Edit model card

kaz_legal_distilbert_full_corpus_3.0_6

This model is a fine-tuned version of kaisar-barlybay-sse/kaz_legal_distilbert_full_corpus_3.0 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.6273
  • Accuracy: 0.4471

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: 4
  • eval_batch_size: 4
  • 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
1.3908 1.0 501 1.3699 0.3593
1.2794 2.0 1002 1.4185 0.3972
1.0076 3.0 1503 1.5770 0.4311
0.7301 4.0 2004 2.1395 0.4172
0.5437 5.0 2505 2.2464 0.4511
0.4292 6.0 3006 2.6273 0.4471

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3
Downloads last month
8
Inference API (serverless) does not yet support transformers models for this pipeline type.