Hugging Face's logo

callmesan
/
indic-sentence-bert-nli-roman-urdu-binary

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
callmesan commited on
Commit
24a1f79
•
1 Parent(s): dd4327d

End of training

Browse files
Files changed (2) hide show
  1. README.md +17 -12
  2. model.safetensors +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [l3cube-pune/indic-sentence-bert-nli](https://huggingface.co/l3cube-pune/indic-sentence-bert-nli) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.4274
25
- - Accuracy: 0.8852
26
- - Precision: 0.8845
27
- - Recall: 0.8859
28
- - F1: 0.8849
29
 
30
  ## Model description
31
 
@@ -44,7 +44,7 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 2e-05
48
  - train_batch_size: 32
49
  - eval_batch_size: 128
50
  - seed: 42
@@ -52,17 +52,22 @@ The following hyperparameters were used during training:
52
  - total_train_batch_size: 128
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: linear
55
- - num_epochs: 5
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
60
  |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
61
- | 0.6197 | 0.9912 | 56 | 0.5759 | 0.8414 | 0.8449 | 0.8375 | 0.8393 |
62
- | 0.4974 | 2.0 | 113 | 0.4997 | 0.8452 | 0.8517 | 0.8501 | 0.8452 |
63
- | 0.4404 | 2.9912 | 169 | 0.4445 | 0.8714 | 0.8711 | 0.8704 | 0.8707 |
64
- | 0.4106 | 4.0 | 226 | 0.4246 | 0.8664 | 0.8657 | 0.8660 | 0.8659 |
65
- | 0.392 | 4.9558 | 280 | 0.4196 | 0.8664 | 0.8664 | 0.8681 | 0.8663 |
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [l3cube-pune/indic-sentence-bert-nli](https://huggingface.co/l3cube-pune/indic-sentence-bert-nli) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.2789
25
+ - Accuracy: 0.9061
26
+ - Precision: 0.9058
27
+ - Recall: 0.9055
28
+ - F1: 0.9057
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 5e-05
48
  - train_batch_size: 32
49
  - eval_batch_size: 128
50
  - seed: 42
 
52
  - total_train_batch_size: 128
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: linear
55
+ - num_epochs: 10
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
60
  |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
61
+ | 0.4984 | 0.9912 | 56 | 0.4611 | 0.8452 | 0.8486 | 0.8489 | 0.8452 |
62
+ | 0.3582 | 2.0 | 113 | 0.3373 | 0.8826 | 0.8843 | 0.8802 | 0.8816 |
63
+ | 0.2724 | 2.9912 | 169 | 0.2869 | 0.8901 | 0.8894 | 0.8901 | 0.8897 |
64
+ | 0.2093 | 4.0 | 226 | 0.2754 | 0.8926 | 0.8922 | 0.8920 | 0.8921 |
65
+ | 0.1622 | 4.9912 | 282 | 0.2980 | 0.8989 | 0.9016 | 0.8961 | 0.8978 |
66
+ | 0.1235 | 6.0 | 339 | 0.3167 | 0.8889 | 0.8883 | 0.8884 | 0.8884 |
67
+ | 0.1125 | 6.9912 | 395 | 0.3369 | 0.8939 | 0.8973 | 0.8907 | 0.8926 |
68
+ | 0.0811 | 8.0 | 452 | 0.3535 | 0.8914 | 0.8906 | 0.8918 | 0.8911 |
69
+ | 0.0797 | 8.9912 | 508 | 0.3833 | 0.8914 | 0.8919 | 0.8898 | 0.8906 |
70
+ | 0.0585 | 9.9115 | 560 | 0.3809 | 0.8926 | 0.8924 | 0.8918 | 0.8920 |
71
 
72
 
73
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:433c7fdf1624154d668fcb0a01bc4e1de524e6ce39dfde04fd4d9617a920c2a5
3
  size 950254592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c1dc06b386f44450b52f392ae0a3e2f7aaa20a20f88bc65788aa2c8966a0c15
3
  size 950254592