esm2_t30_150M_UR50D-pfam-classification

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: 1.2090
• Accuracy: 0.7686

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 9

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.9966	222	3.0116	0.4560
No log	1.9978	445	2.3631	0.5747
2.9792	2.9989	668	1.9594	0.6399
2.9792	4.0	891	1.6825	0.6916
1.6634	4.9966	1113	1.4988	0.7316
1.6634	5.9978	1336	1.3650	0.7539
1.0252	6.9989	1559	1.2806	0.7627
1.0252	8.0	1782	1.2271	0.7699
1.0252	8.9697	1998	1.2090	0.7686

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1