Edit model card

scibert_claim_id_2e-05

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

  • Loss: 0.0162
  • Accuracy: 0.9962
  • F1: 0.9880
  • Precision: 0.9889
  • Recall: 0.9870

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: 6

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.3131 1.0 666 0.2551 0.8880 0.5518 0.7419 0.4392
0.267 2.0 1332 0.1821 0.9280 0.7636 0.7875 0.7410
0.2245 3.0 1998 0.0942 0.9695 0.9034 0.8968 0.9101
0.1135 4.0 2664 0.0514 0.9845 0.9517 0.9339 0.9702
0.0821 5.0 3330 0.0223 0.9944 0.9822 0.9808 0.9837
0.0618 6.0 3996 0.0162 0.9962 0.9880 0.9889 0.9870

Framework versions

  • Transformers 4.28.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3
Downloads last month
8
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.