esm2_t12_35M_UR50D-finetuned-localization

This model is a fine-tuned version of facebook/esm2_t12_35M_UR50D on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5978
• Accuracy: 0.8

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
• 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	Accuracy
No log	1.0	147	0.4621	0.7846
No log	2.0	294	0.4769	0.7974
No log	3.0	441	0.5287	0.8
0.3616	4.0	588	0.5449	0.8051
0.3616	5.0	735	0.5978	0.8

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1.post103
• Datasets 3.1.0
• Tokenizers 0.20.4