Hugging Face's logo

tmnam20
/
bert-base-multilingual-cased-mnli-1

Text Classification
Transformers
Safetensors
English
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
tmnam20 commited on
Commit
ccb6538
•
1 Parent(s): 10b95f1

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +149 -0
README.md ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ base_model: bert-base-multilingual-cased
6
+ tags:
7
+ - generated_from_trainer
8
+ datasets:
9
+ - tmnam20/VieGLUE
10
+ metrics:
11
+ - accuracy
12
+ model-index:
13
+ - name: bert-base-multilingual-cased-mnli-1
14
+ results:
15
+ - task:
16
+ name: Text Classification
17
+ type: text-classification
18
+ dataset:
19
+ name: tmnam20/VieGLUE/MNLI
20
+ type: tmnam20/VieGLUE
21
+ config: mnli
22
+ split: validation_matched
23
+ args: mnli
24
+ metrics:
25
+ - name: Accuracy
26
+ type: accuracy
27
+ value: 0.8031936533767291
28
+ ---
29
+
30
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
+ should probably proofread and complete it, then remove this comment. -->
32
+
33
+ # bert-base-multilingual-cased-mnli-1
34
+
35
+ This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the tmnam20/VieGLUE/MNLI dataset.
36
+ It achieves the following results on the evaluation set:
37
+ - Loss: 0.5349
38
+ - Accuracy: 0.8032
39
+
40
+ ## Model description
41
+
42
+ More information needed
43
+
44
+ ## Intended uses & limitations
45
+
46
+ More information needed
47
+
48
+ ## Training and evaluation data
49
+
50
+ More information needed
51
+
52
+ ## Training procedure
53
+
54
+ ### Training hyperparameters
55
+
56
+ The following hyperparameters were used during training:
57
+ - learning_rate: 2e-05
58
+ - train_batch_size: 32
59
+ - eval_batch_size: 16
60
+ - seed: 1
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - num_epochs: 3.0
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
69
+ | 0.8082 | 0.04 | 500 | 0.7958 | 0.6485 |
70
+ | 0.7259 | 0.08 | 1000 | 0.7455 | 0.6895 |
71
+ | 0.7018 | 0.12 | 1500 | 0.6970 | 0.7118 |
72
+ | 0.7026 | 0.16 | 2000 | 0.6827 | 0.7127 |
73
+ | 0.6696 | 0.2 | 2500 | 0.6500 | 0.7323 |
74
+ | 0.6744 | 0.24 | 3000 | 0.6345 | 0.7380 |
75
+ | 0.6136 | 0.29 | 3500 | 0.6294 | 0.7402 |
76
+ | 0.632 | 0.33 | 4000 | 0.6269 | 0.7472 |
77
+ | 0.6735 | 0.37 | 4500 | 0.6195 | 0.7489 |
78
+ | 0.6202 | 0.41 | 5000 | 0.6336 | 0.7414 |
79
+ | 0.6495 | 0.45 | 5500 | 0.6125 | 0.7517 |
80
+ | 0.6235 | 0.49 | 6000 | 0.6097 | 0.7515 |
81
+ | 0.5852 | 0.53 | 6500 | 0.6068 | 0.7581 |
82
+ | 0.6395 | 0.57 | 7000 | 0.6039 | 0.7493 |
83
+ | 0.6009 | 0.61 | 7500 | 0.5878 | 0.7553 |
84
+ | 0.6059 | 0.65 | 8000 | 0.5876 | 0.7638 |
85
+ | 0.6019 | 0.69 | 8500 | 0.5829 | 0.7651 |
86
+ | 0.5989 | 0.73 | 9000 | 0.5922 | 0.7612 |
87
+ | 0.6195 | 0.77 | 9500 | 0.5868 | 0.7615 |
88
+ | 0.6028 | 0.81 | 10000 | 0.5724 | 0.7709 |
89
+ | 0.5741 | 0.86 | 10500 | 0.5670 | 0.7717 |
90
+ | 0.582 | 0.9 | 11000 | 0.5702 | 0.7732 |
91
+ | 0.5706 | 0.94 | 11500 | 0.5597 | 0.7755 |
92
+ | 0.5676 | 0.98 | 12000 | 0.5655 | 0.7735 |
93
+ | 0.5235 | 1.02 | 12500 | 0.5849 | 0.7662 |
94
+ | 0.521 | 1.06 | 13000 | 0.5646 | 0.7788 |
95
+ | 0.5122 | 1.1 | 13500 | 0.5717 | 0.7738 |
96
+ | 0.5102 | 1.14 | 14000 | 0.5667 | 0.7765 |
97
+ | 0.5152 | 1.18 | 14500 | 0.5598 | 0.7780 |
98
+ | 0.4904 | 1.22 | 15000 | 0.5693 | 0.7746 |
99
+ | 0.507 | 1.26 | 15500 | 0.5584 | 0.7804 |
100
+ | 0.5163 | 1.3 | 16000 | 0.5570 | 0.7787 |
101
+ | 0.4921 | 1.34 | 16500 | 0.5727 | 0.7798 |
102
+ | 0.5249 | 1.39 | 17000 | 0.5653 | 0.7789 |
103
+ | 0.4994 | 1.43 | 17500 | 0.5726 | 0.7783 |
104
+ | 0.5335 | 1.47 | 18000 | 0.5547 | 0.7848 |
105
+ | 0.543 | 1.51 | 18500 | 0.5541 | 0.7785 |
106
+ | 0.5138 | 1.55 | 19000 | 0.5569 | 0.7842 |
107
+ | 0.4626 | 1.59 | 19500 | 0.5625 | 0.7860 |
108
+ | 0.4828 | 1.63 | 20000 | 0.5434 | 0.7858 |
109
+ | 0.5121 | 1.67 | 20500 | 0.5495 | 0.7806 |
110
+ | 0.5012 | 1.71 | 21000 | 0.5318 | 0.7900 |
111
+ | 0.4609 | 1.75 | 21500 | 0.5485 | 0.7878 |
112
+ | 0.4928 | 1.79 | 22000 | 0.5462 | 0.7868 |
113
+ | 0.4922 | 1.83 | 22500 | 0.5305 | 0.7920 |
114
+ | 0.4913 | 1.87 | 23000 | 0.5396 | 0.7891 |
115
+ | 0.4992 | 1.91 | 23500 | 0.5341 | 0.7952 |
116
+ | 0.4732 | 1.96 | 24000 | 0.5277 | 0.7952 |
117
+ | 0.4925 | 2.0 | 24500 | 0.5339 | 0.7943 |
118
+ | 0.4098 | 2.04 | 25000 | 0.5643 | 0.7911 |
119
+ | 0.4168 | 2.08 | 25500 | 0.5534 | 0.7929 |
120
+ | 0.4099 | 2.12 | 26000 | 0.5674 | 0.7925 |
121
+ | 0.4142 | 2.16 | 26500 | 0.5652 | 0.7918 |
122
+ | 0.398 | 2.2 | 27000 | 0.5875 | 0.7899 |
123
+ | 0.3899 | 2.24 | 27500 | 0.5726 | 0.7975 |
124
+ | 0.403 | 2.28 | 28000 | 0.5596 | 0.7968 |
125
+ | 0.399 | 2.32 | 28500 | 0.5716 | 0.7885 |
126
+ | 0.4176 | 2.36 | 29000 | 0.5570 | 0.7941 |
127
+ | 0.3871 | 2.4 | 29500 | 0.5689 | 0.7926 |
128
+ | 0.4156 | 2.44 | 30000 | 0.5648 | 0.7918 |
129
+ | 0.386 | 2.49 | 30500 | 0.5650 | 0.7931 |
130
+ | 0.4131 | 2.53 | 31000 | 0.5525 | 0.7948 |
131
+ | 0.4202 | 2.57 | 31500 | 0.5585 | 0.7914 |
132
+ | 0.4129 | 2.61 | 32000 | 0.5495 | 0.7963 |
133
+ | 0.4215 | 2.65 | 32500 | 0.5524 | 0.7978 |
134
+ | 0.413 | 2.69 | 33000 | 0.5578 | 0.7954 |
135
+ | 0.4296 | 2.73 | 33500 | 0.5509 | 0.7966 |
136
+ | 0.3602 | 2.77 | 34000 | 0.5581 | 0.7974 |
137
+ | 0.3901 | 2.81 | 34500 | 0.5561 | 0.7985 |
138
+ | 0.4163 | 2.85 | 35000 | 0.5502 | 0.7955 |
139
+ | 0.3787 | 2.89 | 35500 | 0.5573 | 0.7951 |
140
+ | 0.4285 | 2.93 | 36000 | 0.5535 | 0.7958 |
141
+ | 0.3578 | 2.97 | 36500 | 0.5563 | 0.7964 |
142
+
143
+
144
+ ### Framework versions
145
+
146
+ - Transformers 4.35.2
147
+ - Pytorch 2.2.0.dev20231203+cu121
148
+ - Datasets 2.15.0
149
+ - Tokenizers 0.15.0