Hugging Face's logo

gokuls
/
bert_12_layer_model_v3_48_massive

Text Classification
Transformers
PyTorch
hybridbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
gokuls commited on
Commit
1fcb2c4
·
1 Parent(s): 22336b2

End of training

Browse files
Files changed (2) hide show
  1. README.md +18 -18
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.8598130841121495
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [gokuls/bert_12_layer_model_v3_complete_training_48](https://huggingface.co/gokuls/bert_12_layer_model_v3_complete_training_48) on the massive dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.8706
35
- - Accuracy: 0.8598
36
 
37
  ## Model description
38
 
@@ -64,21 +64,21 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | 2.151 | 1.0 | 180 | 1.0701 | 0.7083 |
68
- | 0.9461 | 2.0 | 360 | 0.8522 | 0.7737 |
69
- | 0.6903 | 3.0 | 540 | 0.7244 | 0.8165 |
70
- | 0.5397 | 4.0 | 720 | 0.7617 | 0.8160 |
71
- | 0.4321 | 5.0 | 900 | 0.7426 | 0.8234 |
72
- | 0.3281 | 6.0 | 1080 | 0.7274 | 0.8392 |
73
- | 0.2678 | 7.0 | 1260 | 0.8035 | 0.8308 |
74
- | 0.2237 | 8.0 | 1440 | 0.7729 | 0.8431 |
75
- | 0.1689 | 9.0 | 1620 | 0.8122 | 0.8470 |
76
- | 0.1338 | 10.0 | 1800 | 0.8137 | 0.8455 |
77
- | 0.1002 | 11.0 | 1980 | 0.8369 | 0.8534 |
78
- | 0.0735 | 12.0 | 2160 | 0.8526 | 0.8554 |
79
- | 0.055 | 13.0 | 2340 | 0.8546 | 0.8554 |
80
- | 0.0362 | 14.0 | 2520 | 0.8706 | 0.8598 |
81
- | 0.0242 | 15.0 | 2700 | 0.8828 | 0.8598 |
82
 
83
 
84
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.8607968519429414
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [gokuls/bert_12_layer_model_v3_complete_training_48](https://huggingface.co/gokuls/bert_12_layer_model_v3_complete_training_48) on the massive dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.9214
35
+ - Accuracy: 0.8608
36
 
37
  ## Model description
38
 
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 1.7608 | 1.0 | 180 | 0.9351 | 0.7482 |
68
+ | 0.8417 | 2.0 | 360 | 0.8314 | 0.7841 |
69
+ | 0.6057 | 3.0 | 540 | 0.7307 | 0.8160 |
70
+ | 0.4715 | 4.0 | 720 | 0.6995 | 0.8382 |
71
+ | 0.3766 | 5.0 | 900 | 0.7602 | 0.8273 |
72
+ | 0.2933 | 6.0 | 1080 | 0.7537 | 0.8357 |
73
+ | 0.2321 | 7.0 | 1260 | 0.7966 | 0.8426 |
74
+ | 0.1873 | 8.0 | 1440 | 0.8015 | 0.8396 |
75
+ | 0.1447 | 9.0 | 1620 | 0.8281 | 0.8392 |
76
+ | 0.1079 | 10.0 | 1800 | 0.8665 | 0.8446 |
77
+ | 0.0781 | 11.0 | 1980 | 0.8758 | 0.8500 |
78
+ | 0.0573 | 12.0 | 2160 | 0.8646 | 0.8515 |
79
+ | 0.0383 | 13.0 | 2340 | 0.9121 | 0.8603 |
80
+ | 0.024 | 14.0 | 2520 | 0.8963 | 0.8593 |
81
+ | 0.015 | 15.0 | 2700 | 0.9214 | 0.8608 |
82
 
83
 
84
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ff0a9d2d132da7b59dd35b9b9a76be4381d2c4190b99666b3eafe6d5344a0ef
3
  size 472126013
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d97faec223e648f88ae2aaef9a61e2ff115fa000219d2bf43943a8f1eb4db3a8
3
  size 472126013