Hugging Face's logo

NaeemCSECUET18
/
banglabert-MLTC-BB1

Text Classification
Transformers
Safetensors
electra
Generated from Trainer
Inference Endpoints
Model card Files Community
NaeemCSECUET18 commited on
Commit
df8d06b
·
verified ·
1 Parent(s): 5c81d73

End of training

Browse files
Files changed (2) hide show
  1. README.md +12 -17
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [csebuetnlp/banglabert](https://huggingface.co/csebuetnlp/banglabert) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.3509
21
- - F1: 0.8640
22
- - Roc Auc: 0.8624
23
- - Accuracy: 0.5835
24
- - Hamming Loss: 0.1375
25
- - Jaccard Score: 0.7606
26
- - Zero One Loss: 0.4165
27
 
28
  ## Model description
29
 
@@ -54,16 +54,11 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | Hamming Loss | Jaccard Score | Zero One Loss |
56
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|:------------:|:-------------:|:-------------:|
57
- | 0.5844 | 1.0 | 49 | 0.5242 | 0.7746 | 0.7601 | 0.4010 | 0.2397 | 0.6321 | 0.5990 |
58
- | 0.4119 | 2.0 | 98 | 0.4220 | 0.8411 | 0.8341 | 0.5604 | 0.1658 | 0.7258 | 0.4396 |
59
- | 0.372 | 3.0 | 147 | 0.3828 | 0.8454 | 0.8425 | 0.5784 | 0.1575 | 0.7322 | 0.4216 |
60
- | 0.3187 | 4.0 | 196 | 0.3637 | 0.8595 | 0.8566 | 0.5913 | 0.1433 | 0.7536 | 0.4087 |
61
- | 0.285 | 5.0 | 245 | 0.3482 | 0.8638 | 0.8611 | 0.5784 | 0.1388 | 0.7603 | 0.4216 |
62
- | 0.2781 | 6.0 | 294 | 0.3554 | 0.8598 | 0.8573 | 0.5861 | 0.1427 | 0.7542 | 0.4139 |
63
- | 0.2286 | 7.0 | 343 | 0.3528 | 0.8599 | 0.8579 | 0.5810 | 0.1420 | 0.7542 | 0.4190 |
64
- | 0.254 | 8.0 | 392 | 0.3589 | 0.8683 | 0.8650 | 0.5938 | 0.1350 | 0.7672 | 0.4062 |
65
- | 0.2625 | 9.0 | 441 | 0.3537 | 0.8644 | 0.8624 | 0.5887 | 0.1375 | 0.7612 | 0.4113 |
66
- | 0.2333 | 10.0 | 490 | 0.3509 | 0.8640 | 0.8624 | 0.5835 | 0.1375 | 0.7606 | 0.4165 |
67
 
68
 
69
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [csebuetnlp/banglabert](https://huggingface.co/csebuetnlp/banglabert) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.3600
21
+ - F1: 0.8593
22
+ - Roc Auc: 0.8580
23
+ - Accuracy: 0.5733
24
+ - Hamming Loss: 0.1420
25
+ - Jaccard Score: 0.7533
26
+ - Zero One Loss: 0.4267
27
 
28
  ## Model description
29
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | Hamming Loss | Jaccard Score | Zero One Loss |
56
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|:------------:|:-------------:|:-------------:|
57
+ | 0.3266 | 1.0 | 49 | 0.3574 | 0.8629 | 0.8592 | 0.5810 | 0.1407 | 0.7588 | 0.4190 |
58
+ | 0.2635 | 2.0 | 98 | 0.3531 | 0.8645 | 0.8618 | 0.5938 | 0.1382 | 0.7614 | 0.4062 |
59
+ | 0.27 | 3.0 | 147 | 0.3520 | 0.8553 | 0.8541 | 0.5835 | 0.1459 | 0.7472 | 0.4165 |
60
+ | 0.2254 | 4.0 | 196 | 0.3627 | 0.8622 | 0.8592 | 0.5913 | 0.1407 | 0.7577 | 0.4087 |
61
+ | 0.1966 | 5.0 | 245 | 0.3600 | 0.8593 | 0.8580 | 0.5733 | 0.1420 | 0.7533 | 0.4267 |
 
 
 
 
 
62
 
63
 
64
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b82e5407aaddc42cc6b49c2a92e8a67cfb6d39425dd37184bab5d935edb3fb7
3
  size 442505824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bc41a20a0171bbd19572e4ab077fe8789a7208b4b6871df0a83e16b72e0b83e
3
  size 442505824