<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
QuBERTa-finetuned-pos
This model is a fine-tuned version of Llamacha/QuBERTa on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4249
- Precision: 0.8372
- Recall: 0.8702
- F1: 0.8534
- Accuracy: 0.8623
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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 152 | 0.6146 | 0.6876 | 0.7482 | 0.7167 | 0.7360 |
No log | 2.0 | 304 | 0.4937 | 0.7554 | 0.8041 | 0.7790 | 0.7932 |
No log | 3.0 | 456 | 0.4525 | 0.7920 | 0.8238 | 0.8076 | 0.8200 |
0.5624 | 4.0 | 608 | 0.4294 | 0.8144 | 0.8426 | 0.8283 | 0.8391 |
0.5624 | 5.0 | 760 | 0.4245 | 0.8192 | 0.8521 | 0.8353 | 0.8445 |
0.5624 | 6.0 | 912 | 0.4357 | 0.8201 | 0.8607 | 0.8399 | 0.8480 |
0.3064 | 7.0 | 1064 | 0.4240 | 0.8308 | 0.8694 | 0.8497 | 0.8582 |
0.3064 | 8.0 | 1216 | 0.4231 | 0.8406 | 0.8757 | 0.8578 | 0.8653 |
0.3064 | 9.0 | 1368 | 0.4202 | 0.8389 | 0.8686 | 0.8535 | 0.8617 |
0.2227 | 10.0 | 1520 | 0.4249 | 0.8372 | 0.8702 | 0.8534 | 0.8623 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6