metadata

license: mit
base_model: facebook/esm2_t6_8M_UR50D
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: esm2_t6_8M_UR50D-finetuned-epitope-june-12
    results: []

esm2_t6_8M_UR50D-finetuned-epitope-june-12

This model is a fine-tuned version of facebook/esm2_t6_8M_UR50D on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.5492
Accuracy: 0.8234

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: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 2
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4862	0.9997	1525	0.5349	0.8208
0.47	2.0	3051	0.5110	0.8239
0.4023	2.9990	4575	0.5492	0.8234

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.19.2
Tokenizers 0.19.1