Hugging Face's logo

readerbench
/
ro-offense

Text Classification
Transformers
PyTorch
Romanian
bert
hate speech
offensive language
romanian
classification
nlp
Eval Results
Inference Endpoints
Model card Files Community
1
andyP commited on
Commit
ac74139
•
1 Parent(s): ed679ba

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -15
README.md CHANGED
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [readerbench/RoBERT-base](https://huggingface.co/readerbench/RoBERT-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.7285
22
- - Accuracy: 0.8132
23
- - Precision: 0.8131
24
- - Recall: 0.8173
25
- - F1 Macro: 0.8123
26
- - F1 Micro: 0.8132
27
- - F1 Weighted: 0.8094
28
 
29
  ## Model description
30
 
@@ -43,25 +43,26 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 2e-05
47
  - train_batch_size: 64
48
  - eval_batch_size: 128
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
 
52
  - num_epochs: 10
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Macro | F1 Micro | F1 Weighted |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:--------:|:-----------:|
58
- | No log | 1.0 | 125 | 0.6284 | 0.7675 | 0.7662 | 0.7721 | 0.7681 | 0.7675 | 0.7654 |
59
- | No log | 2.0 | 250 | 0.5576 | 0.7820 | 0.7826 | 0.7799 | 0.7796 | 0.7820 | 0.7803 |
60
- | No log | 3.0 | 375 | 0.5405 | 0.8001 | 0.8122 | 0.8077 | 0.8026 | 0.8001 | 0.7943 |
61
- | 0.5338 | 4.0 | 500 | 0.5853 | 0.8172 | 0.8140 | 0.8120 | 0.8124 | 0.8172 | 0.8161 |
62
- | 0.5338 | 5.0 | 625 | 0.6476 | 0.8157 | 0.8143 | 0.8098 | 0.8118 | 0.8157 | 0.8148 |
63
- | 0.5338 | 6.0 | 750 | 0.6607 | 0.8122 | 0.8137 | 0.8173 | 0.8120 | 0.8122 | 0.8082 |
64
- | 0.5338 | 7.0 | 875 | 0.7285 | 0.8132 | 0.8131 | 0.8173 | 0.8123 | 0.8132 | 0.8094 |
65
 
66
 
67
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [readerbench/RoBERT-base](https://huggingface.co/readerbench/RoBERT-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.8411
22
+ - Accuracy: 0.8232
23
+ - Precision: 0.8235
24
+ - Recall: 0.8210
25
+ - F1 Macro: 0.8207
26
+ - F1 Micro: 0.8232
27
+ - F1 Weighted: 0.8210
28
 
29
  ## Model description
30
 
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
+ - learning_rate: 4e-05
47
  - train_batch_size: 64
48
  - eval_batch_size: 128
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_ratio: 0.2
53
  - num_epochs: 10
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Macro | F1 Micro | F1 Weighted |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:--------:|:-----------:|
59
+ | No log | 1.0 | 125 | 0.7789 | 0.7037 | 0.6825 | 0.7000 | 0.6873 | 0.7037 | 0.7132 |
60
+ | No log | 2.0 | 250 | 0.5170 | 0.8006 | 0.8066 | 0.8016 | 0.7986 | 0.8006 | 0.7971 |
61
+ | No log | 3.0 | 375 | 0.5139 | 0.8096 | 0.8168 | 0.8237 | 0.8120 | 0.8096 | 0.8047 |
62
+ | 0.6074 | 4.0 | 500 | 0.6180 | 0.8247 | 0.8251 | 0.8187 | 0.8210 | 0.8247 | 0.8233 |
63
+ | 0.6074 | 5.0 | 625 | 0.7311 | 0.8096 | 0.8071 | 0.8085 | 0.8064 | 0.8096 | 0.8071 |
64
+ | 0.6074 | 6.0 | 750 | 0.8365 | 0.8101 | 0.8117 | 0.8191 | 0.8105 | 0.8101 | 0.8051 |
65
+ | 0.6074 | 7.0 | 875 | 0.8411 | 0.8232 | 0.8235 | 0.8210 | 0.8207 | 0.8232 | 0.8210 |
66
 
67
 
68
  ### Framework versions