<!-- 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. -->
small-mlm-conll2003-from-scratch-target-conll2003
This model is a fine-tuned version of muhtasham/small-mlm-conll2003-from-scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3026
- Precision: 0.6374
- Recall: 0.7129
- F1: 0.6730
- Accuracy: 0.9340
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 |
---|---|---|---|---|---|---|---|
0.5707 | 1.14 | 500 | 0.3994 | 0.3895 | 0.4650 | 0.4239 | 0.8806 |
0.3406 | 2.28 | 1000 | 0.3272 | 0.4662 | 0.5498 | 0.5046 | 0.9016 |
0.257 | 3.42 | 1500 | 0.3064 | 0.4490 | 0.6331 | 0.5254 | 0.9043 |
0.2033 | 4.56 | 2000 | 0.2905 | 0.5185 | 0.6311 | 0.5693 | 0.9154 |
0.1636 | 5.69 | 2500 | 0.2773 | 0.5457 | 0.6585 | 0.5969 | 0.9213 |
0.1333 | 6.83 | 3000 | 0.2734 | 0.5615 | 0.6880 | 0.6183 | 0.9247 |
0.1072 | 7.97 | 3500 | 0.2737 | 0.5653 | 0.6863 | 0.6199 | 0.9263 |
0.0848 | 9.11 | 4000 | 0.2800 | 0.5913 | 0.7095 | 0.6450 | 0.9290 |
0.0687 | 10.25 | 4500 | 0.2878 | 0.6002 | 0.7164 | 0.6532 | 0.9302 |
0.0568 | 11.39 | 5000 | 0.3026 | 0.6374 | 0.7129 | 0.6730 | 0.9340 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2