roberta-base_IA3_lr5e-05_bs4_epoch20_wd0.01

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

  • Loss: 4.8816

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: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss
19.9021 1.0 157 21.8572
19.0595 2.0 314 20.8634
18.1837 3.0 471 18.9005
14.9492 4.0 628 15.5693
12.6827 5.0 785 11.7522
9.1129 6.0 942 8.7107
7.9692 7.0 1099 6.9363
6.5195 8.0 1256 6.1572
5.932 9.0 1413 5.7736
5.8208 10.0 1570 5.5329
5.5728 11.0 1727 5.3653
5.447 12.0 1884 5.2402
5.2935 13.0 2041 5.1424
5.243 14.0 2198 5.0646
5.143 15.0 2355 5.0053
5.0448 16.0 2512 4.9583
5.0317 17.0 2669 4.9230
5.0272 18.0 2826 4.8999
4.9883 19.0 2983 4.8863
4.9729 20.0 3140 4.8816

Framework versions

  • PEFT 0.7.1
  • Transformers 4.36.2
  • Pytorch 2.0.1
  • Datasets 2.16.1
  • Tokenizers 0.15.0
Downloads last month
3
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for jysssacc/roberta-base_IA3_lr5e-05_bs4_epoch20_wd0.01

Adapter
(118)
this model