<!-- 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. -->
bert_base_72
This model is a fine-tuned version of gokuls/bert_base_48 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.3795
- Accuracy: 0.4262
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: 1e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
5.6041 | 0.08 | 10000 | 5.5567 | 0.1751 |
5.4727 | 0.16 | 20000 | 5.3950 | 0.1953 |
5.3385 | 0.25 | 30000 | 5.2277 | 0.2150 |
5.2034 | 0.33 | 40000 | 5.0608 | 0.2335 |
4.7808 | 0.41 | 50000 | 4.5612 | 0.2910 |
4.1997 | 0.49 | 60000 | 4.0041 | 0.3519 |
3.804 | 0.57 | 70000 | 3.6509 | 0.3906 |
3.5517 | 0.66 | 80000 | 3.3795 | 0.4262 |
Framework versions
- Transformers 4.30.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3