Model save

README.md

@@ -1,39 +1,53 @@
 ---
 license: mit
-metrics:
-- accuracy
-- precision
-- recall
-- f1
-datasets:
-- albertmartinez/OSDG
-pipeline_tag: text-classification
-widget:
-- text: "Between the Social and the Spatial - Exploring Multiple Dimensions of Poverty and Social Exclusion, Ashgate. Poverty in Europe and the USA, Exchanging Official Measurement Methods”, Maastricht Graduate School of Governance Working Paper 2007/005. Monitoring Absolute and Relative Poverty, ‘Not Enough’ Is Not the Same as ‘Much Less’”, Review of Income and Wealth, 57(2), 247-269. Poverty and Social Exclusion in Britain, The Policy Press, Bristol."
-- text: "A circular economy is a way of achieving sustainable consumption and production, as well as nature positive outcomes."
+base_model: albertmartinez/bert-sdg-classification
+tags:
+- generated_from_trainer
+model-index:
+- name: bert-sdg-classification
+  results: []
 ---
 
-# albertmartinez/bert-sdg-classification
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
 
-This model (BERT) is for classifying text with respect to the United Nations sustainable development goals (SDG).
+# bert-sdg-classification
 
-## Training Hyperparameters
+This model is a fine-tuned version of [albertmartinez/bert-sdg-classification](https://huggingface.co/albertmartinez/bert-sdg-classification) on an unknown dataset.
 
-- Num_epoch = 10
-- Learning rate = 5e-5
-- Batch size = 16
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 600
+- num_epochs: 3.0
 
 ### Training results
 
-| epoch | eval_loss          | eval_accuracy      | eval_precision     | eval_recall        | eval_f1            |
-|:-----:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|
-| 1     | 0.8289520740509033 | 0.7644437495113752 | 0.7640369944809821 | 0.7644437495113752 | 0.7554162181382816 |
-| 2     | 0.7316043972969055 | 0.792432178875772  | 0.7973419054011932 | 0.792432178875772  | 0.7936523802626467 |
-| 3     | 0.7474315762519836 | 0.7989992963802673 | 0.8003484834993271 | 0.7989992963802673 | 0.7980647892639322 |
-| 4     | 0.9092283248901367 | 0.8023610351028067 | 0.8028028170382215 | 0.8023610351028067 | 0.8010556735181147 |
-| 5     | 1.0973293781280518 | 0.8040028144789305 | 0.806116786873114  | 0.8040028144789305 | 0.8037135940426907 |
-| 6     | 1.2260032892227173 | 0.8032210147760144 | 0.8046046540363118 | 0.8032210147760144 | 0.8009496362737498 |
-| 7     | 1.3465653657913208 | 0.8082245328746775 | 0.8079189056438383 | 0.8082245328746775 | 0.8070935517356475 |
-| 8     | 1.458662509918213  | 0.8132280509733406 | 0.8124031757212116 | 0.8132280509733406 | 0.8124964838774498 |
-| 9     | 1.5251907110214233 | 0.8108044718943007 | 0.8112362484949358 | 0.8108044718943007 | 0.8097338645156864 |
-| 10    | 1.50314199924469   | 0.8152607302009225 | 0.8143774938584517 | 0.8152607302009225 | 0.8144630791491494 |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1