VampeeHuntee
commited on
Commit
•
3996bfc
1
Parent(s):
afb9ddd
End of training
Browse files- README.md +74 -0
- added_tokens.json +3 -0
- bpe.codes +0 -0
- config.json +75 -0
- model.safetensors +3 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +54 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- vi
|
4 |
+
base_model: vinai/phobert-base
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: phobert-base_baseline_syllables
|
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-base_baseline_syllables
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [vinai/phobert-base](https://huggingface.co/vinai/phobert-base) on the covid19_ner dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.0881
|
20 |
+
- Patient Id: 0.9817
|
21 |
+
- Name: 0.9476
|
22 |
+
- Gender: 0.9385
|
23 |
+
- Age: 0.9684
|
24 |
+
- Job: 0.7463
|
25 |
+
- Location: 0.9427
|
26 |
+
- Organization: 0.8958
|
27 |
+
- Date: 0.9883
|
28 |
+
- Symptom And Disease: 0.8849
|
29 |
+
- Transportation: 0.9943
|
30 |
+
- F1 Macro: 0.9288
|
31 |
+
- F1 Micro: 0.9448
|
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 |
+
| 0.3091 | 1.0 | 629 | 0.1389 | 0.9660 | 0.9316 | 0.8391 | 0.9008 | 0.0 | 0.9237 | 0.8249 | 0.9865 | 0.8435 | 0.9444 | 0.8160 | 0.9115 |
|
63 |
+
| 0.0807 | 2.0 | 1258 | 0.0955 | 0.9809 | 0.9178 | 0.9481 | 0.9707 | 0.4646 | 0.9390 | 0.8704 | 0.9883 | 0.8628 | 0.9831 | 0.8926 | 0.9358 |
|
64 |
+
| 0.0491 | 3.0 | 1887 | 0.0898 | 0.9828 | 0.9418 | 0.9401 | 0.9671 | 0.6824 | 0.9457 | 0.9007 | 0.9856 | 0.8715 | 0.9886 | 0.9206 | 0.9436 |
|
65 |
+
| 0.0375 | 4.0 | 2516 | 0.0886 | 0.9817 | 0.9452 | 0.9354 | 0.9644 | 0.7509 | 0.9406 | 0.8887 | 0.9869 | 0.8805 | 0.9943 | 0.9269 | 0.9425 |
|
66 |
+
| 0.0282 | 5.0 | 3145 | 0.0881 | 0.9817 | 0.9476 | 0.9385 | 0.9684 | 0.7463 | 0.9427 | 0.8958 | 0.9883 | 0.8849 | 0.9943 | 0.9288 | 0.9448 |
|
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-base",
|
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": 768,
|
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": 3072,
|
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": 12,
|
66 |
+
"num_hidden_layers": 12,
|
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 sha256:679bdd237400a6467d18b62425a149b54e26987e0410d685d17dd33ff93c30dc
|
3 |
+
size 537719244
|
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:aece8b4a530ea24869d044413b2ca0f13f693b618d87328c169e7f69b19b39b4
|
3 |
+
size 5176
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|