Model save

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-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0064
+- Loss: 0.0010
 - Accuracy: 0.9993
 
 ## Model description
@@ -39,11 +39,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 128
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 2
@@ -52,8 +52,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 44   | 0.0060          | 0.9993   |
-| No log        | 2.0   | 88   | 0.0064          | 0.9993   |
+| No log        | 1.0   | 88   | 0.0088          | 0.9993   |
+| No log        | 2.0   | 176  | 0.0010          | 0.9993   |
 
 
 ### Framework versions