Hugging Face's logo

jsl5710
/
MBERT_uncased_SupervisedContrastiveCrossEntropyLoss_full_ft

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
jsl5710 commited on
Commit
fd66c2f
·
verified ·
1 Parent(s): 9c84d3f

jslai/MBERT_uncased_SupervisedContrastiveCrossEntropyLoss_full_ft_word_order_head_to_tail_20241212-040231

Browse files
Files changed (3) hide show
  1. README.md +9 -9
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -21,12 +21,12 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Accuracy: 0.736
25
- - F1: 0.8451
26
- - Precision: 0.7332
27
- - Recall: 0.9972
28
- - Roc Auc: 0.5274
29
- - Loss: 1.1691
30
 
31
  ## Model description
32
 
@@ -61,9 +61,9 @@ The following hyperparameters were used during training:
61
 
62
  | Training Loss | Epoch | Step | Accuracy | F1 | Precision | Recall | Roc Auc | Validation Loss |
63
  |:-------------:|:-----:|:----:|:--------:|:------:|:---------:|:------:|:-------:|:---------------:|
64
- | No log | 0.992 | 62 | 0.722 | 0.8386 | 0.722 | 1.0 | 0.5 | 1.2341 |
65
- | 1.3894 | 2.0 | 125 | 0.722 | 0.8386 | 0.722 | 1.0 | 0.5 | 1.1617 |
66
- | 1.3894 | 2.976 | 186 | 0.736 | 0.8451 | 0.7332 | 0.9972 | 0.5274 | 1.1691 |
67
 
68
 
69
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Accuracy: 0.714
25
+ - F1: 0.8239
26
+ - Precision: 0.7057
27
+ - Recall: 0.9896
28
+ - Roc Auc: 0.5643
29
+ - Loss: 1.1941
30
 
31
  ## Model description
32
 
 
61
 
62
  | Training Loss | Epoch | Step | Accuracy | F1 | Precision | Recall | Roc Auc | Validation Loss |
63
  |:-------------:|:-----:|:----:|:--------:|:------:|:---------:|:------:|:-------:|:---------------:|
64
+ | No log | 0.992 | 62 | 0.676 | 0.8067 | 0.676 | 1.0 | 0.5 | 1.2394 |
65
+ | 1.4051 | 2.0 | 125 | 0.676 | 0.8065 | 0.6764 | 0.9985 | 0.5008 | 1.1807 |
66
+ | 1.4051 | 2.976 | 186 | 0.714 | 0.8239 | 0.7057 | 0.9896 | 0.5643 | 1.1941 |
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2043acd0cadf33f26a9d3bae0e0478d1e0a5ced6ccbaa11f9c090248431d6223
3
  size 669455360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bd16220790773f64d25bc6178465e95088391c81b09d1a2b1455b3b97ec268f
3
  size 669455360
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f9fe4da266389958bd7b14603e8a293d9ad8b02cca81c50764460d7de8005fd
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41817219ac50db868c5109a77de0fbeb7b969ff267fced7a90ebcb005cce6e4b
3
  size 5368