ailab-bio/PROTAC-Splitter-EncoderDecoder-lr_reduce-opt25
073
1---2base_model: seyonec/ChemBERTa-zinc-base-v13library_name: transformers4license: mit5tags:6- PROTAC7- cheminformatics8- generated_from_trainer9model-index:10- name: ailab-bio/PROTAC-Splitter-EncoderDecoder-lr_reduce-opt2511 results: []12---13 14<!-- This model card has been generated automatically according to the information the Trainer had access to. You15should probably proofread and complete it, then remove this comment. -->16 17# ailab-bio/PROTAC-Splitter-EncoderDecoder-lr_reduce-opt2518 19This 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.20It achieves the following results on the evaluation set:21- Loss: 0.342022- Num Fragments: 3.000223- Linker Heavy Atoms Difference: 0.168924- Linker Graph Edit Distance: 37181303116147309234962303999400365269286085344573508414341120.000025- Tanimoto Similarity: 0.026- Linker Tanimoto Similarity: 0.027- E3 Valid: 0.973228- Linker Has Attachment Point(s): 0.996329- Poi Equal: 0.789730- Heavy Atoms Difference: 8.024431- Poi Has Attachment Point(s): 0.930532- E3 Equal: 0.830233- Linker Graph Edit Distance Norm: inf34- E3 Has Attachment Point(s): 0.973235- Has Three Substructures: 0.999536- Poi Heavy Atoms Difference Norm: 0.069037- Linker Equal: 0.841938- Heavy Atoms Difference Norm: 0.107639- E3 Heavy Atoms Difference: 1.045440- Poi Valid: 0.930541- Valid: 0.902742- Linker Heavy Atoms Difference Norm: -0.004643- Has All Attachment Points: 0.979644- E3 Graph Edit Distance: inf45- Linker Valid: 0.996346- Poi Tanimoto Similarity: 0.047- Poi Graph Edit Distance Norm: inf48- Poi Heavy Atoms Difference: 2.048249- Poi Graph Edit Distance: inf50- Reassembly Nostereo: 0.626151- E3 Graph Edit Distance Norm: inf52- E3 Heavy Atoms Difference Norm: 0.033553- Reassembly: 0.607354- All Ligands Equal: 0.599255- E3 Tanimoto Similarity: 0.056 57## Model description58 59More information needed60 61## Intended uses & limitations62 63More information needed64 65## Training and evaluation data66 67More information needed68 69## Training procedure70 71### Training hyperparameters72 73The following hyperparameters were used during training:74- learning_rate: 5e-0575- train_batch_size: 12876- eval_batch_size: 6477- seed: 4278- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0879- lr_scheduler_type: reduce_lr_on_plateau80- training_steps: 10000081- mixed_precision_training: Native AMP82 83### Training results84 85| Training Loss | Epoch | Step | Validation Loss | Num Fragments | Linker Heavy Atoms Difference | Linker Graph Edit Distance | Tanimoto Similarity | Linker Tanimoto Similarity | E3 Valid | Linker Has Attachment Point(s) | Poi Equal | Heavy Atoms Difference | Poi Has Attachment Point(s) | E3 Equal | Linker Graph Edit Distance Norm | E3 Has Attachment Point(s) | Has Three Substructures | Poi Heavy Atoms Difference Norm | Linker Equal | Heavy Atoms Difference Norm | E3 Heavy Atoms Difference | Poi Valid | Valid | Linker Heavy Atoms Difference Norm | Has All Attachment Points | E3 Graph Edit Distance | Linker Valid | Poi Tanimoto Similarity | Poi Graph Edit Distance Norm | Poi Heavy Atoms Difference | Poi Graph Edit Distance | Reassembly Nostereo | E3 Graph Edit Distance Norm | E3 Heavy Atoms Difference Norm | Reassembly | All Ligands Equal | E3 Tanimoto Similarity |86|:-------------:|:------:|:------:|:---------------:|:-------------:|:-----------------------------:|:-------------------------------------------------------------------:|:-------------------:|:--------------------------:|:--------:|:------------------------------:|:---------:|:----------------------:|:---------------------------:|:--------:|:-------------------------------:|:--------------------------:|:-----------------------:|:-------------------------------:|:------------:|:---------------------------:|:-------------------------:|:---------:|:------:|:----------------------------------:|:-------------------------:|:----------------------:|:------------:|:-----------------------:|:----------------------------:|:--------------------------:|:--------------------------------------------------------------------:|:-------------------:|:---------------------------:|:------------------------------:|:----------:|:-----------------:|:----------------------:|87| 0.0005 | 7.8911 | 80000 | 0.3375 | 2.9994 | 0.2223 | inf | 0.0 | 0.0 | 0.9717 | 0.9961 | 0.7867 | 9.0605 | 0.9179 | 0.8268 | inf | 0.9717 | 0.9994 | 0.0813 | 0.8393 | 0.1211 | 0.9062 | 0.9179 | 0.8893 | 0.0019 | 0.9788 | inf | 0.9961 | 0.0 | inf | 2.4517 | 820644475920679939503384490879847350906393395732940812913213440.0000 | 0.6211 | inf | 0.0334 | 0.6011 | 0.5936 | 0.0 |88| 0.0005 | 9.8639 | 100000 | 0.3420 | 3.0002 | 0.1689 | 37181303116147309234962303999400365269286085344573508414341120.0000 | 0.0 | 0.0 | 0.9732 | 0.9963 | 0.7897 | 8.0244 | 0.9305 | 0.8302 | inf | 0.9732 | 0.9995 | 0.0690 | 0.8419 | 0.1076 | 1.0454 | 0.9305 | 0.9027 | -0.0046 | 0.9796 | inf | 0.9963 | 0.0 | inf | 2.0482 | inf | 0.6261 | inf | 0.0335 | 0.6073 | 0.5992 | 0.0 |89 90 91### Framework versions92 93- Transformers 4.44.294- Pytorch 2.4.1+cu12195- Datasets 3.0.096- Tokenizers 0.19.197