metadata
license: apache-2.0
library_name: peft
tags:
- QNLI
- generated_from_trainer
base_model: google-bert/bert-base-uncased
metrics:
- accuracy
model-index:
- name: check
results: []
check
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3991
- Accuracy: 0.8258
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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 | Accuracy |
|---|---|---|---|---|
| 0.6863 | 1.0 | 613 | 0.6746 | 0.6165 |
| 0.5276 | 2.0 | 1226 | 0.4910 | 0.7723 |
| 0.4828 | 3.0 | 1839 | 0.4693 | 0.7847 |
| 0.4682 | 4.0 | 2452 | 0.4413 | 0.8038 |
| 0.4692 | 5.0 | 3065 | 0.4330 | 0.8071 |
| 0.4387 | 6.0 | 3678 | 0.4344 | 0.8055 |
| 0.428 | 7.0 | 4291 | 0.4109 | 0.8191 |
| 0.4266 | 8.0 | 4904 | 0.4069 | 0.8208 |
| 0.4191 | 9.0 | 5517 | 0.4031 | 0.8233 |
| 0.434 | 10.0 | 6130 | 0.3991 | 0.8258 |
Framework versions
- PEFT 0.10.0
- Transformers 4.41.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1