<!-- 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. -->
Classfication_AlBERT
This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9871
- Accuracy: 0.6
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: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 10 | 0.7858 | 0.8947 |
No log | 2.0 | 20 | 0.7008 | 0.8421 |
No log | 3.0 | 30 | 0.6431 | 0.8421 |
No log | 4.0 | 40 | 0.5523 | 0.7895 |
No log | 5.0 | 50 | 0.4920 | 0.8947 |
No log | 6.0 | 60 | 0.6924 | 0.7368 |
No log | 7.0 | 70 | 0.3422 | 0.8947 |
No log | 8.0 | 80 | 0.8117 | 0.7368 |
No log | 9.0 | 90 | 0.3063 | 0.8947 |
No log | 10.0 | 100 | 0.7765 | 0.6842 |
No log | 11.0 | 110 | 0.4689 | 0.8421 |
No log | 12.0 | 120 | 1.0065 | 0.6842 |
No log | 13.0 | 130 | 0.6344 | 0.7895 |
No log | 14.0 | 140 | 0.9131 | 0.7895 |
No log | 15.0 | 150 | 0.9815 | 0.7895 |
No log | 16.0 | 160 | 0.7772 | 0.8421 |
No log | 17.0 | 170 | 0.8548 | 0.7895 |
No log | 18.0 | 180 | 0.9509 | 0.7895 |
No log | 19.0 | 190 | 0.9574 | 0.7895 |
No log | 20.0 | 200 | 0.9562 | 0.7895 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2