Commit
•
6975796
1
Parent(s):
99ebe00
End of training
Browse files- README.md +101 -0
- added_tokens.json +3 -0
- bpe.codes +0 -0
- config.json +29 -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 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_Dataset59KCoDuoi
|
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 |
+
# PhoBert_Dataset59KCoDuoi
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2804
|
21 |
+
- Accuracy: 0.9582
|
22 |
+
- F1: 0.9583
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
+
- train_batch_size: 64
|
43 |
+
- eval_batch_size: 64
|
44 |
+
- seed: 42
|
45 |
+
- gradient_accumulation_steps: 2
|
46 |
+
- total_train_batch_size: 128
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 20
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
54 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
|
55 |
+
| No log | 0.5115 | 200 | 0.1696 | 0.9382 | 0.9389 |
|
56 |
+
| No log | 1.0230 | 400 | 0.1521 | 0.9538 | 0.9539 |
|
57 |
+
| No log | 1.5345 | 600 | 0.1459 | 0.9524 | 0.9528 |
|
58 |
+
| 0.1561 | 2.0460 | 800 | 0.1362 | 0.9557 | 0.9558 |
|
59 |
+
| 0.1561 | 2.5575 | 1000 | 0.1355 | 0.9577 | 0.9581 |
|
60 |
+
| 0.1561 | 3.0691 | 1200 | 0.1271 | 0.9617 | 0.9618 |
|
61 |
+
| 0.1561 | 3.5806 | 1400 | 0.1243 | 0.9620 | 0.9621 |
|
62 |
+
| 0.0913 | 4.0921 | 1600 | 0.1298 | 0.9598 | 0.9601 |
|
63 |
+
| 0.0913 | 4.6036 | 1800 | 0.1216 | 0.9617 | 0.9619 |
|
64 |
+
| 0.0913 | 5.1151 | 2000 | 0.1332 | 0.9607 | 0.9608 |
|
65 |
+
| 0.0913 | 5.6266 | 2200 | 0.1444 | 0.9609 | 0.9610 |
|
66 |
+
| 0.065 | 6.1381 | 2400 | 0.1573 | 0.9608 | 0.9609 |
|
67 |
+
| 0.065 | 6.6496 | 2600 | 0.1477 | 0.9608 | 0.9610 |
|
68 |
+
| 0.065 | 7.1611 | 2800 | 0.1572 | 0.9610 | 0.9611 |
|
69 |
+
| 0.065 | 7.6726 | 3000 | 0.1521 | 0.9605 | 0.9606 |
|
70 |
+
| 0.047 | 8.1841 | 3200 | 0.1523 | 0.9596 | 0.9598 |
|
71 |
+
| 0.047 | 8.6957 | 3400 | 0.1935 | 0.9591 | 0.9591 |
|
72 |
+
| 0.047 | 9.2072 | 3600 | 0.1751 | 0.9576 | 0.9577 |
|
73 |
+
| 0.047 | 9.7187 | 3800 | 0.1979 | 0.9573 | 0.9573 |
|
74 |
+
| 0.0335 | 10.2302 | 4000 | 0.1905 | 0.9592 | 0.9592 |
|
75 |
+
| 0.0335 | 10.7417 | 4200 | 0.1870 | 0.9582 | 0.9582 |
|
76 |
+
| 0.0335 | 11.2532 | 4400 | 0.1940 | 0.9585 | 0.9586 |
|
77 |
+
| 0.0335 | 11.7647 | 4600 | 0.1787 | 0.9549 | 0.9551 |
|
78 |
+
| 0.0268 | 12.2762 | 4800 | 0.2240 | 0.9602 | 0.9602 |
|
79 |
+
| 0.0268 | 12.7877 | 5000 | 0.2161 | 0.9572 | 0.9572 |
|
80 |
+
| 0.0268 | 13.2992 | 5200 | 0.2160 | 0.9542 | 0.9544 |
|
81 |
+
| 0.0268 | 13.8107 | 5400 | 0.2299 | 0.9553 | 0.9555 |
|
82 |
+
| 0.0177 | 14.3223 | 5600 | 0.2551 | 0.9579 | 0.9580 |
|
83 |
+
| 0.0177 | 14.8338 | 5800 | 0.2355 | 0.9576 | 0.9578 |
|
84 |
+
| 0.0177 | 15.3453 | 6000 | 0.2467 | 0.9587 | 0.9589 |
|
85 |
+
| 0.0177 | 15.8568 | 6200 | 0.2507 | 0.9593 | 0.9594 |
|
86 |
+
| 0.0142 | 16.3683 | 6400 | 0.2482 | 0.9580 | 0.9581 |
|
87 |
+
| 0.0142 | 16.8798 | 6600 | 0.2600 | 0.9599 | 0.9600 |
|
88 |
+
| 0.0142 | 17.3913 | 6800 | 0.2682 | 0.9566 | 0.9568 |
|
89 |
+
| 0.0142 | 17.9028 | 7000 | 0.2782 | 0.9573 | 0.9574 |
|
90 |
+
| 0.0094 | 18.4143 | 7200 | 0.2826 | 0.9572 | 0.9573 |
|
91 |
+
| 0.0094 | 18.9258 | 7400 | 0.2783 | 0.9583 | 0.9584 |
|
92 |
+
| 0.0094 | 19.4373 | 7600 | 0.2819 | 0.9583 | 0.9584 |
|
93 |
+
| 0.0094 | 19.9488 | 7800 | 0.2804 | 0.9582 | 0.9583 |
|
94 |
+
|
95 |
+
|
96 |
+
### Framework versions
|
97 |
+
|
98 |
+
- Transformers 4.41.2
|
99 |
+
- Pytorch 2.1.2
|
100 |
+
- Datasets 2.19.2
|
101 |
+
- 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 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vinai/phobert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
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 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 258,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"tokenizer_class": "PhobertTokenizer",
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.41.2",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 64001
|
29 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19796641aaf364a9428bbdc0bcd4fc51b5de5235c5154c197451200df3fd3e39
|
3 |
+
size 540023384
|
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 sha256:23a438b0218534128772c5a388e07902a41e9e190d03dec433fbc45ad78d16b9
|
3 |
+
size 5048
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|