<!-- 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-tweet_eval-from-scratch-target-conll2003
This model is a fine-tuned version of muhtasham/small-mlm-tweet_eval-from-scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2818
- Precision: 0.6288
- Recall: 0.7415
- F1: 0.6805
- Accuracy: 0.9349
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 |
---|---|---|---|---|---|---|---|
0.6126 | 1.14 | 500 | 0.4262 | 0.3594 | 0.4480 | 0.3988 | 0.8717 |
0.3588 | 2.28 | 1000 | 0.3324 | 0.4554 | 0.5830 | 0.5113 | 0.8995 |
0.2618 | 3.42 | 1500 | 0.3179 | 0.4530 | 0.6437 | 0.5318 | 0.8997 |
0.204 | 4.56 | 2000 | 0.2764 | 0.5381 | 0.6424 | 0.5857 | 0.9177 |
0.162 | 5.69 | 2500 | 0.2695 | 0.5752 | 0.6658 | 0.6172 | 0.9244 |
0.13 | 6.83 | 3000 | 0.2556 | 0.5682 | 0.7035 | 0.6287 | 0.9260 |
0.1027 | 7.97 | 3500 | 0.2557 | 0.5946 | 0.7220 | 0.6521 | 0.9294 |
0.0811 | 9.11 | 4000 | 0.2638 | 0.6097 | 0.7154 | 0.6584 | 0.9325 |
0.0648 | 10.25 | 4500 | 0.2745 | 0.6105 | 0.7324 | 0.6659 | 0.9325 |
0.0533 | 11.39 | 5000 | 0.2818 | 0.6288 | 0.7415 | 0.6805 | 0.9349 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2