Hugging Face's logo

Rahul13
/
distilbert-base-uncased-finetuned-emotion

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Rahul13 commited on
Commit
fdf5f31
•
1 Parent(s): 973da61

Training completed!

Browse files
Files changed (2) hide show
  1. README.md +15 -9
  2. runs/Mar10_14-54-54_87c93e4c0907/events.out.tfevents.1710082648.87c93e4c0907.623.0 +2 -2
README.md CHANGED
@@ -18,15 +18,15 @@ model-index:
18
  name: emotion
19
  type: emotion
20
  config: split
21
- split: test
22
  args: split
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.917
27
  - name: F1
28
  type: f1
29
- value: 0.9165004879105692
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: 0.2182
40
- - Accuracy: 0.917
41
- - F1: 0.9165
42
 
43
  ## Model description
44
 
@@ -63,14 +63,20 @@ 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
- | 0.8247 | 1.0 | 250 | 0.3073 | 0.906 | 0.9047 |
73
- | 0.2464 | 2.0 | 500 | 0.2182 | 0.917 | 0.9165 |
 
 
 
 
 
 
74
 
75
 
76
  ### Framework versions
 
18
  name: emotion
19
  type: emotion
20
  config: split
21
+ split: validation
22
  args: split
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.938
27
  - name: F1
28
  type: f1
29
+ value: 0.9379552147966106
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: 0.1541
40
+ - Accuracy: 0.938
41
+ - F1: 0.9380
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: 8
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
72
+ | 0.7817 | 1.0 | 250 | 0.2605 | 0.917 | 0.9177 |
73
+ | 0.1947 | 2.0 | 500 | 0.1744 | 0.931 | 0.9306 |
74
+ | 0.1305 | 3.0 | 750 | 0.1558 | 0.9375 | 0.9382 |
75
+ | 0.1017 | 4.0 | 1000 | 0.1426 | 0.9375 | 0.9371 |
76
+ | 0.083 | 5.0 | 1250 | 0.1383 | 0.9385 | 0.9381 |
77
+ | 0.0696 | 6.0 | 1500 | 0.1591 | 0.94 | 0.9401 |
78
+ | 0.0604 | 7.0 | 1750 | 0.1557 | 0.9355 | 0.9354 |
79
+ | 0.0521 | 8.0 | 2000 | 0.1541 | 0.938 | 0.9380 |
80
 
81
 
82
  ### Framework versions
runs/Mar10_14-54-54_87c93e4c0907/events.out.tfevents.1710082648.87c93e4c0907.623.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0180236c7353722c32bd39999312d685e495b580528c38a6b7523751d20d740
3
- size 9055
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e785b15bdf6740add7a7038a327698b1343a6f7ed4a6659c4db705d2a7d53fb
3
+ size 9778