metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: Qwen/Qwen2-7B
metrics:
- accuracy
- precision
- recall
model-index:
- name: Qwen_less_data_SUPNT
results: []
Qwen_less_data_SUPNT
This model is a fine-tuned version of Qwen/Qwen2-7B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8747
- Accuracy: 0.7567
- Precision: 0.6860
- Recall: 0.9467
- F1 score: 0.7955
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 score |
|---|---|---|---|---|---|---|---|
| 0.6563 | 1.0 | 200 | 0.8186 | 0.7533 | 0.7209 | 0.8267 | 0.7702 |
| 0.3346 | 2.0 | 400 | 0.9649 | 0.7 | 0.6351 | 0.94 | 0.7581 |
| 0.2537 | 3.0 | 600 | 0.9052 | 0.7133 | 0.6468 | 0.94 | 0.7663 |
| 0.1608 | 4.0 | 800 | 1.0086 | 0.7167 | 0.6484 | 0.9467 | 0.7696 |
| 0.1159 | 5.0 | 1000 | 0.8747 | 0.7567 | 0.6860 | 0.9467 | 0.7955 |
Framework versions
- PEFT 0.11.1
- Transformers 4.44.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1