End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/CodeLlama-7b-Python-hf](https://huggingface.co/meta-llama/CodeLlama-7b-Python-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3235
+- Loss: 1.0021
 
 ## Model description
 
@@ -46,23 +46,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 10
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.7248        | 1.0   | 50   | 1.1969          |
-| 1.019         | 2.0   | 100  | 0.9823          |
-| 0.6937        | 3.0   | 150  | 0.9647          |
-| 0.524         | 4.0   | 200  | 1.0338          |
-| 0.407         | 5.0   | 250  | 1.1739          |
-| 0.3275        | 6.0   | 300  | 1.2034          |
-| 0.288         | 7.0   | 350  | 1.2079          |
-| 0.2545        | 8.0   | 400  | 1.3362          |
-| 0.2252        | 9.0   | 450  | 1.3391          |
-| 0.2198        | 10.0  | 500  | 1.3235          |
+| 1.7698        | 1.0   | 50   | 1.2633          |
+| 1.0717        | 2.0   | 100  | 0.9874          |
+| 0.6987        | 3.0   | 150  | 0.9683          |
+| 0.5192        | 4.0   | 200  | 1.0021          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7b2892889938f9202124e31de9e6320a19109710318d1773b91fbc4700f4126
+oid sha256:e3bc17bfee053c45cdd79a78d1d53f8d9cc382d31dc9a7566232d73a703be427
 size 16794200