metadata
base_model: houdini001/BERT2BERT_try
tags:
- generated_from_trainer
model-index:
- name: BERT2BERT_try_ep11
results: []
BERT2BERT_try_ep11
This model is a fine-tuned version of houdini001/BERT2BERT_try on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0240
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.012 | 1.57 | 1000 | 0.0237 |
| 0.0024 | 3.14 | 2000 | 0.0238 |
| 0.0009 | 4.72 | 3000 | 0.0234 |
| 0.0004 | 6.29 | 4000 | 0.0240 |
| 0.0003 | 7.86 | 5000 | 0.0237 |
| 0.0003 | 9.43 | 6000 | 0.0240 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2