Hugging Face's logo

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

Token Classification
Transformers
PyTorch
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
3
qfrodicio commited on
Commit
35071ad
•
1 Parent(s): 13e9577

Training complete

Browse files
Files changed (3) hide show
  1. README.md +16 -16
  2. model.safetensors +1 -1
  3. runs/May07_18-29-18_7570e4083a5e/events.out.tfevents.1715106563.7570e4083a5e.601.6 +2 -2
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.9626
24
- - Precision: 0.8178
25
- - Recall: 0.8178
26
- - F1: 0.8178
27
- - Accuracy: 0.8075
28
 
29
  ## Model description
30
 
@@ -55,21 +55,21 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | 2.3221 | 1.0 | 26 | 1.4762 | 0.6969 | 0.6969 | 0.6969 | 0.6192 |
59
- | 1.2093 | 2.0 | 52 | 0.9843 | 0.7634 | 0.7634 | 0.7634 | 0.7469 |
60
- | 0.7309 | 3.0 | 78 | 0.8908 | 0.7878 | 0.7878 | 0.7878 | 0.7690 |
61
- | 0.4596 | 4.0 | 104 | 0.8613 | 0.7894 | 0.7894 | 0.7894 | 0.7763 |
62
- | 0.2947 | 5.0 | 130 | 0.8971 | 0.8075 | 0.8075 | 0.8075 | 0.7962 |
63
- | 0.1921 | 6.0 | 156 | 0.8838 | 0.8063 | 0.8063 | 0.8063 | 0.7956 |
64
- | 0.1348 | 7.0 | 182 | 0.9271 | 0.8166 | 0.8166 | 0.8166 | 0.8057 |
65
- | 0.0986 | 8.0 | 208 | 0.9548 | 0.8137 | 0.8137 | 0.8137 | 0.8035 |
66
- | 0.073 | 9.0 | 234 | 0.9553 | 0.8174 | 0.8174 | 0.8174 | 0.8063 |
67
- | 0.0619 | 10.0 | 260 | 0.9626 | 0.8178 | 0.8178 | 0.8178 | 0.8075 |
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
 
20
 
21
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.0260
24
+ - Precision: 0.8125
25
+ - Recall: 0.8125
26
+ - F1: 0.8125
27
+ - Accuracy: 0.8022
28
 
29
  ## Model description
30
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 2.2133 | 1.0 | 26 | 1.4161 | 0.7074 | 0.7074 | 0.7074 | 0.6642 |
59
+ | 1.1038 | 2.0 | 52 | 0.9797 | 0.7678 | 0.7678 | 0.7678 | 0.7521 |
60
+ | 0.6732 | 3.0 | 78 | 0.9139 | 0.7908 | 0.7908 | 0.7908 | 0.7738 |
61
+ | 0.4167 | 4.0 | 104 | 0.9106 | 0.7978 | 0.7978 | 0.7978 | 0.7826 |
62
+ | 0.2739 | 5.0 | 130 | 0.9295 | 0.8017 | 0.8017 | 0.8017 | 0.7883 |
63
+ | 0.1772 | 6.0 | 156 | 0.9294 | 0.8116 | 0.8116 | 0.8116 | 0.7989 |
64
+ | 0.1223 | 7.0 | 182 | 0.9899 | 0.8085 | 0.8085 | 0.8085 | 0.7964 |
65
+ | 0.0916 | 8.0 | 208 | 1.0156 | 0.8130 | 0.8130 | 0.8130 | 0.8012 |
66
+ | 0.0656 | 9.0 | 234 | 1.0234 | 0.8136 | 0.8136 | 0.8136 | 0.8025 |
67
+ | 0.0563 | 10.0 | 260 | 1.0260 | 0.8125 | 0.8125 | 0.8125 | 0.8022 |
68
 
69
 
70
  ### Framework versions
71
 
72
  - Transformers 4.40.1
73
  - Pytorch 2.2.1+cu121
74
+ - Datasets 2.19.1
75
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0dc7280fc8d0c1637790941f9d6645d4e385d4a267d6892d5b1c5b82156b3b8f
3
  size 431031248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd00ce7bdb70ed21378a68874736a155c151c1e1e091b3bc883a3eafebb7bd26
3
  size 431031248
runs/May07_18-29-18_7570e4083a5e/events.out.tfevents.1715106563.7570e4083a5e.601.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c6ebad405464a41811403b9d4b7b8a9454bc6f2ddebf660b41ef498e578af1e
3
- size 12729
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b38fc8469f6a96d2ab294cb883fc08692a211e400658c67af26b26d54f5b670
3
+ size 13766