kirilica
/

HW_DL_10_Competitions_v2

Text Classification

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

kirilica commited on Dec 5, 2024

Commit

789b520

·

verified ·

1 Parent(s): 576a88a

End of training

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8855
-- F1: 0.6078
 ## Model description
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 1.0538        | 1.0   | 563  | 0.9222          | 0.5900 |
-| 0.8844        | 2.0   | 1126 | 0.8855          | 0.6078 |
 ### Framework versions

 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.8703
+- F1: 0.6075
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
+| 1.0446        | 1.0   | 563  | 0.9216          | 0.5840 |
+| 0.8689        | 2.0   | 1126 | 0.8703          | 0.6075 |
 ### Framework versions