Hugging Face's logo

IIIT-L
/
indic-bert-finetuned-code-mixed-DS

Text Classification
Transformers
PyTorch
Safetensors
albert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
dipteshkanojia commited on
Commit
67e196f
•
1 Parent(s): 6a2004c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -11
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: 0.8981
23
- - Accuracy: 0.5594
24
- - Precision: 0.3838
25
- - Recall: 0.5263
26
- - F1: 0.4118
27
 
28
  ## Model description
29
 
@@ -48,17 +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: 10
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
- | 1.0941 | 2.0 | 497 | 1.0845 | 0.3441 | 0.3615 | 0.4180 | 0.2706 |
58
- | 1.0379 | 3.99 | 994 | 0.9775 | 0.5412 | 0.3779 | 0.5128 | 0.4003 |
59
- | 0.9509 | 5.99 | 1491 | 0.9271 | 0.5513 | 0.3752 | 0.5144 | 0.4043 |
60
- | 0.9152 | 7.98 | 1988 | 0.9047 | 0.5614 | 0.3852 | 0.5275 | 0.4131 |
61
- | 0.8953 | 9.98 | 2485 | 0.8981 | 0.5594 | 0.3838 | 0.5263 | 0.4118 |
 
 
 
 
 
62
 
63
 
64
  ### 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: 0.8647
23
+ - Accuracy: 0.5795
24
+ - Precision: 0.5485
25
+ - Recall: 0.5287
26
+ - F1: 0.4391
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
+ | 1.0937 | 2.0 | 497 | 1.0813 | 0.3602 | 0.3587 | 0.4257 | 0.2834 |
58
+ | 1.0189 | 3.99 | 994 | 0.9482 | 0.5493 | 0.3887 | 0.5246 | 0.4080 |
59
+ | 0.9208 | 5.99 | 1491 | 0.9002 | 0.5714 | 0.3813 | 0.5292 | 0.4170 |
60
+ | 0.8803 | 7.98 | 1988 | 0.8758 | 0.5654 | 0.3889 | 0.5300 | 0.4159 |
61
+ | 0.8482 | 9.98 | 2485 | 0.8657 | 0.5795 | 0.3867 | 0.5365 | 0.4228 |
62
+ | 0.8293 | 11.98 | 2982 | 0.8734 | 0.5835 | 0.3796 | 0.5298 | 0.4214 |
63
+ | 0.8131 | 13.97 | 3479 | 0.8567 | 0.5835 | 0.5018 | 0.5414 | 0.4350 |
64
+ | 0.8 | 15.97 | 3976 | 0.8547 | 0.5835 | 0.5610 | 0.5460 | 0.4361 |
65
+ | 0.7933 | 17.96 | 4473 | 0.8650 | 0.5775 | 0.5317 | 0.5252 | 0.4373 |
66
+ | 0.7835 | 19.96 | 4970 | 0.8647 | 0.5795 | 0.5485 | 0.5287 | 0.4391 |
67
 
68
 
69
  ### Framework versions