ahmedgongi/codeLlama_instruct_devops_expert1

README.md

@@ -1,9 +1,9 @@
 ---
-license: apache-2.0
+license: llama2
 library_name: peft
 tags:
 - generated_from_trainer
-base_model: mistralai/Mistral-7B-Instruct-v0.2
+base_model: codellama/CodeLlama-7b-Instruct-hf
 model-index:
 - name: mistral_instruct
   results: []
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral_instruct
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
+This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.0127
+- Loss: 1.6038
 
 ## Model description
 
@@ -44,14 +44,16 @@ 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_steps: 2
-- num_epochs: 60
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.2278        | 60.0  | 300  | 5.0127          |
+| 1.6251        | 1.0   | 361  | 1.5966          |
+| 1.5575        | 2.0   | 723  | 1.5952          |
+| 1.5094        | 3.0   | 1083 | 1.6038          |
 
 
 ### Framework versions