Aleksandar commited on
Commit
8f411cd
1 Parent(s): 02f1aea
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - null
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model_index:
12
+ - name: bert-srb-ner
13
+ results:
14
+ - task:
15
+ name: Token Classification
16
+ type: token-classification
17
+ metric:
18
+ name: Accuracy
19
+ type: accuracy
20
+ value: 0.9334458889076481
21
+ ---
22
+
23
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
24
+ should probably proofread and complete it, then remove this comment. -->
25
+
26
+ # bert-srb-ner
27
+
28
+ This model was trained from scratch on the None dataset.
29
+ It achieves the following results on the evaluation set:
30
+ - Loss: 0.2321
31
+ - Precision: 0.6593
32
+ - Recall: 0.6877
33
+ - F1: 0.6732
34
+ - Accuracy: 0.9334
35
+
36
+ ## Model description
37
+
38
+ More information needed
39
+
40
+ ## Intended uses & limitations
41
+
42
+ More information needed
43
+
44
+ ## Training and evaluation data
45
+
46
+ More information needed
47
+
48
+ ## Training procedure
49
+
50
+ ### Training hyperparameters
51
+
52
+ The following hyperparameters were used during training:
53
+ - learning_rate: 2e-05
54
+ - train_batch_size: 16
55
+ - eval_batch_size: 8
56
+ - seed: 42
57
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
+ - lr_scheduler_type: linear
59
+ - num_epochs: 1
60
+
61
+ ### Training results
62
+
63
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
64
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
65
+ | No log | 1.0 | 207 | 0.2321 | 0.6593 | 0.6877 | 0.6732 | 0.9334 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.9.2
71
+ - Pytorch 1.9.0
72
+ - Datasets 1.11.0
73
+ - Tokenizers 0.10.1
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Aleksandar/bert-srb-base-cased-oscar",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8,
35
+ "LABEL_9": 9
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "bert",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "pad_token_id": 0,
43
+ "position_embedding_type": "absolute",
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.9.2",
46
+ "type_vocab_size": 2,
47
+ "use_cache": true,
48
+ "vocab_size": 28996
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a271d5457ffafe5e6d252aff36283dd7eb35cca2d6a162054747a9e975ba3c
3
+ size 430992881
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "Aleksandar/bert-srb-base-cased-oscar", "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a92bb655947b4ac9f3cc291af0c09bff79248ab340046b462fd3e7bd1166e07f
3
+ size 2671
vocab.txt ADDED
The diff for this file is too large to render. See raw diff