End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7397
-- Accuracy: 0.3431
+- Loss: 1.4498
+- Accuracy: 0.4657
 
 ## Model description
 
@@ -38,21 +38,29 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 12
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 44   | 1.8679          | 0.2598   |
-| No log        | 2.0   | 88   | 1.8270          | 0.25     |
-| No log        | 3.0   | 132  | 1.7757          | 0.3333   |
-| No log        | 4.0   | 176  | 1.7397          | 0.3431   |
+| No log        | 1.0   | 22   | 1.8823          | 0.25     |
+| No log        | 2.0   | 44   | 1.7918          | 0.2892   |
+| No log        | 3.0   | 66   | 1.7041          | 0.3578   |
+| No log        | 4.0   | 88   | 1.6625          | 0.3480   |
+| No log        | 5.0   | 110  | 1.6353          | 0.3971   |
+| No log        | 6.0   | 132  | 1.5817          | 0.4118   |
+| No log        | 7.0   | 154  | 1.5344          | 0.4069   |
+| No log        | 8.0   | 176  | 1.5128          | 0.4804   |
+| No log        | 9.0   | 198  | 1.4906          | 0.4559   |
+| No log        | 10.0  | 220  | 1.4587          | 0.4755   |
+| No log        | 11.0  | 242  | 1.4590          | 0.4951   |
+| No log        | 12.0  | 264  | 1.4498          | 0.4657   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e12b1a8bf4cb07d4213cca6d3a05347de75b13a09b347f68464d07daa02ad879
+oid sha256:3047a8f83e3651225db1af61fd7f6497c0aece279697cfc9f7e1e56b6849f520
 size 433286148