Hugging Face's logo

NaeemCSECUET18
/
banglabert-MLTC-BB

Text Classification
Transformers
Safetensors
electra
Generated from Trainer
Inference Endpoints
Model card Files Community
NaeemCSECUET18 commited on
Commit
7124129
·
verified ·
1 Parent(s): cf16ae3

End of training

Browse files
Files changed (2) hide show
  1. README.md +16 -19
  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: 0.3730
21
- - F1: 0.8628
22
- - Roc Auc: 0.8612
23
- - Accuracy: 0.5784
24
- - Hamming Loss: 0.1388
25
- - Jaccard Score: 0.7587
26
- - Zero One Loss: 0.4216
27
 
28
  ## Model description
29
 
@@ -43,8 +43,8 @@ More information needed
43
 
44
  The following hyperparameters were used during training:
45
  - learning_rate: 2e-05
46
- - train_batch_size: 8
47
- - eval_batch_size: 8
48
  - seed: 42
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
@@ -54,16 +54,13 @@ 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
- | 0.4126 | 1.0 | 146 | 0.4229 | 0.8333 | 0.8303 | 0.5527 | 0.1697 | 0.7143 | 0.4473 |
58
- | 0.381 | 2.0 | 292 | 0.3605 | 0.8551 | 0.8541 | 0.5835 | 0.1459 | 0.7469 | 0.4165 |
59
- | 0.2885 | 3.0 | 438 | 0.3745 | 0.8589 | 0.8521 | 0.5656 | 0.1478 | 0.7527 | 0.4344 |
60
- | 0.2324 | 4.0 | 584 | 0.3612 | 0.8597 | 0.8579 | 0.5835 | 0.1420 | 0.7539 | 0.4165 |
61
- | 0.2618 | 5.0 | 730 | 0.3458 | 0.8632 | 0.8631 | 0.5861 | 0.1369 | 0.7593 | 0.4139 |
62
- | 0.2535 | 6.0 | 876 | 0.3673 | 0.8611 | 0.8579 | 0.5758 | 0.1420 | 0.7561 | 0.4242 |
63
- | 0.1701 | 7.0 | 1022 | 0.3932 | 0.8559 | 0.8528 | 0.5681 | 0.1472 | 0.7481 | 0.4319 |
64
- | 0.1835 | 8.0 | 1168 | 0.3641 | 0.8668 | 0.8650 | 0.5887 | 0.1350 | 0.7648 | 0.4113 |
65
- | 0.1714 | 9.0 | 1314 | 0.3796 | 0.8617 | 0.8605 | 0.5707 | 0.1395 | 0.7570 | 0.4293 |
66
- | 0.1311 | 10.0 | 1460 | 0.3730 | 0.8628 | 0.8612 | 0.5784 | 0.1388 | 0.7587 | 0.4216 |
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: 0.3525
21
+ - F1: 0.8644
22
+ - Roc Auc: 0.8624
23
+ - Accuracy: 0.5938
24
+ - Hamming Loss: 0.1375
25
+ - Jaccard Score: 0.7612
26
+ - Zero One Loss: 0.4062
27
 
28
  ## Model description
29
 
 
43
 
44
  The following hyperparameters were used during training:
45
  - learning_rate: 2e-05
46
+ - train_batch_size: 16
47
+ - eval_batch_size: 16
48
  - seed: 42
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | Hamming Loss | Jaccard Score | Zero One Loss |
56
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|:------------:|:-------------:|:-------------:|
57
+ | 0.4962 | 1.0 | 73 | 0.4868 | 0.8020 | 0.7962 | 0.4730 | 0.2037 | 0.6694 | 0.5270 |
58
+ | 0.3992 | 2.0 | 146 | 0.3993 | 0.8420 | 0.8386 | 0.5656 | 0.1613 | 0.7272 | 0.4344 |
59
+ | 0.3163 | 3.0 | 219 | 0.3647 | 0.8616 | 0.8586 | 0.5810 | 0.1414 | 0.7569 | 0.4190 |
60
+ | 0.2545 | 4.0 | 292 | 0.3626 | 0.8666 | 0.8624 | 0.5861 | 0.1375 | 0.7646 | 0.4139 |
61
+ | 0.2464 | 5.0 | 365 | 0.3537 | 0.8626 | 0.8612 | 0.5835 | 0.1388 | 0.7584 | 0.4165 |
62
+ | 0.2534 | 6.0 | 438 | 0.3591 | 0.8600 | 0.8566 | 0.5707 | 0.1433 | 0.7544 | 0.4293 |
63
+ | 0.194 | 7.0 | 511 | 0.3525 | 0.8644 | 0.8624 | 0.5938 | 0.1375 | 0.7612 | 0.4062 |
 
 
 
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae68142c98c64126919ed8b14af309d7c1572afca4f349185d590d6b0a8881dc
3
  size 442505824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9209b7de48d738135d745cf39b96ef024af64a75d5c3021a2dad01fafcd18385
3
  size 442505824