Hugging Face's logo

NasimB
/
bert-concat

Fill-Mask
Transformers
PyTorch
bert
Generated from Trainer
Model card Files
xet
Community
1
NasimB commited on
Commit
cc50762
·
1 Parent(s): 47050f2

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +113 -0
README.md ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - generator
6
+ model-index:
7
+ - name: bert-concat
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # bert-concat
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on the generator dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 5.9507
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0005
38
+ - train_batch_size: 64
39
+ - eval_batch_size: 64
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: cosine
43
+ - lr_scheduler_warmup_steps: 1000
44
+ - num_epochs: 14
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 7.3397 | 0.25 | 500 | 6.6405 |
52
+ | 6.5835 | 0.51 | 1000 | 6.5183 |
53
+ | 6.4967 | 0.76 | 1500 | 6.4926 |
54
+ | 6.451 | 1.01 | 2000 | 6.4507 |
55
+ | 6.4104 | 1.26 | 2500 | 6.4097 |
56
+ | 6.3868 | 1.52 | 3000 | 6.4019 |
57
+ | 6.3717 | 1.77 | 3500 | 6.3789 |
58
+ | 6.3361 | 2.02 | 4000 | 6.3596 |
59
+ | 6.3099 | 2.28 | 4500 | 6.3345 |
60
+ | 6.2807 | 2.53 | 5000 | 6.3050 |
61
+ | 6.2578 | 2.78 | 5500 | 6.2843 |
62
+ | 6.2356 | 3.03 | 6000 | 6.2735 |
63
+ | 6.2017 | 3.29 | 6500 | 6.2527 |
64
+ | 6.1837 | 3.54 | 7000 | 6.2277 |
65
+ | 6.1682 | 3.79 | 7500 | 6.2102 |
66
+ | 6.1443 | 4.04 | 8000 | 6.1917 |
67
+ | 6.1128 | 4.3 | 8500 | 6.1767 |
68
+ | 6.1034 | 4.55 | 9000 | 6.1678 |
69
+ | 6.0838 | 4.8 | 9500 | 6.1552 |
70
+ | 6.0641 | 5.06 | 10000 | 6.1401 |
71
+ | 6.0417 | 5.31 | 10500 | 6.1350 |
72
+ | 6.0247 | 5.56 | 11000 | 6.1123 |
73
+ | 6.0125 | 5.81 | 11500 | 6.1082 |
74
+ | 6.0028 | 6.07 | 12000 | 6.1022 |
75
+ | 5.9788 | 6.32 | 12500 | 6.0895 |
76
+ | 5.9739 | 6.57 | 13000 | 6.0828 |
77
+ | 5.9545 | 6.83 | 13500 | 6.0687 |
78
+ | 5.9441 | 7.08 | 14000 | 6.0652 |
79
+ | 5.923 | 7.33 | 14500 | 6.0567 |
80
+ | 5.9115 | 7.58 | 15000 | 6.0492 |
81
+ | 5.9106 | 7.84 | 15500 | 6.0466 |
82
+ | 5.8943 | 8.09 | 16000 | 6.0315 |
83
+ | 5.8726 | 8.34 | 16500 | 6.0339 |
84
+ | 5.8665 | 8.59 | 17000 | 6.0243 |
85
+ | 5.8548 | 8.85 | 17500 | 6.0193 |
86
+ | 5.8431 | 9.1 | 18000 | 6.0111 |
87
+ | 5.8218 | 9.35 | 18500 | 6.0053 |
88
+ | 5.8193 | 9.61 | 19000 | 6.0026 |
89
+ | 5.8174 | 9.86 | 19500 | 5.9927 |
90
+ | 5.7954 | 10.11 | 20000 | 5.9873 |
91
+ | 5.7779 | 10.36 | 20500 | 5.9823 |
92
+ | 5.7749 | 10.62 | 21000 | 5.9799 |
93
+ | 5.7739 | 10.87 | 21500 | 5.9784 |
94
+ | 5.7582 | 11.12 | 22000 | 5.9757 |
95
+ | 5.7415 | 11.38 | 22500 | 5.9686 |
96
+ | 5.7467 | 11.63 | 23000 | 5.9650 |
97
+ | 5.7448 | 11.88 | 23500 | 5.9648 |
98
+ | 5.7372 | 12.13 | 24000 | 5.9585 |
99
+ | 5.7207 | 12.39 | 24500 | 5.9596 |
100
+ | 5.7264 | 12.64 | 25000 | 5.9546 |
101
+ | 5.7212 | 12.89 | 25500 | 5.9516 |
102
+ | 5.7142 | 13.14 | 26000 | 5.9553 |
103
+ | 5.7103 | 13.4 | 26500 | 5.9551 |
104
+ | 5.7093 | 13.65 | 27000 | 5.9527 |
105
+ | 5.7183 | 13.9 | 27500 | 5.9507 |
106
+
107
+
108
+ ### Framework versions
109
+
110
+ - Transformers 4.26.1
111
+ - Pytorch 1.11.0+cu113
112
+ - Datasets 2.13.0
113
+ - Tokenizers 0.13.3