Hugging Face's logo

SheldonSides
/
distilbert-base-uncased-finetuned-emotion

Text Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
SheldonSides commited on
Commit
fbe18df
•
1 Parent(s): 0922378

Fine-tuning Complete

Browse files
Files changed (3) hide show
  1. README.md +12 -14
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -23,10 +23,10 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.9295
27
  - name: F1
28
  type: f1
29
- value: 0.9298521812632715
30
  ---
31
 
32
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -36,9 +36,9 @@ should probably proofread and complete it, then remove this comment. -->
36
 
37
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
38
  It achieves the following results on the evaluation set:
39
- - Loss: 0.1771
40
- - Accuracy: 0.9295
41
- - F1: 0.9299
42
 
43
  ## Model description
44
 
@@ -57,23 +57,21 @@ More information needed
57
  ### Training hyperparameters
58
 
59
  The following hyperparameters were used during training:
60
- - learning_rate: 1e-05
61
- - train_batch_size: 62
62
- - eval_batch_size: 62
63
  - seed: 42
64
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
  - lr_scheduler_type: linear
66
- - num_epochs: 5
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
72
- | 1.0628 | 1.0 | 259 | 0.5461 | 0.8285 | 0.8100 |
73
- | 0.3852 | 2.0 | 518 | 0.2561 | 0.919 | 0.9192 |
74
- | 0.2204 | 3.0 | 777 | 0.2030 | 0.927 | 0.9272 |
75
- | 0.1722 | 4.0 | 1036 | 0.1826 | 0.9285 | 0.9286 |
76
- | 0.1485 | 5.0 | 1295 | 0.1771 | 0.9295 | 0.9299 |
77
 
78
 
79
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.9225
27
  - name: F1
28
  type: f1
29
+ value: 0.922592096883482
30
  ---
31
 
32
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
36
 
37
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
38
  It achieves the following results on the evaluation set:
39
+ - Loss: 0.2122
40
+ - Accuracy: 0.9225
41
+ - F1: 0.9226
42
 
43
  ## Model description
44
 
 
57
  ### Training hyperparameters
58
 
59
  The following hyperparameters were used during training:
60
+ - learning_rate: 2e-05
61
+ - train_batch_size: 128
62
+ - eval_batch_size: 128
63
  - seed: 42
64
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
  - lr_scheduler_type: linear
66
+ - num_epochs: 3
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
72
+ | 1.0761 | 1.0 | 125 | 0.4942 | 0.8605 | 0.8469 |
73
+ | 0.3519 | 2.0 | 250 | 0.2466 | 0.919 | 0.9190 |
74
+ | 0.2221 | 3.0 | 375 | 0.2122 | 0.9225 | 0.9226 |
 
 
75
 
76
 
77
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5162c6b076842ead180beb8569d668a4c782e70b110803a7ce4bc9b6a44c85b
3
  size 267867821
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d48ad798f60d4a79c5fb52a38d2347bbc8745d5ac8ce9985a48d0cf92bd2c0
3
  size 267867821
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cca0f298935d7d052c725313f9fd22edebfb06620d4ea832d643d6c260bab33
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0540c8fcbe65ab4643a244cb7ae0f653f3c9e99704f96e2f4f4756dade291ef4
3
  size 4155