metadata
tags:
- generated_from_trainer
model-index:
- name: BERT2BERT_try_epoch15
results: []
BERT2BERT_try_epoch15
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0176
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0145 | 1.57 | 1000 | 0.0147 |
| 0.0058 | 3.14 | 2000 | 0.0157 |
| 0.002 | 4.72 | 3000 | 0.0167 |
| 0.0012 | 6.29 | 4000 | 0.0154 |
| 0.0005 | 7.86 | 5000 | 0.0155 |
| 0.0004 | 9.43 | 6000 | 0.0159 |
| 0.0005 | 11.01 | 7000 | 0.0167 |
| 0.0004 | 12.58 | 8000 | 0.0172 |
| 0.0003 | 14.15 | 9000 | 0.0176 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2