Commit
•
6460f9d
1
Parent(s):
278bfbf
End of training
Browse files- README.md +140 -0
- added_tokens.json +3 -0
- bpe.codes +0 -0
- config.json +37 -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 +1,140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: vinai/phobert-base-v2
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
- f1
|
8 |
+
model-index:
|
9 |
+
- name: PhoBert_Lexical_Datasnet51KBoDuoiWithNewLexical
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/phunganhsang123/huggingface/runs/ueje0ytn)
|
17 |
+
# PhoBert_Lexical_Datasnet51KBoDuoiWithNewLexical
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.9059
|
22 |
+
- Accuracy: 0.848
|
23 |
+
- F1: 0.8469
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 2e-05
|
43 |
+
- train_batch_size: 64
|
44 |
+
- eval_batch_size: 64
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 20
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
53 |
+
|:-------------:|:-------:|:-----:|:---------------:|:--------:|:------:|
|
54 |
+
| No log | 0.2506 | 200 | 0.6421 | 0.727 | 0.7274 |
|
55 |
+
| No log | 0.5013 | 400 | 0.5851 | 0.745 | 0.7340 |
|
56 |
+
| No log | 0.7519 | 600 | 0.5522 | 0.758 | 0.7561 |
|
57 |
+
| 0.3486 | 1.0025 | 800 | 0.5461 | 0.779 | 0.7693 |
|
58 |
+
| 0.3486 | 1.2531 | 1000 | 0.5009 | 0.786 | 0.7796 |
|
59 |
+
| 0.3486 | 1.5038 | 1200 | 0.5538 | 0.77 | 0.7681 |
|
60 |
+
| 0.3486 | 1.7544 | 1400 | 0.5067 | 0.777 | 0.7676 |
|
61 |
+
| 0.2582 | 2.0050 | 1600 | 0.5031 | 0.792 | 0.7842 |
|
62 |
+
| 0.2582 | 2.2556 | 1800 | 0.5232 | 0.786 | 0.7811 |
|
63 |
+
| 0.2582 | 2.5063 | 2000 | 0.5484 | 0.785 | 0.7827 |
|
64 |
+
| 0.2582 | 2.7569 | 2200 | 0.5155 | 0.798 | 0.7950 |
|
65 |
+
| 0.2134 | 3.0075 | 2400 | 0.5280 | 0.787 | 0.7847 |
|
66 |
+
| 0.2134 | 3.2581 | 2600 | 0.5263 | 0.793 | 0.7860 |
|
67 |
+
| 0.2134 | 3.5088 | 2800 | 0.5273 | 0.794 | 0.7930 |
|
68 |
+
| 0.2134 | 3.7594 | 3000 | 0.5354 | 0.792 | 0.7871 |
|
69 |
+
| 0.1799 | 4.0100 | 3200 | 0.5071 | 0.804 | 0.7982 |
|
70 |
+
| 0.1799 | 4.2607 | 3400 | 0.5655 | 0.802 | 0.7975 |
|
71 |
+
| 0.1799 | 4.5113 | 3600 | 0.5497 | 0.809 | 0.8034 |
|
72 |
+
| 0.1799 | 4.7619 | 3800 | 0.5645 | 0.808 | 0.8020 |
|
73 |
+
| 0.1493 | 5.0125 | 4000 | 0.5565 | 0.807 | 0.8003 |
|
74 |
+
| 0.1493 | 5.2632 | 4200 | 0.5861 | 0.813 | 0.8091 |
|
75 |
+
| 0.1493 | 5.5138 | 4400 | 0.6189 | 0.807 | 0.8055 |
|
76 |
+
| 0.1493 | 5.7644 | 4600 | 0.5003 | 0.819 | 0.8151 |
|
77 |
+
| 0.1278 | 6.0150 | 4800 | 0.5903 | 0.81 | 0.8080 |
|
78 |
+
| 0.1278 | 6.2657 | 5000 | 0.6112 | 0.81 | 0.8090 |
|
79 |
+
| 0.1278 | 6.5163 | 5200 | 0.5987 | 0.818 | 0.8150 |
|
80 |
+
| 0.1278 | 6.7669 | 5400 | 0.6466 | 0.802 | 0.8006 |
|
81 |
+
| 0.1091 | 7.0175 | 5600 | 0.6515 | 0.818 | 0.8172 |
|
82 |
+
| 0.1091 | 7.2682 | 5800 | 0.6541 | 0.819 | 0.8174 |
|
83 |
+
| 0.1091 | 7.5188 | 6000 | 0.6148 | 0.828 | 0.8246 |
|
84 |
+
| 0.1091 | 7.7694 | 6200 | 0.6246 | 0.827 | 0.8262 |
|
85 |
+
| 0.0917 | 8.0201 | 6400 | 0.6751 | 0.812 | 0.812 |
|
86 |
+
| 0.0917 | 8.2707 | 6600 | 0.6371 | 0.829 | 0.8281 |
|
87 |
+
| 0.0917 | 8.5213 | 6800 | 0.6979 | 0.823 | 0.8212 |
|
88 |
+
| 0.0917 | 8.7719 | 7000 | 0.6792 | 0.827 | 0.8241 |
|
89 |
+
| 0.0764 | 9.0226 | 7200 | 0.6833 | 0.835 | 0.8324 |
|
90 |
+
| 0.0764 | 9.2732 | 7400 | 0.6810 | 0.84 | 0.8383 |
|
91 |
+
| 0.0764 | 9.5238 | 7600 | 0.6799 | 0.826 | 0.8233 |
|
92 |
+
| 0.0764 | 9.7744 | 7800 | 0.6988 | 0.823 | 0.8211 |
|
93 |
+
| 0.0676 | 10.0251 | 8000 | 0.7213 | 0.832 | 0.8299 |
|
94 |
+
| 0.0676 | 10.2757 | 8200 | 0.7325 | 0.83 | 0.8288 |
|
95 |
+
| 0.0676 | 10.5263 | 8400 | 0.7338 | 0.831 | 0.8293 |
|
96 |
+
| 0.0676 | 10.7769 | 8600 | 0.7210 | 0.827 | 0.8262 |
|
97 |
+
| 0.0585 | 11.0276 | 8800 | 0.7874 | 0.829 | 0.8282 |
|
98 |
+
| 0.0585 | 11.2782 | 9000 | 0.7764 | 0.836 | 0.8347 |
|
99 |
+
| 0.0585 | 11.5288 | 9200 | 0.8112 | 0.835 | 0.8342 |
|
100 |
+
| 0.0585 | 11.7794 | 9400 | 0.7485 | 0.832 | 0.8307 |
|
101 |
+
| 0.0536 | 12.0301 | 9600 | 0.7640 | 0.835 | 0.8339 |
|
102 |
+
| 0.0536 | 12.2807 | 9800 | 0.7865 | 0.837 | 0.8344 |
|
103 |
+
| 0.0536 | 12.5313 | 10000 | 0.7579 | 0.836 | 0.8350 |
|
104 |
+
| 0.0536 | 12.7820 | 10200 | 0.7846 | 0.837 | 0.8357 |
|
105 |
+
| 0.0449 | 13.0326 | 10400 | 0.7385 | 0.84 | 0.8384 |
|
106 |
+
| 0.0449 | 13.2832 | 10600 | 0.8481 | 0.838 | 0.8372 |
|
107 |
+
| 0.0449 | 13.5338 | 10800 | 0.8422 | 0.838 | 0.8368 |
|
108 |
+
| 0.0449 | 13.7845 | 11000 | 0.7742 | 0.846 | 0.8445 |
|
109 |
+
| 0.0387 | 14.0351 | 11200 | 0.8304 | 0.842 | 0.8406 |
|
110 |
+
| 0.0387 | 14.2857 | 11400 | 0.7922 | 0.84 | 0.8386 |
|
111 |
+
| 0.0387 | 14.5363 | 11600 | 0.8284 | 0.843 | 0.8415 |
|
112 |
+
| 0.0387 | 14.7870 | 11800 | 0.8289 | 0.846 | 0.8449 |
|
113 |
+
| 0.0345 | 15.0376 | 12000 | 0.8012 | 0.849 | 0.8475 |
|
114 |
+
| 0.0345 | 15.2882 | 12200 | 0.8320 | 0.85 | 0.8489 |
|
115 |
+
| 0.0345 | 15.5388 | 12400 | 0.8118 | 0.853 | 0.8516 |
|
116 |
+
| 0.0345 | 15.7895 | 12600 | 0.8084 | 0.849 | 0.8480 |
|
117 |
+
| 0.0292 | 16.0401 | 12800 | 0.8427 | 0.841 | 0.8399 |
|
118 |
+
| 0.0292 | 16.2907 | 13000 | 0.8499 | 0.848 | 0.8469 |
|
119 |
+
| 0.0292 | 16.5414 | 13200 | 0.8477 | 0.848 | 0.8470 |
|
120 |
+
| 0.0292 | 16.7920 | 13400 | 0.8211 | 0.846 | 0.8441 |
|
121 |
+
| 0.0263 | 17.0426 | 13600 | 0.8418 | 0.848 | 0.8466 |
|
122 |
+
| 0.0263 | 17.2932 | 13800 | 0.8637 | 0.842 | 0.8408 |
|
123 |
+
| 0.0263 | 17.5439 | 14000 | 0.8693 | 0.845 | 0.8440 |
|
124 |
+
| 0.0263 | 17.7945 | 14200 | 0.8415 | 0.85 | 0.8483 |
|
125 |
+
| 0.0243 | 18.0451 | 14400 | 0.8735 | 0.848 | 0.8470 |
|
126 |
+
| 0.0243 | 18.2957 | 14600 | 0.8827 | 0.847 | 0.8460 |
|
127 |
+
| 0.0243 | 18.5464 | 14800 | 0.8729 | 0.85 | 0.8489 |
|
128 |
+
| 0.0243 | 18.7970 | 15000 | 0.8964 | 0.848 | 0.8469 |
|
129 |
+
| 0.0207 | 19.0476 | 15200 | 0.8939 | 0.846 | 0.8449 |
|
130 |
+
| 0.0207 | 19.2982 | 15400 | 0.9019 | 0.847 | 0.8460 |
|
131 |
+
| 0.0207 | 19.5489 | 15600 | 0.8948 | 0.848 | 0.8469 |
|
132 |
+
| 0.0207 | 19.7995 | 15800 | 0.9059 | 0.848 | 0.8469 |
|
133 |
+
|
134 |
+
|
135 |
+
### Framework versions
|
136 |
+
|
137 |
+
- Transformers 4.43.1
|
138 |
+
- Pytorch 2.1.2
|
139 |
+
- Datasets 2.20.0
|
140 |
+
- 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 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vinai/phobert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"PhoBertLexical"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "B\u00ecnh th\u01b0\u1eddng",
|
15 |
+
"1": "T\u00ednh nhi\u1ec7m th\u1ea5p"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"B\u00ecnh th\u01b0\u1eddng": 0,
|
21 |
+
"T\u00ednh nhi\u1ec7m th\u1ea5p": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-05,
|
24 |
+
"max_position_embeddings": 258,
|
25 |
+
"model_type": "roberta",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_classes": 2,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"pad_token_id": 1,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"tokenizer_class": "PhobertTokenizer",
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.43.1",
|
34 |
+
"type_vocab_size": 1,
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 64001
|
37 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b7199d198e19931fbbf64d60d1cc53336020dabfd609c5d46f8f3efeef053fe
|
3 |
+
size 538468008
|
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 sha256:5ec51ffbc41c5e7f7410d5815dbd93703ee6180fcbc4c38c8403dae50dff7358
|
3 |
+
size 5176
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|