VampeeHuntee commited on
Commit
724e1e8
1 Parent(s): 72f87b5

End of training

Browse files
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - vi
4
+ base_model: vinai/phobert-large
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: phobert-large_baseline_words
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # phobert-large_baseline_words
16
+
17
+ This model is a fine-tuned version of [vinai/phobert-large](https://huggingface.co/vinai/phobert-large) on the covid19_ner dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0943
20
+ - Patient Id: 0.9863
21
+ - Name: 0.9542
22
+ - Gender: 0.9664
23
+ - Age: 0.9633
24
+ - Job: 0.8300
25
+ - Location: 0.9521
26
+ - Organization: 0.9188
27
+ - Date: 0.9842
28
+ - Symptom And Disease: 0.8773
29
+ - Transportation: 1.0
30
+ - F1 Macro: 0.9433
31
+ - F1 Micro: 0.9521
32
+
33
+ ## Model description
34
+
35
+ More information needed
36
+
37
+ ## Intended uses & limitations
38
+
39
+ More information needed
40
+
41
+ ## Training and evaluation data
42
+
43
+ More information needed
44
+
45
+ ## Training procedure
46
+
47
+ ### Training hyperparameters
48
+
49
+ The following hyperparameters were used during training:
50
+ - learning_rate: 2e-05
51
+ - train_batch_size: 8
52
+ - eval_batch_size: 8
53
+ - seed: 42
54
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
+ - lr_scheduler_type: linear
56
+ - num_epochs: 5
57
+
58
+ ### Training results
59
+
60
+ | Training Loss | Epoch | Step | Validation Loss | Patient Id | Name | Gender | Age | Job | Location | Organization | Date | Symptom And Disease | Transportation | F1 Macro | F1 Micro |
61
+ |:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:------:|:------:|:------:|:--------:|:------------:|:------:|:-------------------:|:--------------:|:--------:|:--------:|
62
+ | 0.2801 | 1.0 | 629 | 0.0981 | 0.9840 | 0.9455 | 0.9045 | 0.9010 | 0.5837 | 0.9265 | 0.8726 | 0.9812 | 0.8611 | 0.9831 | 0.8943 | 0.9266 |
63
+ | 0.0446 | 2.0 | 1258 | 0.0897 | 0.9863 | 0.9549 | 0.9501 | 0.9722 | 0.7833 | 0.9355 | 0.8907 | 0.9852 | 0.8814 | 0.9721 | 0.9312 | 0.9434 |
64
+ | 0.0283 | 3.0 | 1887 | 0.0809 | 0.9867 | 0.9516 | 0.9551 | 0.9695 | 0.7857 | 0.9487 | 0.9086 | 0.9860 | 0.8845 | 1.0 | 0.9376 | 0.9502 |
65
+ | 0.0198 | 4.0 | 2516 | 0.0905 | 0.9863 | 0.9542 | 0.9647 | 0.9633 | 0.8287 | 0.9483 | 0.9159 | 0.9842 | 0.8897 | 1.0 | 0.9435 | 0.9516 |
66
+ | 0.0134 | 5.0 | 3145 | 0.0943 | 0.9863 | 0.9542 | 0.9664 | 0.9633 | 0.8300 | 0.9521 | 0.9188 | 0.9842 | 0.8773 | 1.0 | 0.9433 | 0.9521 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.41.2
72
+ - Pytorch 2.1.2
73
+ - Datasets 2.19.2
74
+ - Tokenizers 0.19.1
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/phobert-large",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "O",
16
+ "1": "B-PATIENT_ID",
17
+ "2": "I-PATIENT_ID",
18
+ "3": "B-NAME",
19
+ "4": "I-NAME",
20
+ "5": "B-GENDER",
21
+ "6": "I-GENDER",
22
+ "7": "B-AGE",
23
+ "8": "I-AGE",
24
+ "9": "B-JOB",
25
+ "10": "I-JOB",
26
+ "11": "B-LOCATION",
27
+ "12": "I-LOCATION",
28
+ "13": "B-ORGANIZATION",
29
+ "14": "I-ORGANIZATION",
30
+ "15": "B-DATE",
31
+ "16": "I-DATE",
32
+ "17": "B-SYMPTOM_AND_DISEASE",
33
+ "18": "I-SYMPTOM_AND_DISEASE",
34
+ "19": "B-TRANSPORTATION",
35
+ "20": "I-TRANSPORTATION"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 4096,
39
+ "label2id": {
40
+ "B-AGE": 7,
41
+ "B-DATE": 15,
42
+ "B-GENDER": 5,
43
+ "B-JOB": 9,
44
+ "B-LOCATION": 11,
45
+ "B-NAME": 3,
46
+ "B-ORGANIZATION": 13,
47
+ "B-PATIENT_ID": 1,
48
+ "B-SYMPTOM_AND_DISEASE": 17,
49
+ "B-TRANSPORTATION": 19,
50
+ "I-AGE": 8,
51
+ "I-DATE": 16,
52
+ "I-GENDER": 6,
53
+ "I-JOB": 10,
54
+ "I-LOCATION": 12,
55
+ "I-NAME": 4,
56
+ "I-ORGANIZATION": 14,
57
+ "I-PATIENT_ID": 2,
58
+ "I-SYMPTOM_AND_DISEASE": 18,
59
+ "I-TRANSPORTATION": 20,
60
+ "O": 0
61
+ },
62
+ "layer_norm_eps": 1e-05,
63
+ "max_position_embeddings": 258,
64
+ "model_type": "roberta",
65
+ "num_attention_heads": 16,
66
+ "num_hidden_layers": 24,
67
+ "pad_token_id": 1,
68
+ "position_embedding_type": "absolute",
69
+ "tokenizer_class": "PhobertTokenizer",
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.41.2",
72
+ "type_vocab_size": 1,
73
+ "use_cache": true,
74
+ "vocab_size": 64001
75
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ced38e6a22337f29a84378ee5ad0a8f81f1c8dcd0520d0bc1542e1fc611460
3
+ size 1472588812
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "64000": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "PhobertTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7c59ca1f891414705a16760fb9f00758b7f1f44c4faac942b327bd763d6a866
3
+ size 5176
vocab.txt ADDED
The diff for this file is too large to render. See raw diff