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
cbc630e
•
1 Parent(s): 9a9722a

Model save

Browse files
Files changed (1) hide show
  1. README.md +16 -14
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: 0.5120
21
- - F1 Macro: 0.7346
22
- - F1: 0.8315
23
- - F1 Neg: 0.6378
24
- - Acc: 0.77
25
- - Prec: 0.7828
26
- - Recall: 0.8867
27
- - Mcc: 0.4829
28
 
29
  ## Model description
30
 
@@ -50,16 +50,18 @@ The following hyperparameters were used during training:
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
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc |
59
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:-----:|:------:|:------:|:------:|
60
- | 0.6427 | 1.0 | 600 | 0.6329 | 0.6619 | 0.6941 | 0.6298 | 0.665 | 0.8352 | 0.5938 | 0.3715 |
61
- | 0.5445 | 2.0 | 1200 | 0.5193 | 0.7363 | 0.8233 | 0.6493 | 0.765 | 0.7935 | 0.8555 | 0.4770 |
62
- | 0.4446 | 3.0 | 1800 | 0.5120 | 0.7346 | 0.8315 | 0.6378 | 0.77 | 0.7828 | 0.8867 | 0.4829 |
 
 
63
 
64
 
65
  ### 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: 0.5822
21
+ - F1 Macro: 0.7750
22
+ - F1: 0.8571
23
+ - F1 Neg: 0.6929
24
+ - Acc: 0.805
25
+ - Prec: 0.8069
26
+ - Recall: 0.9141
27
+ - Mcc: 0.5646
28
 
29
  ## Model description
30
 
 
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: 5
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
60
+ | 0.6482 | 1.0 | 600 | 0.5610 | 0.6822 | 0.8022 | 0.5622 | 0.7275 | 0.7492 | 0.8633 | 0.3812 |
61
+ | 0.5567 | 2.0 | 1200 | 0.5125 | 0.7382 | 0.8364 | 0.64 | 0.775 | 0.7823 | 0.8984 | 0.4938 |
62
+ | 0.4549 | 3.0 | 1800 | 0.6164 | 0.7195 | 0.7588 | 0.6802 | 0.725 | 0.865 | 0.6758 | 0.4688 |
63
+ | 0.4021 | 4.0 | 2400 | 0.5785 | 0.7344 | 0.7875 | 0.6812 | 0.745 | 0.8438 | 0.7383 | 0.4789 |
64
+ | 0.3159 | 5.0 | 3000 | 0.5822 | 0.7750 | 0.8571 | 0.6929 | 0.805 | 0.8069 | 0.9141 | 0.5646 |
65
 
66
 
67
  ### Framework versions