metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: google-bert/bert-base-uncased
metrics:
- accuracy
- f1
model-index:
- name: loha_fine_tuned_cb
results: []
loha_fine_tuned_cb
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: 5.8911
- Accuracy: 0.3182
- F1: 0.2555
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: 0.003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 400
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.8122 | 3.5714 | 50 | 1.9445 | 0.3182 | 0.1536 |
| 0.6951 | 7.1429 | 100 | 2.3078 | 0.3182 | 0.1536 |
| 0.4233 | 10.7143 | 150 | 1.7892 | 0.4545 | 0.4260 |
| 0.2006 | 14.2857 | 200 | 5.9008 | 0.3182 | 0.1591 |
| 0.0846 | 17.8571 | 250 | 5.5773 | 0.2727 | 0.1469 |
| 0.05 | 21.4286 | 300 | 5.9074 | 0.2727 | 0.1667 |
| 0.0167 | 25.0 | 350 | 5.0730 | 0.3182 | 0.2552 |
| 0.0069 | 28.5714 | 400 | 5.8911 | 0.3182 | 0.2555 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.40.1
- Pytorch 2.3.0
- Datasets 2.19.0
- Tokenizers 0.19.1