Hugging Face's logo

Vlasta
/
DNADebertaSentencepiece10k_continuation_continuation_continuation

Fill-Mask
Transformers
PyTorch
deberta
Generated from Trainer
Model card Files
xet
 Community
1
Vlasta commited on
Commit
03acdb7
·
1 Parent(s): 6595eea

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_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_continuation
13
+
14
+ This model is a fine-tuned version of [Vlasta/DNADebertaSentencepiece10k_continuation_continuation](https://huggingface.co/Vlasta/DNADebertaSentencepiece10k_continuation_continuation) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 5.2605
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
+ | 5.4076 | 0.36 | 5000 | 5.3702 |
51
+ | 5.4146 | 0.72 | 10000 | 5.3677 |
52
+ | 5.4119 | 1.08 | 15000 | 5.3661 |
53
+ | 5.4093 | 1.45 | 20000 | 5.3577 |
54
+ | 5.4055 | 1.81 | 25000 | 5.3574 |
55
+ | 5.3987 | 2.17 | 30000 | 5.3539 |
56
+ | 5.3974 | 2.53 | 35000 | 5.3509 |
57
+ | 5.3931 | 2.89 | 40000 | 5.3431 |
58
+ | 5.387 | 3.25 | 45000 | 5.3447 |
59
+ | 5.3868 | 3.61 | 50000 | 5.3404 |
60
+ | 5.3874 | 3.97 | 55000 | 5.3362 |
61
+ | 5.3797 | 4.34 | 60000 | 5.3275 |
62
+ | 5.3775 | 4.7 | 65000 | 5.3316 |
63
+ | 5.3737 | 5.06 | 70000 | 5.3245 |
64
+ | 5.367 | 5.42 | 75000 | 5.3228 |
65
+ | 5.3679 | 5.78 | 80000 | 5.3193 |
66
+ | 5.3648 | 6.14 | 85000 | 5.3185 |
67
+ | 5.3586 | 6.5 | 90000 | 5.3149 |
68
+ | 5.361 | 6.86 | 95000 | 5.3086 |
69
+ | 5.3572 | 7.23 | 100000 | 5.3080 |
70
+ | 5.3521 | 7.59 | 105000 | 5.3057 |
71
+ | 5.3516 | 7.95 | 110000 | 5.3020 |
72
+ | 5.3481 | 8.31 | 115000 | 5.2997 |
73
+ | 5.3453 | 8.67 | 120000 | 5.2990 |
74
+ | 5.3446 | 9.03 | 125000 | 5.2951 |
75
+ | 5.3418 | 9.39 | 130000 | 5.2888 |
76
+ | 5.3341 | 9.75 | 135000 | 5.2860 |
77
+ | 5.3371 | 10.12 | 140000 | 5.2879 |
78
+ | 5.3319 | 10.48 | 145000 | 5.2845 |
79
+ | 5.3316 | 10.84 | 150000 | 5.2822 |
80
+ | 5.3306 | 11.2 | 155000 | 5.2803 |
81
+ | 5.3272 | 11.56 | 160000 | 5.2743 |
82
+ | 5.3224 | 11.92 | 165000 | 5.2724 |
83
+ | 5.3224 | 12.28 | 170000 | 5.2726 |
84
+ | 5.3217 | 12.64 | 175000 | 5.2712 |
85
+ | 5.3167 | 13.01 | 180000 | 5.2663 |
86
+ | 5.3148 | 13.37 | 185000 | 5.2659 |
87
+ | 5.3154 | 13.73 | 190000 | 5.2624 |
88
+ | 5.3119 | 14.09 | 195000 | 5.2627 |
89
+ | 5.3122 | 14.45 | 200000 | 5.2599 |
90
+ | 5.3091 | 14.81 | 205000 | 5.2586 |
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