QWEN_without_time

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: 0.3017

• Balanced Accuracy: 0.8957

• Accuracy: 0.8957

• Micro F1: 0.8957

• Macro F1: 0.8957

• Weighted F1: 0.8957

• Classification Report: precision recall f1-score support

       0       0.90      0.89      0.90       386
       1       0.89      0.90      0.90       381
  

  accuracy 0.90 767 macro avg 0.90 0.90 0.90 767

weighted avg 0.90 0.90 0.90 767

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Balanced Accuracy	Accuracy	Micro F1	Macro F1	Weighted F1	Classification Report
0.5773	1.0	384	0.3372	0.8736	0.8735	0.8735	0.8735	0.8735	precision recall f1-score support

       0       0.88      0.87      0.87       386
       1       0.87      0.88      0.87       381

accuracy                           0.87       767

macro avg 0.87 0.87 0.87 767 weighted avg 0.87 0.87 0.87 767 | | 0.3341 | 2.0 | 768 | 0.4140 | 0.8624 | 0.8631 | 0.8631 | 0.8612 | 0.8613 | precision recall f1-score support

       0       0.80      0.97      0.88       386
       1       0.97      0.75      0.84       381

accuracy                           0.86       767

macro avg 0.88 0.86 0.86 767 weighted avg 0.88 0.86 0.86 767 | | 0.2934 | 3.0 | 1152 | 0.3017 | 0.8957 | 0.8957 | 0.8957 | 0.8957 | 0.8957 | precision recall f1-score support

       0       0.90      0.89      0.90       386
       1       0.89      0.90      0.90       381

accuracy                           0.90       767

macro avg 0.90 0.90 0.90 767 weighted avg 0.90 0.90 0.90 767 |

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1