<!-- 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. -->
tiny-mlm-wikitext-from-scratch-target-conll2003
This model is a fine-tuned version of muhtasham/tiny-mlm-wikitext-from-scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3285
- Precision: 0.4521
- Recall: 0.6104
- F1: 0.5194
- Accuracy: 0.9045
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- training_steps: 5000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.9995 | 1.14 | 500 | 0.6676 | 0.1574 | 0.1503 | 0.1538 | 0.8239 |
0.5765 | 2.28 | 1000 | 0.5452 | 0.2558 | 0.3120 | 0.2811 | 0.8510 |
0.4842 | 3.42 | 1500 | 0.4775 | 0.3120 | 0.4002 | 0.3507 | 0.8660 |
0.4146 | 4.56 | 2000 | 0.4244 | 0.3769 | 0.4761 | 0.4208 | 0.8826 |
0.3612 | 5.69 | 2500 | 0.3866 | 0.3858 | 0.5226 | 0.4439 | 0.8905 |
0.3229 | 6.83 | 3000 | 0.3641 | 0.4154 | 0.5547 | 0.4751 | 0.8968 |
0.2904 | 7.97 | 3500 | 0.3482 | 0.4208 | 0.5771 | 0.4867 | 0.8992 |
0.2641 | 9.11 | 4000 | 0.3387 | 0.4396 | 0.5863 | 0.5025 | 0.9021 |
0.2431 | 10.25 | 4500 | 0.3313 | 0.4455 | 0.5953 | 0.5096 | 0.9040 |
0.23 | 11.39 | 5000 | 0.3285 | 0.4521 | 0.6104 | 0.5194 | 0.9045 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2