QWEN_FACT_updates

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: 0.5144

• Balanced Accuracy: 0.7801

• Accuracy: 0.7998

• Micro F1: 0.7998

• Macro F1: 0.7392

• Weighted F1: 0.8114

• Classification Report: precision recall f1-score support

       0       0.92      0.81      0.86       857
       1       0.52      0.75      0.61       232
  

  accuracy 0.80 1089 macro avg 0.72 0.78 0.74 1089

weighted avg 0.84 0.80 0.81 1089

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	Accuracy	Balanced Accuracy	Classification Report	Validation Loss	Macro F1	Micro F1	Weighted F1
0.6846	1.0	391	0.7980	0.7553	precision recall f1-score support

       0       0.91      0.83      0.87       857
       1       0.52      0.68      0.59       232

accuracy                           0.80      1089

macro avg 0.71 0.76 0.73 1089 weighted avg 0.82 0.80 0.81 1089 | 0.5173 | 0.7278 | 0.7980 | 0.8071 | | 0.5021 | 2.0 | 782 | 0.8044 | 0.7673 | precision recall f1-score support

       0       0.91      0.83      0.87       857
       1       0.53      0.70      0.60       232

accuracy                           0.80      1089

macro avg 0.72 0.77 0.74 1089 weighted avg 0.83 0.80 0.81 1089 | 0.4834 | 0.7374 | 0.8044 | 0.8135 | | 0.408 | 3.0 | 1173 | 0.8356 | 0.7667 | precision recall f1-score support

       0       0.90      0.89      0.89       857
       1       0.61      0.65      0.63       232

accuracy                           0.84      1089

macro avg 0.75 0.77 0.76 1089 weighted avg 0.84 0.84 0.84 1089 | 0.4296 | 0.7605 | 0.8356 | 0.8375 | | 0.3032 | 4.0 | 1564 | 0.7511 | 0.7712 | precision recall f1-score support

       0       0.93      0.74      0.82       857
       1       0.45      0.81      0.58       232

accuracy                           0.75      1089

macro avg 0.69 0.77 0.70 1089 weighted avg 0.83 0.75 0.77 1089 | 0.5927 | 0.7015 | 0.7511 | 0.7714 | | 0.234 | 5.0 | 1955 | 0.5144 | 0.7801 | 0.7998 | 0.7998 | 0.7392 | 0.8114 | precision recall f1-score support

       0       0.92      0.81      0.86       857
       1       0.52      0.75      0.61       232

accuracy                           0.80      1089

macro avg 0.72 0.78 0.74 1089 weighted avg 0.84 0.80 0.81 1089 |

Framework versions

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