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
Downloads last month
12
Safetensors
Model size
149M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for keanhean/esm2_t30_150M_UR50D-pfam-classification

Finetuned
(11)
this model