metadata

license: mit
base_model: facebook/esm2_t30_150M_UR50D
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: esm2_t30_150M_UR50D-finetuned-localization
    results: []

esm2_t30_150M_UR50D-finetuned-localization

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: 0.4079
Accuracy: 0.8236
Ppv: 0.8115
Npv: 0.8374

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: 128
eval_batch_size: 128
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Ppv	Npv
No log	1.0	205	0.4267	0.8023	0.7698	0.8459
No log	2.0	410	0.4030	0.8173	0.7968	0.8421
0.4156	3.0	615	0.3984	0.8211	0.8099	0.8337
0.4156	4.0	820	0.4079	0.8236	0.8115	0.8374

Framework versions

Transformers 4.42.3
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1