Cleverlytics
/

offres_classification_bert_v1

Text Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

smerchi commited on 10 days ago

Commit

663df54

·

verified ·

1 Parent(s): 63a61ee

End of training

Files changed (1) hide show

README.md +13 -15

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [SI2M-Lab/DarijaBERT](https://huggingface.co/SI2M-Lab/DarijaBERT) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0247
 ## Model description
@@ -36,28 +36,26 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
 - train_batch_size: 16
-- eval_batch_size: 16
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 12
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 141  | 0.0312          |
-| No log        | 2.0   | 282  | 0.0781          |
-| No log        | 3.0   | 423  | 0.0229          |
-| 0.1308        | 4.0   | 564  | 0.0187          |
-| 0.1308        | 5.0   | 705  | 0.0208          |
-| 0.1308        | 6.0   | 846  | 0.0261          |
-| 0.1308        | 7.0   | 987  | 0.0242          |
-| 0.0008        | 8.0   | 1128 | 0.0244          |
-| 0.0008        | 9.0   | 1269 | 0.0247          |
-| 0.0008        | 10.0  | 1410 | 0.0247          |
-| 0.0005        | 11.0  | 1551 | 0.0247          |
-| 0.0005        | 12.0  | 1692 | 0.0247          |
 ### Framework versions

 This model is a fine-tuned version of [SI2M-Lab/DarijaBERT](https://huggingface.co/SI2M-Lab/DarijaBERT) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0256
 ## Model description
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
 - train_batch_size: 16
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
+- num_epochs: 10
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 132  | 0.0484          |
+| No log        | 2.0   | 264  | 0.0225          |
+| No log        | 3.0   | 396  | 0.0269          |
+| 0.1331        | 4.0   | 528  | 0.0217          |
+| 0.1331        | 5.0   | 660  | 0.0240          |
+| 0.1331        | 6.0   | 792  | 0.0248          |
+| 0.1331        | 7.0   | 924  | 0.0250          |
+| 0.0014        | 8.0   | 1056 | 0.0253          |
+| 0.0014        | 9.0   | 1188 | 0.0256          |
+| 0.0014        | 10.0  | 1320 | 0.0256          |
 ### Framework versions