metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: bert-base-uncased
datasets:
- swag
metrics:
- accuracy
model-index:
- name: fine-tuned-bert-base-uncased-swag-peft
results: []
fine-tuned-bert-base-uncased-swag-peft
This model is a fine-tuned version of bert-base-uncased on the swag dataset. It achieves the following results on the evaluation set:
- Loss: 0.6912
- Accuracy: 0.7347
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: 1.5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.02 | 1.0 | 1150 | 0.8192 | 0.6860 |
0.9222 | 2.0 | 2300 | 0.7436 | 0.7128 |
0.8859 | 3.0 | 3450 | 0.7166 | 0.7247 |
0.8639 | 4.0 | 4600 | 0.7008 | 0.7295 |
0.8689 | 5.0 | 5750 | 0.6954 | 0.7335 |
0.8639 | 6.0 | 6900 | 0.6912 | 0.7347 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1