Aleksandar commited on
Commit
cae2b7d
1 Parent(s): 76272a5
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: distilbert-srb-ner-setimes
13
+ results:
14
+ - task:
15
+ name: Token Classification
16
+ type: token-classification
17
+ metric:
18
+ name: Accuracy
19
+ type: accuracy
20
+ value: 0.962385099177552
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
+ # distilbert-srb-ner-setimes
27
+
28
+ This model was trained from scratch on the None dataset.
29
+ It achieves the following results on the evaluation set:
30
+ - Loss: 0.1354
31
+ - Precision: 0.8
32
+ - Recall: 0.8319
33
+ - F1: 0.8156
34
+ - Accuracy: 0.9624
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: 5
60
+
61
+ ### Training results
62
+
63
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
64
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
65
+ | No log | 1.0 | 207 | 0.2206 | 0.7029 | 0.7267 | 0.7146 | 0.9384 |
66
+ | No log | 2.0 | 414 | 0.1582 | 0.7449 | 0.7813 | 0.7627 | 0.9532 |
67
+ | 0.2358 | 3.0 | 621 | 0.1449 | 0.7756 | 0.8171 | 0.7958 | 0.9579 |
68
+ | 0.2358 | 4.0 | 828 | 0.1382 | 0.7903 | 0.8329 | 0.8110 | 0.9609 |
69
+ | 0.0895 | 5.0 | 1035 | 0.1354 | 0.8 | 0.8319 | 0.8156 | 0.9624 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.9.2
75
+ - Pytorch 1.9.0
76
+ - Datasets 1.11.0
77
+ - Tokenizers 0.10.1
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Aleksandar/distilbert-srb-base-cased-oscar",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
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
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2,
28
+ "LABEL_3": 3,
29
+ "LABEL_4": 4,
30
+ "LABEL_5": 5,
31
+ "LABEL_6": 6,
32
+ "LABEL_7": 7,
33
+ "LABEL_8": 8,
34
+ "LABEL_9": 9
35
+ },
36
+ "max_position_embeddings": 512,
37
+ "model_type": "distilbert",
38
+ "n_heads": 12,
39
+ "n_layers": 6,
40
+ "output_past": true,
41
+ "pad_token_id": 0,
42
+ "qa_dropout": 0.1,
43
+ "seq_classif_dropout": 0.2,
44
+ "sinusoidal_pos_embds": false,
45
+ "tie_weights_": true,
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.9.2",
48
+ "vocab_size": 50257
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89f96d2c75a31f0230ac8177426f328ee78256c17f95ea933459ec4e136aa9b0
3
+ size 326147573
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/distilbert-srb-base-cased-oscar", "tokenizer_class": "DistilBertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3b4043154c0af293032a1d5318a9a9e25b29ce6ef48005e4346e383bfe901a8
3
+ size 2735
vocab.txt ADDED
The diff for this file is too large to render. See raw diff