Hugging Face's logo

tech4betterlife
/
distilbert-base-uncased_emotion_ft_0416

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
tech4betterlife commited on
Commit
b22b559
·
1 Parent(s): d0424b6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -13
README.md CHANGED
@@ -1,5 +1,6 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
  datasets:
@@ -23,13 +24,13 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.9365
27
  - name: F1
28
  type: f1
29
- value: 0.9367095468423076
30
  - name: Precision
31
  type: precision
32
- value: 0.9084962660186648
33
  ---
34
 
35
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -39,10 +40,10 @@ should probably proofread and complete it, then remove this comment. -->
39
 
40
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
41
  It achieves the following results on the evaluation set:
42
- - Loss: 0.1520
43
- - Accuracy: 0.9365
44
- - F1: 0.9367
45
- - Precision: 0.9085
46
 
47
  ## Model description
48
 
@@ -67,21 +68,25 @@ The following hyperparameters were used during training:
67
  - seed: 42
68
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
69
  - lr_scheduler_type: linear
70
- - num_epochs: 4
71
 
72
  ### Training results
73
 
74
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision |
75
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|
76
- | 0.8004 | 1.0 | 250 | 0.2687 | 0.9185 | 0.9179 | 0.8974 |
77
- | 0.2055 | 2.0 | 500 | 0.1749 | 0.929 | 0.9292 | 0.9032 |
78
- | 0.1386 | 3.0 | 750 | 0.1596 | 0.933 | 0.9332 | 0.9093 |
79
- | 0.1128 | 4.0 | 1000 | 0.1520 | 0.9365 | 0.9367 | 0.9085 |
 
 
 
 
80
 
81
 
82
  ### Framework versions
83
 
84
- - Transformers 4.29.2
85
  - Pytorch 2.0.1
86
  - Datasets 2.12.0
87
  - Tokenizers 0.13.2
 
1
  ---
2
  license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  datasets:
 
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
+ value: 0.94
28
  - name: F1
29
  type: f1
30
+ value: 0.9399689929524555
31
  - name: Precision
32
  type: precision
33
+ value: 0.9171180948520368
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
40
 
41
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
42
  It achieves the following results on the evaluation set:
43
+ - Loss: 0.1559
44
+ - Accuracy: 0.94
45
+ - F1: 0.9400
46
+ - Precision: 0.9171
47
 
48
  ## Model description
49
 
 
68
  - seed: 42
69
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
70
  - lr_scheduler_type: linear
71
+ - num_epochs: 8
72
 
73
  ### Training results
74
 
75
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision |
76
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|
77
+ | 0.7983 | 1.0 | 250 | 0.2761 | 0.91 | 0.9103 | 0.8773 |
78
+ | 0.2021 | 2.0 | 500 | 0.1690 | 0.935 | 0.9358 | 0.9022 |
79
+ | 0.1342 | 3.0 | 750 | 0.1606 | 0.9385 | 0.9386 | 0.9256 |
80
+ | 0.1034 | 4.0 | 1000 | 0.1471 | 0.937 | 0.9367 | 0.9236 |
81
+ | 0.0828 | 5.0 | 1250 | 0.1572 | 0.9355 | 0.9355 | 0.9132 |
82
+ | 0.0716 | 6.0 | 1500 | 0.1547 | 0.942 | 0.9415 | 0.9305 |
83
+ | 0.0595 | 7.0 | 1750 | 0.1584 | 0.9385 | 0.9385 | 0.9170 |
84
+ | 0.0514 | 8.0 | 2000 | 0.1559 | 0.94 | 0.9400 | 0.9171 |
85
 
86
 
87
  ### Framework versions
88
 
89
+ - Transformers 4.31.0.dev0
90
  - Pytorch 2.0.1
91
  - Datasets 2.12.0
92
  - Tokenizers 0.13.2