Hugging Face's logo

gayanin
/
ec-biogpt-noised-pubmed-v4

Text Generation
Transformers
PyTorch
biogpt
Generated from Trainer
Inference Endpoints
Model card Files Community
gayanin commited on
Commit
bc9f446
·
1 Parent(s): a279f77

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-v4
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-v4
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: 1.8204
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
+ | 1.7942 | 0.11 | 500 | 1.8358 |
51
+ | 1.9793 | 0.21 | 1000 | 1.8000 |
52
+ | 1.9244 | 0.32 | 1500 | 1.7763 |
53
+ | 1.8871 | 0.43 | 2000 | 1.7623 |
54
+ | 1.6525 | 0.54 | 2500 | 1.7511 |
55
+ | 1.6871 | 0.64 | 3000 | 1.7401 |
56
+ | 1.5771 | 0.75 | 3500 | 1.7315 |
57
+ | 1.732 | 0.86 | 4000 | 1.7278 |
58
+ | 1.9909 | 0.96 | 4500 | 1.7196 |
59
+ | 1.5173 | 1.07 | 5000 | 1.7204 |
60
+ | 1.6015 | 1.18 | 5500 | 1.7206 |
61
+ | 1.6817 | 1.28 | 6000 | 1.7183 |
62
+ | 1.6475 | 1.39 | 6500 | 1.7161 |
63
+ | 1.7425 | 1.5 | 7000 | 1.7114 |
64
+ | 1.4702 | 1.61 | 7500 | 1.7067 |
65
+ | 1.5635 | 1.71 | 8000 | 1.7078 |
66
+ | 1.574 | 1.82 | 8500 | 1.7020 |
67
+ | 1.6691 | 1.93 | 9000 | 1.6985 |
68
+ | 1.4796 | 2.03 | 9500 | 1.7339 |
69
+ | 1.472 | 2.14 | 10000 | 1.7354 |
70
+ | 1.4476 | 2.25 | 10500 | 1.7331 |
71
+ | 1.4402 | 2.35 | 11000 | 1.7327 |
72
+ | 1.5988 | 2.46 | 11500 | 1.7328 |
73
+ | 1.3682 | 2.57 | 12000 | 1.7299 |
74
+ | 1.4988 | 2.68 | 12500 | 1.7281 |
75
+ | 1.4514 | 2.78 | 13000 | 1.7257 |
76
+ | 1.6356 | 2.89 | 13500 | 1.7264 |
77
+ | 1.6653 | 3.0 | 14000 | 1.7240 |
78
+ | 1.2013 | 3.1 | 14500 | 1.7782 |
79
+ | 1.2864 | 3.21 | 15000 | 1.7770 |
80
+ | 1.4638 | 3.32 | 15500 | 1.7817 |
81
+ | 1.2501 | 3.43 | 16000 | 1.7787 |
82
+ | 1.4613 | 3.53 | 16500 | 1.7791 |
83
+ | 1.1816 | 3.64 | 17000 | 1.7767 |
84
+ | 1.1841 | 3.75 | 17500 | 1.7786 |
85
+ | 1.2382 | 3.85 | 18000 | 1.7743 |
86
+ | 1.2868 | 3.96 | 18500 | 1.7749 |
87
+ | 1.2074 | 4.07 | 19000 | 1.8167 |
88
+ | 1.1657 | 4.17 | 19500 | 1.8224 |
89
+ | 1.1851 | 4.28 | 20000 | 1.8197 |
90
+ | 1.1141 | 4.39 | 20500 | 1.8225 |
91
+ | 1.0628 | 4.5 | 21000 | 1.8202 |
92
+ | 1.0946 | 4.6 | 21500 | 1.8209 |
93
+ | 1.037 | 4.71 | 22000 | 1.8201 |
94
+ | 1.1277 | 4.82 | 22500 | 1.8206 |
95
+ | 1.2766 | 4.92 | 23000 | 1.8204 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.27.4
101
+ - Pytorch 2.0.0+cu117
102
+ - Datasets 2.11.0
103
+ - Tokenizers 0.13.3