Hugging Face's logo

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

Text Classification
Transformers
PyTorch
Safetensors
albert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
dipteshkanojia commited on
Commit
d7c65da
•
1 Parent(s): ec86292

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -17
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: 1.0631
23
- - Accuracy: 0.28
24
- - Precision: 0.3767
25
- - Recall: 0.3569
26
- - F1: 0.1792
27
 
28
  ## Model description
29
 
@@ -42,28 +42,43 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - learning_rate: 1e-06
46
  - train_batch_size: 16
47
  - eval_batch_size: 32
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
- | 1.0974 | 0.99 | 99 | 1.0955 | 0.3 | 0.2936 | 0.3566 | 0.2146 |
58
- | 1.0936 | 1.98 | 198 | 1.0918 | 0.245 | 0.0817 | 0.3333 | 0.1312 |
59
- | 1.0907 | 2.97 | 297 | 1.0883 | 0.245 | 0.0817 | 0.3333 | 0.1312 |
60
- | 1.0867 | 3.96 | 396 | 1.0842 | 0.245 | 0.0817 | 0.3333 | 0.1312 |
61
- | 1.0827 | 4.95 | 495 | 1.0795 | 0.245 | 0.0817 | 0.3333 | 0.1312 |
62
- | 1.0781 | 5.94 | 594 | 1.0743 | 0.25 | 0.4154 | 0.3367 | 0.1384 |
63
- | 1.0683 | 6.93 | 693 | 1.0692 | 0.25 | 0.4154 | 0.3367 | 0.1384 |
64
- | 1.0629 | 7.92 | 792 | 1.0656 | 0.265 | 0.3504 | 0.3468 | 0.1595 |
65
- | 1.067 | 8.91 | 891 | 1.0637 | 0.275 | 0.3703 | 0.3535 | 0.1727 |
66
- | 1.0604 | 9.9 | 990 | 1.0631 | 0.28 | 0.3767 | 0.3569 | 0.1792 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
 
68
 
69
  ### 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: 1.0941
23
+ - Accuracy: 0.275
24
+ - Precision: 0.3056
25
+ - Recall: 0.3467
26
+ - F1: 0.1803
27
 
28
  ## Model description
29
 
 
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
+ - learning_rate: 1e-07
46
  - train_batch_size: 16
47
  - eval_batch_size: 32
48
  - seed: 43
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
+ - num_epochs: 25
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
+ | 1.0988 | 0.99 | 99 | 1.0984 | 0.3 | 0.3611 | 0.3661 | 0.2750 |
58
+ | 1.0981 | 1.98 | 198 | 1.0980 | 0.29 | 0.2713 | 0.3568 | 0.1997 |
59
+ | 1.0981 | 2.97 | 297 | 1.0977 | 0.315 | 0.3029 | 0.3736 | 0.2259 |
60
+ | 1.0976 | 3.96 | 396 | 1.0974 | 0.3 | 0.2816 | 0.3601 | 0.2122 |
61
+ | 1.0976 | 4.95 | 495 | 1.0971 | 0.295 | 0.2780 | 0.3601 | 0.2041 |
62
+ | 1.097 | 5.94 | 594 | 1.0968 | 0.29 | 0.2680 | 0.3533 | 0.2012 |
63
+ | 1.0962 | 6.93 | 693 | 1.0965 | 0.3 | 0.2816 | 0.3601 | 0.2122 |
64
+ | 1.0963 | 7.92 | 792 | 1.0963 | 0.29 | 0.2761 | 0.3533 | 0.2012 |
65
+ | 1.0969 | 8.91 | 891 | 1.0961 | 0.3 | 0.2895 | 0.3601 | 0.2122 |
66
+ | 1.0958 | 9.9 | 990 | 1.0958 | 0.3 | 0.2895 | 0.3601 | 0.2122 |
67
+ | 1.0959 | 10.89 | 1089 | 1.0956 | 0.3 | 0.2983 | 0.3601 | 0.2122 |
68
+ | 1.0953 | 11.88 | 1188 | 1.0954 | 0.3 | 0.2983 | 0.3601 | 0.2122 |
69
+ | 1.0955 | 12.87 | 1287 | 1.0952 | 0.295 | 0.3019 | 0.3567 | 0.2067 |
70
+ | 1.0948 | 13.86 | 1386 | 1.0951 | 0.295 | 0.3083 | 0.3601 | 0.2040 |
71
+ | 1.095 | 14.85 | 1485 | 1.0949 | 0.29 | 0.3013 | 0.3568 | 0.1983 |
72
+ | 1.0951 | 15.84 | 1584 | 1.0948 | 0.29 | 0.3013 | 0.3568 | 0.1983 |
73
+ | 1.0948 | 16.83 | 1683 | 1.0946 | 0.29 | 0.3143 | 0.3568 | 0.1982 |
74
+ | 1.0942 | 17.82 | 1782 | 1.0945 | 0.29 | 0.3291 | 0.3568 | 0.1982 |
75
+ | 1.0949 | 18.81 | 1881 | 1.0944 | 0.28 | 0.3145 | 0.3500 | 0.1863 |
76
+ | 1.095 | 19.8 | 1980 | 1.0943 | 0.275 | 0.3056 | 0.3467 | 0.1803 |
77
+ | 1.0945 | 20.79 | 2079 | 1.0943 | 0.275 | 0.3056 | 0.3467 | 0.1803 |
78
+ | 1.0942 | 21.78 | 2178 | 1.0942 | 0.275 | 0.3056 | 0.3467 | 0.1803 |
79
+ | 1.0938 | 22.77 | 2277 | 1.0942 | 0.275 | 0.3056 | 0.3467 | 0.1803 |
80
+ | 1.0953 | 23.76 | 2376 | 1.0941 | 0.275 | 0.3056 | 0.3467 | 0.1803 |
81
+ | 1.0943 | 24.75 | 2475 | 1.0941 | 0.275 | 0.3056 | 0.3467 | 0.1803 |
82
 
83
 
84
  ### Framework versions