Hugging Face's logo

TeamResearch
/
bnb-sentiment-model-saagie

Text Classification
Transformers
PyTorch
roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
TeamResearch commited on
Commit
8bc85b5
•
1 Parent(s): 063fa6c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -11
README.md CHANGED
@@ -18,7 +18,7 @@ model-index:
18
  metrics:
19
  - name: Accuracy
20
  type: accuracy
21
- value: 0.91
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,8 +28,8 @@ should probably proofread and complete it, then remove this comment. -->
28
 
29
  This model is a fine-tuned version of [j-hartmann/emotion-english-distilroberta-base](https://huggingface.co/j-hartmann/emotion-english-distilroberta-base) on the emotion dataset.
30
  It achieves the following results on the evaluation set:
31
- - Loss: 0.5415
32
- - Accuracy: 0.91
33
 
34
  ## Model description
35
 
@@ -54,17 +54,20 @@ The following hyperparameters were used during training:
54
  - seed: 42
55
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
  - lr_scheduler_type: linear
57
- - num_epochs: 5
58
 
59
  ### Training results
60
 
61
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
62
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
63
- | 0.3917 | 1.0 | 1250 | 0.3667 | 0.9133 |
64
- | 0.2212 | 2.0 | 2500 | 0.3316 | 0.9267 |
65
- | 0.1565 | 3.0 | 3750 | 0.3674 | 0.9167 |
66
- | 0.1152 | 4.0 | 5000 | 0.4097 | 0.9167 |
67
- | 0.0787 | 5.0 | 6250 | 0.5415 | 0.91 |
 
 
 
68
 
69
 
70
  ### Framework versions
 
18
  metrics:
19
  - name: Accuracy
20
  type: accuracy
21
+ value: 0.9477777777777778
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
28
 
29
  This model is a fine-tuned version of [j-hartmann/emotion-english-distilroberta-base](https://huggingface.co/j-hartmann/emotion-english-distilroberta-base) on the emotion dataset.
30
  It achieves the following results on the evaluation set:
31
+ - Loss: 0.3199
32
+ - Accuracy: 0.9478
33
 
34
  ## Model description
35
 
 
54
  - seed: 42
55
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
  - lr_scheduler_type: linear
57
+ - num_epochs: 8
58
 
59
  ### Training results
60
 
61
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
62
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
63
+ | 0.3763 | 1.0 | 1875 | 0.1789 | 0.9411 |
64
+ | 0.2179 | 2.0 | 3750 | 0.2558 | 0.9356 |
65
+ | 0.1789 | 3.0 | 5625 | 0.1786 | 0.9422 |
66
+ | 0.1543 | 4.0 | 7500 | 0.2059 | 0.9511 |
67
+ | 0.1181 | 5.0 | 9375 | 0.2070 | 0.9478 |
68
+ | 0.0791 | 6.0 | 11250 | 0.2392 | 0.9433 |
69
+ | 0.0497 | 7.0 | 13125 | 0.3182 | 0.9411 |
70
+ | 0.0356 | 8.0 | 15000 | 0.3199 | 0.9478 |
71
 
72
 
73
  ### Framework versions