Philipp Schmid commited on
Commit
90e8162
1 Parent(s): 345828a
README.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - token-classification
5
+ datasets:
6
+ - wikiann-conll2003
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+
13
+ model-index:
14
+ - name: distilroberta-base-ner-wikiann-conll2003-3-class
15
+ results:
16
+ - task:
17
+ name: Token Classification
18
+ type: token-classification
19
+ dataset:
20
+ name: wikiann-conll2003
21
+ type: wikiann-conll2003
22
+ metrics:
23
+ - name: Precision
24
+ type: precision
25
+ value: 0.9624757386241104
26
+ - name: Recall
27
+ type: recall
28
+ value: 0.9667497021553124
29
+ - name: F1
30
+ type: f1
31
+ value: 0.964607986167396
32
+ - name: Accuracy
33
+ type: accuracy
34
+ value: 0.9913626461292995
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
+ # distilroberta-base-ner-wikiann-conll2003-3-class
41
+
42
+ This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the wikiann-conll2003 dataset.
43
+ It achieves the following results on the evaluation set:
44
+ - Loss: 0.0520
45
+ - Precision: 0.9625
46
+ - Recall: 0.9667
47
+ - F1: 0.9646
48
+ - Accuracy: 0.9914
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: 4.9086903597787154e-05
68
+ - train_batch_size: 32
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: 5.0
74
+ - mixed_precision_training: Native AMP
75
+
76
+ ### Training results
77
+
78
+
79
+
80
+ ### Framework versions
81
+
82
+ - Transformers 4.6.1
83
+ - Pytorch 1.8.1+cu101
84
+ - Datasets 1.6.2
85
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "finetuning_task": "ner",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2",
18
+ "3": "LABEL_3",
19
+ "4": "LABEL_4",
20
+ "5": "LABEL_5",
21
+ "6": "LABEL_6"
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
+ },
34
+ "layer_norm_eps": 1e-05,
35
+ "max_position_embeddings": 514,
36
+ "model_type": "roberta",
37
+ "num_attention_heads": 12,
38
+ "num_hidden_layers": 6,
39
+ "pad_token_id": 1,
40
+ "position_embedding_type": "absolute",
41
+ "transformers_version": "4.6.1",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 50265
45
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04fe971151b3871aafe85511a85565218715f90c7c1e209861edae0a8aecc826
3
+ size 326181207
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilroberta-base"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff