Hugging Face's logo

Vlasta
/
DNADebertaSentencepiece10k_continuation_continuation

Fill-Mask
Transformers
PyTorch
deberta
Generated from Trainer
Inference Endpoints
Model card Files Community
1
Vlasta commited on
Commit
3b17aae
•
1 Parent(s): 2e47ab3

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +98 -0
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: DNADebertaSentencepiece10k_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
+ # DNADebertaSentencepiece10k_continuation_continuation
13
+
14
+ This model is a fine-tuned version of [Vlasta/DNADebertaSentencepiece10k_continuation](https://huggingface.co/Vlasta/DNADebertaSentencepiece10k_continuation) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 5.3056
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
+ | 5.4806 | 0.36 | 5000 | 5.4385 |
51
+ | 5.4848 | 0.72 | 10000 | 5.4333 |
52
+ | 5.4803 | 1.08 | 15000 | 5.4312 |
53
+ | 5.4759 | 1.45 | 20000 | 5.4223 |
54
+ | 5.4703 | 1.81 | 25000 | 5.4199 |
55
+ | 5.4626 | 2.17 | 30000 | 5.4147 |
56
+ | 5.4596 | 2.53 | 35000 | 5.4094 |
57
+ | 5.4534 | 2.89 | 40000 | 5.4014 |
58
+ | 5.4466 | 3.25 | 45000 | 5.4017 |
59
+ | 5.445 | 3.61 | 50000 | 5.3954 |
60
+ | 5.4446 | 3.97 | 55000 | 5.3916 |
61
+ | 5.4359 | 4.34 | 60000 | 5.3809 |
62
+ | 5.4327 | 4.7 | 65000 | 5.3846 |
63
+ | 5.4281 | 5.06 | 70000 | 5.3765 |
64
+ | 5.4207 | 5.42 | 75000 | 5.3744 |
65
+ | 5.4207 | 5.78 | 80000 | 5.3704 |
66
+ | 5.4167 | 6.14 | 85000 | 5.3685 |
67
+ | 5.41 | 6.5 | 90000 | 5.3641 |
68
+ | 5.4117 | 6.86 | 95000 | 5.3582 |
69
+ | 5.4075 | 7.23 | 100000 | 5.3568 |
70
+ | 5.4017 | 7.59 | 105000 | 5.3547 |
71
+ | 5.4006 | 7.95 | 110000 | 5.3494 |
72
+ | 5.3969 | 8.31 | 115000 | 5.3475 |
73
+ | 5.3935 | 8.67 | 120000 | 5.3453 |
74
+ | 5.3926 | 9.03 | 125000 | 5.3422 |
75
+ | 5.3895 | 9.39 | 130000 | 5.3351 |
76
+ | 5.3813 | 9.75 | 135000 | 5.3326 |
77
+ | 5.3841 | 10.12 | 140000 | 5.3340 |
78
+ | 5.3787 | 10.48 | 145000 | 5.3301 |
79
+ | 5.3781 | 10.84 | 150000 | 5.3280 |
80
+ | 5.3769 | 11.2 | 155000 | 5.3258 |
81
+ | 5.3733 | 11.56 | 160000 | 5.3198 |
82
+ | 5.3683 | 11.92 | 165000 | 5.3180 |
83
+ | 5.3682 | 12.28 | 170000 | 5.3181 |
84
+ | 5.3673 | 12.64 | 175000 | 5.3167 |
85
+ | 5.3623 | 13.01 | 180000 | 5.3116 |
86
+ | 5.3602 | 13.37 | 185000 | 5.3109 |
87
+ | 5.361 | 13.73 | 190000 | 5.3071 |
88
+ | 5.3573 | 14.09 | 195000 | 5.3078 |
89
+ | 5.3575 | 14.45 | 200000 | 5.3051 |
90
+ | 5.3544 | 14.81 | 205000 | 5.3038 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.19.2
96
+ - Pytorch 1.11.0
97
+ - Datasets 2.2.2
98
+ - Tokenizers 0.12.1