<!-- 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. -->
deberta-v3-NER-ind
This model is a fine-tuned version of microsoft/deberta-v3-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1461
- Precision: 0.7969
- Recall: 0.8346
- F1: 0.8153
- Accuracy: 0.9531
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
- gradient_accumulation_steps: 3
- total_train_batch_size: 96
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.1757 | 0.4 | 1000 | 0.1635 | 0.7737 | 0.8197 | 0.7960 | 0.9481 |
0.161 | 0.8 | 2000 | 0.1567 | 0.7794 | 0.8260 | 0.8020 | 0.9502 |
0.1365 | 1.2 | 3000 | 0.1517 | 0.7919 | 0.8321 | 0.8115 | 0.9522 |
0.1325 | 1.59 | 4000 | 0.1468 | 0.7947 | 0.8349 | 0.8143 | 0.9536 |
0.1302 | 1.99 | 5000 | 0.1461 | 0.7969 | 0.8346 | 0.8153 | 0.9531 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3