metadata
base_model: dura-garage/nepberta2nepberta
tags:
- generated_from_trainer
model-index:
- name: finetuning-b2b
results: []
finetuning-b2b
This model is a fine-tuned version of dura-garage/nepberta2nepberta on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
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
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0038 | 0.5 | 1000 | 0.0012 |
| 0.0009 | 1.0 | 2000 | 0.0007 |
| 0.0052 | 1.5 | 3000 | 0.0002 |
| 0.0069 | 2.0 | 4000 | 0.0002 |
| 0.0011 | 2.5 | 5000 | 0.0003 |
| 0.0045 | 3.0 | 6000 | 0.0007 |
| 0.0012 | 3.5 | 7000 | 0.0002 |
| 0.0028 | 4.0 | 8000 | 0.0001 |
| 0.0001 | 4.5 | 9000 | 0.0004 |
| 0.0001 | 5.0 | 10000 | 0.0000 |
| 0.0092 | 5.5 | 11000 | 0.0001 |
| 0.0006 | 6.0 | 12000 | 0.0002 |
| 0.0003 | 6.5 | 13000 | 0.0000 |
| 0.0057 | 7.0 | 14000 | 0.0000 |
| 0.0 | 7.5 | 15000 | 0.0000 |
| 0.0093 | 8.0 | 16000 | 0.0000 |
| 0.03 | 8.5 | 17000 | 0.0002 |
| 0.0144 | 9.0 | 18000 | 0.0004 |
| 0.0018 | 9.5 | 19000 | 0.0000 |
| 0.0024 | 10.0 | 20000 | 0.0000 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.17.0
- Tokenizers 0.15.1