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
ed62a2a
•
1 Parent(s): 5d3bc21

End of training

Browse files
Files changed (3) hide show
  1. README.md +21 -20
  2. events.out.tfevents.1719825310.f5f93b040f77.2713.0 +2 -2
  3. model.safetensors +1 -1
README.md CHANGED
@@ -8,8 +8,6 @@ tags:
8
  - generated_from_trainer
9
  datasets:
10
  - stsb_multi_mt
11
- metrics:
12
- - accuracy
13
  model-index:
14
  - name: bert-base-uncased-FinedTuned
15
  results: []
@@ -22,8 +20,9 @@ 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: 2.7821
26
- - Accuracy: 0.1762
 
27
 
28
  ## Model description
29
 
@@ -42,7 +41,7 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - learning_rate: 5e-05
46
  - train_batch_size: 16
47
  - eval_batch_size: 16
48
  - seed: 42
@@ -51,28 +50,30 @@ 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: 10000
55
  - mixed_precision_training: Native AMP
56
 
57
  ### Training results
58
 
59
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
60
- |:-------------:|:-------:|:-----:|:---------------:|:--------:|
61
- | 0.2457 | 5.5556 | 1000 | 2.4913 | 0.1762 |
62
- | 0.1759 | 11.1111 | 2000 | 2.8424 | 0.1762 |
63
- | 0.1458 | 16.6667 | 3000 | 2.9765 | 0.1762 |
64
- | 0.1132 | 22.2222 | 4000 | 2.7163 | 0.1762 |
65
- | 0.1118 | 27.7778 | 5000 | 2.7272 | 0.1762 |
66
- | 0.1272 | 33.3333 | 6000 | 2.8354 | 0.1762 |
67
- | 0.1233 | 38.8889 | 7000 | 2.6948 | 0.1762 |
68
- | 0.1161 | 44.4444 | 8000 | 2.7358 | 0.1762 |
69
- | 0.0736 | 50.0 | 9000 | 2.7748 | 0.1762 |
70
- | 0.0924 | 55.5556 | 10000 | 2.7821 | 0.1762 |
 
 
71
 
72
 
73
  ### Framework versions
74
 
75
- - Transformers 4.41.2
76
  - Pytorch 2.3.1+cu121
77
- - Datasets 2.19.2
78
  - Tokenizers 0.19.1
 
8
  - generated_from_trainer
9
  datasets:
10
  - stsb_multi_mt
 
 
11
  model-index:
12
  - name: bert-base-uncased-FinedTuned
13
  results: []
 
20
 
21
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the stsb_multi_mt dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 2.7197
24
+ - Pearson: 0.2346
25
+ - Mse: 2.7197
26
 
27
  ## Model description
28
 
 
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
+ - learning_rate: 2e-05
45
  - train_batch_size: 16
46
  - eval_batch_size: 16
47
  - seed: 42
 
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
  - lr_scheduler_warmup_steps: 1000
53
+ - training_steps: 12000
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Pearson | Mse |
59
+ |:-------------:|:-------:|:-----:|:---------------:|:-------:|:------:|
60
+ | 0.051 | 5.5556 | 1000 | 2.8182 | 0.2432 | 2.8182 |
61
+ | 0.0623 | 11.1111 | 2000 | 2.8367 | 0.2164 | 2.8367 |
62
+ | 0.0471 | 16.6667 | 3000 | 2.7305 | 0.2126 | 2.7305 |
63
+ | 0.0357 | 22.2222 | 4000 | 2.6918 | 0.2324 | 2.6918 |
64
+ | 0.032 | 27.7778 | 5000 | 2.7902 | 0.2379 | 2.7902 |
65
+ | 0.0793 | 33.3333 | 6000 | 2.7368 | 0.2480 | 2.7368 |
66
+ | 0.0775 | 38.8889 | 7000 | 2.6499 | 0.2382 | 2.6499 |
67
+ | 0.0728 | 44.4444 | 8000 | 2.6974 | 0.2368 | 2.6974 |
68
+ | 0.0596 | 50.0 | 9000 | 2.7313 | 0.2302 | 2.7313 |
69
+ | 0.1012 | 55.5556 | 10000 | 2.7291 | 0.2332 | 2.7291 |
70
+ | 0.0644 | 61.1111 | 11000 | 2.7338 | 0.2315 | 2.7338 |
71
+ | 0.1595 | 66.6667 | 12000 | 2.7197 | 0.2346 | 2.7197 |
72
 
73
 
74
  ### Framework versions
75
 
76
+ - Transformers 4.42.3
77
  - Pytorch 2.3.1+cu121
78
+ - Datasets 2.20.0
79
  - Tokenizers 0.19.1
events.out.tfevents.1719825310.f5f93b040f77.2713.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e62c517a1c813eb32ea2759a3c09104d1905a7695102c3e7558e58be0704e037
3
- size 110721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae1e1dae13da7ccaaa653952c5dd330905dd06ce0ac8a644e6c35cf577d2c616
3
+ size 111075
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5280dc43031e93f4d59bf2f50533eabe0fa87d3a821f723888f787e596d4dee
3
  size 437955572
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32db1a5d7bca255a598887f5a4d093174c8618b7cc0b5242bd11e7730f4c0afe
3
  size 437955572