ceva / README.md
dianamihalache27's picture
End of training
71dade0 verified
|
raw
history blame
2.38 kB
metadata
base_model: dianamihalache27/Twroberta-baseB_5epoch
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: ceva
    results: []

ceva

This model is a fine-tuned version of dianamihalache27/Twroberta-baseB_5epoch on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1932
  • Accuracy: 0.7714
  • F1: 0.2892
  • Precision: 0.2435
  • Recall: 0.3579
  • Precision Sarcastic: 0.3372
  • Recall Sarcastic: 0.4833
  • F1 Sarcastic: 0.3973

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: 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: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall Precision Sarcastic Recall Sarcastic F1 Sarcastic
No log 1.0 217 0.1618 0.7893 0.2947 0.2611 0.3395 0.3458 0.4611 0.3952
No log 2.0 434 0.1815 0.7629 0.3104 0.2560 0.4059 0.3299 0.5278 0.4060
0.0559 3.0 651 0.1762 0.8 0.2957 0.2991 0.3173 0.3721 0.4444 0.4051
0.0559 4.0 868 0.1811 0.7636 0.2933 0.2418 0.3727 0.3297 0.5111 0.4009
0.0245 5.0 1085 0.1932 0.7714 0.2892 0.2435 0.3579 0.3372 0.4833 0.3973

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1