Hugging Face's logo

Vlasta
/
DNADebertaSentencepiece30k_continuation_continuation_continuation

Fill-Mask
Transformers
PyTorch
deberta
Generated from Trainer
Inference Endpoints
Model card Files Community
Vlasta commited on
Commit
90ac4cb
•
1 Parent(s): c699a30

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +93 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: DNADebertaSentencepiece30k_continuation_continuation_continuation
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
+ # DNADebertaSentencepiece30k_continuation_continuation_continuation
13
+
14
+ This model is a fine-tuned version of [Vlasta/DNADebertaSentencepiece30k_continuation_continuation](https://huggingface.co/Vlasta/DNADebertaSentencepiece30k_continuation_continuation) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 5.9319
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: 16
37
+ - eval_batch_size: 16
38
+ - seed: 42
39
+ - gradient_accumulation_steps: 4
40
+ - total_train_batch_size: 64
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 15
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:------:|:---------------:|
50
+ | 6.0844 | 0.41 | 5000 | 6.0623 |
51
+ | 6.0962 | 0.81 | 10000 | 6.0659 |
52
+ | 6.0903 | 1.22 | 15000 | 6.0566 |
53
+ | 6.0874 | 1.62 | 20000 | 6.0550 |
54
+ | 6.082 | 2.03 | 25000 | 6.0485 |
55
+ | 6.0756 | 2.44 | 30000 | 6.0446 |
56
+ | 6.0722 | 2.84 | 35000 | 6.0429 |
57
+ | 6.0698 | 3.25 | 40000 | 6.0317 |
58
+ | 6.0627 | 3.66 | 45000 | 6.0297 |
59
+ | 6.0606 | 4.06 | 50000 | 6.0301 |
60
+ | 6.0521 | 4.47 | 55000 | 6.0224 |
61
+ | 6.0526 | 4.87 | 60000 | 6.0159 |
62
+ | 6.0473 | 5.28 | 65000 | 6.0140 |
63
+ | 6.0435 | 5.69 | 70000 | 6.0076 |
64
+ | 6.039 | 6.09 | 75000 | 6.0022 |
65
+ | 6.032 | 6.5 | 80000 | 6.0037 |
66
+ | 6.0319 | 6.91 | 85000 | 5.9979 |
67
+ | 6.0232 | 7.31 | 90000 | 5.9937 |
68
+ | 6.0279 | 7.72 | 95000 | 5.9844 |
69
+ | 6.0198 | 8.12 | 100000 | 5.9854 |
70
+ | 6.0165 | 8.53 | 105000 | 5.9796 |
71
+ | 6.0153 | 8.94 | 110000 | 5.9741 |
72
+ | 6.0111 | 9.34 | 115000 | 5.9722 |
73
+ | 6.0082 | 9.75 | 120000 | 5.9679 |
74
+ | 6.0035 | 10.16 | 125000 | 5.9654 |
75
+ | 5.999 | 10.56 | 130000 | 5.9624 |
76
+ | 5.998 | 10.97 | 135000 | 5.9572 |
77
+ | 5.9926 | 11.37 | 140000 | 5.9535 |
78
+ | 5.9927 | 11.78 | 145000 | 5.9533 |
79
+ | 5.9903 | 12.19 | 150000 | 5.9517 |
80
+ | 5.986 | 12.59 | 155000 | 5.9459 |
81
+ | 5.9816 | 13.0 | 160000 | 5.9439 |
82
+ | 5.9786 | 13.41 | 165000 | 5.9390 |
83
+ | 5.9781 | 13.81 | 170000 | 5.9357 |
84
+ | 5.9779 | 14.22 | 175000 | 5.9346 |
85
+ | 5.9756 | 14.62 | 180000 | 5.9339 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.19.2
91
+ - Pytorch 1.11.0
92
+ - Datasets 2.2.2
93
+ - Tokenizers 0.12.1