metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
model-index:
- name: elvis_bert_base
results: []
elvis_bert_base
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6325
- Rmse: 0.6731
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: 3e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rmse |
|---|---|---|---|---|
| 0.6635 | 1.0 | 1000 | 0.6325 | 0.6731 |
| 0.5302 | 2.0 | 2000 | 0.6340 | 0.6797 |
| 0.3606 | 3.0 | 3000 | 0.9009 | 0.6481 |
| 0.2501 | 4.0 | 4000 | 1.4259 | 0.6671 |
| 0.1369 | 5.0 | 5000 | 1.6598 | 0.6823 |
| 0.0979 | 6.0 | 6000 | 1.8117 | 0.6477 |
| 0.0495 | 7.0 | 7000 | 1.9325 | 0.6504 |
| 0.0388 | 8.0 | 8000 | 2.0611 | 0.6745 |
| 0.0321 | 9.0 | 9000 | 2.1235 | 0.6734 |
| 0.0233 | 10.0 | 10000 | 2.1389 | 0.6618 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3