Hugging Face's logo

ailab-bio
/
PROTAC-Splitter-EncoderDecoder-lr_cosine_restarts-opt25

Transformers
TensorBoard
Safetensors
encoder-decoder
text2text-generation
PROTAC
cheminformatics
Generated from Trainer
Model card Files
xet
Metrics Community
ribesstefano commited on
Commit
c00961b
·
verified ·
1 Parent(s): 4eeafc1

Initial version

Browse files
Files changed (2) hide show
  1. README.md +98 -0
  2. generation_config.json +10 -0
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: seyonec/ChemBERTa-zinc-base-v1
5
+ tags:
6
+ - PROTAC
7
+ - cheminformatics
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: ailab-bio/PROTAC-Splitter-EncoderDecoder-lr_cosine_restarts-opt25
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # ailab-bio/PROTAC-Splitter-EncoderDecoder-lr_cosine_restarts-opt25
18
+
19
+ This model is a fine-tuned version of [seyonec/ChemBERTa-zinc-base-v1](https://huggingface.co/seyonec/ChemBERTa-zinc-base-v1) on the ailab-bio/PROTAC-Splitter-Dataset dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.3086
22
+ - Poi Heavy Atoms Difference: 2.1208
23
+ - E3 Valid: 0.9896
24
+ - Poi Valid: 0.9272
25
+ - Poi Has Attachment Point(s): 0.9272
26
+ - All Ligands Equal: 0.5462
27
+ - Valid: 0.9157
28
+ - Reassembly: 0.5544
29
+ - Poi Tanimoto Similarity: 0.0
30
+ - Linker Tanimoto Similarity: 0.0
31
+ - Poi Graph Edit Distance: inf
32
+ - Linker Heavy Atoms Difference: 0.3144
33
+ - Linker Graph Edit Distance Norm: inf
34
+ - E3 Graph Edit Distance Norm: inf
35
+ - Num Fragments: 2.9998
36
+ - E3 Heavy Atoms Difference Norm: 0.0131
37
+ - Linker Valid: 0.9961
38
+ - E3 Heavy Atoms Difference: 0.5553
39
+ - E3 Tanimoto Similarity: 0.0
40
+ - Poi Heavy Atoms Difference Norm: 0.0719
41
+ - Reassembly Nostereo: 0.5796
42
+ - Linker Equal: 0.7666
43
+ - Linker Has Attachment Point(s): 0.9961
44
+ - Has All Attachment Points: 0.9836
45
+ - Poi Equal: 0.7680
46
+ - E3 Graph Edit Distance: inf
47
+ - Tanimoto Similarity: 0.0
48
+ - E3 Has Attachment Point(s): 0.9896
49
+ - Poi Graph Edit Distance Norm: inf
50
+ - E3 Equal: 0.8045
51
+ - Heavy Atoms Difference Norm: 0.0939
52
+ - Has Three Substructures: 0.9991
53
+ - Linker Graph Edit Distance: inf
54
+ - Heavy Atoms Difference: 7.0102
55
+ - Linker Heavy Atoms Difference Norm: 0.0033
56
+
57
+ ## Model description
58
+
59
+ More information needed
60
+
61
+ ## Intended uses & limitations
62
+
63
+ More information needed
64
+
65
+ ## Training and evaluation data
66
+
67
+ More information needed
68
+
69
+ ## Training procedure
70
+
71
+ ### Training hyperparameters
72
+
73
+ The following hyperparameters were used during training:
74
+ - learning_rate: 5e-05
75
+ - train_batch_size: 128
76
+ - eval_batch_size: 64
77
+ - seed: 42
78
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
79
+ - lr_scheduler_type: cosine_with_restarts
80
+ - lr_scheduler_warmup_steps: 100
81
+ - training_steps: 10000
82
+ - mixed_precision_training: Native AMP
83
+
84
+ ### Training results
85
+
86
+ | Training Loss | Epoch | Step | Validation Loss | Poi Heavy Atoms Difference | E3 Valid | Poi Valid | Poi Has Attachment Point(s) | All Ligands Equal | Valid | Reassembly | Poi Tanimoto Similarity | Linker Tanimoto Similarity | Poi Graph Edit Distance | Linker Heavy Atoms Difference | Linker Graph Edit Distance Norm | E3 Graph Edit Distance Norm | Num Fragments | E3 Heavy Atoms Difference Norm | Linker Valid | E3 Heavy Atoms Difference | E3 Tanimoto Similarity | Poi Heavy Atoms Difference Norm | Reassembly Nostereo | Linker Equal | Linker Has Attachment Point(s) | Has All Attachment Points | Poi Equal | E3 Graph Edit Distance | Tanimoto Similarity | E3 Has Attachment Point(s) | Poi Graph Edit Distance Norm | E3 Equal | Heavy Atoms Difference Norm | Has Three Substructures | Linker Graph Edit Distance | Heavy Atoms Difference | Linker Heavy Atoms Difference Norm |
87
+ |:-------------:|:------:|:-----:|:---------------:|:--------------------------:|:--------:|:---------:|:---------------------------:|:-----------------:|:------:|:----------:|:-----------------------:|:--------------------------:|:-----------------------:|:-----------------------------:|:-------------------------------:|:---------------------------:|:-------------:|:------------------------------:|:------------:|:-------------------------:|:----------------------:|:-------------------------------:|:-------------------:|:------------:|:------------------------------:|:-------------------------:|:---------:|:----------------------:|:-------------------:|:--------------------------:|:----------------------------:|:--------:|:---------------------------:|:-----------------------:|:-------------------------------------------------------------------:|:----------------------:|:----------------------------------:|
88
+ | 0.0156 | 0.4932 | 5000 | 0.2891 | 2.3129 | 0.9916 | 0.9252 | 0.9252 | 0.4596 | 0.9169 | 0.4665 | 0.0 | 0.0 | inf | 0.3805 | inf | inf | 3.0006 | 0.0061 | 0.9965 | 0.3913 | 0.0 | 0.0739 | 0.4911 | 0.6623 | 0.9965 | 0.9863 | 0.7265 | inf | 0.0 | 0.9916 | inf | 0.7815 | 0.0918 | 0.9988 | 35410764872521246890440289523238443113605795566260484204134400.0000 | 7.0030 | 0.0005 |
89
+ | 0.0077 | 0.7398 | 7500 | 0.3073 | 2.5750 | 0.9857 | 0.9161 | 0.9161 | 0.4898 | 0.8987 | 0.4975 | 0.0 | 0.0 | inf | 0.4483 | inf | inf | 3.0002 | 0.0088 | 0.9943 | 0.4845 | 0.0 | 0.0832 | 0.5220 | 0.7095 | 0.9943 | 0.9812 | 0.7363 | inf | 0.0 | 0.9857 | inf | 0.7908 | 0.1093 | 0.9995 | 56657223796033995024704463237181508981769272906016774726615040.0000 | 8.2839 | 0.0090 |
90
+ | 0.0046 | 0.9864 | 10000 | 0.3086 | 2.1208 | 0.9896 | 0.9272 | 0.9272 | 0.5462 | 0.9157 | 0.5544 | 0.0 | 0.0 | inf | 0.3144 | inf | inf | 2.9998 | 0.0131 | 0.9961 | 0.5553 | 0.0 | 0.0719 | 0.5796 | 0.7666 | 0.9961 | 0.9836 | 0.7680 | inf | 0.0 | 0.9896 | inf | 0.8045 | 0.0939 | 0.9991 | inf | 7.0102 | 0.0033 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.44.2
96
+ - Pytorch 2.4.1+cu121
97
+ - Datasets 3.0.0
98
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 512,
6
+ "num_beams": 5,
7
+ "pad_token_id": 1,
8
+ "top_k": 20,
9
+ "transformers_version": "4.44.2"
10
+ }