<!-- 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. -->
assignment2_attempt11
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6058
- Precision: 0.2642
- Recall: 0.1186
- F1: 0.1637
- Accuracy: 0.9370
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 128 | 0.3124 | 0.2308 | 0.0254 | 0.0458 | 0.9401 |
No log | 2.0 | 256 | 0.2862 | 0.1636 | 0.0763 | 0.1040 | 0.9353 |
No log | 3.0 | 384 | 0.3899 | 0.2093 | 0.0763 | 0.1118 | 0.9359 |
0.1996 | 4.0 | 512 | 0.4161 | 0.3095 | 0.1102 | 0.1625 | 0.9382 |
0.1996 | 5.0 | 640 | 0.4845 | 0.3077 | 0.1017 | 0.1529 | 0.9392 |
0.1996 | 6.0 | 768 | 0.4841 | 0.2692 | 0.1186 | 0.1647 | 0.9365 |
0.1996 | 7.0 | 896 | 0.4987 | 0.2258 | 0.1186 | 0.1556 | 0.9349 |
0.0254 | 8.0 | 1024 | 0.5512 | 0.2766 | 0.1102 | 0.1576 | 0.9370 |
0.0254 | 9.0 | 1152 | 0.5772 | 0.3171 | 0.1102 | 0.1635 | 0.9379 |
0.0254 | 10.0 | 1280 | 0.5764 | 0.2586 | 0.1271 | 0.1705 | 0.9342 |
0.0254 | 11.0 | 1408 | 0.5964 | 0.2917 | 0.1186 | 0.1687 | 0.9380 |
0.005 | 12.0 | 1536 | 0.5952 | 0.2642 | 0.1186 | 0.1637 | 0.9368 |
0.005 | 13.0 | 1664 | 0.5980 | 0.2593 | 0.1186 | 0.1628 | 0.9367 |
0.005 | 14.0 | 1792 | 0.6033 | 0.2642 | 0.1186 | 0.1637 | 0.9370 |
0.005 | 15.0 | 1920 | 0.6058 | 0.2642 | 0.1186 | 0.1637 | 0.9370 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1