Hugging Face's logo

g-assismoraes
/
mdeberta-domain_fold1

Text Classification
Transformers
TensorBoard
Safetensors
deberta-v2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
g-assismoraes commited on
Commit
60f805b
•
1 Parent(s): c506a6d

End of training

Browse files
Files changed (2) hide show
  1. README.md +15 -15
  2. runs/Oct28_15-45-46_icuff-Z790-UD/events.out.tfevents.1730141147.icuff-Z790-UD.1116241.0 +2 -2
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.4372
25
- - Accuracy: 0.875
26
- - Precision: 0.9141
27
- - Recall: 0.6300
28
- - F1: 0.6042
29
 
30
  ## Model description
31
 
@@ -56,16 +56,16 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
59
- | No log | 1.0 | 5 | 0.9920 | 0.525 | 0.8417 | 0.3333 | 0.2295 |
60
- | 0.9966 | 2.0 | 10 | 0.9362 | 0.525 | 0.8417 | 0.3333 | 0.2295 |
61
- | 0.9966 | 3.0 | 15 | 0.8382 | 0.525 | 0.8417 | 0.3333 | 0.2295 |
62
- | 0.8568 | 4.0 | 20 | 0.7050 | 0.9 | 0.9318 | 0.6458 | 0.6212 |
63
- | 0.8568 | 5.0 | 25 | 0.6132 | 0.9 | 0.9318 | 0.6458 | 0.6212 |
64
- | 0.6425 | 6.0 | 30 | 0.5345 | 0.9 | 0.9318 | 0.6458 | 0.6212 |
65
- | 0.6425 | 7.0 | 35 | 0.4872 | 0.9 | 0.9318 | 0.6458 | 0.6212 |
66
- | 0.5041 | 8.0 | 40 | 0.4586 | 0.9 | 0.9318 | 0.6458 | 0.6212 |
67
- | 0.5041 | 9.0 | 45 | 0.4438 | 0.875 | 0.9141 | 0.6300 | 0.6042 |
68
- | 0.4538 | 10.0 | 50 | 0.4372 | 0.875 | 0.9141 | 0.6300 | 0.6042 |
69
 
70
 
71
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.5289
25
+ - Accuracy: 0.8562
26
+ - Precision: 0.8293
27
+ - Recall: 0.7956
28
+ - F1: 0.8011
29
 
30
  ## Model description
31
 
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
59
+ | 1.0269 | 1.0 | 19 | 0.8985 | 0.5890 | 0.8630 | 0.3333 | 0.2471 |
60
+ | 0.8123 | 2.0 | 38 | 0.7571 | 0.5890 | 0.8630 | 0.3333 | 0.2471 |
61
+ | 0.7079 | 3.0 | 57 | 0.7243 | 0.5890 | 0.8630 | 0.3333 | 0.2471 |
62
+ | 0.6259 | 4.0 | 76 | 0.7249 | 0.7808 | 0.8511 | 0.6444 | 0.5909 |
63
+ | 0.5818 | 5.0 | 95 | 0.7192 | 0.7671 | 0.6242 | 0.6222 | 0.5773 |
64
+ | 0.5081 | 6.0 | 114 | 0.6343 | 0.7877 | 0.7129 | 0.6628 | 0.6687 |
65
+ | 0.4902 | 7.0 | 133 | 0.5858 | 0.8219 | 0.7819 | 0.7256 | 0.7107 |
66
+ | 0.3946 | 8.0 | 152 | 0.5584 | 0.8288 | 0.7766 | 0.7656 | 0.7603 |
67
+ | 0.3876 | 9.0 | 171 | 0.5457 | 0.8562 | 0.8396 | 0.7811 | 0.7859 |
68
+ | 0.3239 | 10.0 | 190 | 0.5289 | 0.8562 | 0.8293 | 0.7956 | 0.8011 |
69
 
70
 
71
  ### Framework versions
runs/Oct28_15-45-46_icuff-Z790-UD/events.out.tfevents.1730141147.icuff-Z790-UD.1116241.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3571c51bfde005a142e2e6858cf83640edca6ed0e4b42b8f19bec84649bdd8fd
3
- size 13505
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c52fe95fde2791b0884fd31940d968ee84fa5bbd4fadaf2a078695c78bf0b3ed
3
+ size 14331