metadata
base_model: Qwen/Qwen2-7B
library_name: peft
license: apache-2.0
metrics:
- accuracy
- precision
- recall
tags:
- generated_from_trainer
model-index:
- name: Qwen2_7B_Task2_semantic_pred
results: []
Qwen2_7B_Task2_semantic_pred
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: 0.5963
- Accuracy: 0.8123
- Precision: 0.8123
- Recall: 0.8123
- F1 score: 0.8123
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 |
|---|---|---|---|---|---|---|---|
| 0.6405 | 0.5208 | 200 | 0.5790 | 0.7666 | 0.7666 | 0.7666 | 0.7666 |
| 0.4689 | 1.0417 | 400 | 0.9852 | 0.6649 | 0.6649 | 0.6649 | 0.6649 |
| 0.3635 | 1.5625 | 600 | 0.4249 | 0.8188 | 0.8188 | 0.8188 | 0.8188 |
| 0.3197 | 2.0833 | 800 | 0.7777 | 0.7353 | 0.7353 | 0.7353 | 0.7353 |
| 0.267 | 2.6042 | 1000 | 0.7223 | 0.7679 | 0.7679 | 0.7679 | 0.7679 |
| 0.2272 | 3.125 | 1200 | 0.4841 | 0.8201 | 0.8201 | 0.8201 | 0.8201 |
| 0.1848 | 3.6458 | 1400 | 0.4985 | 0.8227 | 0.8227 | 0.8227 | 0.8227 |
| 0.1744 | 4.1667 | 1600 | 0.6254 | 0.8044 | 0.8044 | 0.8044 | 0.8044 |
| 0.1402 | 4.6875 | 1800 | 0.5963 | 0.8123 | 0.8123 | 0.8123 | 0.8123 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.3.0
- Datasets 2.20.0
- Tokenizers 0.19.1