Hugging Face's logo

anikethjr
/
PromoGen_K562_2080Ti_restart

Text Generation
Transformers
PyTorch
TensorBoard
prophetnet
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
anikethjr commited on
Commit
796d40e
•
1 Parent(s): 658a3e9

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +109 -0
README.md ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: PromoGen_K562_2080Ti_restart
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
+ # PromoGen_K562_2080Ti_restart
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: 0.4624
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: 0.0005
36
+ - train_batch_size: 8
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - gradient_accumulation_steps: 8
40
+ - total_train_batch_size: 64
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: 25
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:------:|:---------------:|
51
+ | 0.7676 | 0.49 | 2500 | 0.7383 |
52
+ | 0.7121 | 0.97 | 5000 | 0.6867 |
53
+ | 0.6914 | 1.46 | 7500 | 0.6705 |
54
+ | 0.6837 | 1.95 | 10000 | 0.6622 |
55
+ | 0.6778 | 2.44 | 12500 | 0.6558 |
56
+ | 0.6748 | 2.92 | 15000 | 0.6517 |
57
+ | 0.6676 | 3.41 | 17500 | 0.6433 |
58
+ | 0.6593 | 3.9 | 20000 | 0.6358 |
59
+ | 0.6584 | 4.38 | 22500 | 0.6320 |
60
+ | 0.6557 | 4.87 | 25000 | 0.6301 |
61
+ | 0.6523 | 5.36 | 27500 | 0.6257 |
62
+ | 0.6478 | 5.84 | 30000 | 0.6236 |
63
+ | 0.6393 | 6.33 | 32500 | 0.6145 |
64
+ | 0.6039 | 6.82 | 35000 | 0.5658 |
65
+ | 0.5616 | 7.31 | 37500 | 0.5376 |
66
+ | 0.5518 | 7.79 | 40000 | 0.5310 |
67
+ | 0.5509 | 8.28 | 42500 | 0.5273 |
68
+ | 0.5487 | 8.77 | 45000 | 0.5261 |
69
+ | 0.5479 | 9.25 | 47500 | 0.5249 |
70
+ | 0.546 | 9.74 | 50000 | 0.5242 |
71
+ | 0.5447 | 10.23 | 52500 | 0.5229 |
72
+ | 0.5439 | 10.71 | 55000 | 0.5220 |
73
+ | 0.5433 | 11.2 | 57500 | 0.5209 |
74
+ | 0.5394 | 11.69 | 60000 | 0.5162 |
75
+ | 0.5153 | 12.18 | 62500 | 0.4944 |
76
+ | 0.5137 | 12.66 | 65000 | 0.4932 |
77
+ | 0.514 | 13.15 | 67500 | 0.4924 |
78
+ | 0.5131 | 13.64 | 70000 | 0.4919 |
79
+ | 0.5104 | 14.12 | 72500 | 0.4914 |
80
+ | 0.5122 | 14.61 | 75000 | 0.4906 |
81
+ | 0.5089 | 15.1 | 77500 | 0.4901 |
82
+ | 0.5076 | 15.59 | 80000 | 0.4891 |
83
+ | 0.4986 | 16.07 | 82500 | 0.4721 |
84
+ | 0.4875 | 16.56 | 85000 | 0.4672 |
85
+ | 0.4887 | 17.05 | 87500 | 0.4669 |
86
+ | 0.4839 | 17.53 | 90000 | 0.4661 |
87
+ | 0.4849 | 18.02 | 92500 | 0.4654 |
88
+ | 0.4848 | 18.51 | 95000 | 0.4649 |
89
+ | 0.4831 | 18.99 | 97500 | 0.4646 |
90
+ | 0.4816 | 19.48 | 100000 | 0.4644 |
91
+ | 0.4808 | 19.97 | 102500 | 0.4637 |
92
+ | 0.4812 | 20.46 | 105000 | 0.4634 |
93
+ | 0.4813 | 20.94 | 107500 | 0.4633 |
94
+ | 0.4818 | 21.43 | 110000 | 0.4631 |
95
+ | 0.4813 | 21.92 | 112500 | 0.4629 |
96
+ | 0.4782 | 22.4 | 115000 | 0.4628 |
97
+ | 0.4804 | 22.89 | 117500 | 0.4626 |
98
+ | 0.4815 | 23.38 | 120000 | 0.4625 |
99
+ | 0.4812 | 23.87 | 122500 | 0.4625 |
100
+ | 0.4785 | 24.35 | 125000 | 0.4624 |
101
+ | 0.4795 | 24.84 | 127500 | 0.4624 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - Transformers 4.24.0
107
+ - Pytorch 1.13.0
108
+ - Datasets 2.7.0
109
+ - Tokenizers 0.13.0.dev0