Model save

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.1610
+- Loss: 1.8627
 
 ## Model description
 
@@ -36,22 +36,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
-- gradient_accumulation_steps: 32
+- gradient_accumulation_steps: 16
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 14.5596       | 0.9978 | 14   | 9.4378          |
-| 9.3982        | 1.9955 | 28   | 6.1610          |
+| 14.506        | 0.9956 | 14   | 8.9908          |
+| 8.89          | 1.9911 | 28   | 3.8102          |
+| 2.553         | 2.9867 | 42   | 1.8627          |
 
 
 ### Framework versions