Hugging Face's logo

bonurtek
/
custom-flan-t5-small-hallucination-classification

Text Classification
Transformers
TensorBoard
Safetensors
t5
Generated from Trainer
text-generation-inference
Model card Files Metrics Community
1
bonurtek commited on
Commit
0dd7817
·
verified ·
1 Parent(s): fd91ce6

End of training

Browse files
Files changed (1) hide show
  1. README.md +13 -10
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.6767
24
- - Precision: 0.7253
25
- - Recall: 0.7289
26
- - F1: 0.7248
27
- - Accuracy: 0.7289
28
 
29
  ## Model description
30
 
@@ -49,16 +49,19 @@ The following hyperparameters were used during training:
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - num_epochs: 2
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | 0.8953 | 0.4016 | 100 | 0.8406 | 0.6192 | 0.5994 | 0.5096 | 0.5994 |
59
- | 0.7764 | 0.8032 | 200 | 0.7486 | 0.7113 | 0.7088 | 0.6951 | 0.7088 |
60
- | 0.7031 | 1.2048 | 300 | 0.7159 | 0.7358 | 0.7309 | 0.7201 | 0.7309 |
61
- | 0.6345 | 1.6064 | 400 | 0.6767 | 0.7253 | 0.7289 | 0.7248 | 0.7289 |
 
 
 
62
 
63
 
64
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.6832
24
+ - Precision: 0.7473
25
+ - Recall: 0.7470
26
+ - F1: 0.7393
27
+ - Accuracy: 0.7470
28
 
29
  ## Model description
30
 
 
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 3
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 0.9007 | 0.4016 | 100 | 0.8154 | 0.6926 | 0.6596 | 0.6202 | 0.6596 |
59
+ | 0.7915 | 0.8032 | 200 | 0.7602 | 0.7181 | 0.6867 | 0.6585 | 0.6867 |
60
+ | 0.7089 | 1.2048 | 300 | 0.6769 | 0.7323 | 0.7329 | 0.7250 | 0.7329 |
61
+ | 0.6381 | 1.6064 | 400 | 0.6954 | 0.7338 | 0.7329 | 0.7240 | 0.7329 |
62
+ | 0.6528 | 2.0080 | 500 | 0.6510 | 0.7423 | 0.7410 | 0.7318 | 0.7410 |
63
+ | 0.5652 | 2.4096 | 600 | 0.6856 | 0.7340 | 0.7339 | 0.7303 | 0.7339 |
64
+ | 0.5446 | 2.8112 | 700 | 0.6832 | 0.7473 | 0.7470 | 0.7393 | 0.7470 |
65
 
66
 
67
  ### Framework versions