Update README.md
Browse files
README.md
CHANGED
@@ -18,12 +18,19 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
# bert-finetuned-gesture-prediction-5-classes
|
19 |
|
20 |
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
|
21 |
-
It achieves the following results on the
|
22 |
-
- Loss: 0.
|
23 |
-
- Accuracy: 0.
|
24 |
-
- Precision: 0.
|
25 |
-
- Recall: 0.
|
26 |
-
- F1: 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
|
28 |
## Model description
|
29 |
|
@@ -35,7 +42,7 @@ More information needed
|
|
35 |
|
36 |
## Training and evaluation data
|
37 |
|
38 |
-
|
39 |
|
40 |
## Training procedure
|
41 |
|
@@ -43,6 +50,7 @@ More information needed
|
|
43 |
|
44 |
The following hyperparameters were used during training:
|
45 |
- learning_rate: 2e-05
|
|
|
46 |
- train_batch_size: 16
|
47 |
- eval_batch_size: 16
|
48 |
- seed: 42
|
|
|
18 |
# bert-finetuned-gesture-prediction-5-classes
|
19 |
|
20 |
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
|
21 |
+
It achieves the following results on the validation set:
|
22 |
+
- Loss: 0.4958
|
23 |
+
- Accuracy: 0.8636
|
24 |
+
- Precision: 0.8662
|
25 |
+
- Recall: 0.8636
|
26 |
+
- F1: 0.8625
|
27 |
+
|
28 |
+
It achieves the following results on the test set:
|
29 |
+
- Loss: 0.4599
|
30 |
+
- Accuracy: 0.8561
|
31 |
+
- Precision: 0.8578
|
32 |
+
- Recall: 0.8561
|
33 |
+
- F1: 0.8533
|
34 |
|
35 |
## Model description
|
36 |
|
|
|
42 |
|
43 |
## Training and evaluation data
|
44 |
|
45 |
+
The model has been trained with the qfrodicio/gesture-prediction-5-classes dataset
|
46 |
|
47 |
## Training procedure
|
48 |
|
|
|
50 |
|
51 |
The following hyperparameters were used during training:
|
52 |
- learning_rate: 2e-05
|
53 |
+
- weight_decay: 0.01
|
54 |
- train_batch_size: 16
|
55 |
- eval_batch_size: 16
|
56 |
- seed: 42
|