Hugging Face's logo

miyagawaorj
/
distilbert-base-uncased-finetuned-emotion

Text Classification
Transformers
PyTorch
TensorBoard
distilbert
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
4
miyagawaorj commited on
Commit
d4a2bbc
•
1 Parent(s): d3c2eda

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -16,14 +16,14 @@ model-index:
16
  dataset:
17
  name: emotion
18
  type: emotion
19
- args: default
20
  metrics:
21
  - name: Accuracy
22
  type: accuracy
23
- value: 0.9425
24
  - name: F1
25
  type: f1
26
- value: 0.9422011075095515
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,9 +33,9 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.2285
37
- - Accuracy: 0.9425
38
- - F1: 0.9422
39
 
40
  ## Model description
41
 
@@ -55,8 +55,8 @@ More information needed
55
 
56
  The following hyperparameters were used during training:
57
  - learning_rate: 2e-05
58
- - train_batch_size: 2
59
- - eval_batch_size: 2
60
  - seed: 42
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
@@ -64,15 +64,15 @@ The following hyperparameters were used during training:
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
68
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
69
- | 0.4656 | 1.0 | 8000 | 0.2912 | 0.9365 | 0.9362 |
70
- | 0.2046 | 2.0 | 16000 | 0.2285 | 0.9425 | 0.9422 |
71
 
72
 
73
  ### Framework versions
74
 
75
- - Transformers 4.11.3
76
- - Pytorch 1.11.0
77
  - Datasets 1.16.1
78
- - Tokenizers 0.10.3
 
16
  dataset:
17
  name: emotion
18
  type: emotion
19
+ args: split
20
  metrics:
21
  - name: Accuracy
22
  type: accuracy
23
+ value: 0.925
24
  - name: F1
25
  type: f1
26
+ value: 0.924826229002455
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.2224
37
+ - Accuracy: 0.925
38
+ - F1: 0.9248
39
 
40
  ## Model description
41
 
 
55
 
56
  The following hyperparameters were used during training:
57
  - learning_rate: 2e-05
58
+ - train_batch_size: 64
59
+ - eval_batch_size: 64
60
  - seed: 42
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
 
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
69
+ | 0.8366 | 1.0 | 250 | 0.3242 | 0.9075 | 0.9029 |
70
+ | 0.2563 | 2.0 | 500 | 0.2224 | 0.925 | 0.9248 |
71
 
72
 
73
  ### Framework versions
74
 
75
+ - Transformers 4.16.2
76
+ - Pytorch 2.0.1+cu118
77
  - Datasets 1.16.1
78
+ - Tokenizers 0.13.3