<!-- 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_attempt10
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: 0.5285
- Precision: 0.4333
- Recall: 0.1102
- F1: 0.1757
- Accuracy: 0.9417
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: 100
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 128 | 0.3044 | 0.0 | 0.0 | 0.0 | 0.9385 |
No log | 2.0 | 256 | 0.2727 | 0.1341 | 0.0932 | 0.11 | 0.9370 |
No log | 3.0 | 384 | 0.3383 | 0.2973 | 0.0932 | 0.1419 | 0.9413 |
0.2087 | 4.0 | 512 | 0.3512 | 0.3171 | 0.1102 | 0.1635 | 0.9409 |
0.2087 | 5.0 | 640 | 0.3298 | 0.175 | 0.1186 | 0.1414 | 0.9383 |
0.2087 | 6.0 | 768 | 0.3793 | 0.2209 | 0.1610 | 0.1863 | 0.9363 |
0.2087 | 7.0 | 896 | 0.5285 | 0.4333 | 0.1102 | 0.1757 | 0.9417 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1