Hugging Face's logo

amirhamza11
/
Banglabert_nwp_finetuning_test1

Fill-Mask
Transformers
PyTorch
TensorBoard
electra
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
amirhamza11 commited on
Commit
3f136f7
•
1 Parent(s): c36ae03

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +105 -0
README.md ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: csebuetnlp/banglabert
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: Banglabert_nwp_finetuning_test1
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
+ # Banglabert_nwp_finetuning_test1
14
+
15
+ This model is a fine-tuned version of [csebuetnlp/banglabert](https://huggingface.co/csebuetnlp/banglabert) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 4.1145
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: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 50
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:-----:|:---------------:|
48
+ | No log | 1.0 | 403 | 7.4663 |
49
+ | 7.9712 | 2.0 | 806 | 6.5917 |
50
+ | 6.8071 | 3.0 | 1209 | 6.0256 |
51
+ | 6.0374 | 4.0 | 1612 | 5.6658 |
52
+ | 5.6471 | 5.0 | 2015 | 5.4585 |
53
+ | 5.6471 | 6.0 | 2418 | 5.2872 |
54
+ | 5.3912 | 7.0 | 2821 | 5.2068 |
55
+ | 5.1951 | 8.0 | 3224 | 4.9943 |
56
+ | 4.9863 | 9.0 | 3627 | 4.9361 |
57
+ | 4.8637 | 10.0 | 4030 | 5.0372 |
58
+ | 4.8637 | 11.0 | 4433 | 4.8487 |
59
+ | 4.7391 | 12.0 | 4836 | 4.7716 |
60
+ | 4.6406 | 13.0 | 5239 | 4.6486 |
61
+ | 4.5531 | 14.0 | 5642 | 4.6206 |
62
+ | 4.438 | 15.0 | 6045 | 4.5695 |
63
+ | 4.438 | 16.0 | 6448 | 4.5419 |
64
+ | 4.349 | 17.0 | 6851 | 4.5311 |
65
+ | 4.2898 | 18.0 | 7254 | 4.5808 |
66
+ | 4.215 | 19.0 | 7657 | 4.4420 |
67
+ | 4.1477 | 20.0 | 8060 | 4.4000 |
68
+ | 4.1477 | 21.0 | 8463 | 4.4062 |
69
+ | 4.0975 | 22.0 | 8866 | 4.4725 |
70
+ | 4.0181 | 23.0 | 9269 | 4.3565 |
71
+ | 3.9865 | 24.0 | 9672 | 4.2207 |
72
+ | 3.9196 | 25.0 | 10075 | 4.2460 |
73
+ | 3.9196 | 26.0 | 10478 | 4.2876 |
74
+ | 3.9069 | 27.0 | 10881 | 4.2645 |
75
+ | 3.8349 | 28.0 | 11284 | 4.2974 |
76
+ | 3.7824 | 29.0 | 11687 | 4.3730 |
77
+ | 3.736 | 30.0 | 12090 | 4.2604 |
78
+ | 3.736 | 31.0 | 12493 | 4.3195 |
79
+ | 3.7202 | 32.0 | 12896 | 4.1342 |
80
+ | 3.6897 | 33.0 | 13299 | 4.3159 |
81
+ | 3.6388 | 34.0 | 13702 | 4.1019 |
82
+ | 3.6448 | 35.0 | 14105 | 4.1839 |
83
+ | 3.6099 | 36.0 | 14508 | 4.1900 |
84
+ | 3.6099 | 37.0 | 14911 | 4.0979 |
85
+ | 3.5708 | 38.0 | 15314 | 4.1737 |
86
+ | 3.5502 | 39.0 | 15717 | 4.1915 |
87
+ | 3.5159 | 40.0 | 16120 | 4.1158 |
88
+ | 3.5086 | 41.0 | 16523 | 4.0181 |
89
+ | 3.5086 | 42.0 | 16926 | 4.1328 |
90
+ | 3.4808 | 43.0 | 17329 | 4.0247 |
91
+ | 3.4733 | 44.0 | 17732 | 4.1688 |
92
+ | 3.4681 | 45.0 | 18135 | 4.1177 |
93
+ | 3.4689 | 46.0 | 18538 | 4.1093 |
94
+ | 3.4689 | 47.0 | 18941 | 4.1418 |
95
+ | 3.434 | 48.0 | 19344 | 4.0152 |
96
+ | 3.4513 | 49.0 | 19747 | 4.1412 |
97
+ | 3.4158 | 50.0 | 20150 | 4.1036 |
98
+
99
+
100
+ ### Framework versions
101
+
102
+ - Transformers 4.31.0
103
+ - Pytorch 2.0.1+cu118
104
+ - Datasets 2.14.4
105
+ - Tokenizers 0.13.3