Hugging Face's logo

SjardiWillems
/
distilbert-base-uncased-finetuned-stsb

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files Metrics Community
SjardiWillems commited on
Commit
dd37b84
·
verified ·
1 Parent(s): f71e060

End of training

Browse files
Files changed (2) hide show
  1. README.md +13 -14
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # distilbert-base-uncased-finetuned-stsb
17
 
18
- This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.5468
21
- - Pearson: 0.8721
22
- - Spearmanr: 0.8691
23
 
24
  ## Model description
25
 
@@ -38,23 +38,22 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 2e-05
42
- - train_batch_size: 16
43
  - eval_batch_size: 16
44
- - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
- - num_epochs: 5
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
52
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|
53
- | No log | 1.0 | 360 | 0.5950 | 0.8674 | 0.8650 |
54
- | 1.0355 | 2.0 | 720 | 0.5793 | 0.8691 | 0.8671 |
55
- | 0.3987 | 3.0 | 1080 | 0.5628 | 0.8713 | 0.8683 |
56
- | 0.3987 | 4.0 | 1440 | 0.5486 | 0.8706 | 0.8678 |
57
- | 0.2437 | 5.0 | 1800 | 0.5468 | 0.8721 | 0.8691 |
58
 
59
 
60
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: SjardiWillems/distilbert-base-uncased-finetuned-stsb
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
15
 
16
  # distilbert-base-uncased-finetuned-stsb
17
 
18
+ This model is a fine-tuned version of [SjardiWillems/distilbert-base-uncased-finetuned-stsb](https://huggingface.co/SjardiWillems/distilbert-base-uncased-finetuned-stsb) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.5419
21
+ - Pearson: 0.8736
22
+ - Spearmanr: 0.8702
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 3.1992432473500055e-06
42
+ - train_batch_size: 64
43
  - eval_batch_size: 16
44
+ - seed: 25
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 4
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
52
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|
53
+ | No log | 1.0 | 90 | 0.5404 | 0.8727 | 0.8690 |
54
+ | No log | 2.0 | 180 | 0.5394 | 0.8736 | 0.8701 |
55
+ | No log | 3.0 | 270 | 0.5394 | 0.8738 | 0.8703 |
56
+ | No log | 4.0 | 360 | 0.5419 | 0.8736 | 0.8702 |
 
57
 
58
 
59
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da441763cabae0320f06ae00d4bab624b4304c700c2711581a1ceb32363235b2
3
  size 267829484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0af9df9ce01dd077ca727d82afac1f5d70db3034dc0d77f21fa3e86e6cf9167
3
  size 267829484