metadata
base_model: youscan/ukr-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: ukr-roberta-base-finetuned-sarc
results: []
ukr-roberta-base-finetuned-sarc
This model is a fine-tuned version of youscan/ukr-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6150
- Accuracy: 0.7983
- Precision: 0.7945
- Recall: 0.8048
- F1: 0.7996
- Roc Auc: 0.7983
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: 1e-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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Roc Auc |
|---|---|---|---|---|---|---|---|---|
| 0.5014 | 1.0 | 538 | 0.4564 | 0.7844 | 0.8048 | 0.7509 | 0.7769 | 0.7844 |
| 0.4035 | 2.0 | 1076 | 0.4711 | 0.7918 | 0.8019 | 0.7751 | 0.7883 | 0.7918 |
| 0.314 | 3.0 | 1614 | 0.5327 | 0.7928 | 0.7933 | 0.7918 | 0.7926 | 0.7928 |
| 0.2431 | 4.0 | 2152 | 0.6150 | 0.7983 | 0.7945 | 0.8048 | 0.7996 | 0.7983 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2