Edit model card

emotion-bert-large-uncased-balanced-lora

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

  • Loss: 0.1721
  • Accuracy: 0.942

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: 0.0005
  • train_batch_size: 64
  • eval_batch_size: 64
  • 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 Accuracy
No log 1.0 250 0.4374 0.86
0.7097 2.0 500 0.2582 0.9195
0.7097 3.0 750 0.2047 0.9345
0.1878 4.0 1000 0.1667 0.9385
0.1878 5.0 1250 0.1861 0.935
0.1306 6.0 1500 0.1871 0.9415
0.1306 7.0 1750 0.1720 0.943
0.1035 8.0 2000 0.1696 0.9425
0.1035 9.0 2250 0.1706 0.9415
0.0851 10.0 2500 0.1721 0.942

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.2
  • Pytorch 2.3.0
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
4
Inference Examples
Inference API (serverless) does not yet support peft models for this pipeline type.

Model tree for leonvanbokhorst/emotion-bert-large-uncased-balanced-lora

Adapter
(11)
this model

Dataset used to train leonvanbokhorst/emotion-bert-large-uncased-balanced-lora