|
--- |
|
license: apache-2.0 |
|
base_model: tiiuae/falcon-7b |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: CuATR-falcon7b |
|
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. --> |
|
|
|
# CuATR-falcon7b |
|
|
|
This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4351 |
|
- Accuracy: 0.5652 |
|
- F1: 0.7222 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 7 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 1.4522 | 1.0 | 23 | 0.8684 | 0.5652 | 0.7222 | |
|
| 0.9683 | 2.0 | 46 | 0.7938 | 0.5652 | 0.7222 | |
|
| 1.5347 | 3.0 | 69 | 0.7187 | 0.5652 | 0.7222 | |
|
| 0.6854 | 4.0 | 92 | 0.6314 | 0.5652 | 0.7222 | |
|
| 0.5356 | 5.0 | 115 | 0.5313 | 0.5652 | 0.7222 | |
|
| 0.2435 | 6.0 | 138 | 0.4704 | 0.5652 | 0.7222 | |
|
| 0.3844 | 7.0 | 161 | 0.4351 | 0.5652 | 0.7222 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.1+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
