End of training
Browse files- README.md +128 -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 +1,128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-base-v2-70k-khduoi
|
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-base-v2-70k-khduoi
|
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: 0.6366
|
21 |
+
- Accuracy: 0.9152
|
22 |
+
- F1: 0.9155
|
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: 32
|
43 |
+
- eval_batch_size: 32
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 20
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
52 |
+
|:-------------:|:-------:|:-----:|:---------------:|:--------:|:------:|
|
53 |
+
| No log | 0.2909 | 500 | 0.2524 | 0.8975 | 0.8969 |
|
54 |
+
| No log | 0.5817 | 1000 | 0.2447 | 0.9009 | 0.8999 |
|
55 |
+
| No log | 0.8726 | 1500 | 0.2319 | 0.9018 | 0.9015 |
|
56 |
+
| 0.263 | 1.1635 | 2000 | 0.2539 | 0.9060 | 0.9063 |
|
57 |
+
| 0.263 | 1.4543 | 2500 | 0.2433 | 0.9017 | 0.9029 |
|
58 |
+
| 0.263 | 1.7452 | 3000 | 0.2358 | 0.9100 | 0.9099 |
|
59 |
+
| 0.2084 | 2.0361 | 3500 | 0.2755 | 0.9044 | 0.9059 |
|
60 |
+
| 0.2084 | 2.3269 | 4000 | 0.2547 | 0.9102 | 0.9100 |
|
61 |
+
| 0.2084 | 2.6178 | 4500 | 0.2223 | 0.9109 | 0.9125 |
|
62 |
+
| 0.2084 | 2.9087 | 5000 | 0.2189 | 0.9150 | 0.9150 |
|
63 |
+
| 0.1729 | 3.1995 | 5500 | 0.2825 | 0.9101 | 0.9112 |
|
64 |
+
| 0.1729 | 3.4904 | 6000 | 0.2663 | 0.9110 | 0.9121 |
|
65 |
+
| 0.1729 | 3.7813 | 6500 | 0.2367 | 0.9157 | 0.9165 |
|
66 |
+
| 0.1448 | 4.0721 | 7000 | 0.2891 | 0.9118 | 0.9121 |
|
67 |
+
| 0.1448 | 4.3630 | 7500 | 0.3180 | 0.9042 | 0.9060 |
|
68 |
+
| 0.1448 | 4.6539 | 8000 | 0.2441 | 0.9117 | 0.9126 |
|
69 |
+
| 0.1448 | 4.9447 | 8500 | 0.2638 | 0.9142 | 0.9145 |
|
70 |
+
| 0.1234 | 5.2356 | 9000 | 0.3499 | 0.9130 | 0.9141 |
|
71 |
+
| 0.1234 | 5.5265 | 9500 | 0.3086 | 0.9123 | 0.9135 |
|
72 |
+
| 0.1234 | 5.8173 | 10000 | 0.3203 | 0.9141 | 0.9140 |
|
73 |
+
| 0.1033 | 6.1082 | 10500 | 0.3234 | 0.9170 | 0.9173 |
|
74 |
+
| 0.1033 | 6.3991 | 11000 | 0.3367 | 0.9095 | 0.9105 |
|
75 |
+
| 0.1033 | 6.6899 | 11500 | 0.3402 | 0.9157 | 0.9159 |
|
76 |
+
| 0.1033 | 6.9808 | 12000 | 0.3843 | 0.9107 | 0.9111 |
|
77 |
+
| 0.0904 | 7.2717 | 12500 | 0.3559 | 0.9182 | 0.9182 |
|
78 |
+
| 0.0904 | 7.5625 | 13000 | 0.3646 | 0.9079 | 0.9096 |
|
79 |
+
| 0.0904 | 7.8534 | 13500 | 0.3392 | 0.9130 | 0.9137 |
|
80 |
+
| 0.0785 | 8.1443 | 14000 | 0.4064 | 0.9155 | 0.9164 |
|
81 |
+
| 0.0785 | 8.4351 | 14500 | 0.4013 | 0.9126 | 0.9135 |
|
82 |
+
| 0.0785 | 8.7260 | 15000 | 0.4351 | 0.9124 | 0.9135 |
|
83 |
+
| 0.0701 | 9.0169 | 15500 | 0.4190 | 0.9158 | 0.9161 |
|
84 |
+
| 0.0701 | 9.3077 | 16000 | 0.4567 | 0.9116 | 0.9126 |
|
85 |
+
| 0.0701 | 9.5986 | 16500 | 0.4230 | 0.9147 | 0.9147 |
|
86 |
+
| 0.0701 | 9.8895 | 17000 | 0.3956 | 0.9148 | 0.9150 |
|
87 |
+
| 0.0599 | 10.1803 | 17500 | 0.4854 | 0.9133 | 0.9135 |
|
88 |
+
| 0.0599 | 10.4712 | 18000 | 0.4958 | 0.9156 | 0.9158 |
|
89 |
+
| 0.0599 | 10.7621 | 18500 | 0.4552 | 0.9148 | 0.9146 |
|
90 |
+
| 0.0536 | 11.0529 | 19000 | 0.4678 | 0.9160 | 0.9163 |
|
91 |
+
| 0.0536 | 11.3438 | 19500 | 0.4802 | 0.9142 | 0.9135 |
|
92 |
+
| 0.0536 | 11.6347 | 20000 | 0.5360 | 0.9130 | 0.9133 |
|
93 |
+
| 0.0536 | 11.9255 | 20500 | 0.5305 | 0.9133 | 0.9137 |
|
94 |
+
| 0.0464 | 12.2164 | 21000 | 0.5413 | 0.9115 | 0.9122 |
|
95 |
+
| 0.0464 | 12.5073 | 21500 | 0.4867 | 0.9150 | 0.9155 |
|
96 |
+
| 0.0464 | 12.7981 | 22000 | 0.5100 | 0.9147 | 0.9153 |
|
97 |
+
| 0.0446 | 13.0890 | 22500 | 0.5750 | 0.9161 | 0.9157 |
|
98 |
+
| 0.0446 | 13.3799 | 23000 | 0.5742 | 0.9174 | 0.9172 |
|
99 |
+
| 0.0446 | 13.6707 | 23500 | 0.5790 | 0.9142 | 0.9146 |
|
100 |
+
| 0.0446 | 13.9616 | 24000 | 0.5476 | 0.9151 | 0.9150 |
|
101 |
+
| 0.0374 | 14.2525 | 24500 | 0.5621 | 0.9160 | 0.9163 |
|
102 |
+
| 0.0374 | 14.5433 | 25000 | 0.5633 | 0.9140 | 0.9146 |
|
103 |
+
| 0.0374 | 14.8342 | 25500 | 0.5496 | 0.9148 | 0.9152 |
|
104 |
+
| 0.0341 | 15.1251 | 26000 | 0.5869 | 0.9138 | 0.9142 |
|
105 |
+
| 0.0341 | 15.4159 | 26500 | 0.5901 | 0.9142 | 0.9141 |
|
106 |
+
| 0.0341 | 15.7068 | 27000 | 0.5548 | 0.9154 | 0.9158 |
|
107 |
+
| 0.0303 | 15.9977 | 27500 | 0.5832 | 0.9141 | 0.9136 |
|
108 |
+
| 0.0303 | 16.2885 | 28000 | 0.6070 | 0.9148 | 0.9157 |
|
109 |
+
| 0.0303 | 16.5794 | 28500 | 0.6208 | 0.9159 | 0.9162 |
|
110 |
+
| 0.0303 | 16.8703 | 29000 | 0.6134 | 0.9137 | 0.9143 |
|
111 |
+
| 0.0273 | 17.1611 | 29500 | 0.6021 | 0.9166 | 0.9168 |
|
112 |
+
| 0.0273 | 17.4520 | 30000 | 0.6063 | 0.9150 | 0.9153 |
|
113 |
+
| 0.0273 | 17.7429 | 30500 | 0.5942 | 0.9135 | 0.9142 |
|
114 |
+
| 0.0254 | 18.0337 | 31000 | 0.6073 | 0.9150 | 0.9155 |
|
115 |
+
| 0.0254 | 18.3246 | 31500 | 0.6304 | 0.9165 | 0.9167 |
|
116 |
+
| 0.0254 | 18.6155 | 32000 | 0.6121 | 0.9155 | 0.9157 |
|
117 |
+
| 0.0254 | 18.9063 | 32500 | 0.6087 | 0.9153 | 0.9156 |
|
118 |
+
| 0.0221 | 19.1972 | 33000 | 0.6234 | 0.9147 | 0.9151 |
|
119 |
+
| 0.0221 | 19.4881 | 33500 | 0.6312 | 0.9145 | 0.9149 |
|
120 |
+
| 0.0221 | 19.7789 | 34000 | 0.6366 | 0.9152 | 0.9155 |
|
121 |
+
|
122 |
+
|
123 |
+
### Framework versions
|
124 |
+
|
125 |
+
- Transformers 4.41.2
|
126 |
+
- Pytorch 2.3.0+cu121
|
127 |
+
- Datasets 2.20.0
|
128 |
+
- 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:b3a8e89bf4edd05f7418a98b045c2fd48b47a6a4af06e5cb55526bcd393444a6
|
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:d274cf64807cf71d42977750484b025b717d11fcb9e9d21b9453dd6ae797aedb
|
3 |
+
size 5048
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|