<!-- 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-custom-tokenizer-target-rotten_tomatoes
This model is a fine-tuned version of muhtasham/small-mlm-conll2003-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7430
- Accuracy: 0.7158
- F1: 0.7155
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 | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6525 | 1.87 | 500 | 0.5692 | 0.7054 | 0.7029 |
| 0.3985 | 3.75 | 1000 | 0.6429 | 0.7186 | 0.7130 |
| 0.2904 | 5.62 | 1500 | 0.7378 | 0.7205 | 0.7199 |
| 0.2054 | 7.49 | 2000 | 0.9005 | 0.7195 | 0.7173 |
| 0.1568 | 9.36 | 2500 | 1.2897 | 0.6951 | 0.6907 |
| 0.1188 | 11.24 | 3000 | 1.3048 | 0.7223 | 0.7221 |
| 0.0911 | 13.11 | 3500 | 1.3360 | 0.7167 | 0.7167 |
| 0.0814 | 14.98 | 4000 | 1.5301 | 0.7073 | 0.7053 |
| 0.0592 | 16.85 | 4500 | 1.7430 | 0.7158 | 0.7155 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
