deval commited on
Commit
80c7c10
·
1 Parent(s): a8951d8
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - x_glue
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: bert-base-NER-finetuned-ner
14
+ results:
15
+ - task:
16
+ name: Token Classification
17
+ type: token-classification
18
+ dataset:
19
+ name: x_glue
20
+ type: x_glue
21
+ args: ner
22
+ metrics:
23
+ - name: Precision
24
+ type: precision
25
+ value: 0.2273838630806846
26
+ - name: Recall
27
+ type: recall
28
+ value: 0.11185727172496743
29
+ - name: F1
30
+ type: f1
31
+ value: 0.14994961370507223
32
+ - name: Accuracy
33
+ type: accuracy
34
+ value: 0.8485324947589099
35
+ ---
36
+
37
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
38
+ should probably proofread and complete it, then remove this comment. -->
39
+
40
+ # bert-base-NER-finetuned-ner
41
+
42
+ This model is a fine-tuned version of [dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER) on the x_glue dataset.
43
+ It achieves the following results on the evaluation set:
44
+ - Loss: 1.4380
45
+ - Precision: 0.2274
46
+ - Recall: 0.1119
47
+ - F1: 0.1499
48
+ - Accuracy: 0.8485
49
+
50
+ ## Model description
51
+
52
+ More information needed
53
+
54
+ ## Intended uses & limitations
55
+
56
+ More information needed
57
+
58
+ ## Training and evaluation data
59
+
60
+ More information needed
61
+
62
+ ## Training procedure
63
+
64
+ ### Training hyperparameters
65
+
66
+ The following hyperparameters were used during training:
67
+ - learning_rate: 2e-05
68
+ - train_batch_size: 16
69
+ - eval_batch_size: 16
70
+ - seed: 42
71
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
72
+ - lr_scheduler_type: linear
73
+ - num_epochs: 5
74
+
75
+ ### Training results
76
+
77
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
78
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
79
+ | 0.0822 | 1.0 | 878 | 1.1648 | 0.2068 | 0.1101 | 0.1437 | 0.8471 |
80
+ | 0.0102 | 2.0 | 1756 | 1.2697 | 0.2073 | 0.1110 | 0.1445 | 0.8447 |
81
+ | 0.0049 | 3.0 | 2634 | 1.3945 | 0.2006 | 0.1073 | 0.1399 | 0.8368 |
82
+ | 0.0025 | 4.0 | 3512 | 1.3994 | 0.2243 | 0.1126 | 0.1499 | 0.8501 |
83
+ | 0.0011 | 5.0 | 4390 | 1.4380 | 0.2274 | 0.1119 | 0.1499 | 0.8485 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.10.2
89
+ - Pytorch 1.9.0+cu102
90
+ - Datasets 1.12.1
91
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dslim/bert-base-NER",
3
+ "_num_labels": 9,
4
+ "architectures": [
5
+ "BertForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-MISC",
16
+ "2": "I-MISC",
17
+ "3": "B-PER",
18
+ "4": "I-PER",
19
+ "5": "B-ORG",
20
+ "6": "I-ORG",
21
+ "7": "B-LOC",
22
+ "8": "I-LOC"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "B-LOC": 7,
28
+ "B-MISC": 1,
29
+ "B-ORG": 5,
30
+ "B-PER": 3,
31
+ "I-LOC": 8,
32
+ "I-MISC": 2,
33
+ "I-ORG": 6,
34
+ "I-PER": 4,
35
+ "O": 0
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
+ "output_past": true,
43
+ "pad_token_id": 0,
44
+ "position_embedding_type": "absolute",
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.10.2",
47
+ "type_vocab_size": 2,
48
+ "use_cache": true,
49
+ "vocab_size": 28996
50
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f0c450a14fafb7e659fcb7dd2bf718e4c26f7bf4f299807a12b05a57c4adfad
3
+ size 430989809
runs/Sep20_15-27-41_8dd6cc4e87b3/1632151675.5835438/events.out.tfevents.1632151675.8dd6cc4e87b3.77.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b69e15e37f72d737ef9aec3299973abfb7b47120d851bfdf16901dcea1adfc2
3
+ size 4188
runs/Sep20_15-27-41_8dd6cc4e87b3/events.out.tfevents.1632151675.8dd6cc4e87b3.77.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fda4f833c929220dfb4a6e16ca5d68f281dbc928fb306e4a00c31c2b40325711
3
+ size 7317
runs/Sep20_15-27-41_8dd6cc4e87b3/events.out.tfevents.1632153390.8dd6cc4e87b3.77.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e174c3e31025dfd6dbbba710a56e5d1cbd5b9a41caadfb1c2448d50bab9a8f06
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": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/8ecdadef2bc275e74e0d4541ae8a5db151fba13174b86dfa88ef5765d30feb77.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "dslim/bert-base-NER", "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:b36ed4b35aca4f4debe952db2dd62007956b1f300f95f0855a78c3b1589ea148
3
+ size 2671
vocab.txt ADDED
The diff for this file is too large to render. See raw diff