ZenMan67 commited on
Commit
a480adf
·
verified ·
1 Parent(s): b2713c8

End of training

Browse files
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: BAAI/bge-small-en-v1.5
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: bert-finetuned-ner
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # bert-finetuned-ner
21
+
22
+ This model is a fine-tuned version of [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.0890
25
+ - Precision: 0.9050
26
+ - Recall: 0.9287
27
+ - F1: 0.9167
28
+ - Accuracy: 0.9828
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 2e-05
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 8
50
+ - seed: 42
51
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 10
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | 0.0647 | 1.0 | 1250 | 0.0937 | 0.8574 | 0.9124 | 0.8840 | 0.9769 |
60
+ | 0.0465 | 2.0 | 2500 | 0.0914 | 0.8914 | 0.9156 | 0.9033 | 0.9802 |
61
+ | 0.0351 | 3.0 | 3750 | 0.0871 | 0.8950 | 0.9168 | 0.9058 | 0.9814 |
62
+ | 0.0298 | 4.0 | 5000 | 0.0891 | 0.8966 | 0.9262 | 0.9111 | 0.9816 |
63
+ | 0.025 | 5.0 | 6250 | 0.0888 | 0.8962 | 0.9282 | 0.9119 | 0.9819 |
64
+ | 0.0193 | 6.0 | 7500 | 0.0836 | 0.9068 | 0.9291 | 0.9178 | 0.9827 |
65
+ | 0.0165 | 7.0 | 8750 | 0.0874 | 0.9051 | 0.9292 | 0.9170 | 0.9829 |
66
+ | 0.0132 | 8.0 | 10000 | 0.0890 | 0.9050 | 0.9287 | 0.9167 | 0.9828 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.56.2
72
+ - Pytorch 2.8.0+cu126
73
+ - Datasets 4.0.0
74
+ - Tokenizers 0.22.1
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 384,
11
+ "id2label": {
12
+ "0": "B-LOC",
13
+ "1": "B-MISC",
14
+ "2": "B-ORG",
15
+ "3": "B-PER",
16
+ "4": "I-LOC",
17
+ "5": "I-MISC",
18
+ "6": "I-ORG",
19
+ "7": "I-PER",
20
+ "8": "O"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 1536,
24
+ "label2id": {
25
+ "B-LOC": 0,
26
+ "B-MISC": 1,
27
+ "B-ORG": 2,
28
+ "B-PER": 3,
29
+ "I-LOC": 4,
30
+ "I-MISC": 5,
31
+ "I-ORG": 6,
32
+ "I-PER": 7,
33
+ "O": 8
34
+ },
35
+ "layer_norm_eps": 1e-12,
36
+ "max_position_embeddings": 512,
37
+ "model_type": "bert",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "transformers_version": "4.56.2",
43
+ "type_vocab_size": 2,
44
+ "use_cache": true,
45
+ "vocab_size": 30522
46
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13abcf1e790ce45ac39c89e51aab3c95ca75d7050ff5659117844b6e9c8fdaae
3
+ size 132885604
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:789174d514e9812d0f16b795ba5daa8e91e9a8a61175a84f9af5abf64d7409cc
3
+ size 5841
vocab.txt ADDED
The diff for this file is too large to render. See raw diff