Edit model card

mdeberta-v3-base-finetuned-recores

This model is a fine-tuned version of microsoft/mdeberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6094
  • Accuracy: 0.2011

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: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 3000
  • num_epochs: 25

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.6112 1.0 1047 1.6094 0.1901
1.608 2.0 2094 1.6094 0.1873
1.6127 3.0 3141 1.6095 0.1983
1.6125 4.0 4188 1.6094 0.2424
1.6118 5.0 5235 1.6094 0.1956
1.6181 6.0 6282 1.6094 0.2094
1.6229 7.0 7329 1.6095 0.1680
1.6125 8.0 8376 1.6094 0.1736
1.6134 9.0 9423 1.6094 0.2066
1.6174 10.0 10470 1.6093 0.2204
1.6161 11.0 11517 1.6096 0.2121
1.6198 12.0 12564 1.6094 0.2039
1.6182 13.0 13611 1.6094 0.2287
1.6208 14.0 14658 1.6094 0.2287
1.6436 15.0 15705 1.6092 0.2287
1.6209 16.0 16752 1.6094 0.2094
1.6097 17.0 17799 1.6094 0.2094
1.6115 18.0 18846 1.6094 0.2149
1.6249 19.0 19893 1.6094 0.1956
1.6201 20.0 20940 1.6094 0.1763
1.6217 21.0 21987 1.6094 0.1956
1.6193 22.0 23034 1.6094 0.1846
1.6171 23.0 24081 1.6095 0.1983
1.6123 24.0 25128 1.6095 0.1846
1.6164 25.0 26175 1.6094 0.2011

Framework versions

  • Transformers 4.19.0
  • Pytorch 1.10.1+cu102
  • Datasets 2.2.1
  • Tokenizers 0.12.1
Downloads last month
1