Edit model card

deberta-v3-large-finetuned-ner-10epochs

This model is a fine-tuned version of microsoft/deberta-v3-large on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0776
  • Precision: 0.9247
  • Recall: 0.9531
  • F1: 0.9387
  • Accuracy: 0.9890

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
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.0415 1.0 2261 0.0479 0.8894 0.9572 0.9220 0.9861
0.039 2.0 4522 0.0415 0.9051 0.9498 0.9269 0.9871
0.0304 3.0 6783 0.0390 0.9086 0.9579 0.9326 0.9883
0.0275 4.0 9044 0.0383 0.9146 0.9528 0.9333 0.9887
0.0224 5.0 11305 0.0421 0.9122 0.9583 0.9346 0.9884
0.0172 6.0 13566 0.0459 0.9204 0.9568 0.9382 0.9890
0.0122 7.0 15827 0.0561 0.9273 0.9429 0.9350 0.9885
0.0096 8.0 18088 0.0616 0.9223 0.9568 0.9393 0.9891
0.0051 9.0 20349 0.0718 0.9240 0.9568 0.9401 0.9890
0.0034 10.0 22610 0.0776 0.9247 0.9531 0.9387 0.9890

Framework versions

  • Transformers 4.30.1
  • Pytorch 2.0.1+cu117
  • Datasets 2.12.0
  • Tokenizers 0.13.3
Downloads last month
3
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.