Hugging Face's logo

alex-miller
/
iati-climate-classifier

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
alex-miller commited on
Commit
c0083b3
·
verified ·
1 Parent(s): 71c3ed2

End of training

Browse files
Files changed (3) hide show
  1. README.md +23 -30
  2. model.safetensors +1 -1
  3. runs/Apr16_14-05-54_e91cb29cabd1/events.out.tfevents.1713276355.e91cb29cabd1.628.0 +2 -2
README.md CHANGED
@@ -5,30 +5,30 @@ tags:
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
 
 
 
8
  model-index:
9
  - name: iati-climate-classifier
10
  results: []
11
- datasets:
12
- - alex-miller/iati-policy-markers
13
- language:
14
- - en
15
- - fr
16
- - es
17
- - de
18
- pipeline_tag: text-classification
19
  ---
20
 
21
- # iati-climate-classifier
 
22
 
23
- This model is a fine-tuned version of [alex-miller/ODABert](https://huggingface.co/alex-miller/ODABert) on a subset of the [alex-miller/iati-policy-markers](https://huggingface.co/datasets/alex-miller/iati-policy-markers) dataset.
24
 
 
25
  It achieves the following results on the evaluation set:
26
- - Loss: 0.3397
27
- - Accuracy: 0.8562
 
 
 
28
 
29
  ## Model description
30
 
31
- This model has been trained to identify climate mitigation and climate adaptation project titles and/or descriptions. It returns "0" for projects with no climate component, and "1" for projects with adaptation or mitigation as a principal or significant objective.
32
 
33
  ## Intended uses & limitations
34
 
@@ -40,8 +40,6 @@ More information needed
40
 
41
  ## Training procedure
42
 
43
- Code to subset the dataset and train the model is available [here](https://github.com/akmiller01/iati-policy-marker-hf-dataset/blob/main/use_cases/climate_mitigation_adaptation_train.ipynb).
44
-
45
  ### Training hyperparameters
46
 
47
  The following hyperparameters were used during training:
@@ -51,27 +49,22 @@ The following hyperparameters were used during training:
51
  - seed: 42
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
- - num_epochs: 10
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
59
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
60
- | 0.4374 | 1.0 | 2739 | 0.3603 | 0.8443 |
61
- | 0.3492 | 2.0 | 5478 | 0.3553 | 0.8508 |
62
- | 0.3265 | 3.0 | 8217 | 0.3397 | 0.8562 |
63
- | 0.3099 | 4.0 | 10956 | 0.3404 | 0.8607 |
64
- | 0.2955 | 5.0 | 13695 | 0.3536 | 0.8602 |
65
- | 0.2849 | 6.0 | 16434 | 0.3486 | 0.8628 |
66
- | 0.2746 | 7.0 | 19173 | 0.3484 | 0.8634 |
67
- | 0.2681 | 8.0 | 21912 | 0.3518 | 0.8630 |
68
- | 0.2619 | 9.0 | 24651 | 0.3560 | 0.8639 |
69
- | 0.2597 | 10.0 | 27390 | 0.3535 | 0.8649 |
70
 
71
 
72
  ### Framework versions
73
 
74
  - Transformers 4.38.2
75
- - Pytorch 2.0.1
76
  - Datasets 2.18.0
77
- - Tokenizers 0.15.2
 
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
8
+ - f1
9
+ - precision
10
+ - recall
11
  model-index:
12
  - name: iati-climate-classifier
13
  results: []
 
 
 
 
 
 
 
 
14
  ---
15
 
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
 
19
+ # iati-climate-classifier
20
 
21
+ This model is a fine-tuned version of [alex-miller/ODABert](https://huggingface.co/alex-miller/ODABert) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.2380
24
+ - Accuracy: 0.9124
25
+ - F1: 0.9152
26
+ - Precision: 0.8870
27
+ - Recall: 0.9452
28
 
29
  ## Model description
30
 
31
+ More information needed
32
 
33
  ## Intended uses & limitations
34
 
 
40
 
41
  ## Training procedure
42
 
 
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
 
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 5
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
58
+ | 0.4992 | 1.0 | 876 | 0.2831 | 0.8921 | 0.8978 | 0.8530 | 0.9475 |
59
+ | 0.2706 | 2.0 | 1752 | 0.2446 | 0.9038 | 0.9057 | 0.8881 | 0.9241 |
60
+ | 0.2494 | 3.0 | 2628 | 0.2370 | 0.9095 | 0.9114 | 0.8927 | 0.9309 |
61
+ | 0.2393 | 4.0 | 3504 | 0.2385 | 0.9112 | 0.9140 | 0.8863 | 0.9435 |
62
+ | 0.2306 | 5.0 | 4380 | 0.2380 | 0.9124 | 0.9152 | 0.8870 | 0.9452 |
 
 
 
 
 
63
 
64
 
65
  ### Framework versions
66
 
67
  - Transformers 4.38.2
68
+ - Pytorch 2.2.1+cu121
69
  - Datasets 2.18.0
70
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7078a1985eefd0789391a21655e74cfec034ae9fbc71f0e8d086ab2de95659d5
3
  size 672708608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00416784f9d176a1debaf29dc51c8519fe6e0a7274ea7f1cbf0d9d83a75e5293
3
  size 672708608
runs/Apr16_14-05-54_e91cb29cabd1/events.out.tfevents.1713276355.e91cb29cabd1.628.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7b798719e29fcffef51f71949cd5950dc247967206bc8d74e9817880f8b5fb1
3
- size 8277
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3341f1e1b789d581900797a1b8549106359cb06c9217ed80f0b63251f850b9f5
3
+ size 8631