Hugging Face's logo

qfrodicio
/
roberta-finetuned-gesture-prediction-9-classes

Token Classification
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
qfrodicio commited on
Commit
c9aaf0a
•
1 Parent(s): 5781850

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.7459
23
- - Accuracy: 0.8536
24
- - Precision: 0.8561
25
- - Recall: 0.8536
26
- - F1: 0.8520
27
 
28
  ## Model description
29
 
@@ -54,16 +54,16 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
- | 1.707 | 1.0 | 87 | 1.1502 | 0.6656 | 0.6124 | 0.6656 | 0.6133 |
58
- | 0.8587 | 2.0 | 174 | 0.7766 | 0.7866 | 0.7738 | 0.7866 | 0.7675 |
59
- | 0.5593 | 3.0 | 261 | 0.7240 | 0.8114 | 0.8063 | 0.8114 | 0.8017 |
60
- | 0.4122 | 4.0 | 348 | 0.6559 | 0.8248 | 0.8266 | 0.8248 | 0.8217 |
61
- | 0.3081 | 5.0 | 435 | 0.7089 | 0.8373 | 0.8431 | 0.8373 | 0.8326 |
62
- | 0.2322 | 6.0 | 522 | 0.7230 | 0.8234 | 0.8312 | 0.8234 | 0.8237 |
63
- | 0.1848 | 7.0 | 609 | 0.7016 | 0.8457 | 0.8491 | 0.8457 | 0.8434 |
64
- | 0.141 | 8.0 | 696 | 0.7443 | 0.8489 | 0.8540 | 0.8489 | 0.8451 |
65
- | 0.1181 | 9.0 | 783 | 0.7478 | 0.8534 | 0.8567 | 0.8534 | 0.8509 |
66
- | 0.1008 | 10.0 | 870 | 0.7459 | 0.8536 | 0.8561 | 0.8536 | 0.8520 |
67
 
68
 
69
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.7439
23
+ - Accuracy: 0.8495
24
+ - Precision: 0.8501
25
+ - Recall: 0.8495
26
+ - F1: 0.8465
27
 
28
  ## Model description
29
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
+ | 1.7138 | 1.0 | 87 | 1.0975 | 0.6915 | 0.6290 | 0.6915 | 0.6303 |
58
+ | 0.846 | 2.0 | 174 | 0.7497 | 0.7948 | 0.7790 | 0.7948 | 0.7772 |
59
+ | 0.5545 | 3.0 | 261 | 0.7078 | 0.8020 | 0.8000 | 0.8020 | 0.7927 |
60
+ | 0.3955 | 4.0 | 348 | 0.6668 | 0.8289 | 0.8288 | 0.8289 | 0.8258 |
61
+ | 0.279 | 5.0 | 435 | 0.6922 | 0.8291 | 0.8340 | 0.8291 | 0.8277 |
62
+ | 0.2203 | 6.0 | 522 | 0.6955 | 0.8373 | 0.8390 | 0.8373 | 0.8336 |
63
+ | 0.1595 | 7.0 | 609 | 0.7149 | 0.8395 | 0.8405 | 0.8395 | 0.8365 |
64
+ | 0.1349 | 8.0 | 696 | 0.7065 | 0.8436 | 0.8447 | 0.8436 | 0.8399 |
65
+ | 0.1047 | 9.0 | 783 | 0.7408 | 0.8481 | 0.8502 | 0.8481 | 0.8445 |
66
+ | 0.0906 | 10.0 | 870 | 0.7439 | 0.8495 | 0.8501 | 0.8495 | 0.8465 |
67
 
68
 
69
  ### Framework versions