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/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7089
+- Loss: 1.6552
 
 ## Model description
 
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 0.0001
 - train_batch_size: 1
 - eval_batch_size: 1
 - seed: 42
@@ -44,16 +44,22 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.05
-- num_epochs: 3
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.5026        | 1.0   | 1457 | 1.7267          |
-| 1.4926        | 2.0   | 2915 | 1.7124          |
-| 1.4237        | 3.0   | 4371 | 1.7089          |
+| 1.548         | 0.21  | 300  | 1.7227          |
+| 1.3576        | 0.41  | 600  | 1.7006          |
+| 1.3032        | 0.62  | 900  | 1.6854          |
+| 1.4151        | 0.82  | 1200 | 1.6771          |
+| 1.8081        | 1.03  | 1500 | 1.6698          |
+| 1.6592        | 1.23  | 1800 | 1.6649          |
+| 1.6466        | 1.44  | 2100 | 1.6600          |
+| 1.7293        | 1.65  | 2400 | 1.6574          |
+| 1.6455        | 1.85  | 2700 | 1.6552          |
 
 
 ### Framework versions