Hugging Face's logo

gayanin
/
ec-biogpt-noised-pubmed-v2

Text Generation
Transformers
PyTorch
biogpt
Generated from Trainer
Model card Files Community
1
gayanin commited on
Commit
211a1ae
·
1 Parent(s): 91f1680

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: ec-biogpt-noised-pubmed-v2
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # ec-biogpt-noised-pubmed-v2
14
+
15
+ This model is a fine-tuned version of [microsoft/biogpt](https://huggingface.co/microsoft/biogpt) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.2703
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 16
38
+ - eval_batch_size: 16
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - lr_scheduler_warmup_steps: 10
43
+ - num_epochs: 5
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 1.1503 | 0.11 | 500 | 1.3369 |
51
+ | 1.3766 | 0.21 | 1000 | 1.2721 |
52
+ | 1.3523 | 0.32 | 1500 | 1.2516 |
53
+ | 1.3123 | 0.43 | 2000 | 1.2394 |
54
+ | 1.1954 | 0.54 | 2500 | 1.2265 |
55
+ | 1.226 | 0.64 | 3000 | 1.2182 |
56
+ | 1.1269 | 0.75 | 3500 | 1.2118 |
57
+ | 1.212 | 0.86 | 4000 | 1.2053 |
58
+ | 1.3253 | 0.96 | 4500 | 1.1984 |
59
+ | 1.0722 | 1.07 | 5000 | 1.2016 |
60
+ | 1.1208 | 1.18 | 5500 | 1.2009 |
61
+ | 1.132 | 1.28 | 6000 | 1.1992 |
62
+ | 1.1228 | 1.39 | 6500 | 1.1967 |
63
+ | 1.1529 | 1.5 | 7000 | 1.1918 |
64
+ | 1.0342 | 1.61 | 7500 | 1.1916 |
65
+ | 1.0881 | 1.71 | 8000 | 1.1889 |
66
+ | 1.084 | 1.82 | 8500 | 1.1852 |
67
+ | 1.1409 | 1.93 | 9000 | 1.1807 |
68
+ | 0.9794 | 2.03 | 9500 | 1.2098 |
69
+ | 0.9821 | 2.14 | 10000 | 1.2146 |
70
+ | 0.9695 | 2.25 | 10500 | 1.2096 |
71
+ | 0.9866 | 2.35 | 11000 | 1.2088 |
72
+ | 1.0305 | 2.46 | 11500 | 1.2059 |
73
+ | 0.9532 | 2.57 | 12000 | 1.2060 |
74
+ | 0.9978 | 2.68 | 12500 | 1.2041 |
75
+ | 1.0013 | 2.78 | 13000 | 1.2006 |
76
+ | 1.0401 | 2.89 | 13500 | 1.2023 |
77
+ | 1.0899 | 3.0 | 14000 | 1.1988 |
78
+ | 0.8229 | 3.1 | 14500 | 1.2410 |
79
+ | 0.8598 | 3.21 | 15000 | 1.2420 |
80
+ | 0.9295 | 3.32 | 15500 | 1.2414 |
81
+ | 0.8477 | 3.43 | 16000 | 1.2386 |
82
+ | 0.9302 | 3.53 | 16500 | 1.2382 |
83
+ | 0.8284 | 3.64 | 17000 | 1.2374 |
84
+ | 0.8242 | 3.75 | 17500 | 1.2410 |
85
+ | 0.8422 | 3.85 | 18000 | 1.2346 |
86
+ | 0.8742 | 3.96 | 18500 | 1.2362 |
87
+ | 0.798 | 4.07 | 19000 | 1.2667 |
88
+ | 0.7821 | 4.17 | 19500 | 1.2701 |
89
+ | 0.7788 | 4.28 | 20000 | 1.2714 |
90
+ | 0.7701 | 4.39 | 20500 | 1.2702 |
91
+ | 0.7348 | 4.5 | 21000 | 1.2722 |
92
+ | 0.762 | 4.6 | 21500 | 1.2705 |
93
+ | 0.7385 | 4.71 | 22000 | 1.2705 |
94
+ | 0.7837 | 4.82 | 22500 | 1.2695 |
95
+ | 0.8371 | 4.92 | 23000 | 1.2703 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.27.4
101
+ - Pytorch 2.0.0+cu118
102
+ - Datasets 2.11.0
103
+ - Tokenizers 0.13.3