<!-- 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. -->
pos-ner-tagging-v4
This model is a fine-tuned version of om-ashish-soni/pos-ner-tagging-v3 on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6642
- Precision: 0.9243
- Recall: 0.9264
- F1: 0.9244
- Accuracy: 0.9264
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.98 | 54 | 0.6425 | 0.9254 | 0.9272 | 0.9250 | 0.9272 |
No log | 1.99 | 109 | 0.6624 | 0.9239 | 0.9261 | 0.9240 | 0.9261 |
No log | 2.99 | 164 | 0.6593 | 0.9245 | 0.9267 | 0.9245 | 0.9267 |
No log | 3.99 | 219 | 0.6608 | 0.9251 | 0.9270 | 0.9250 | 0.9270 |
No log | 4.99 | 274 | 0.6698 | 0.9246 | 0.9269 | 0.9245 | 0.9269 |
No log | 6.0 | 329 | 0.6648 | 0.9246 | 0.9264 | 0.9244 | 0.9264 |
No log | 7.0 | 384 | 0.6651 | 0.9244 | 0.9266 | 0.9245 | 0.9266 |
No log | 7.87 | 432 | 0.6642 | 0.9243 | 0.9264 | 0.9244 | 0.9264 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3