<!-- 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-rotten_tomatoes-from-scratch-target-conll2003
This model is a fine-tuned version of muhtasham/small-mlm-rotten_tomatoes-from-scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2814
- Precision: 0.5816
- Recall: 0.7099
- F1: 0.6394
- Accuracy: 0.9299
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 |
---|---|---|---|---|---|---|---|
0.6075 | 1.14 | 500 | 0.4273 | 0.3917 | 0.4366 | 0.4129 | 0.8743 |
0.3582 | 2.28 | 1000 | 0.3436 | 0.4459 | 0.5478 | 0.4916 | 0.8969 |
0.2718 | 3.42 | 1500 | 0.3134 | 0.4499 | 0.6254 | 0.5233 | 0.9032 |
0.2142 | 4.56 | 2000 | 0.2927 | 0.4969 | 0.6298 | 0.5555 | 0.9122 |
0.1751 | 5.69 | 2500 | 0.2815 | 0.5500 | 0.6570 | 0.5988 | 0.9192 |
0.1468 | 6.83 | 3000 | 0.2693 | 0.5472 | 0.6930 | 0.6115 | 0.9221 |
0.119 | 7.97 | 3500 | 0.2669 | 0.5506 | 0.6880 | 0.6117 | 0.9245 |
0.0959 | 9.11 | 4000 | 0.2817 | 0.5691 | 0.6747 | 0.6174 | 0.9267 |
0.0804 | 10.25 | 4500 | 0.2860 | 0.5572 | 0.7065 | 0.6230 | 0.9251 |
0.0687 | 11.39 | 5000 | 0.2814 | 0.5816 | 0.7099 | 0.6394 | 0.9299 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2