End of training

README.md

@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [sagorsarker/bangla-bert-base](https://huggingface.co/sagorsarker/bangla-bert-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3991
-- F1: 0.8412
-- Roc Auc: 0.8406
-- Accuracy: 0.5553
-- Hamming Loss: 0.1594
-- Jaccard Score: 0.7260
-- Zero One Loss: 0.4447
+- Loss: 0.3641
+- F1: 0.8505
+- Roc Auc: 0.8470
+- Accuracy: 0.5578
+- Hamming Loss: 0.1530
+- Jaccard Score: 0.7399
+- Zero One Loss: 0.4422
 
 ## Model description
 
@@ -43,7 +43,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 2e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -55,11 +55,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy | Hamming Loss | Jaccard Score | Zero One Loss |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|:------------:|:-------------:|:-------------:|
-| 0.5041        | 1.0   | 73   | 0.4024          | 0.8227 | 0.8252  | 0.5141   | 0.1748       | 0.6988        | 0.4859        |
-| 0.4299        | 2.0   | 146  | 0.4437          | 0.8005 | 0.7995  | 0.4859   | 0.2005       | 0.6674        | 0.5141        |
-| 0.4039        | 3.0   | 219  | 0.4073          | 0.8402 | 0.8374  | 0.5424   | 0.1626       | 0.7244        | 0.4576        |
-| 0.2797        | 4.0   | 292  | 0.4140          | 0.8238 | 0.8226  | 0.5270   | 0.1774       | 0.7003        | 0.4730        |
-| 0.2532        | 5.0   | 365  | 0.3991          | 0.8412 | 0.8406  | 0.5553   | 0.1594       | 0.7260        | 0.4447        |
+| 0.3991        | 1.0   | 73   | 0.4026          | 0.8245 | 0.8193  | 0.4884   | 0.1806       | 0.7014        | 0.5116        |
+| 0.3621        | 2.0   | 146  | 0.3670          | 0.8479 | 0.8464  | 0.5578   | 0.1536       | 0.7359        | 0.4422        |
+| 0.2817        | 3.0   | 219  | 0.3620          | 0.8502 | 0.8463  | 0.5604   | 0.1536       | 0.7394        | 0.4396        |
+| 0.2081        | 4.0   | 292  | 0.3630          | 0.8532 | 0.8496  | 0.5630   | 0.1504       | 0.7440        | 0.4370        |
+| 0.1962        | 5.0   | 365  | 0.3641          | 0.8505 | 0.8470  | 0.5578   | 0.1530       | 0.7399        | 0.4422        |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9282e52727421ae456bdd5a2c1ed3e0a83887fc1eedb8e11c206e124c565665d
+oid sha256:6ea9bb7319792f6bd6d96b4dda81c244e455baccaf7ecc3d7b978de4f420e446
 size 657622024