Text Classification
English

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

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Dataset used to train halilbabacan/roberta_cognitive_distortions_gpt