learn2therm / README.md
evankomp's picture
update model card README.md
46d6a31
|
raw
history blame
1.34 kB
metadata
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
model-index:
  - name: learn2therm
    results: []

learn2therm

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

  • Loss: 0.6942
  • F1: 0.0
  • Accuracy: 0.5125
  • Matthew: -0.0308
  • Cfm: [1025, 2, 973, 0]

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: 5e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 25
  • total_train_batch_size: 1600
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.26.0
  • Pytorch 2.0.1
  • Datasets 2.12.0
  • Tokenizers 0.13.3