Hugging Face's logo

DandinPower
/
deberta-v3-xsmall-otat-recommened-hp

Text Classification
Transformers
Safetensors
English
deberta-v2
nycu-112-2-datamining-hw2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
DandinPower commited on
Commit
c05546d
•
1 Parent(s): e20ed48

End of training

Browse files
Files changed (2) hide show
  1. README.md +13 -9
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.6544285714285715
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [microsoft/deberta-v3-xsmall](https://huggingface.co/microsoft/deberta-v3-xsmall) on the DandinPower/review_onlytitleandtext dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.8557
36
- - Accuracy: 0.6544
37
- - Macro F1: 0.6530
38
 
39
  ## Model description
40
 
@@ -62,16 +62,20 @@ The following hyperparameters were used during training:
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 1000
65
- - num_epochs: 5
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
71
- | 0.9839 | 1.14 | 500 | 0.9456 | 0.6059 | 0.5947 |
72
- | 0.8351 | 2.29 | 1000 | 0.8711 | 0.6367 | 0.6268 |
73
- | 0.7364 | 3.43 | 1500 | 0.8376 | 0.6433 | 0.6463 |
74
- | 0.6687 | 4.57 | 2000 | 0.8557 | 0.6544 | 0.6530 |
 
 
 
 
75
 
76
 
77
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6391428571428571
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [microsoft/deberta-v3-xsmall](https://huggingface.co/microsoft/deberta-v3-xsmall) on the DandinPower/review_onlytitleandtext dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.0799
36
+ - Accuracy: 0.6391
37
+ - Macro F1: 0.6372
38
 
39
  ## Model description
40
 
 
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 1000
65
+ - num_epochs: 10
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
71
+ | 0.97 | 1.14 | 500 | 0.9598 | 0.5957 | 0.5847 |
72
+ | 0.8311 | 2.29 | 1000 | 0.8698 | 0.6371 | 0.6267 |
73
+ | 0.7452 | 3.43 | 1500 | 0.8271 | 0.6457 | 0.6471 |
74
+ | 0.678 | 4.57 | 2000 | 0.8802 | 0.6421 | 0.6359 |
75
+ | 0.6161 | 5.71 | 2500 | 0.9048 | 0.6457 | 0.6463 |
76
+ | 0.5784 | 6.86 | 3000 | 0.9604 | 0.6439 | 0.6452 |
77
+ | 0.5068 | 8.0 | 3500 | 1.0170 | 0.6453 | 0.6452 |
78
+ | 0.4247 | 9.14 | 4000 | 1.0799 | 0.6391 | 0.6372 |
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f458df2668d2548a9c8d7287be8682d3d092163ac585edf0e1db408dade537a
3
  size 283352060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dee2435cd24703113e0f380bb9399af8767b286e71f03b7452ce18ae5ab62645
3
  size 283352060