<!-- 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-conll2003-from-scratch-target-conll2003
This model is a fine-tuned version of muhtasham/tiny-mlm-conll2003-from-scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3255
- Precision: 0.4607
- Recall: 0.6060
- F1: 0.5234
- Accuracy: 0.9053
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 |
---|---|---|---|---|---|---|---|
1.0233 | 1.14 | 500 | 0.6786 | 0.1712 | 0.1419 | 0.1552 | 0.8249 |
0.5801 | 2.28 | 1000 | 0.5489 | 0.2545 | 0.2928 | 0.2723 | 0.8497 |
0.4936 | 3.42 | 1500 | 0.4847 | 0.3008 | 0.3612 | 0.3282 | 0.8619 |
0.4297 | 4.56 | 2000 | 0.4325 | 0.3697 | 0.4478 | 0.4050 | 0.8785 |
0.3753 | 5.69 | 2500 | 0.3901 | 0.3922 | 0.5126 | 0.4444 | 0.8892 |
0.3337 | 6.83 | 3000 | 0.3638 | 0.4135 | 0.5401 | 0.4684 | 0.8958 |
0.2989 | 7.97 | 3500 | 0.3460 | 0.4300 | 0.5786 | 0.4934 | 0.8993 |
0.2716 | 9.11 | 4000 | 0.3359 | 0.4375 | 0.5890 | 0.5021 | 0.9022 |
0.2493 | 10.25 | 4500 | 0.3320 | 0.4489 | 0.5867 | 0.5086 | 0.9035 |
0.2374 | 11.39 | 5000 | 0.3255 | 0.4607 | 0.6060 | 0.5234 | 0.9053 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2