Hugging Face's logo

dtorber
/
bertweet-base

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
dtorber commited on
Commit
d8908a5
•
1 Parent(s): 9fe27aa

Model save

Browse files
Files changed (1) hide show
  1. README.md +16 -15
README.md CHANGED
@@ -17,14 +17,14 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [vinai/bertweet-base](https://huggingface.co/vinai/bertweet-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.6568
21
- - F1 Macro: 0.3902
22
- - F1: 0.7805
23
- - F1 Neg: 0.0
24
- - Acc: 0.64
25
- - Prec: 0.64
26
- - Recall: 1.0
27
- - Mcc: 0.0
28
 
29
  ## Model description
30
 
@@ -44,9 +44,10 @@ More information needed
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 2e-05
47
- - train_batch_size: 16
48
- - eval_batch_size: 16
49
  - seed: 42
 
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
  - num_epochs: 3
@@ -54,11 +55,11 @@ The following hyperparameters were used during training:
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc |
58
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:----:|:----:|:------:|:---:|
59
- | No log | 1.0 | 10 | 0.7766 | 0.3902 | 0.7805 | 0.0 | 0.64 | 0.64 | 1.0 | 0.0 |
60
- | No log | 2.0 | 20 | 0.6608 | 0.3902 | 0.7805 | 0.0 | 0.64 | 0.64 | 1.0 | 0.0 |
61
- | No log | 3.0 | 30 | 0.6568 | 0.3902 | 0.7805 | 0.0 | 0.64 | 0.64 | 1.0 | 0.0 |
62
 
63
 
64
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [vinai/bertweet-base](https://huggingface.co/vinai/bertweet-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4738
21
+ - F1 Macro: 0.7848
22
+ - F1: 0.8370
23
+ - F1 Neg: 0.7327
24
+ - Acc: 0.7975
25
+ - Prec: 0.8631
26
+ - Recall: 0.8125
27
+ - Mcc: 0.5722
28
 
29
  ## Model description
30
 
 
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 2e-05
47
+ - train_batch_size: 8
48
+ - eval_batch_size: 8
49
  - seed: 42
50
+ - distributed_type: multi-GPU
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
  - num_epochs: 3
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
60
+ | 0.6845 | 1.0 | 1161 | 0.6190 | 0.6706 | 0.7085 | 0.6328 | 0.675 | 0.8316 | 0.6172 | 0.3796 |
61
+ | 0.5137 | 2.0 | 2322 | 0.5512 | 0.7170 | 0.8366 | 0.5974 | 0.7675 | 0.7604 | 0.9297 | 0.4757 |
62
+ | 0.3724 | 3.0 | 3483 | 0.4738 | 0.7848 | 0.8370 | 0.7327 | 0.7975 | 0.8631 | 0.8125 | 0.5722 |
63
 
64
 
65
  ### Framework versions