Hugging Face's logo

IIIT-L
/
indic-bert-finetuned-TRAC-DS

Text Classification
Transformers
PyTorch
albert
Generated from Trainer
Model card Files
xet
 Community
1
dipteshkanojia commited on
Commit
7b0811a
·
1 Parent(s): 160fbe1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -12
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [ai4bharat/indic-bert](https://huggingface.co/ai4bharat/indic-bert) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.9926
23
- - Accuracy: 0.5752
24
- - Precision: 0.5471
25
- - Recall: 0.5312
26
- - F1: 0.5317
27
 
28
  ## Model description
29
 
@@ -48,18 +48,22 @@ The following hyperparameters were used during training:
48
  - seed: 43
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
- - num_epochs: 15
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
- | 1.0766 | 1.99 | 612 | 1.0368 | 0.5008 | 0.4082 | 0.4523 | 0.3761 |
58
- | 1.019 | 3.99 | 1224 | 1.0099 | 0.5703 | 0.6030 | 0.5048 | 0.4500 |
59
- | 0.9998 | 5.98 | 1836 | 1.0017 | 0.5801 | 0.5578 | 0.5223 | 0.5051 |
60
- | 0.9853 | 7.97 | 2448 | 0.9962 | 0.5735 | 0.5489 | 0.5373 | 0.5393 |
61
- | 0.9736 | 9.97 | 3060 | 0.9936 | 0.5760 | 0.5516 | 0.5287 | 0.5270 |
62
- | 0.964 | 11.96 | 3672 | 0.9926 | 0.5752 | 0.5471 | 0.5312 | 0.5317 |
 
 
 
 
63
 
64
 
65
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [ai4bharat/indic-bert](https://huggingface.co/ai4bharat/indic-bert) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.9922
23
+ - Accuracy: 0.5825
24
+ - Precision: 0.5493
25
+ - Recall: 0.5412
26
+ - F1: 0.5428
27
 
28
  ## Model description
29
 
 
48
  - seed: 43
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
+ - num_epochs: 20
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
+ | 1.0755 | 1.99 | 612 | 1.0346 | 0.5057 | 0.4072 | 0.4554 | 0.3806 |
58
+ | 1.0175 | 3.99 | 1224 | 1.0096 | 0.5678 | 0.6135 | 0.5011 | 0.4422 |
59
+ | 0.9974 | 5.98 | 1836 | 1.0010 | 0.5776 | 0.5637 | 0.5140 | 0.4799 |
60
+ | 0.9812 | 7.97 | 2448 | 0.9960 | 0.5694 | 0.5426 | 0.5283 | 0.5298 |
61
+ | 0.9675 | 9.97 | 3060 | 0.9956 | 0.5776 | 0.5565 | 0.5422 | 0.5442 |
62
+ | 0.9542 | 11.96 | 3672 | 0.9925 | 0.5882 | 0.5601 | 0.5420 | 0.5419 |
63
+ | 0.944 | 13.95 | 4284 | 0.9907 | 0.5866 | 0.5525 | 0.5441 | 0.5454 |
64
+ | 0.9347 | 15.95 | 4896 | 0.9921 | 0.5858 | 0.5527 | 0.5441 | 0.5456 |
65
+ | 0.9271 | 17.94 | 5508 | 0.9906 | 0.5931 | 0.5596 | 0.5482 | 0.5490 |
66
+ | 0.9236 | 19.93 | 6120 | 0.9922 | 0.5825 | 0.5493 | 0.5412 | 0.5428 |
67
 
68
 
69
  ### Framework versions