Hugging Face's logo

tingtone
/
jq_emo_gpt

Text Classification
Transformers
PyTorch
TensorBoard
gpt2
Generated from Trainer
Eval Results
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
1
tingtone commited on
Commit
cffffa3
•
1 Parent(s): 19f4557

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -17
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.941
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the emotion dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.3379
35
- - Accuracy: 0.941
36
 
37
  ## Model description
38
 
@@ -57,23 +57,17 @@ The following hyperparameters were used during training:
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
- - lr_scheduler_warmup_steps: 16000
61
- - num_epochs: 10
62
 
63
  ### Training results
64
 
65
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
- |:-------------:|:-----:|:------:|:---------------:|:--------:|
67
- | 0.7328 | 1.0 | 16000 | 0.6227 | 0.899 |
68
- | 0.3989 | 2.0 | 32000 | 0.4351 | 0.927 |
69
- | 0.2888 | 3.0 | 48000 | 0.3162 | 0.9385 |
70
- | 0.2325 | 4.0 | 64000 | 0.2936 | 0.9445 |
71
- | 0.2774 | 5.0 | 80000 | 0.2903 | 0.94 |
72
- | 0.1423 | 6.0 | 96000 | 0.3410 | 0.9405 |
73
- | 0.1681 | 7.0 | 112000 | 0.3259 | 0.9385 |
74
- | 0.1743 | 8.0 | 128000 | 0.3225 | 0.9415 |
75
- | 0.1011 | 9.0 | 144000 | 0.3356 | 0.942 |
76
- | 0.1138 | 10.0 | 160000 | 0.3379 | 0.941 |
77
 
78
 
79
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.939
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the emotion dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.2836
35
+ - Accuracy: 0.939
36
 
37
  ## Model description
38
 
 
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
+ - lr_scheduler_warmup_steps: 6400
61
+ - num_epochs: 4
62
 
63
  ### Training results
64
 
65
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
67
+ | 0.5336 | 1.0 | 16000 | 0.6176 | 0.9215 |
68
+ | 0.2962 | 2.0 | 32000 | 0.3453 | 0.9375 |
69
+ | 0.3416 | 3.0 | 48000 | 0.3061 | 0.938 |
70
+ | 0.1796 | 4.0 | 64000 | 0.2836 | 0.939 |
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions