Hugging Face's logo

mljn
/
mdeberta-v3-base-finetuned-climate-vs-environment-classification

Text Classification
Transformers
Safetensors
deberta-v2
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
mljn commited on
Commit
513c49c
·
verified ·
1 Parent(s): 61d18dd

Model save

Browse files
Files changed (2) hide show
  1. README.md +19 -26
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,23 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.3046
22
- - Accuracy: 0.9412
23
- - Accuracy Balanced: 0.9408
24
- - F1 Macro: 0.9407
25
- - F1 Micro: 0.9412
26
- - Precision Macro: 0.9405
27
- - Recall Macro: 0.9408
28
- - Precision Micro: 0.9412
29
- - Recall Micro: 0.9412
30
- - Precision Class 0: 0.9332
31
- - Recall Class 0: 0.9369
32
- - F1 Class 0: 0.9350
33
- - Support Class 0: 745
34
- - Precision Class 1: 0.9479
35
- - Recall Class 1: 0.9448
36
- - F1 Class 1: 0.9463
37
- - Support Class 1: 905
38
 
39
  ## Model description
40
 
@@ -64,19 +56,20 @@ The following hyperparameters were used during training:
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Accuracy Balanced | F1 Macro | F1 Micro | Precision Macro | Recall Macro | Precision Micro | Recall Micro | Precision Class 0 | Recall Class 0 | F1 Class 0 | Support Class 0 | Precision Class 1 | Recall Class 1 | F1 Class 1 | Support Class 1 |
68
- |:-------------:|:------:|:----:|:---------------:|:--------:|:-----------------:|:--------:|:--------:|:---------------:|:------------:|:---------------:|:------------:|:-----------------:|:--------------:|:----------:|:---------------:|:-----------------:|:--------------:|:----------:|:---------------:|
69
- | 0.5189 | 0.6061 | 500 | 0.5022 | 0.8521 | 0.8638 | 0.8519 | 0.8521 | 0.8710 | 0.8638 | 0.8521 | 0.8521 | 0.7596 | 0.9839 | 0.8573 | 745 | 0.9825 | 0.7436 | 0.8465 | 905 |
70
- | 0.2674 | 1.2121 | 1000 | 0.3443 | 0.9291 | 0.9284 | 0.9284 | 0.9291 | 0.9285 | 0.9284 | 0.9291 | 0.9291 | 0.9220 | 0.9208 | 0.9214 | 745 | 0.9349 | 0.9359 | 0.9354 | 905 |
71
- | 0.253 | 1.8182 | 1500 | 0.2558 | 0.9261 | 0.9218 | 0.9247 | 0.9261 | 0.9302 | 0.9218 | 0.9261 | 0.9261 | 0.9547 | 0.8779 | 0.9147 | 745 | 0.9057 | 0.9657 | 0.9348 | 905 |
72
- | 0.1733 | 2.4242 | 2000 | 0.2983 | 0.94 | 0.9394 | 0.9394 | 0.94 | 0.9395 | 0.9394 | 0.94 | 0.94 | 0.9341 | 0.9329 | 0.9335 | 745 | 0.9448 | 0.9459 | 0.9453 | 905 |
73
- | 0.151 | 3.0303 | 2500 | 0.2986 | 0.9394 | 0.9372 | 0.9386 | 0.9394 | 0.9406 | 0.9372 | 0.9394 | 0.9394 | 0.9498 | 0.9141 | 0.9316 | 745 | 0.9314 | 0.9602 | 0.9456 | 905 |
74
- | 0.1003 | 3.6364 | 3000 | 0.3046 | 0.9412 | 0.9408 | 0.9407 | 0.9412 | 0.9405 | 0.9408 | 0.9412 | 0.9412 | 0.9332 | 0.9369 | 0.9350 | 745 | 0.9479 | 0.9448 | 0.9463 | 905 |
 
75
 
76
 
77
  ### Framework versions
78
 
79
- - Transformers 4.51.3
80
  - Pytorch 2.6.0+cu124
81
  - Datasets 2.14.4
82
  - Tokenizers 0.21.1
 
18
 
19
  This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.3534
22
+ - Accuracy: 0.9337
23
+ - F1 Macro: 0.9322
24
+ - Accuracy Balanced: 0.9309
25
+ - F1 Micro: 0.9337
26
+ - Precision Macro: 0.9336
27
+ - Recall Macro: 0.9309
28
+ - Precision Micro: 0.9337
29
+ - Recall Micro: 0.9337
 
 
 
 
 
 
 
 
30
 
31
  ## Model description
32
 
 
56
 
57
  ### Training results
58
 
59
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Accuracy Balanced | F1 Micro | Precision Macro | Recall Macro | Precision Micro | Recall Micro |
60
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:-----------------:|:--------:|:---------------:|:------------:|:---------------:|:------------:|
61
+ | 0.5053 | 0.5663 | 500 | 0.3745 | 0.8924 | 0.8911 | 0.8953 | 0.8924 | 0.8892 | 0.8953 | 0.8924 | 0.8924 |
62
+ | 0.3056 | 1.1325 | 1000 | 0.3315 | 0.9151 | 0.9139 | 0.9174 | 0.9151 | 0.9119 | 0.9174 | 0.9151 | 0.9151 |
63
+ | 0.2184 | 1.6988 | 1500 | 0.3414 | 0.9264 | 0.9253 | 0.9280 | 0.9264 | 0.9234 | 0.9280 | 0.9264 | 0.9264 |
64
+ | 0.2006 | 2.2650 | 2000 | 0.3502 | 0.9298 | 0.9279 | 0.9255 | 0.9298 | 0.9310 | 0.9255 | 0.9298 | 0.9298 |
65
+ | 0.1464 | 2.8313 | 2500 | 0.3143 | 0.9337 | 0.9323 | 0.9321 | 0.9337 | 0.9325 | 0.9321 | 0.9337 | 0.9337 |
66
+ | 0.1177 | 3.3975 | 3000 | 0.3550 | 0.9349 | 0.9332 | 0.9313 | 0.9349 | 0.9356 | 0.9313 | 0.9349 | 0.9349 |
67
+ | 0.0992 | 3.9638 | 3500 | 0.3534 | 0.9337 | 0.9322 | 0.9309 | 0.9337 | 0.9336 | 0.9309 | 0.9337 | 0.9337 |
68
 
69
 
70
  ### Framework versions
71
 
72
+ - Transformers 4.52.2
73
  - Pytorch 2.6.0+cu124
74
  - Datasets 2.14.4
75
  - Tokenizers 0.21.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5474008043f728577febed0053579f63f96680ba629ca17d69b894359b5fddf8
3
  size 1115268200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef1cf6fd408425a8ec9aa758301236f960a8f6148d6bff40eda2bc8a5f44756
3
  size 1115268200