Edit model card

N_bert_sst5_padding80model

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 4.1055
  • Accuracy: 0.5335

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.3295 1.0 534 1.2788 0.4231
1.0046 2.0 1068 1.1005 0.5362
0.7632 3.0 1602 1.1567 0.5357
0.588 4.0 2136 1.4030 0.5308
0.4198 5.0 2670 1.6242 0.5244
0.3036 6.0 3204 1.8412 0.5385
0.222 7.0 3738 2.2298 0.5299
0.1677 8.0 4272 2.4165 0.5376
0.1407 9.0 4806 2.7191 0.5285
0.1199 10.0 5340 3.1297 0.5226
0.0916 11.0 5874 3.3297 0.5466
0.0716 12.0 6408 3.4776 0.5385
0.0717 13.0 6942 3.6198 0.5339
0.047 14.0 7476 3.7826 0.5376
0.0322 15.0 8010 3.8744 0.5294
0.0268 16.0 8544 4.0318 0.5145
0.0204 17.0 9078 4.0118 0.5380
0.0201 18.0 9612 4.0902 0.5308
0.0149 19.0 10146 4.0749 0.5357
0.012 20.0 10680 4.1055 0.5335

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.13.3
Downloads last month
12

Finetuned from