deberta-semeval25_justEN08_fold5
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 7.9713
- Precision Samples: 0.475
- Recall Samples: 0.475
- F1 Samples: 0.475
- Precision Macro: 0.9925
- Recall Macro: 0.4571
- F1 Macro: 0.4521
- Precision Micro: 0.475
- Recall Micro: 0.2262
- F1 Micro: 0.3065
- Precision Weighted: 0.8813
- Recall Weighted: 0.2262
- F1 Weighted: 0.1457
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision Samples | Recall Samples | F1 Samples | Precision Macro | Recall Macro | F1 Macro | Precision Micro | Recall Micro | F1 Micro | Precision Weighted | Recall Weighted | F1 Weighted |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
No log | 1.0 | 5 | 8.9279 | 1.0 | 0.0 | 0.0 | 1.0 | 0.4429 | 0.4429 | 1.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
8.5855 | 2.0 | 10 | 8.6667 | 1.0 | 0.0 | 0.0 | 1.0 | 0.4429 | 0.4429 | 1.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 |
8.5855 | 3.0 | 15 | 8.4430 | 0.5 | 0.475 | 0.475 | 0.9927 | 0.4571 | 0.4522 | 0.4872 | 0.2262 | 0.3089 | 0.8840 | 0.2262 | 0.1482 |
8.0997 | 4.0 | 20 | 8.2709 | 0.475 | 0.475 | 0.475 | 0.9925 | 0.4571 | 0.4521 | 0.475 | 0.2262 | 0.3065 | 0.8813 | 0.2262 | 0.1457 |
8.0997 | 5.0 | 25 | 8.1691 | 0.475 | 0.475 | 0.475 | 0.9925 | 0.4571 | 0.4521 | 0.475 | 0.2262 | 0.3065 | 0.8813 | 0.2262 | 0.1457 |
7.7542 | 6.0 | 30 | 8.0883 | 0.475 | 0.475 | 0.475 | 0.9925 | 0.4571 | 0.4521 | 0.475 | 0.2262 | 0.3065 | 0.8813 | 0.2262 | 0.1457 |
7.7542 | 7.0 | 35 | 8.0312 | 0.475 | 0.475 | 0.475 | 0.9925 | 0.4571 | 0.4521 | 0.475 | 0.2262 | 0.3065 | 0.8813 | 0.2262 | 0.1457 |
7.5757 | 8.0 | 40 | 7.9983 | 0.475 | 0.475 | 0.475 | 0.9925 | 0.4571 | 0.4521 | 0.475 | 0.2262 | 0.3065 | 0.8813 | 0.2262 | 0.1457 |
7.5757 | 9.0 | 45 | 7.9795 | 0.475 | 0.475 | 0.475 | 0.9925 | 0.4571 | 0.4521 | 0.475 | 0.2262 | 0.3065 | 0.8813 | 0.2262 | 0.1457 |
7.4644 | 10.0 | 50 | 7.9713 | 0.475 | 0.475 | 0.475 | 0.9925 | 0.4571 | 0.4521 | 0.475 | 0.2262 | 0.3065 | 0.8813 | 0.2262 | 0.1457 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.3.1
- Datasets 2.21.0
- Tokenizers 0.20.1
- Downloads last month
- 52
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support
Model tree for g-assismoraes/deberta-semeval25_justEN08_fold5
Base model
microsoft/deberta-v3-base