training

Browse files
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: dbmdz/bert-base-turkish-cased
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: bert-ner-turkish-cased
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
+ # bert-ner-turkish-cased
21
+
22
+ This model is a fine-tuned version of [dbmdz/bert-base-turkish-cased](https://huggingface.co/dbmdz/bert-base-turkish-cased) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 1.5613
25
+ - Precision: 0.0
26
+ - Recall: 0.0
27
+ - F1: 0.0
28
+ - Accuracy: 0.4699
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: 2e-05
48
+ - train_batch_size: 32
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: linear
53
+ - num_epochs: 20
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
59
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
60
+ | No log | 1.0 | 3 | 2.5088 | 0.0 | 0.0 | 0.0 | 0.0843 |
61
+ | No log | 2.0 | 6 | 2.2394 | 0.0 | 0.0 | 0.0 | 0.2259 |
62
+ | No log | 3.0 | 9 | 1.8687 | 0.0 | 0.0 | 0.0 | 0.4367 |
63
+ | No log | 4.0 | 12 | 1.5613 | 0.0 | 0.0 | 0.0 | 0.4699 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.47.0
69
+ - Pytorch 2.5.1+cu121
70
+ - Datasets 3.2.0
71
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-PER",
14
+ "2": "I-PER",
15
+ "3": "B-LOC",
16
+ "4": "I-LOC",
17
+ "5": "B-ORG",
18
+ "6": "I-ORG",
19
+ "7": "B-DATE",
20
+ "8": "I-DATE",
21
+ "9": "B-MONEY",
22
+ "10": "I-MONEY",
23
+ "11": "B-MISC",
24
+ "12": "I-MISC"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "label2id": {
29
+ "B-DATE": 7,
30
+ "B-LOC": 3,
31
+ "B-MISC": 11,
32
+ "B-MONEY": 9,
33
+ "B-ORG": 5,
34
+ "B-PER": 1,
35
+ "I-DATE": 8,
36
+ "I-LOC": 4,
37
+ "I-MISC": 12,
38
+ "I-MONEY": 10,
39
+ "I-ORG": 6,
40
+ "I-PER": 2,
41
+ "O": 0
42
+ },
43
+ "layer_norm_eps": 1e-12,
44
+ "max_position_embeddings": 512,
45
+ "model_type": "bert",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 12,
48
+ "pad_token_id": 0,
49
+ "position_embedding_type": "absolute",
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.47.0",
52
+ "type_vocab_size": 2,
53
+ "use_cache": true,
54
+ "vocab_size": 32000
55
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8d9c70571a3194940a71b64b19c7a81bd8bb5b6ace2ac61056e3b9c844685ad
3
+ size 440170348
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": 512,
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 sha256:1a6a050f0f0227134a5cdffbc5c827c47b35710e9738a43341be40e08950eb84
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff