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
ca4afb5
•
1 Parent(s): 68e8718

End of training

Browse files
Files changed (3) hide show
  1. README.md +9 -15
  2. events.out.tfevents.1717708005.3bac7868ad93.1610.0 +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: 2.3210
26
  - Accuracy: 0.1762
27
 
28
  ## Model description
@@ -50,24 +50,18 @@ The following hyperparameters were used during training:
50
  - total_train_batch_size: 32
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
- - lr_scheduler_warmup_steps: 100
54
- - training_steps: 100
55
  - mixed_precision_training: Native AMP
56
 
57
  ### Training results
58
 
59
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
60
- |:-------------:|:------:|:----:|:---------------:|:--------:|
61
- | No log | 0.0556 | 10 | 7.6479 | 0.1762 |
62
- | No log | 0.1111 | 20 | 6.9937 | 0.1762 |
63
- | 8.2277 | 0.1667 | 30 | 6.2531 | 0.1762 |
64
- | 8.2277 | 0.2222 | 40 | 5.6151 | 0.1762 |
65
- | 6.019 | 0.2778 | 50 | 4.8978 | 0.1762 |
66
- | 6.019 | 0.3333 | 60 | 3.6924 | 0.1762 |
67
- | 6.019 | 0.3889 | 70 | 2.9463 | 0.1762 |
68
- | 3.6301 | 0.4444 | 80 | 2.5056 | 0.1762 |
69
- | 3.6301 | 0.5 | 90 | 2.3194 | 0.1762 |
70
- | 2.2789 | 0.5556 | 100 | 2.3210 | 0.1762 |
71
 
72
 
73
  ### 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: 2.9693
26
  - Accuracy: 0.1762
27
 
28
  ## Model description
 
50
  - total_train_batch_size: 32
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: 4000
55
  - mixed_precision_training: Native AMP
56
 
57
  ### Training results
58
 
59
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
60
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
61
+ | 1.5754 | 5.5556 | 1000 | 2.2186 | 0.1762 |
62
+ | 0.7323 | 11.1111 | 2000 | 2.8135 | 0.1762 |
63
+ | 0.4394 | 16.6667 | 3000 | 2.9377 | 0.1762 |
64
+ | 0.3782 | 22.2222 | 4000 | 2.9693 | 0.1762 |
 
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
events.out.tfevents.1717708005.3bac7868ad93.1610.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6e479d8e987d359652494da4e1995f12de35b35abf656c439dcb39829bd072f
3
- size 40037
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee8c73d4852baa315b5db2b777b8ffa30baaa1cb21910ab62474ac4720877c6
3
+ size 40391
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32aa5c6bf6acbe551983dd6abac9a05967173b23a5b18f7e463e079c95471cad
3
  size 437955572
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3a424af955cf4e2e509c78d24894f4291db69d99b1f6e167cd0f92ea38d683
3
  size 437955572