Edit model card

emotion-turkish19

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

  • Loss: 0.4518
  • Accuracy: 0.9333

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: 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 71 0.2237 0.9333
No log 2.0 142 0.2419 0.9333
No log 3.0 213 0.3137 0.9238
No log 4.0 284 0.3441 0.9143
No log 5.0 355 0.3309 0.9524
No log 6.0 426 0.3131 0.9524
No log 7.0 497 0.3892 0.9333
0.1143 8.0 568 0.4482 0.9238
0.1143 9.0 639 0.4669 0.9238
0.1143 10.0 710 0.4518 0.9333

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
111M params
Tensor type
F32
·

Finetuned from