Hugging Face's logo

Gridflow
/
distilbert-base-uncased-finetuned-emotion

Text Classification
Transformers
PyTorch
Safetensors
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Gridflow commited on
Commit
3681d0b
•
1 Parent(s): 56489f0

Training completed!

Browse files
Files changed (1) hide show
  1. README.md +16 -8
README.md CHANGED
@@ -23,10 +23,10 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.9275
27
  - name: F1
28
  type: f1
29
- value: 0.9271762618731211
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: 0.2137
40
- - Accuracy: 0.9275
41
- - F1: 0.9272
42
 
43
  ## Model description
44
 
@@ -63,14 +63,22 @@ The following hyperparameters were used during training:
63
  - seed: 42
64
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
  - lr_scheduler_type: linear
66
- - num_epochs: 2
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
72
- | 0.85 | 1.0 | 250 | 0.3162 | 0.909 | 0.9076 |
73
- | 0.2526 | 2.0 | 500 | 0.2137 | 0.9275 | 0.9272 |
 
 
 
 
 
 
 
 
74
 
75
 
76
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.9455
27
  - name: F1
28
  type: f1
29
+ value: 0.9455317055605632
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: 0.1789
40
+ - Accuracy: 0.9455
41
+ - F1: 0.9455
42
 
43
  ## Model description
44
 
 
63
  - seed: 42
64
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
  - lr_scheduler_type: linear
66
+ - num_epochs: 10
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
72
+ | 0.799 | 1.0 | 250 | 0.2667 | 0.92 | 0.9206 |
73
+ | 0.2043 | 2.0 | 500 | 0.1661 | 0.9345 | 0.9341 |
74
+ | 0.1359 | 3.0 | 750 | 0.1580 | 0.938 | 0.9387 |
75
+ | 0.1028 | 4.0 | 1000 | 0.1517 | 0.943 | 0.9435 |
76
+ | 0.0838 | 5.0 | 1250 | 0.1485 | 0.9385 | 0.9384 |
77
+ | 0.0691 | 6.0 | 1500 | 0.1514 | 0.94 | 0.9402 |
78
+ | 0.0578 | 7.0 | 1750 | 0.1854 | 0.9345 | 0.9338 |
79
+ | 0.0488 | 8.0 | 2000 | 0.1707 | 0.9405 | 0.9406 |
80
+ | 0.0414 | 9.0 | 2250 | 0.1822 | 0.944 | 0.9441 |
81
+ | 0.0355 | 10.0 | 2500 | 0.1789 | 0.9455 | 0.9455 |
82
 
83
 
84
  ### Framework versions