Hugging Face's logo

tiennvcs
/
bert-large-uncased-finetuned-vi-infovqa

Question Answering
Transformers
PyTorch
TensorBoard
bert
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
1
tiennvcs commited on
Commit
05bd8ed
•
1 Parent(s): a3ce48b

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +111 -0
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: bert-large-uncased-finetuned-vi-infovqa
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # bert-large-uncased-finetuned-vi-infovqa
14
+
15
+ This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 7.4878
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 2
39
+ - seed: 250500
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 6
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | No log | 0.11 | 100 | 4.6256 |
49
+ | No log | 0.21 | 200 | 4.4042 |
50
+ | No log | 0.32 | 300 | 5.0021 |
51
+ | No log | 0.43 | 400 | 4.2825 |
52
+ | 4.6758 | 0.53 | 500 | 4.3886 |
53
+ | 4.6758 | 0.64 | 600 | 4.2519 |
54
+ | 4.6758 | 0.75 | 700 | 4.2977 |
55
+ | 4.6758 | 0.85 | 800 | 3.9916 |
56
+ | 4.6758 | 0.96 | 900 | 4.1650 |
57
+ | 4.1715 | 1.07 | 1000 | 4.5001 |
58
+ | 4.1715 | 1.17 | 1100 | 4.0898 |
59
+ | 4.1715 | 1.28 | 1200 | 4.1623 |
60
+ | 4.1715 | 1.39 | 1300 | 4.3271 |
61
+ | 4.1715 | 1.49 | 1400 | 3.9661 |
62
+ | 3.7926 | 1.6 | 1500 | 3.8727 |
63
+ | 3.7926 | 1.71 | 1600 | 3.8934 |
64
+ | 3.7926 | 1.81 | 1700 | 3.7262 |
65
+ | 3.7926 | 1.92 | 1800 | 3.7701 |
66
+ | 3.7926 | 2.03 | 1900 | 3.7653 |
67
+ | 3.5041 | 2.13 | 2000 | 3.9261 |
68
+ | 3.5041 | 2.24 | 2100 | 4.0915 |
69
+ | 3.5041 | 2.35 | 2200 | 4.0348 |
70
+ | 3.5041 | 2.45 | 2300 | 4.0212 |
71
+ | 3.5041 | 2.56 | 2400 | 4.4653 |
72
+ | 2.8475 | 2.67 | 2500 | 4.2959 |
73
+ | 2.8475 | 2.77 | 2600 | 4.1039 |
74
+ | 2.8475 | 2.88 | 2700 | 3.8037 |
75
+ | 2.8475 | 2.99 | 2800 | 3.7552 |
76
+ | 2.8475 | 3.09 | 2900 | 4.2476 |
77
+ | 2.5488 | 3.2 | 3000 | 4.6716 |
78
+ | 2.5488 | 3.3 | 3100 | 4.7058 |
79
+ | 2.5488 | 3.41 | 3200 | 4.6266 |
80
+ | 2.5488 | 3.52 | 3300 | 4.5697 |
81
+ | 2.5488 | 3.62 | 3400 | 5.1017 |
82
+ | 2.0347 | 3.73 | 3500 | 4.6254 |
83
+ | 2.0347 | 3.84 | 3600 | 4.4822 |
84
+ | 2.0347 | 3.94 | 3700 | 4.9413 |
85
+ | 2.0347 | 4.05 | 3800 | 5.3600 |
86
+ | 2.0347 | 4.16 | 3900 | 5.7323 |
87
+ | 1.6566 | 4.26 | 4000 | 5.8822 |
88
+ | 1.6566 | 4.37 | 4100 | 6.0173 |
89
+ | 1.6566 | 4.48 | 4200 | 5.6688 |
90
+ | 1.6566 | 4.58 | 4300 | 6.0617 |
91
+ | 1.6566 | 4.69 | 4400 | 6.6631 |
92
+ | 1.3348 | 4.8 | 4500 | 6.0290 |
93
+ | 1.3348 | 4.9 | 4600 | 6.2455 |
94
+ | 1.3348 | 5.01 | 4700 | 6.0963 |
95
+ | 1.3348 | 5.12 | 4800 | 7.0983 |
96
+ | 1.3348 | 5.22 | 4900 | 7.5483 |
97
+ | 1.0701 | 5.33 | 5000 | 7.7187 |
98
+ | 1.0701 | 5.44 | 5100 | 7.4630 |
99
+ | 1.0701 | 5.54 | 5200 | 7.1394 |
100
+ | 1.0701 | 5.65 | 5300 | 7.0703 |
101
+ | 1.0701 | 5.76 | 5400 | 7.5611 |
102
+ | 0.9414 | 5.86 | 5500 | 7.6038 |
103
+ | 0.9414 | 5.97 | 5600 | 7.4878 |
104
+
105
+
106
+ ### Framework versions
107
+
108
+ - Transformers 4.15.0
109
+ - Pytorch 1.10.0+cu111
110
+ - Datasets 1.17.0
111
+ - Tokenizers 0.10.3