Omidh
/

mDeBERTa-v3-base-xnli-multilingual-nli-2mil7-energy

@@ -20,12 +20,12 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7](https://huggingface.co/MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2328
-- Accuracy: 0.9637
-- Precision: 0.9637
-- Recall: 0.9636
-- F1: 0.9637
-- Ratio: 0.4847
 ## Model description
@@ -54,24 +54,19 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.06
 - lr_scheduler_warmup_steps: 3
-- num_epochs: 5
 - label_smoothing_factor: 0.01
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Ratio  |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
-| 0.5212        | 0.43  | 400  | 0.3449          | 0.8948   | 0.8964    | 0.8940 | 0.8945 | 0.4596 |
-| 0.4083        | 0.86  | 800  | 0.3203          | 0.9224   | 0.9232    | 0.9218 | 0.9222 | 0.4684 |
-| 0.2384        | 1.29  | 1200 | 0.3149          | 0.9361   | 0.9365    | 0.9358 | 0.9360 | 0.4759 |
-| 0.213         | 1.72  | 1600 | 0.3024          | 0.9443   | 0.9442    | 0.9442 | 0.9442 | 0.4865 |
-| 0.1686        | 2.15  | 2000 | 0.2742          | 0.9493   | 0.6332    | 0.6329 | 0.6330 | 0.4934 |
-| 0.105         | 2.58  | 2400 | 0.2641          | 0.9518   | 0.9519    | 0.9522 | 0.9518 | 0.5041 |
-| 0.116         | 3.01  | 2800 | 0.2515          | 0.9555   | 0.6374    | 0.6372 | 0.6372 | 0.4997 |
-| 0.077         | 3.44  | 3200 | 0.2511          | 0.9580   | 0.9580    | 0.9583 | 0.9580 | 0.4966 |
-| 0.0622        | 3.86  | 3600 | 0.2355          | 0.9643   | 0.9644    | 0.9642 | 0.9643 | 0.4828 |
-| 0.0524        | 4.29  | 4000 | 0.2289          | 0.9637   | 0.9636    | 0.9637 | 0.9637 | 0.4884 |
-| 0.0498        | 4.72  | 4400 | 0.2336          | 0.9643   | 0.9644    | 0.9642 | 0.9643 | 0.4840 |
 ### Framework versions

 This model is a fine-tuned version of [MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7](https://huggingface.co/MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.2358
+- Accuracy: 0.9580
+- Precision: 0.9583
+- Recall: 0.9578
+- F1: 0.9580
+- Ratio: 0.4803
 ## Model description
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.06
 - lr_scheduler_warmup_steps: 3
+- num_epochs: 3
 - label_smoothing_factor: 0.01
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Ratio  |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
+| 0.5219        | 0.43  | 400  | 0.3524          | 0.8954   | 0.8972    | 0.8946 | 0.8951 | 0.4577 |
+| 0.4069        | 0.86  | 800  | 0.3178          | 0.9249   | 0.9250    | 0.9246 | 0.9248 | 0.4809 |
+| 0.2326        | 1.29  | 1200 | 0.3055          | 0.9355   | 0.9360    | 0.9351 | 0.9354 | 0.4740 |
+| 0.2045        | 1.72  | 1600 | 0.2847          | 0.9455   | 0.9457    | 0.9453 | 0.9455 | 0.4803 |
+| 0.1423        | 2.15  | 2000 | 0.2477          | 0.9555   | 0.9555    | 0.9556 | 0.9555 | 0.4903 |
+| 0.0935        | 2.58  | 2400 | 0.2367          | 0.9599   | 0.9598    | 0.9600 | 0.9599 | 0.4922 |
 ### Framework versions