Hugging Face's logo

mljn
/
mdeberta-v3-base-finetuned-green-classification

Text Classification
Transformers
Safetensors
deberta-v2
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
mljn commited on
Commit
d11ff3e
·
verified ·
1 Parent(s): b9b4965

Model save

Browse files
Files changed (2) hide show
  1. README.md +17 -16
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,15 +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: 0.3988
22
- - Accuracy: 0.9230
23
- - F1 Macro: 0.8948
24
- - Accuracy Balanced: 0.8886
25
- - F1 Micro: 0.9230
26
- - Precision Macro: 0.9015
27
- - Recall Macro: 0.8886
28
- - Precision Micro: 0.9230
29
- - Recall Micro: 0.9230
30
 
31
  ## Model description
32
 
@@ -58,17 +58,18 @@ The following hyperparameters were used during training:
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
- | 0.5523 | 0.6061 | 500 | 0.4128 | 0.8582 | 0.7870 | 0.7605 | 0.8582 | 0.8350 | 0.7605 | 0.8582 | 0.8582 |
62
- | 0.3454 | 1.2121 | 1000 | 0.4055 | 0.9036 | 0.8687 | 0.8642 | 0.9036 | 0.8736 | 0.8642 | 0.9036 | 0.9036 |
63
- | 0.2914 | 1.8182 | 1500 | 0.3141 | 0.9085 | 0.8681 | 0.8451 | 0.9085 | 0.9008 | 0.8451 | 0.9085 | 0.9085 |
64
- | 0.218 | 2.4242 | 2000 | 0.4303 | 0.9097 | 0.8693 | 0.8450 | 0.9097 | 0.9044 | 0.8450 | 0.9097 | 0.9097 |
65
- | 0.1618 | 3.0303 | 2500 | 0.4054 | 0.9164 | 0.8837 | 0.8718 | 0.9164 | 0.8979 | 0.8718 | 0.9164 | 0.9164 |
66
- | 0.1256 | 3.6364 | 3000 | 0.3988 | 0.9230 | 0.8948 | 0.8886 | 0.9230 | 0.9015 | 0.8886 | 0.9230 | 0.9230 |
 
67
 
68
 
69
  ### Framework versions
70
 
71
- - Transformers 4.51.3
72
  - Pytorch 2.6.0+cu124
73
  - Datasets 2.14.4
74
  - 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: 0.3960
22
+ - Accuracy: 0.9213
23
+ - F1 Macro: 0.8801
24
+ - Accuracy Balanced: 0.8710
25
+ - F1 Micro: 0.9213
26
+ - Precision Macro: 0.8902
27
+ - Recall Macro: 0.8710
28
+ - Precision Micro: 0.9213
29
+ - Recall Micro: 0.9213
30
 
31
  ## Model description
32
 
 
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
+ | 0.469 | 0.5663 | 500 | 0.6021 | 0.8437 | 0.6974 | 0.6628 | 0.8437 | 0.8325 | 0.6628 | 0.8437 | 0.8437 |
62
+ | 0.3238 | 1.1325 | 1000 | 0.3677 | 0.9117 | 0.8728 | 0.8851 | 0.9117 | 0.8622 | 0.8851 | 0.9117 | 0.9117 |
63
+ | 0.2588 | 1.6988 | 1500 | 0.3823 | 0.8947 | 0.8590 | 0.9022 | 0.8947 | 0.8334 | 0.9022 | 0.8947 | 0.8947 |
64
+ | 0.2108 | 2.2650 | 2000 | 0.4186 | 0.9094 | 0.8559 | 0.8336 | 0.9094 | 0.8858 | 0.8336 | 0.9094 | 0.9094 |
65
+ | 0.178 | 2.8313 | 2500 | 0.3558 | 0.9230 | 0.8864 | 0.8894 | 0.9230 | 0.8835 | 0.8894 | 0.9230 | 0.9230 |
66
+ | 0.112 | 3.3975 | 3000 | 0.4100 | 0.9219 | 0.8813 | 0.8733 | 0.9219 | 0.8902 | 0.8733 | 0.9219 | 0.9219 |
67
+ | 0.116 | 3.9638 | 3500 | 0.3960 | 0.9213 | 0.8801 | 0.8710 | 0.9213 | 0.8902 | 0.8710 | 0.9213 | 0.9213 |
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 sha256:45ba277152c0bc2f09647acb8f19b52667172a02b8439f2a41977207d199046e
3
  size 1115268200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c9f2f8fef181a45ed0f92a2a0b9b5a604c410ab07ede0f0a1dfb654cb057b0a
3
  size 1115268200