Hugging Face's logo

theCuiCoders
/
bert-base-uncased-FinedTuned

Text Classification
Transformers
TensorBoard
Safetensors
Dutch
bert
abc
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
theCuiCoders commited on
Commit
8eabf14
•
1 Parent(s): e88e1f6

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -8
  2. events.out.tfevents.1717768789.25dcf196d7e6.1682.3 +2 -2
  3. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
22
 
23
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the stsb_multi_mt dataset.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 2.9242
26
  - Accuracy: 0.1762
27
 
28
  ## Model description
@@ -51,19 +51,21 @@ The following hyperparameters were used during training:
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
  - lr_scheduler_warmup_steps: 1000
54
- - training_steps: 6000
55
  - mixed_precision_training: Native AMP
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
60
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
61
- | 0.8079 | 5.5556 | 1000 | 2.6347 | 0.1762 |
62
- | 0.6349 | 11.1111 | 2000 | 2.8882 | 0.1762 |
63
- | 0.3961 | 16.6667 | 3000 | 2.9309 | 0.1762 |
64
- | 0.3026 | 22.2222 | 4000 | 2.9788 | 0.1762 |
65
- | 0.2523 | 27.7778 | 5000 | 2.9326 | 0.1762 |
66
- | 0.3039 | 33.3333 | 6000 | 2.9242 | 0.1762 |
 
 
67
 
68
 
69
  ### Framework versions
 
22
 
23
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the stsb_multi_mt dataset.
24
  It achieves the following results on the evaluation set:
25
+ - Loss: 2.8164
26
  - Accuracy: 0.1762
27
 
28
  ## Model description
 
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
  - lr_scheduler_warmup_steps: 1000
54
+ - training_steps: 8000
55
  - mixed_precision_training: Native AMP
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
60
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
61
+ | 0.5321 | 5.5556 | 1000 | 2.7300 | 0.1762 |
62
+ | 0.5563 | 11.1111 | 2000 | 2.8975 | 0.1762 |
63
+ | 0.3628 | 16.6667 | 3000 | 2.9325 | 0.1762 |
64
+ | 0.2808 | 22.2222 | 4000 | 2.8846 | 0.1762 |
65
+ | 0.2323 | 27.7778 | 5000 | 2.8512 | 0.1762 |
66
+ | 0.2743 | 33.3333 | 6000 | 2.8551 | 0.1762 |
67
+ | 0.2075 | 38.8889 | 7000 | 2.8403 | 0.1762 |
68
+ | 0.2195 | 44.4444 | 8000 | 2.8164 | 0.1762 |
69
 
70
 
71
  ### Framework versions
events.out.tfevents.1717768789.25dcf196d7e6.1682.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:221d734ddebc7720cb9dc047509d00f1747b3cf0fbc47416c792328b70972fb2
3
- size 66326
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a1f42488bc2da307b66e8c4d552692ae52c811fa2c0093772b6d88c8fdd805
3
+ size 75443
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78d9c21f91d1b4e0c0551e91115c5f208abcbb6a3fe0d096fc65c7b2ecdb9536
3
  size 437955572
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35a52b29d3f9d487b377d5d50737b857203783c0b590e4f661b98abb89146acd
3
  size 437955572