Hugging Face's logo

simecek
/
DNADebertaK6b

Fill-Mask
Transformers
PyTorch
deberta
generated_from_trainer
Inference Endpoints
Model card Files Community
1
simecek commited on
Commit
d045450
•
1 Parent(s): edd31d2

Manual comit

Browse files
Files changed (1) hide show
  1. README.md +115 -0
README.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: DNADebertaK6b
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # DNADebertaK6b
13
+
14
+ This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 1.4362
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 64
37
+ - eval_batch_size: 64
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 15
42
+ - mixed_precision_training: Native AMP
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:-------:|:---------------:|
48
+ | 4.061 | 0.25 | 20000 | 1.7733 |
49
+ | 1.7344 | 0.5 | 40000 | 1.6608 |
50
+ | 1.6651 | 0.75 | 60000 | 1.6319 |
51
+ | 1.6359 | 0.99 | 80000 | 1.6092 |
52
+ | 1.6131 | 1.24 | 100000 | 1.5932 |
53
+ | 1.5959 | 1.49 | 120000 | 1.5753 |
54
+ | 1.5827 | 1.74 | 140000 | 1.5624 |
55
+ | 1.5719 | 1.99 | 160000 | 1.5534 |
56
+ | 1.5617 | 2.24 | 180000 | 1.5454 |
57
+ | 1.5551 | 2.49 | 200000 | 1.5403 |
58
+ | 1.5477 | 2.74 | 220000 | 1.5322 |
59
+ | 1.5414 | 2.98 | 240000 | 1.5262 |
60
+ | 1.5366 | 3.23 | 260000 | 1.5220 |
61
+ | 1.5308 | 3.48 | 280000 | 1.5184 |
62
+ | 1.5274 | 3.73 | 300000 | 1.5121 |
63
+ | 1.5224 | 3.98 | 320000 | 1.5085 |
64
+ | 1.5194 | 4.23 | 340000 | 1.5050 |
65
+ | 1.5164 | 4.48 | 360000 | 1.5027 |
66
+ | 1.5126 | 4.72 | 380000 | 1.4984 |
67
+ | 1.5086 | 4.97 | 400000 | 1.4947 |
68
+ | 1.5048 | 5.22 | 420000 | 1.4914 |
69
+ | 1.5025 | 5.47 | 440000 | 1.4914 |
70
+ | 1.5006 | 5.72 | 460000 | 1.4877 |
71
+ | 1.4982 | 5.97 | 480000 | 1.4840 |
72
+ | 1.4952 | 6.22 | 500000 | 1.4825 |
73
+ | 1.4926 | 6.46 | 520000 | 1.4800 |
74
+ | 1.4907 | 6.71 | 540000 | 1.4778 |
75
+ | 1.4886 | 6.96 | 560000 | 1.4761 |
76
+ | 1.4864 | 7.21 | 580000 | 1.4746 |
77
+ | 1.4854 | 7.46 | 600000 | 1.4730 |
78
+ | 1.484 | 7.71 | 620000 | 1.4709 |
79
+ | 1.4826 | 7.96 | 640000 | 1.4676 |
80
+ | 1.4794 | 8.21 | 660000 | 1.4674 |
81
+ | 1.479 | 8.45 | 680000 | 1.4658 |
82
+ | 1.4777 | 8.7 | 700000 | 1.4661 |
83
+ | 1.4751 | 8.95 | 720000 | 1.4649 |
84
+ | 1.4742 | 9.2 | 740000 | 1.4614 |
85
+ | 1.4728 | 9.45 | 760000 | 1.4602 |
86
+ | 1.472 | 9.7 | 780000 | 1.4603 |
87
+ | 1.4703 | 9.95 | 800000 | 1.4577 |
88
+ | 1.4694 | 10.19 | 820000 | 1.4578 |
89
+ | 1.4662 | 10.44 | 840000 | 1.4557 |
90
+ | 1.4668 | 10.69 | 860000 | 1.4545 |
91
+ | 1.466 | 10.94 | 880000 | 1.4548 |
92
+ | 1.465 | 11.19 | 900000 | 1.4513 |
93
+ | 1.4626 | 11.44 | 920000 | 1.4511 |
94
+ | 1.4616 | 11.69 | 940000 | 1.4509 |
95
+ | 1.4609 | 11.93 | 960000 | 1.4485 |
96
+ | 1.4595 | 12.18 | 980000 | 1.4474 |
97
+ | 1.4588 | 12.43 | 1000000 | 1.4470 |
98
+ | 1.4588 | 12.68 | 1020000 | 1.4452 |
99
+ | 1.4565 | 12.93 | 1040000 | 1.4443 |
100
+ | 1.4556 | 13.18 | 1060000 | 1.4433 |
101
+ | 1.4543 | 13.43 | 1080000 | 1.4409 |
102
+ | 1.453 | 13.68 | 1100000 | 1.4409 |
103
+ | 1.4524 | 13.92 | 1120000 | 1.4397 |
104
+ | 1.4511 | 14.17 | 1140000 | 1.4402 |
105
+ | 1.4501 | 14.42 | 1160000 | 1.4385 |
106
+ | 1.4484 | 14.67 | 1180000 | 1.4373 |
107
+ | 1.449 | 14.92 | 1200000 | 1.4360 |
108
+
109
+
110
+ ### Framework versions
111
+
112
+ - Transformers 4.19.2
113
+ - Pytorch 1.11.0
114
+ - Datasets 2.2.2
115
+ - Tokenizers 0.12.1