End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/rembert](https://huggingface.co/google/rembert) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4856
+- Loss: 0.5128
 - Accuracy: 0.9833
 - 1-f1: 0.0
 - 1-recall: 0.0
@@ -44,7 +44,7 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 16
-- eval_batch_size: 16
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
@@ -55,15 +55,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|:--------:|:-----------:|:------------:|
-| 0.9981        | 1.0   | 449  | 0.4919          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 1.9468        | 2.0   | 898  | 0.5090          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.0076        | 3.0   | 1347 | 0.4793          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.0091        | 4.0   | 1796 | 0.4637          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.0116        | 5.0   | 2245 | 0.4451          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.827         | 6.0   | 2694 | 0.4285          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.8788        | 7.0   | 3143 | 0.4710          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 1.6416        | 8.0   | 3592 | 0.4322          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.0082        | 9.0   | 4041 | 0.4856          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.9794        | 1.0   | 449  | 0.5783          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 2.0372        | 2.0   | 898  | 0.6057          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.007         | 3.0   | 1347 | 0.5683          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.0084        | 4.0   | 1796 | 0.5528          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.0109        | 5.0   | 2245 | 0.5314          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.8213        | 6.0   | 2694 | 0.5101          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.8681        | 7.0   | 3143 | 0.5652          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 1.7764        | 8.0   | 3592 | 0.5128          | 0.9833   | 0.0  | 0.0      | 0.0         | 0.5          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97e073292fa38771d57864a18f59c1ad780118f2b032acc0587d3b7fb12e7db0
+oid sha256:92d1cf79d69938f7b46d835c03faa9d404634d228453a2eedf2b8f04c382abd4
 size 2303755328

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b098f7529edca0ef2b7b2c177bb8da0026be422236b8952b738a37eed95503f3
+oid sha256:803f0bda174aed8879ea69b8a9642747a18d8b4ea928c1ecf48aac2ec26714af
 size 5432