<!-- 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. -->
1L-BERT-finetuned-newcode
This model is a fine-tuned version of Youssef320/LSTM-finetuned-50label-15epoch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0668
- Top 1 Macro F1 Score: 0.1385
- Top 1 Weighted F1score: 0.1902
- Top 3 Macro F1 Score: 0.2868
- Top3 3 Weighted F1 Score : 0.3758
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: 0.0002
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 2048
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 3.0
Training results
Training Loss | Epoch | Step | Validation Loss | Top 1 Macro F1 Score | Top 1 Weighted F1score | Top 3 Macro F1 Score | Top3 3 Weighted F1 Score |
---|---|---|---|---|---|---|---|
2.8006 | 0.13 | 32 | 3.1069 | 0.1217 | 0.1745 | 0.2614 | 0.3568 |
2.8197 | 0.26 | 64 | 3.0678 | 0.1271 | 0.1797 | 0.2715 | 0.3654 |
2.7933 | 0.4 | 96 | 3.0518 | 0.1279 | 0.1819 | 0.2714 | 0.3661 |
2.7852 | 0.53 | 128 | 3.0463 | 0.1322 | 0.1853 | 0.2787 | 0.3699 |
2.7847 | 0.66 | 160 | 3.0273 | 0.1294 | 0.1817 | 0.2773 | 0.3725 |
2.7899 | 0.79 | 192 | 3.0185 | 0.1316 | 0.1877 | 0.2769 | 0.3717 |
2.793 | 0.93 | 224 | 3.0140 | 0.1332 | 0.1864 | 0.2794 | 0.3731 |
2.6818 | 1.06 | 256 | 3.0629 | 0.1345 | 0.1879 | 0.2829 | 0.3739 |
2.6676 | 1.19 | 288 | 3.0798 | 0.1335 | 0.1867 | 0.2806 | 0.3724 |
2.6859 | 1.32 | 320 | 3.0595 | 0.1320 | 0.1845 | 0.2787 | 0.3704 |
2.6939 | 1.45 | 352 | 3.0650 | 0.1321 | 0.1841 | 0.2801 | 0.3710 |
2.7114 | 1.59 | 384 | 3.0594 | 0.1319 | 0.1841 | 0.2823 | 0.3735 |
2.7414 | 1.72 | 416 | 3.0475 | 0.1340 | 0.1864 | 0.2788 | 0.3710 |
2.7102 | 1.85 | 448 | 3.0464 | 0.1347 | 0.1883 | 0.2817 | 0.3741 |
2.7537 | 1.98 | 480 | 3.0270 | 0.1344 | 0.1879 | 0.2794 | 0.3736 |
2.616 | 2.12 | 512 | 3.0929 | 0.1361 | 0.1883 | 0.2798 | 0.3706 |
2.621 | 2.25 | 544 | 3.0821 | 0.1347 | 0.1867 | 0.2785 | 0.3709 |
2.6409 | 2.38 | 576 | 3.0870 | 0.1352 | 0.1873 | 0.2806 | 0.3705 |
2.6904 | 2.51 | 608 | 3.0735 | 0.1349 | 0.1867 | 0.2854 | 0.3748 |
2.6531 | 2.64 | 640 | 3.0732 | 0.1357 | 0.1895 | 0.2820 | 0.3731 |
2.6643 | 2.78 | 672 | 3.0677 | 0.1374 | 0.1896 | 0.2814 | 0.3729 |
2.6948 | 2.91 | 704 | 3.0668 | 0.1385 | 0.1902 | 0.2868 | 0.3758 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.1+cu102
- Datasets 2.0.0
- Tokenizers 0.11.0