<!-- 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-custom-tokenizer-target-conll2003
This model is a fine-tuned version of muhtasham/tiny-mlm-conll2003-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3519
- Precision: 0.4521
- Recall: 0.5990
- F1: 0.5152
- Accuracy: 0.9001
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 |
---|---|---|---|---|---|---|---|
0.9087 | 1.14 | 500 | 0.6605 | 0.2378 | 0.1520 | 0.1854 | 0.8258 |
0.51 | 2.28 | 1000 | 0.5308 | 0.2599 | 0.3129 | 0.2839 | 0.8546 |
0.4331 | 3.42 | 1500 | 0.4741 | 0.3499 | 0.4145 | 0.3795 | 0.8727 |
0.3751 | 4.56 | 2000 | 0.4309 | 0.3909 | 0.4783 | 0.4302 | 0.8821 |
0.3283 | 5.69 | 2500 | 0.4053 | 0.4271 | 0.5278 | 0.4721 | 0.8886 |
0.2964 | 6.83 | 3000 | 0.3853 | 0.4342 | 0.5587 | 0.4887 | 0.8925 |
0.2691 | 7.97 | 3500 | 0.3727 | 0.4417 | 0.5774 | 0.5005 | 0.8951 |
0.2458 | 9.11 | 4000 | 0.3666 | 0.4253 | 0.5848 | 0.4925 | 0.8954 |
0.2258 | 10.25 | 4500 | 0.3628 | 0.4514 | 0.5852 | 0.5096 | 0.8982 |
0.2143 | 11.39 | 5000 | 0.3519 | 0.4521 | 0.5990 | 0.5152 | 0.9001 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2