matr1xx's picture
End of training
452ee32 verified
metadata
base_model: allenai/scibert_scivocab_uncased
tags:
  - generated_from_trainer
model-index:
  - name: scibert_scivocab_uncased-finetuned-mol-mlm-0.3
    results: []

scibert_scivocab_uncased-finetuned-mol-mlm-0.3

This model is a fine-tuned version of allenai/scibert_scivocab_uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5049

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: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 12
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.8725 1.0 180 0.6730
0.6668 2.0 360 0.6203
0.6078 3.0 540 0.5739
0.5656 4.0 720 0.5537
0.5385 5.0 900 0.5483
0.5163 6.0 1080 0.5335
0.5043 7.0 1260 0.5350
0.4927 8.0 1440 0.5173
0.4841 9.0 1620 0.5093
0.4765 10.0 1800 0.5058
0.4709 11.0 1980 0.5104
0.4673 12.0 2160 0.5017

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.0.1
  • Datasets 2.16.1
  • Tokenizers 0.15.0