End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3379
+- Loss: 1.0044
 
 ## Model description
 
@@ -35,8 +35,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.001
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -46,14 +46,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.688         | 1.0   | 1    | 2.7996          |
-| 2.3351        | 2.0   | 2    | 2.5544          |
-| 2.1185        | 3.0   | 3    | 2.2144          |
-| 1.8101        | 4.0   | 4    | 1.9601          |
-| 1.5507        | 5.0   | 5    | 1.7337          |
-| 1.3137        | 6.0   | 6    | 1.5424          |
-| 1.109         | 7.0   | 7    | 1.4134          |
-| 0.96          | 8.0   | 8    | 1.3379          |
+| 2.688         | 1.0   | 1    | 2.6557          |
+| 2.1862        | 2.0   | 2    | 2.0614          |
+| 1.6295        | 3.0   | 3    | 1.5751          |
+| 1.1295        | 4.0   | 4    | 1.1448          |
+| 0.596         | 5.0   | 5    | 0.9583          |
+| 0.2845        | 6.0   | 6    | 0.9543          |
+| 0.1825        | 7.0   | 7    | 1.0156          |
+| 0.1624        | 8.0   | 8    | 1.0044          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1a0759bc5feed386bb2030f7fb80c5a1c7a86429fb38bd3ff0e4198becb114c
+oid sha256:64ceb737ed0fac10fc9e8759f8a42ad4768ba5452004138431f9bb00cc65a7a1
 size 50400909