vschem-sol102

wzqww23/vschem-sol102

vschem-sol102 is a machine learning model from wzqww23. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

33% of all-time downloads

All-time downloads

Public

Parameters

49M

6.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors294 MB · 85%

Parameter types

How the weights are stored.

BF1649M · 100%

Base models

ibm-research/GP-MoLFormer-Uniq

Model card

From the Hugging Face model README

vschem-sol102

This model is a fine-tuned version of ibm-research/GP-MoLFormer-Uniq on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2514
Rmse: 0.9112
Mae: 0.7027
R2: 0.3930

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0005
train_batch_size: 384
eval_batch_size: 1024
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
lr_scheduler_warmup_ratio: 0.05
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rmse	Mae	R2
0.2471	1.0	211	0.2720	0.9807	0.7292	0.4177
0.2855	2.0	422	0.2667	0.9668	0.7204	0.4341
0.2567	3.0	633	0.2736	0.9718	0.7360	0.4282
0.2071	4.0	844	0.2735	0.9591	0.7474	0.4431
0.2042	5.0	1055	0.2986	0.9993	0.7911	0.3954

Framework versions

Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

Library: transformers
Type: molformer
License: apache-2.0
Created: Dec 18, 2025
Updated: Dec 18, 2025