|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: google-bert/bert-base-uncased |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: lora_fine_tuned_cb |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# lora_fine_tuned_cb |
|
|
|
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4310 |
|
- Accuracy: 0.3182 |
|
- F1: 0.1536 |
|
|
|
## 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 | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:| |
|
| 0.8568 | 3.5714 | 50 | 2.3106 | 0.3182 | 0.1536 | |
|
| 0.8465 | 7.1429 | 100 | 1.3703 | 0.3182 | 0.1536 | |
|
| 0.7884 | 10.7143 | 150 | 1.3701 | 0.3182 | 0.1536 | |
|
| 0.7275 | 14.2857 | 200 | 1.5024 | 0.3182 | 0.1536 | |
|
| 0.7691 | 17.8571 | 250 | 1.3990 | 0.3182 | 0.1536 | |
|
| 0.742 | 21.4286 | 300 | 1.3898 | 0.3182 | 0.1536 | |
|
| 0.7094 | 25.0 | 350 | 1.4059 | 0.3182 | 0.1536 | |
|
| 0.7238 | 28.5714 | 400 | 1.4310 | 0.3182 | 0.1536 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.1.dev0 |
|
- Transformers 4.40.1 |
|
- Pytorch 2.3.0 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
