tiny-mlm-rotten_tomatoes-from-scratch-custom-tokenizer-target-conll2003
This model is a fine-tuned version of muhtasham/tiny-mlm-rotten_tomatoes-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3866
- Precision: 0.2926
- Recall: 0.4611
- F1: 0.3580
- Accuracy: 0.8772
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 |
|---|---|---|---|---|---|---|---|
| 1.0779 | 1.14 | 500 | 0.7741 | 0.0628 | 0.0628 | 0.0628 | 0.7972 |
| 0.6749 | 2.28 | 1000 | 0.6240 | 0.1095 | 0.1542 | 0.1281 | 0.8198 |
| 0.5795 | 3.42 | 1500 | 0.5582 | 0.1644 | 0.2497 | 0.1983 | 0.8358 |
| 0.5224 | 4.56 | 2000 | 0.5173 | 0.1843 | 0.3007 | 0.2286 | 0.8456 |
| 0.4832 | 5.69 | 2500 | 0.4865 | 0.1964 | 0.3394 | 0.2488 | 0.8528 |
| 0.4491 | 6.83 | 3000 | 0.4519 | 0.2300 | 0.3746 | 0.2850 | 0.8621 |
| 0.4138 | 7.97 | 3500 | 0.4238 | 0.2540 | 0.4214 | 0.3170 | 0.8684 |
| 0.3843 | 9.11 | 4000 | 0.4093 | 0.2598 | 0.4313 | 0.3243 | 0.8711 |
| 0.3638 | 10.25 | 4500 | 0.3973 | 0.2734 | 0.4465 | 0.3392 | 0.8741 |
| 0.3483 | 11.39 | 5000 | 0.3866 | 0.2926 | 0.4611 | 0.3580 | 0.8772 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2