SheldonSides commited on
Commit
cd4bfdf
1 Parent(s): d01ae7b

Fine-tuning Complete

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -23,10 +23,10 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.9335
27
  - name: F1
28
  type: f1
29
- value: 0.933619945274824
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: 0.1579
40
- - Accuracy: 0.9335
41
- - F1: 0.9336
42
 
43
  ## Model description
44
 
@@ -69,8 +69,8 @@ The following hyperparameters were used during training:
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
72
- | 0.1798 | 1.0 | 250 | 0.1691 | 0.9345 | 0.9344 |
73
- | 0.127 | 2.0 | 500 | 0.1579 | 0.9335 | 0.9336 |
74
 
75
 
76
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.9245
27
  - name: F1
28
  type: f1
29
+ value: 0.9244990073753523
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: 0.2143
40
+ - Accuracy: 0.9245
41
+ - F1: 0.9245
42
 
43
  ## Model description
44
 
 
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
72
+ | 0.5513 | 1.0 | 250 | 0.3057 | 0.908 | 0.9076 |
73
+ | 0.2227 | 2.0 | 500 | 0.2143 | 0.9245 | 0.9245 |
74
 
75
 
76
  ### Framework versions