Freesolv

This model is a fine-tuned version of ibm/MoLFormer-XL-both-10pct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 8.5598
• Mse: 8.5598

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• 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: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Mse
No log	1.0	32	12.5710	12.5710
No log	2.0	64	10.1404	10.1404
No log	3.0	96	9.0233	9.0233
20.1739	4.0	128	8.6011	8.6011
20.1739	5.0	160	8.5598	8.5598

Framework versions

• PEFT 0.14.0
• Transformers 4.47.1
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0