metadata
license: apache-2.0
base_model: tiiuae/falcon-7b
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: CuATR-falcon7b-v1
results: []
CuATR-falcon7b-v1
This model is a fine-tuned version of tiiuae/falcon-7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.0246
- Accuracy: 0.5
- F1: 0.6667
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 |
|---|---|---|---|---|---|
| 3.8889 | 0.92 | 3 | 3.0637 | 0.5 | 0.6667 |
| 5.8673 | 1.85 | 6 | 3.0774 | 0.5 | 0.6667 |
| 3.9181 | 2.77 | 9 | 3.0334 | 0.5 | 0.6667 |
| 3.8567 | 4.0 | 13 | 3.0286 | 0.5 | 0.6667 |
| 1.9671 | 4.92 | 16 | 3.0071 | 0.5 | 0.6667 |
| 1.9456 | 5.85 | 19 | 3.0315 | 0.5 | 0.6667 |
| 5.8213 | 6.46 | 21 | 3.0246 | 0.5 | 0.6667 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0