gagan3012 commited on
Commit
f01cf59
1 Parent(s): 18ecf00
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - conll2003
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: bert-tiny-finetuned-ner
13
+ results:
14
+ - task:
15
+ name: Token Classification
16
+ type: token-classification
17
+ dataset:
18
+ name: conll2003
19
+ type: conll2003
20
+ args: conll2003
21
+ metrics:
22
+ - name: Precision
23
+ type: precision
24
+ value: 0.5147295742232451
25
+ - name: Recall
26
+ type: recall
27
+ value: 0.5003915426781519
28
+ - name: F1
29
+ type: f1
30
+ value: 0.5074593000170173
31
+ - name: Accuracy
32
+ type: accuracy
33
+ value: 0.8967226396810015
34
+ ---
35
+
36
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
37
+ should probably proofread and complete it, then remove this comment. -->
38
+
39
+ # bert-tiny-finetuned-ner
40
+
41
+ This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the conll2003 dataset.
42
+ It achieves the following results on the evaluation set:
43
+ - Loss: 0.4053
44
+ - Precision: 0.5147
45
+ - Recall: 0.5004
46
+ - F1: 0.5075
47
+ - Accuracy: 0.8967
48
+
49
+ ## Model description
50
+
51
+ More information needed
52
+
53
+ ## Intended uses & limitations
54
+
55
+ More information needed
56
+
57
+ ## Training and evaluation data
58
+
59
+ More information needed
60
+
61
+ ## Training procedure
62
+
63
+ ### Training hyperparameters
64
+
65
+ The following hyperparameters were used during training:
66
+ - learning_rate: 2e-05
67
+ - train_batch_size: 16
68
+ - eval_batch_size: 16
69
+ - seed: 42
70
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
71
+ - lr_scheduler_type: linear
72
+ - num_epochs: 3
73
+
74
+ ### Training results
75
+
76
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
77
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
78
+ | 0.9306 | 1.0 | 878 | 0.5040 | 0.4321 | 0.4099 | 0.4207 | 0.8762 |
79
+ | 0.4777 | 2.0 | 1756 | 0.4240 | 0.4978 | 0.4851 | 0.4913 | 0.8926 |
80
+ | 0.4306 | 3.0 | 2634 | 0.4053 | 0.5147 | 0.5004 | 0.5075 | 0.8967 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.10.0
86
+ - Pytorch 1.9.0+cu102
87
+ - Datasets 1.11.0
88
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "prajjwal1/bert-tiny",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 128,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 512,
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
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 2,
40
+ "num_hidden_layers": 2,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.10.0",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0dccbeb362f2306350dd202988495fab5e609f95e7c275a914fdb77d600842f
3
+ size 17501357
runs/Sep01_23-19-08_6032072e4978/1630538367.2229316/events.out.tfevents.1630538367.6032072e4978.75.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c7a2a239a66f42743063bc625596336cc0c727582b1a10e7d4366e3361b900f
3
+ size 4184
runs/Sep01_23-19-08_6032072e4978/events.out.tfevents.1630538367.6032072e4978.75.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b17f1c6336808f263c1f650667a5ef7b9018d82953bb4a0209e367a1d152304c
3
+ size 5833
runs/Sep01_23-19-08_6032072e4978/events.out.tfevents.1630538431.6032072e4978.75.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6a555d3e1d44aad7e948d24949a13ccebc3e265295804589a331df34272817
3
+ size 512
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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "prajjwal1/bert-tiny", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9824e73909300e4fe6d7b5aef5778e9d87b21046860efaad22a90089f4b632cc
3
+ size 2671
vocab.txt ADDED
The diff for this file is too large to render. See raw diff