<!-- 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. -->
gpt2-token-class
This model is a fine-tuned version of Jean-Baptiste/roberta-large-ner-english on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4239
- Precision: 0.8559
- Recall: 0.7666
- F1: 0.8020
- Accuracy: 0.9193
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: 7
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2451 | 1.0 | 1796 | 0.2658 | 0.8781 | 0.6962 | 0.7480 | 0.9099 |
0.1938 | 2.0 | 3592 | 0.2473 | 0.8683 | 0.7312 | 0.7778 | 0.9153 |
0.1452 | 3.0 | 5388 | 0.2614 | 0.8525 | 0.7588 | 0.7953 | 0.9172 |
0.1068 | 4.0 | 7184 | 0.3033 | 0.8491 | 0.7584 | 0.7940 | 0.9164 |
0.0792 | 5.0 | 8980 | 0.3507 | 0.8612 | 0.7586 | 0.7978 | 0.9190 |
0.0597 | 6.0 | 10776 | 0.3924 | 0.8569 | 0.7632 | 0.7999 | 0.9189 |
0.0479 | 7.0 | 12572 | 0.4239 | 0.8559 | 0.7666 | 0.8020 | 0.9193 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3