emotion / README.md
darkbladecr's picture
update model card README.md
238063f
|
raw
history blame
1.67 kB
metadata
license: apache-2.0
base_model: bhadresh-savani/distilbert-base-uncased-emotion
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: emotion
    results: []

emotion

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

  • Loss: 1.3358
  • Accuracy: 0.4667

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy
2.2664 1.0 15 1.4388 0.4
1.4542 2.0 30 1.3942 0.4
1.2951 3.0 45 1.3433 0.4
1.1394 4.0 60 1.3303 0.4667
1.0582 5.0 75 1.3358 0.4667

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1
  • Datasets 2.14.0
  • Tokenizers 0.13.3