esm2_t30_150M_UR50D-finetuned-SO2F

This model is a fine-tuned version of facebook/esm2_t30_150M_UR50D on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6608
• Accuracy: 0.7158
• Precision: 0.1682
• Recall: 0.5068
• F1: 0.2526
• Auc: 0.6223
• Mcc: 0.1585

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Auc	Mcc
No log	1.0	108	0.6768	0.6886	0.1465	0.4740	0.2238	0.5925	0.1175
No log	2.0	216	0.6646	0.6935	0.1628	0.5397	0.2502	0.6247	0.1573
No log	3.0	324	0.6608	0.7158	0.1682	0.5068	0.2526	0.6223	0.1585

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2