bert-large-uncased-pp-20000-1e-06-16
This model is a fine-tuned version of bert-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6833
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-06
- train_batch_size: 64
- eval_batch_size: 1024
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.7048 | 1.0 | 313 | 0.6895 |
0.6989 | 2.0 | 626 | 0.6877 |
0.6962 | 3.0 | 939 | 0.6864 |
0.6893 | 4.0 | 1252 | 0.6846 |
0.6878 | 5.0 | 1565 | 0.6838 |
0.684 | 6.0 | 1878 | 0.6834 |
0.6788 | 7.0 | 2191 | 0.6833 |
0.6755 | 8.0 | 2504 | 0.6836 |
0.6738 | 9.0 | 2817 | 0.6836 |
0.6676 | 10.0 | 3130 | 0.6833 |
0.6652 | 11.0 | 3443 | 0.6839 |
0.6636 | 12.0 | 3756 | 0.6842 |
0.6555 | 13.0 | 4069 | 0.6861 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 8
Inference API (serverless) is not available, repository is disabled.
Model tree for mhr2004/bert-large-uncased-pp-20000-1e-06-16
Base model
google-bert/bert-large-uncased
Finetuned
this model