almaghrabima commited on
Commit
1aa8bd6
·
1 Parent(s): 5543a98

End of training

Browse files
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: Gladiator/microsoft-deberta-v3-large_ner_conll2003
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: ner_tag_model
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # ner_tag_model
20
+
21
+ This model is a fine-tuned version of [Gladiator/microsoft-deberta-v3-large_ner_conll2003](https://huggingface.co/Gladiator/microsoft-deberta-v3-large_ner_conll2003) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.1712
24
+ - Precision: 0.8569
25
+ - Recall: 0.8551
26
+ - F1: 0.8560
27
+ - Accuracy: 0.9151
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 2e-05
47
+ - train_batch_size: 16
48
+ - eval_batch_size: 16
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 10
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 0.2322 | 1.0 | 2495 | 0.1925 | 0.7990 | 0.7924 | 0.7957 | 0.8969 |
59
+ | 0.1674 | 2.0 | 4990 | 0.1488 | 0.8218 | 0.8316 | 0.8267 | 0.9116 |
60
+ | 0.1381 | 3.0 | 7485 | 0.1438 | 0.8204 | 0.8350 | 0.8276 | 0.9130 |
61
+ | 0.1284 | 4.0 | 9980 | 0.1381 | 0.8419 | 0.8405 | 0.8412 | 0.9148 |
62
+ | 0.1198 | 5.0 | 12475 | 0.1400 | 0.8280 | 0.8410 | 0.8345 | 0.9148 |
63
+ | 0.1155 | 6.0 | 14970 | 0.1395 | 0.8379 | 0.8467 | 0.8423 | 0.9154 |
64
+ | 0.1125 | 7.0 | 17465 | 0.1496 | 0.8438 | 0.8487 | 0.8462 | 0.9151 |
65
+ | 0.1068 | 8.0 | 19960 | 0.1510 | 0.8518 | 0.8529 | 0.8523 | 0.9156 |
66
+ | 0.1002 | 9.0 | 22455 | 0.1616 | 0.8536 | 0.8539 | 0.8537 | 0.9150 |
67
+ | 0.0964 | 10.0 | 24950 | 0.1712 | 0.8569 | 0.8551 | 0.8560 | 0.9151 |
68
+
69
+
70
+ ### Framework versions
71
+
72
+ - Transformers 4.33.1
73
+ - Pytorch 1.13.1+cu116
74
+ - Datasets 2.14.5
75
+ - Tokenizers 0.13.3
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Gladiator/microsoft-deberta-v3-large_ner_conll2003",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 1024,
10
+ "id2label": {
11
+ "0": "ProductNameEn",
12
+ "1": "TradeMarkEn",
13
+ "2": "Country",
14
+ "3": "HSCode",
15
+ "4": "HSCodeEn",
16
+ "5": "ManufacturerEn",
17
+ "6": "ModelNo"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4096,
21
+ "label2id": {
22
+ "Country": 2,
23
+ "HSCode": 3,
24
+ "HSCodeEn": 4,
25
+ "ManufacturerEn": 5,
26
+ "ModelNo": 6,
27
+ "ProductNameEn": 0,
28
+ "TradeMarkEn": 1
29
+ },
30
+ "layer_norm_eps": 1e-07,
31
+ "max_position_embeddings": 512,
32
+ "max_relative_positions": -1,
33
+ "model_type": "deberta-v2",
34
+ "norm_rel_ebd": "layer_norm",
35
+ "num_attention_heads": 16,
36
+ "num_hidden_layers": 24,
37
+ "pad_token_id": 0,
38
+ "pooler_dropout": 0,
39
+ "pooler_hidden_act": "gelu",
40
+ "pooler_hidden_size": 1024,
41
+ "pos_att_type": [
42
+ "p2c",
43
+ "c2p"
44
+ ],
45
+ "position_biased_input": false,
46
+ "position_buckets": 256,
47
+ "relative_attention": true,
48
+ "share_att_key": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.33.1",
51
+ "type_vocab_size": 0,
52
+ "vocab_size": 128100
53
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c2ef45064e330f9371e29fa251c481f4768f7e7b576c67094e637d20be27f02
3
+ size 1736213293
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": false,
6
+ "eos_token": "[SEP]",
7
+ "mask_token": "[MASK]",
8
+ "max_length": 512,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "sp_model_kwargs": {},
13
+ "split_by_punct": false,
14
+ "stride": 0,
15
+ "tokenizer_class": "DebertaV2Tokenizer",
16
+ "truncation_side": "right",
17
+ "truncation_strategy": "longest_first",
18
+ "unk_token": "[UNK]",
19
+ "vocab_type": "spm"
20
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e975e9bda0829eaeee753ebff776709ebbfd50a07b8ebb4a0b2b8bc73779493
3
+ size 3963