Text Classification
English
halilbabacan's picture
Create README.md
1a88e2c verified
|
raw
history blame
3.64 kB
metadata
license: mit
datasets:
  - halilbabacan/combined_synthetic_cognitive_distortions
language:
  - en
metrics:
  - accuracy
pipeline_tag: text-classification

Epoch 1/3: 100%|██████████| 227/227 [01:15<00:00, 3.01it/s] Validation: 100%|██████████| 57/57 [00:06<00:00, 9.39it/s] Epoch: 1 Train Loss: 1.5372 Validation Loss: 0.8488 Accuracy: 0.7200 Error Rate: 0.2800 Epoch 2/3: 100%|██████████| 227/227 [01:17<00:00, 2.93it/s] Validation: 100%|██████████| 57/57 [00:06<00:00, 9.28it/s] Epoch: 2 Train Loss: 0.7906 Validation Loss: 0.7300 Accuracy: 0.7850 Error Rate: 0.2150 Epoch 3/3: 100%|██████████| 227/227 [01:17<00:00, 2.94it/s] Validation: 100%|██████████| 57/57 [00:06<00:00, 9.28it/s] Epoch: 3 Train Loss: 0.5461 Validation Loss: 0.7143 Accuracy: 0.7718 Error Rate: 0.2282

Sınıf Bazlı Metrikler:

Mind Reading: Precision: 0.8933 Recall: 0.7444 F1-Score: 0.8121 Support: 90

Overgeneralization: Precision: 0.5977 Recall: 0.6118 F1-Score: 0.6047 Support: 85

Magnification: Precision: 0.7015 Recall: 0.6026 F1-Score: 0.6483 Support: 78

Labelling: Precision: 0.7347 Recall: 0.9730 F1-Score: 0.8372 Support: 37

Personalization: Precision: 0.5800 Recall: 0.8657 F1-Score: 0.6946 Support: 67

Fortune-telling: Precision: 0.8608 Recall: 0.7816 F1-Score: 0.8193 Support: 87

Emotional Reasoning: Precision: 0.5676 Recall: 0.7500 F1-Score: 0.6462 Support: 56

Mental Filter: Precision: 1.0000 Recall: 1.0000 F1-Score: 1.0000 Support: 46

Should Statements: Precision: 1.0000 Recall: 1.0000 F1-Score: 1.0000 Support: 46

All-or-Nothing Thinking: Precision: 1.0000 Recall: 1.0000 F1-Score: 1.0000 Support: 23

Labeling: Precision: 0.7692 Recall: 0.2857 F1-Score: 0.4167 Support: 35

No Distortion: Precision: 0.9442 Recall: 0.9789 F1-Score: 0.9612 Support: 190

All-or-nothing thinking: Precision: 0.5000 Recall: 0.0625 F1-Score: 0.1111 Support: 16

Mental filter: Precision: 0.2500 Recall: 0.3750 F1-Score: 0.3000 Support: 24

Should statements: Precision: 0.6923 Recall: 0.3333 F1-Score: 0.4500 Support: 27

Sınıf Mind Reading: True Positive: 67 False Positive: 8 True Negative: 809 False Negative: 23

Sınıf Overgeneralization: True Positive: 52 False Positive: 35 True Negative: 787 False Negative: 33

Sınıf Magnification: True Positive: 47 False Positive: 20 True Negative: 809 False Negative: 31

Sınıf Labelling: True Positive: 36 False Positive: 13 True Negative: 857 False Negative: 1

Sınıf Personalization: True Positive: 58 False Positive: 42 True Negative: 798 False Negative: 9

Sınıf Fortune-telling: True Positive: 68 False Positive: 11 True Negative: 809 False Negative: 19

Sınıf Emotional Reasoning: True Positive: 42 False Positive: 32 True Negative: 819 False Negative: 14

Sınıf Mental Filter: True Positive: 46 False Positive: 0 True Negative: 861 False Negative: 0

Sınıf Should Statements: True Positive: 46 False Positive: 0 True Negative: 861 False Negative: 0

Sınıf All-or-Nothing Thinking: True Positive: 23 False Positive: 0 True Negative: 884 False Negative: 0

Sınıf Labeling: True Positive: 10 False Positive: 3 True Negative: 869 False Negative: 25

Sınıf No Distortion: True Positive: 186 False Positive: 11 True Negative: 706 False Negative: 4

Sınıf All-or-nothing thinking: True Positive: 1 False Positive: 1 True Negative: 890 False Negative: 15

Sınıf Mental filter: True Positive: 9 False Positive: 27 True Negative: 856 False Negative: 15

Sınıf Should statements: True Positive: 9 False Positive: 4 True Negative: 876 False Negative: 18