wwwtwwwt commited on
Commit
0711cb3
·
verified ·
1 Parent(s): 412b88a

End of training

Browse files
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: bert-large-cased
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - conll2003
9
+ metrics:
10
+ - precision
11
+ - recall
12
+ - f1
13
+ - accuracy
14
+ model-index:
15
+ - name: bert-large-cased-NER-Model
16
+ results:
17
+ - task:
18
+ name: Token Classification
19
+ type: token-classification
20
+ dataset:
21
+ name: conll2003
22
+ type: conll2003
23
+ config: conll2003
24
+ split: test
25
+ args: conll2003
26
+ metrics:
27
+ - name: Precision
28
+ type: precision
29
+ value: 0.90625
30
+ - name: Recall
31
+ type: recall
32
+ value: 0.9190864022662889
33
+ - name: F1
34
+ type: f1
35
+ value: 0.9126230661040787
36
+ - name: Accuracy
37
+ type: accuracy
38
+ value: 0.9824916550016152
39
+ ---
40
+
41
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
42
+ should probably proofread and complete it, then remove this comment. -->
43
+
44
+ # bert-large-cased-NER-Model
45
+
46
+ This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on the conll2003 dataset.
47
+ It achieves the following results on the evaluation set:
48
+ - Loss: 0.1281
49
+ - Precision: 0.9062
50
+ - Recall: 0.9191
51
+ - F1: 0.9126
52
+ - Accuracy: 0.9825
53
+
54
+ ## Model description
55
+
56
+ More information needed
57
+
58
+ ## Intended uses & limitations
59
+
60
+ More information needed
61
+
62
+ ## Training and evaluation data
63
+
64
+ More information needed
65
+
66
+ ## Training procedure
67
+
68
+ ### Training hyperparameters
69
+
70
+ The following hyperparameters were used during training:
71
+ - learning_rate: 1e-05
72
+ - train_batch_size: 16
73
+ - eval_batch_size: 16
74
+ - seed: 42
75
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
76
+ - lr_scheduler_type: linear
77
+ - num_epochs: 2
78
+
79
+ ### Training results
80
+
81
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
82
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
83
+ | 0.0319 | 1.0 | 1756 | 0.1147 | 0.9025 | 0.9198 | 0.9111 | 0.9822 |
84
+ | 0.0113 | 2.0 | 3512 | 0.1281 | 0.9062 | 0.9191 | 0.9126 | 0.9825 |
85
+
86
+
87
+ ### Framework versions
88
+
89
+ - Transformers 4.51.1
90
+ - Pytorch 2.5.1+cu124
91
+ - Datasets 3.5.0
92
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-PER",
15
+ "2": "I-PER",
16
+ "3": "B-ORG",
17
+ "4": "I-ORG",
18
+ "5": "B-LOC",
19
+ "6": "I-LOC",
20
+ "7": "B-MISC",
21
+ "8": "I-MISC"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 4096,
25
+ "label2id": {
26
+ "B-LOC": 5,
27
+ "B-MISC": 7,
28
+ "B-ORG": 3,
29
+ "B-PER": 1,
30
+ "I-LOC": 6,
31
+ "I-MISC": 8,
32
+ "I-ORG": 4,
33
+ "I-PER": 2,
34
+ "O": 0
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 16,
40
+ "num_hidden_layers": 24,
41
+ "pad_token_id": 0,
42
+ "pooler_fc_size": 768,
43
+ "pooler_num_attention_heads": 12,
44
+ "pooler_num_fc_layers": 3,
45
+ "pooler_size_per_head": 128,
46
+ "pooler_type": "first_token_transform",
47
+ "position_embedding_type": "absolute",
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.51.1",
50
+ "type_vocab_size": 2,
51
+ "use_cache": true,
52
+ "vocab_size": 28996
53
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c0fe67271cb30916dcf6cba7414d847c86893e75aff5fd95edc43868bf2826d
3
+ size 1330202364
runs/Apr15_13-35-48_cadb9ff2fc63/events.out.tfevents.1744724150.cadb9ff2fc63.32.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5cb6bc06f7e23a9855d7c0d88feef45f1213d251c441b68a0fdf547c0a279cb
3
+ size 8327
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20074f12203f2f31b5d7eb8e01fa982e74e0a2a95fce3cf9301ce865f20157f
3
+ size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff