Model save

README.md

@@ -8,8 +8,6 @@ metrics:
 model-index:
 - name: distilbert-multilingual-sdg-classification
   results: []
-datasets:
-- albertmartinez/OSDG
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert-multilingual-sdg-classification
 
-This model is a fine-tuned version of [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased)
+This model is a fine-tuned version of [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8312
-- F1: 0.7621
+- Loss: 0.7341
+- F1: 0.7954
 
 ## Model description
 
@@ -39,22 +37,29 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 2e-05
 - train_batch_size: 32
-- eval_batch_size: 8
+- eval_batch_size: 32
 - 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
+- num_epochs: 5.0
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 1.484         | 1.0   | 1076 | 0.8800          | 0.7463 |
+| 0.7957        | 2.0   | 2152 | 0.7796          | 0.7735 |
+| 0.612         | 3.0   | 3228 | 0.7352          | 0.7904 |
+| 0.4784        | 4.0   | 4304 | 0.7243          | 0.7948 |
+| 0.3959        | 5.0   | 5380 | 0.7341          | 0.7954 |
 
 
 ### Framework versions
 
-- Transformers 4.42.4
-- Pytorch 2.3.1+cu121
+- Transformers 4.43.2
+- Pytorch 2.4.0+cu121
 - Datasets 2.20.0
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1