<!-- 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. -->
fine-tune-bert-combined
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4606
- Accuracy: 0.7326
- F1: 0.6954
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.444 | 1.0 | 1819 | 0.6302 | 0.6948 | 0.6182 |
0.3182 | 2.0 | 3638 | 0.6042 | 0.7703 | 0.7508 |
0.2082 | 3.0 | 5457 | 0.9061 | 0.7064 | 0.6505 |
0.1301 | 4.0 | 7276 | 1.1842 | 0.7413 | 0.7262 |
0.0883 | 5.0 | 9095 | 1.6491 | 0.7529 | 0.7267 |
0.0564 | 6.0 | 10914 | 2.1418 | 0.7093 | 0.6429 |
0.0385 | 7.0 | 12733 | 2.0313 | 0.7384 | 0.7134 |
0.0156 | 8.0 | 14552 | 2.2918 | 0.7413 | 0.7245 |
0.0108 | 9.0 | 16371 | 2.3513 | 0.7413 | 0.7101 |
0.0131 | 10.0 | 18190 | 2.4606 | 0.7326 | 0.6954 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2