rishavranaut / QWEN_with_time

QWEN_with_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: 0.3495

• Balanced Accuracy: 0.8801

• Accuracy: 0.8801

• Micro F1: 0.8801

• Macro F1: 0.8800

• Weighted F1: 0.8800

• Classification Report: precision recall f1-score support

       0       0.89      0.87      0.88       386
       1       0.87      0.89      0.88       381
  

  accuracy 0.88 767 macro avg 0.88 0.88 0.88 767

weighted avg 0.88 0.88 0.88 767

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

       0       0.89      0.76      0.82       386
       1       0.79      0.91      0.84       381

accuracy                           0.83       767

macro avg 0.84 0.83 0.83 767 weighted avg 0.84 0.83 0.83 767 | | 0.3513 | 2.0 | 768 | 0.4065 | 0.8639 | 0.8644 | 0.8644 | 0.8634 | 0.8635 | precision recall f1-score support

       0       0.82      0.94      0.88       386
       1       0.93      0.78      0.85       381

accuracy                           0.86       767

macro avg 0.87 0.86 0.86 767 weighted avg 0.87 0.86 0.86 767 | | 0.2858 | 3.0 | 1152 | 0.3495 | 0.8801 | 0.8801 | 0.8801 | 0.8800 | 0.8800 | precision recall f1-score support

       0       0.89      0.87      0.88       386
       1       0.87      0.89      0.88       381

accuracy                           0.88       767

macro avg 0.88 0.88 0.88 767 weighted avg 0.88 0.88 0.88 767 |

Framework versions

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