Hugging Face's logo

qfrodicio
/
distilbert-finetuned-gesture-prediction-21-classes

Token Classification
Transformers
PyTorch
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
qfrodicio commited on
Commit
ef9bf2f
•
1 Parent(s): 17ba257

Training complete

Browse files
Files changed (3) hide show
  1. README.md +28 -37
  2. model.safetensors +1 -1
  3. runs/May04_10-50-36_19b9be41010d/events.out.tfevents.1714819841.19b9be41010d.571.1 +2 -2
README.md CHANGED
@@ -1,13 +1,13 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
- datasets: qfrodicio/gesture-prediction-21-classes
6
  metrics:
7
- - accuracy
8
  - precision
9
  - recall
10
  - f1
 
11
  model-index:
12
  - name: distilbert-finetuned-gesture-prediction-21-classes
13
  results: []
@@ -18,21 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # distilbert-finetuned-gesture-prediction-21-classes
20
 
21
- This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.8430
24
- - Accuracy: 0.8077
25
- - Precision: 0.8063
26
- - Recall: 0.8077
27
- - F1: 0.8038
28
-
29
- It achieves the following results on the test set:
30
- - Loss: 0.8332
31
- - Accuracy: 0.7934
32
- - Precision: 0.7925
33
- - Recall: 0.7934
34
- - F1: 0.7875
35
-
36
 
37
  ## Model description
38
 
@@ -44,17 +36,16 @@ More information needed
44
 
45
  ## Training and evaluation data
46
 
47
- This model has been trained with the qfrodicio/gesture-prediction-21-classes dataset
48
 
49
  ## Training procedure
50
 
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
- - learning_rate: 2e-05
55
- - weight_decay: 0.01
56
- - train_batch_size: 16
57
- - eval_batch_size: 16
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
@@ -62,23 +53,23 @@ The following hyperparameters were used during training:
62
 
63
  ### Training results
64
 
65
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
66
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
67
- | 2.2082 | 1.0 | 104 | 1.3318 | 0.6956 | 0.6361 | 0.6956 | 0.6473 |
68
- | 1.1512 | 2.0 | 208 | 1.0114 | 0.7604 | 0.7463 | 0.7604 | 0.7368 |
69
- | 0.8152 | 3.0 | 312 | 0.8805 | 0.7860 | 0.7677 | 0.7860 | 0.7698 |
70
- | 0.6142 | 4.0 | 416 | 0.8486 | 0.8025 | 0.8035 | 0.8025 | 0.7961 |
71
- | 0.4726 | 5.0 | 520 | 0.8651 | 0.7992 | 0.7987 | 0.7992 | 0.7894 |
72
- | 0.3677 | 6.0 | 624 | 0.8430 | 0.8077 | 0.8063 | 0.8077 | 0.8038 |
73
- | 0.2967 | 7.0 | 728 | 0.8564 | 0.8037 | 0.8029 | 0.8037 | 0.7995 |
74
- | 0.2494 | 8.0 | 832 | 0.8567 | 0.8077 | 0.8054 | 0.8077 | 0.8041 |
75
- | 0.2163 | 9.0 | 936 | 0.8789 | 0.8075 | 0.8060 | 0.8075 | 0.8035 |
76
- | 0.193 | 10.0 | 1040 | 0.8880 | 0.8077 | 0.8072 | 0.8077 | 0.8032 |
77
 
78
 
79
  ### Framework versions
80
 
81
- - Transformers 4.26.1
82
- - Pytorch 1.13.1+cu116
83
- - Datasets 2.10.1
84
- - Tokenizers 0.13.2
 
1
  ---
2
  license: apache-2.0
3
+ base_model: distilbert-base-cased
4
  tags:
5
  - generated_from_trainer
 
6
  metrics:
 
7
  - precision
8
  - recall
9
  - f1
10
+ - accuracy
11
  model-index:
12
  - name: distilbert-finetuned-gesture-prediction-21-classes
13
  results: []
 
18
 
19
  # distilbert-finetuned-gesture-prediction-21-classes
20
 
21
+ This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.9438
24
+ - Precision: 0.7910
25
+ - Recall: 0.7910
26
+ - F1: 0.7910
27
+ - Accuracy: 0.7817
 
 
 
 
 
 
 
 
28
 
29
  ## Model description
30
 
 
36
 
37
  ## Training and evaluation data
38
 
39
+ More information needed
40
 
41
  ## Training procedure
42
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
+ - learning_rate: 6.042200829392303e-05
47
+ - train_batch_size: 64
48
+ - eval_batch_size: 64
 
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 2.4003 | 1.0 | 26 | 1.4948 | 0.6512 | 0.6512 | 0.6512 | 0.6206 |
59
+ | 1.2197 | 2.0 | 52 | 1.0008 | 0.7501 | 0.7501 | 0.7501 | 0.7356 |
60
+ | 0.81 | 3.0 | 78 | 0.8907 | 0.7696 | 0.7696 | 0.7696 | 0.7555 |
61
+ | 0.5619 | 4.0 | 104 | 0.9091 | 0.7628 | 0.7628 | 0.7628 | 0.7495 |
62
+ | 0.3944 | 5.0 | 130 | 0.8791 | 0.7853 | 0.7853 | 0.7853 | 0.7749 |
63
+ | 0.2907 | 6.0 | 156 | 0.8973 | 0.7845 | 0.7845 | 0.7845 | 0.7733 |
64
+ | 0.2214 | 7.0 | 182 | 0.9209 | 0.7874 | 0.7874 | 0.7874 | 0.7779 |
65
+ | 0.1722 | 8.0 | 208 | 0.9446 | 0.7878 | 0.7878 | 0.7878 | 0.7787 |
66
+ | 0.1454 | 9.0 | 234 | 0.9406 | 0.7882 | 0.7882 | 0.7882 | 0.7789 |
67
+ | 0.128 | 10.0 | 260 | 0.9438 | 0.7910 | 0.7910 | 0.7910 | 0.7817 |
68
 
69
 
70
  ### Framework versions
71
 
72
+ - Transformers 4.40.1
73
+ - Pytorch 2.2.1+cu121
74
+ - Datasets 2.19.0
75
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e83485cbaa16fe75f08c761c6fd79a4e6444d9a1a1d82d9beb4cc8c4a8c099bb
3
  size 260905184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382b632e6022024256743c059c842977c71d6128b34a7e1b2b115b8022d42bbe
3
  size 260905184
runs/May04_10-50-36_19b9be41010d/events.out.tfevents.1714819841.19b9be41010d.571.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62a5ad998c49698fa2d4629c8d86452bb0cc6066b93fc093edbff4742685b001
3
- size 12658
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6db4b410333a92435e7a5227cb7e972066a9380b8fbd2ee0f104db739602bd3
3
+ size 13695