herbert-large-cased-upos
This model is a fine-tuned version of allegro/herbert-large-cased on the universal_dependencies dataset. It achieves the following results on the evaluation set:
- Loss: 0.0398
- Precision: 0.9876
- Recall: 0.9913
- F1: 0.9894
- Accuracy: 0.9953
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
Framework versions
- Transformers 4.39.3
- Pytorch 1.11.0a0+17540c5
- Datasets 2.21.0
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for izaitova/herbert-large-cased-upos
Base model
allegro/herbert-large-cased
Finetuned
this model
Dataset used to train izaitova/herbert-large-cased-upos
Evaluation results
- Precision on universal_dependenciesvalidation set self-reported0.988
- Recall on universal_dependenciesvalidation set self-reported0.991
- F1 on universal_dependenciesvalidation set self-reported0.989
- Accuracy on universal_dependenciesvalidation set self-reported0.995