Hugging Face's logo

gayanin
/
ec-biogpt-noised-pubmed-v3

Text Generation
Transformers
PyTorch
biogpt
Generated from Trainer
Model card Files Community
gayanin commited on
Commit
fa2c1a7
·
1 Parent(s): 15a11fc

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +126 -0
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: ec-biogpt-noised-pubmed-v3
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-v3
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: 1.7552
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
+ | 1.9981 | 0.07 | 500 | 1.8163 |
51
+ | 1.7501 | 0.14 | 1000 | 1.7809 |
52
+ | 2.0623 | 0.22 | 1500 | 1.7638 |
53
+ | 1.8094 | 0.29 | 2000 | 1.7458 |
54
+ | 1.8711 | 0.36 | 2500 | 1.7326 |
55
+ | 1.6588 | 0.43 | 3000 | 1.7244 |
56
+ | 1.5469 | 0.5 | 3500 | 1.7153 |
57
+ | 1.6981 | 0.57 | 4000 | 1.7084 |
58
+ | 1.6728 | 0.65 | 4500 | 1.7025 |
59
+ | 1.8203 | 0.72 | 5000 | 1.6973 |
60
+ | 1.8318 | 0.79 | 5500 | 1.6924 |
61
+ | 1.6916 | 0.86 | 6000 | 1.6906 |
62
+ | 1.6369 | 0.93 | 6500 | 1.6816 |
63
+ | 1.4371 | 1.01 | 7000 | 1.6838 |
64
+ | 1.381 | 1.08 | 7500 | 1.6829 |
65
+ | 1.6214 | 1.15 | 8000 | 1.6846 |
66
+ | 1.6218 | 1.22 | 8500 | 1.6790 |
67
+ | 1.6278 | 1.29 | 9000 | 1.6788 |
68
+ | 1.4046 | 1.36 | 9500 | 1.6774 |
69
+ | 1.4866 | 1.44 | 10000 | 1.6728 |
70
+ | 1.4712 | 1.51 | 10500 | 1.6716 |
71
+ | 1.5896 | 1.58 | 11000 | 1.6702 |
72
+ | 1.4818 | 1.65 | 11500 | 1.6681 |
73
+ | 1.4261 | 1.72 | 12000 | 1.6638 |
74
+ | 1.5318 | 1.79 | 12500 | 1.6624 |
75
+ | 1.4814 | 1.87 | 13000 | 1.6620 |
76
+ | 1.5131 | 1.94 | 13500 | 1.6583 |
77
+ | 1.3971 | 2.01 | 14000 | 1.6806 |
78
+ | 1.4146 | 2.08 | 14500 | 1.6842 |
79
+ | 1.5739 | 2.15 | 15000 | 1.6888 |
80
+ | 1.312 | 2.23 | 15500 | 1.6857 |
81
+ | 1.4992 | 2.3 | 16000 | 1.6876 |
82
+ | 1.2725 | 2.37 | 16500 | 1.6845 |
83
+ | 1.3904 | 2.44 | 17000 | 1.6840 |
84
+ | 1.4569 | 2.51 | 17500 | 1.6855 |
85
+ | 1.4358 | 2.58 | 18000 | 1.6811 |
86
+ | 1.4747 | 2.66 | 18500 | 1.6814 |
87
+ | 1.3272 | 2.73 | 19000 | 1.6818 |
88
+ | 1.3743 | 2.8 | 19500 | 1.6756 |
89
+ | 1.3953 | 2.87 | 20000 | 1.6759 |
90
+ | 1.4173 | 2.94 | 20500 | 1.6748 |
91
+ | 1.3998 | 3.02 | 21000 | 1.7133 |
92
+ | 1.3396 | 3.09 | 21500 | 1.7205 |
93
+ | 1.1953 | 3.16 | 22000 | 1.7218 |
94
+ | 1.2047 | 3.23 | 22500 | 1.7223 |
95
+ | 1.0788 | 3.3 | 23000 | 1.7214 |
96
+ | 1.3048 | 3.37 | 23500 | 1.7230 |
97
+ | 1.3271 | 3.45 | 24000 | 1.7195 |
98
+ | 1.4236 | 3.52 | 24500 | 1.7208 |
99
+ | 1.1851 | 3.59 | 25000 | 1.7209 |
100
+ | 1.285 | 3.66 | 25500 | 1.7207 |
101
+ | 1.3013 | 3.73 | 26000 | 1.7174 |
102
+ | 1.2734 | 3.81 | 26500 | 1.7182 |
103
+ | 1.3496 | 3.88 | 27000 | 1.7168 |
104
+ | 1.3628 | 3.95 | 27500 | 1.7134 |
105
+ | 1.0063 | 4.02 | 28000 | 1.7507 |
106
+ | 1.1155 | 4.09 | 28500 | 1.7557 |
107
+ | 1.1886 | 4.16 | 29000 | 1.7571 |
108
+ | 1.1304 | 4.24 | 29500 | 1.7575 |
109
+ | 1.0328 | 4.31 | 30000 | 1.7563 |
110
+ | 1.2631 | 4.38 | 30500 | 1.7584 |
111
+ | 1.2212 | 4.45 | 31000 | 1.7564 |
112
+ | 1.1825 | 4.52 | 31500 | 1.7583 |
113
+ | 1.4374 | 4.6 | 32000 | 1.7562 |
114
+ | 1.1568 | 4.67 | 32500 | 1.7554 |
115
+ | 1.3035 | 4.74 | 33000 | 1.7565 |
116
+ | 1.27 | 4.81 | 33500 | 1.7557 |
117
+ | 1.2518 | 4.88 | 34000 | 1.7560 |
118
+ | 1.0965 | 4.95 | 34500 | 1.7552 |
119
+
120
+
121
+ ### Framework versions
122
+
123
+ - Transformers 4.27.4
124
+ - Pytorch 2.0.0+cu117
125
+ - Datasets 2.11.0
126
+ - Tokenizers 0.13.3